+

CN118656271B - IC substrate manufacturing data monitoring method, system and medium based on cloud computing - Google Patents

IC substrate manufacturing data monitoring method, system and medium based on cloud computing Download PDF

Info

Publication number
CN118656271B
CN118656271B CN202411131895.2A CN202411131895A CN118656271B CN 118656271 B CN118656271 B CN 118656271B CN 202411131895 A CN202411131895 A CN 202411131895A CN 118656271 B CN118656271 B CN 118656271B
Authority
CN
China
Prior art keywords
data
substrate
manufacturing
fog computing
server
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202411131895.2A
Other languages
Chinese (zh)
Other versions
CN118656271A (en
Inventor
于永生
刘东虎
孙敏义
王猛
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Qinghe Electronic Technology Shandong Co ltd
Original Assignee
Qinghe Electronic Technology Shandong Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Qinghe Electronic Technology Shandong Co ltd filed Critical Qinghe Electronic Technology Shandong Co ltd
Priority to CN202411131895.2A priority Critical patent/CN118656271B/en
Publication of CN118656271A publication Critical patent/CN118656271A/en
Application granted granted Critical
Publication of CN118656271B publication Critical patent/CN118656271B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00Error detection; Error correction; Monitoring
    • G06F11/30Monitoring
    • G06F11/3003Monitoring arrangements specially adapted to the computing system or computing system component being monitored
    • G06F11/3006Monitoring arrangements specially adapted to the computing system or computing system component being monitored where the computing system is distributed, e.g. networked systems, clusters, multiprocessor systems
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00Error detection; Error correction; Monitoring
    • G06F11/30Monitoring
    • G06F11/3003Monitoring arrangements specially adapted to the computing system or computing system component being monitored
    • G06F11/3031Monitoring arrangements specially adapted to the computing system or computing system component being monitored where the computing system component is a motherboard or an expansion card
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00Error detection; Error correction; Monitoring
    • G06F11/30Monitoring
    • G06F11/3058Monitoring arrangements for monitoring environmental properties or parameters of the computing system or of the computing system component, e.g. monitoring of power, currents, temperature, humidity, position, vibrations
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks
    • G06N3/04Architecture, e.g. interconnection topology
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks
    • G06N3/08Learning methods

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Computing Systems (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Quality & Reliability (AREA)
  • Biomedical Technology (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Data Mining & Analysis (AREA)
  • Computational Linguistics (AREA)
  • Biophysics (AREA)
  • Artificial Intelligence (AREA)
  • Software Systems (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • General Factory Administration (AREA)

Abstract

The application discloses an IC carrier plate manufacturing data monitoring method, system and medium based on cloud computing, which mainly relate to the technical field of carrier plate manufacturing monitoring and are used for solving the problem that the existing scheme mainly focuses on self-monitoring of a single flow and cannot realize comprehensive analysis of integral data. The method comprises the steps of determining a first fog computing server and a second fog computing server, uploading manufacturing data, equipment data, purchasing data and result data to the first fog computing server, uploading the manufacturing data, the equipment data and the purchasing data to the second fog computing server in real time, uploading the manufacturing data, the equipment data and the purchasing data to a cloud computing terminal through the first fog computing server to obtain model parameters of a trained neural network model, and sending the model parameters to the second fog computing server to enable the second fog computing server to update the internal neural network model through the model parameters to obtain predicted result data.

Description

IC carrier plate manufacturing data monitoring method, system and medium based on cloud computing
Technical Field
The present application relates to the field of IC carrier manufacturing technologies, and in particular, to a cloud computing-based IC carrier manufacturing data monitoring method, system, and medium.
Background
An IC carrier board (INTEGRATED CIRCUIT integrated circuit), also known as an IC package substrate or package substrate, is a highly technically difficult product in the PCB (Printed Circuit Board printed circuit board) industry. The semiconductor IC chip is used as a connecting bridge between the chip and the PCB to realize signal transmission connection. Protect, fix, support IC chip to provide the heat dissipation passageway, ensure the normal work and the stability of chip. Compared with the common PCB, the IC carrier board has the advantages of thinner board body, finer line width and line distance, smaller aperture and the like, so that more precise alignment technology, electroplating technology and the like are required.
The existing monitoring scheme of the IC carrier plate manufacturing process is that a high-precision sensor or a vision system is used for realizing real-time monitoring of manufacturing speed, manufacturing time, manufacturing quantity and defect rate of plate processing. And the qualification rate and the dimensional accuracy of parameters such as the position, the direction, the size and the like of the components in the mounting process are monitored through a machine vision system. Automatic test equipment or manual inspection is used to achieve comprehensive inspection of the finished circuit board.
However, the above solution mainly focuses on self-monitoring of a single process and cannot realize comprehensive analysis of overall data, so that a method, a system and a medium for monitoring manufacturing data of an IC carrier based on cloud computing are needed, and the problem that the existing solution mainly focuses on self-monitoring of a single process and cannot realize comprehensive analysis of overall data is solved.
Disclosure of Invention
Aiming at the defects in the prior art, the application provides a cloud computing-based method, a cloud computing-based system and a cloud computing-based medium for monitoring manufacturing data of an IC carrier, which are used for solving the problem that the existing scheme mainly focuses on self-monitoring of a single flow and cannot realize comprehensive analysis of integral data.
According to a first aspect, the application provides a cloud computing-based method for monitoring manufacturing data of an IC carrier, the method comprises the steps of acquiring manufacturing data of the IC carrier through a preset sensor on a manufacturing line, determining corresponding first fog computing servers and second fog computing servers based on the type of the IC carrier, the manufacturing speed, the manufacturing time and the manufacturing quantity, acquiring equipment data, purchase data and result data of manufacturing equipment corresponding to the IC carrier through an IC carrier data recording server, wherein the equipment data at least comprise working states, operation parameters and fault information, the purchase data at least comprise purchase raw material types, supplier names and purchase dates, the result data at least comprise defect types, defect rates, qualification rates and dimensional accuracy, determining corresponding first fog computing servers and second fog computing servers based on the position information of the preset sensor and the position information of the IC carrier data recording server, uploading the manufacturing data, the equipment data, the purchase data and the result data to the second fog computing servers in real time, uploading the manufacturing data, the equipment data and the purchase data to the first fog computing servers, transmitting the corresponding to the first fog computing servers through the preset time, acquiring the data in a neural network model, training the cloud computing model, and obtaining the result data in the cloud computing model by the cloud computing model, and training the cloud computing model by the cloud computing model, and inputting the manufacturing data, the equipment data and the purchase data obtained in real time into the neural network model to obtain the prediction result data.
The method comprises the steps of acquiring equipment data, purchase data and result data of manufacturing equipment corresponding to an IC carrier through an IC carrier data recording server, acquiring the equipment data of the manufacturing equipment corresponding to the IC carrier through an equipment data uploading interface of the IC carrier data recording server, acquiring the purchase data through a purchase uploading terminal which is in communication connection with the IC carrier data recording server, and acquiring the result data through a detection terminal which is in communication connection with the IC carrier data recording server.
The method comprises the steps of obtaining a plurality of mist computing servers from an idle mist computing server set based on the type of an IC carrier plate, and further selecting two mist computing servers with a linear distance between the position information of a preset sensor and the position information of an IC carrier plate data recording server being smaller than a preset distance range from the mist computing servers based on the position information of the mist computing servers, wherein the position information is longitude and latitude information, and one of the two mist computing servers is determined to be the first mist computing server and the other is determined to be the second mist computing server.
Further, the first fog calculation server and the second fog calculation server both comprise a newly-added data uploading interface for acquiring newly-added participation data of the IC carrier board, the newly-added participation data, manufacturing data, equipment data, purchasing data and result data are uploaded to the cloud calculation terminal together after the newly-added participation data are acquired by the first fog calculation server, then an initial neural network model is trained again to acquire model parameters of the trained neural network model, the neural network model is updated after model parameters corresponding to the newly-added participation data are acquired by the second fog calculation server, and the newly-added participation data, the manufacturing data, the equipment data and the purchasing data are taken as input data after the neural network model is updated, and the neural network model is input.
Further, after inputting the manufacturing data, the equipment data and the purchase data obtained in real time into the neural network model to obtain the prediction result data, the method further comprises the step of sending the prediction result data to a preset detection terminal.
The application provides a cloud computing-based Integrated Circuit (IC) carrier manufacturing data monitoring system, which comprises a sensor preset on a manufacturing line and used for acquiring manufacturing data of an IC carrier, wherein the manufacturing data at least comprise an IC carrier type, a manufacturing speed, manufacturing time and manufacturing quantity, an IC carrier data recording server is used for acquiring equipment data, purchase data and result data of manufacturing equipment corresponding to the IC carrier, the equipment data at least comprise working states, operation parameters and fault information, the purchase data at least comprise purchase raw material types, supplier names and purchase dates, the result data at least comprise defect types, defect rates and qualification rates, dimensional accuracy, a determining module is used for determining corresponding first fog computing servers and second fog computing servers based on the IC carrier type, position information of the preset sensor and position information of the IC carrier data recording server, uploading the manufacturing data, the equipment data, the purchase data and the result data to the second fog computing servers in real time, uploading the manufacturing data, the equipment data and the purchase data to the first fog computing servers, the first fog computing servers and the first cloud computing servers and obtaining the result data through a cloud computing model, training the cloud computing model by using the first cloud computing servers and the cloud computing servers in the cloud computing model, and obtaining the result data through a cloud computing model, and inputting the manufacturing data, the equipment data and the purchasing data obtained in real time into the neural network model to obtain the prediction result data.
The IC carrier plate data recording server further comprises an equipment data uploading interface and a communication connection component, wherein the equipment data uploading interface is used for acquiring equipment data of manufacturing equipment corresponding to the IC carrier plate, the communication connection component is used for establishing communication connection with a purchase uploading terminal to acquire purchase data, and the communication connection with a detection terminal to acquire result data.
The method comprises the steps of acquiring a plurality of mist computing servers from a set of idle mist computing servers based on the type of an Integrated Circuit (IC) carrier of the IC carrier, selecting two mist computing servers with the linear distance between the position information of the preset sensor and the position information of a data recording server of the IC carrier being smaller than a preset distance range from the mist computing servers based on the position information of the mist computing servers, wherein the position information is longitude and latitude information, and determining any one of the two mist computing servers as the first mist computing server and the other as the second mist computing server.
The first fog calculation server is further used for uploading the new participation data, manufacturing data, equipment data, purchasing data and result data to the cloud calculation terminal after the new participation data are acquired by the first fog calculation server, further training the initial neural network model again to acquire model parameters of the trained neural network model, the second fog calculation server is further used for updating the neural network model after the model parameters corresponding to the new participation data are acquired, and inputting the new participation data, the manufacturing data, the equipment data and the purchasing data into the neural network model after the neural network model is updated.
In a third aspect, the present application provides a non-volatile computer storage medium having stored thereon computer instructions that, when executed, implement a cloud computing based IC carrier manufacturing data monitoring method as in any of the above.
As will be appreciated by those skilled in the art, the present application has at least the following beneficial effects:
According to the application, the manufacturing data, the equipment data, the purchasing data and the result data are obtained through the sensor and the IC carrier plate data recording server which are preset on the manufacturing line, so that the neural network model is trained, and the trained neural network model is obtained. As the result data is uploaded subsequently and has hysteresis, the result data corresponding to the current manufacturing data, the equipment data and the purchasing data is predicted through the trained neural network model, the result data can be obtained through the comprehensive analysis of the Integrated Circuit (IC) carrier plate through the whole data, and the problem that the comprehensive analysis of the whole data cannot be realized due to the fact that the existing scheme mainly focuses on self-monitoring of a single process is solved.
In addition, the application relates to two fog calculation servers, wherein one fog calculation server performs data acquisition of a preset IC carrier plate type, updates and trains a neural network model of a cloud calculation terminal, and sends model parameters to the other fog calculation server, so that the neural network model in the other fog calculation server can always adapt to data change, and has higher detection precision.
Drawings
Some embodiments of the present disclosure are described below with reference to the accompanying drawings, in which:
fig. 1 is a flowchart of a method for monitoring IC carrier board manufacturing data based on cloud computing according to an embodiment of the present application.
Fig. 2 is a schematic diagram of an internal structure of an IC carrier manufacturing data monitoring system based on cloud computing according to an embodiment of the present application.
Detailed Description
It should be understood by those skilled in the art that the embodiments described below are only preferred embodiments of the present disclosure, and do not represent that the present disclosure can be realized only by the preferred embodiments, which are merely for explaining the technical principles of the present disclosure, not for limiting the scope of the present disclosure. Based on the preferred embodiments provided by the present disclosure, all other embodiments that may be obtained by one of ordinary skill in the art without inventive effort shall still fall within the scope of the present disclosure.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises an element.
The following describes the technical scheme provided by the embodiment of the application in detail through the attached drawings.
The embodiment of the application provides a cloud computing-based method for monitoring manufacturing data of an IC carrier plate, which mainly comprises the following steps:
step 110, acquiring manufacturing data of the IC carrier by a sensor preset on a manufacturing line.
The manufacturing data includes at least an IC carrier type, a manufacturing speed, a manufacturing time, and a manufacturing number.
And 120, acquiring equipment data, purchase data and result data of manufacturing equipment corresponding to the IC carrier through the IC carrier data recording server.
The equipment data at least comprises working state, operation parameters and fault information, the purchase data at least comprises purchase raw material types, supplier names and purchase dates, and the result data at least comprises defect types, defect rates, qualification rates and dimensional accuracy. In addition, the result data is uploaded by the detection terminal of the subsequent test and has hysteresis.
The method comprises the following steps:
The method comprises the steps of obtaining equipment data of manufacturing equipment corresponding to an IC carrier through an equipment data uploading interface of an IC carrier data recording server, obtaining purchase data through a purchase uploading terminal which is in communication connection with the IC carrier data recording server, and obtaining result data through a detection terminal which is in communication connection with the IC carrier data recording server.
Step 130, determining a first fog calculation server and a second fog calculation server corresponding to the type of the IC carrier plate, the position information of a preset sensor and the position information of the IC carrier plate data recording server, uploading manufacturing data, equipment data, purchasing data and result data to the first fog calculation server, and uploading the manufacturing data, the equipment data and the purchasing data to the second fog calculation server in real time.
It should be noted that there are a preset number of fog calculating servers, the preset number is greater than 100, and the first fog calculating server and the second fog calculating server both have preset service types, and the preset service types and the IC carrier plate types have a one-to-one relationship. The fog computing server may be any feasible server capable of transmitting data and supporting network model operations.
The determining, based on the type of the IC carrier, the position information of the preset sensor and the position information of the IC carrier data recording server, the corresponding first fog calculating server and second fog calculating server may specifically be:
Based on the type of the IC carrier plate, acquiring a plurality of fog calculation servers from an idle fog calculation server set, further based on the position information of the fog calculation servers, selecting two fog calculation servers with the linear distance between the position information of a preset sensor and the position information of the data recording server of the IC carrier plate smaller than a preset distance range from the fog calculation servers, wherein the position information is longitude and latitude information, and determining that any one of the two fog calculation servers is a first fog calculation server and the other is a second fog calculation server.
And 140, uploading manufacturing data, equipment data, purchasing data and result data corresponding to the IC carrier plate in a preset time period to the cloud computing terminal through the first fog computing server, and training an initial neural network model in the cloud computing terminal through the manufacturing data, the equipment data, the purchasing data and the result data in the preset time period to obtain a trained neural network model and further obtain model parameters of the trained neural network model.
In addition, in order to realize compatibility with newly added parameter data, the first fog calculation server and the second fog calculation server related to the application both comprise newly added data uploading interfaces for acquiring newly added participation data of the IC carrier plate.
The method comprises the steps of obtaining newly added participation data by a first fog calculation server, uploading the newly added participation data, manufacturing data, equipment data, purchasing data and result data to a cloud calculation terminal, further training an initial neural network model again to obtain model parameters of a trained neural network model, updating the neural network model after obtaining model parameters corresponding to the newly added participation data by a second fog calculation server, and taking the newly added participation data, the manufacturing data, the equipment data and the purchasing data as input data after finishing updating the neural network model, and inputting the newly added participation data, the manufacturing data, the equipment data and the purchasing data into the neural network model.
And 150, issuing model parameters to a second fog calculation server through the cloud calculation terminal, enabling the second fog calculation server to update an internal neural network model through the model parameters, and inputting manufacturing data, equipment data and purchase data obtained in real time into the neural network model to obtain prediction result data.
After inputting the manufacturing data, the equipment data and the procurement data obtained in real time into the neural network model to obtain the prediction result data, the method further comprises:
And sending the predicted result data to a preset detection terminal.
In addition, the person skilled in the art can send the prediction result data to any feasible terminal according to the actual requirements.
In addition, fig. 2 is a schematic diagram of an IC carrier manufacturing data monitoring system based on cloud computing according to an embodiment of the present application. As shown in fig. 2, the system provided by the embodiment of the present application mainly includes:
The sensor 210 is preset on the manufacturing line and is used for acquiring manufacturing data of the IC carrier.
The manufacturing data includes at least an IC carrier type, a manufacturing speed, a manufacturing time, and a manufacturing number.
The IC carrier data recording server 220 is configured to obtain equipment data, purchase data, and result data of manufacturing equipment corresponding to the IC carrier.
The equipment data at least comprises working state, operation parameters and fault information, the purchase data at least comprises purchase raw material types, supplier names and purchase dates, and the result data at least comprises defect types, defect rates, qualification rates and dimensional accuracy.
The IC carrier data recording server 220 comprises an equipment data uploading interface and a communication connection component, wherein the equipment data uploading interface is used for acquiring equipment data of manufacturing equipment corresponding to the IC carrier, the communication connection component is used for establishing communication connection with a purchase uploading terminal to acquire purchase data, and the communication connection with a detection terminal to acquire result data.
The determining module 230 is configured to determine the corresponding first fog calculating server 240 and second fog calculating server 260 based on the type of the IC carrier board, the preset position information of the sensor and the position information of the IC carrier board data recording server 220, upload the manufacturing data, the equipment data, the purchasing data and the result data to the first fog calculating server 240, and upload the manufacturing data, the equipment data and the purchasing data to the second fog calculating server 260 in real time.
It should be noted that there are a preset number of fog calculating servers, the preset number is greater than 100, and the first fog calculating server 240 and the second fog calculating server 260 each have a preset service type, and the preset service type and the IC carrier plate type have a one-to-one relationship.
The determining module 230 includes a determining unit, configured to obtain a plurality of fog calculating servers from an idle fog calculating server set based on an IC carrier type of the IC carrier, and further select two fog calculating servers with a linear distance between the position information of the sensor and the position information of the IC carrier data recording server 220 smaller than a preset distance range from the fog calculating servers based on the position information of the fog calculating servers, where the position information is longitude and latitude information, and determine any one of the two fog calculating servers as the first fog calculating server 240 and the other as the second fog calculating server 260.
The first fog calculating server 240 is configured to upload manufacturing data, equipment data, purchase data and result data corresponding to the IC carrier board in a preset period of time to the cloud calculating terminal 250.
The cloud computing terminal 250 is configured to train an initial neural network model in the cloud computing terminal 250 through manufacturing data, equipment data, purchase data and result data in a preset time period, further obtain a trained neural network model, further obtain model parameters of the trained neural network model, and send the model parameters to the second mist computing server 260 through the cloud computing terminal 250.
And a second mist calculating server 260 for updating the internal neural network model by the model parameters, and inputting the manufacturing data, the equipment data and the purchase data obtained in real time into the neural network model to obtain the prediction result data.
In addition, the first fog calculating server 240 and the second fog calculating server 260 each include a new data uploading interface for acquiring new participation data of the IC carrier board.
The first fog calculating server 240 is further configured to upload the newly added participation data, the manufacturing data, the equipment data, the purchasing data and the result data to the cloud computing terminal 250 after the newly added participation data is acquired by the first fog calculating server 240, and further train the initial neural network model again to obtain model parameters of the trained neural network model.
The second fog calculating server 260 is further configured to update the neural network model after obtaining the model parameters corresponding to the newly added participation data, and input the newly added participation data, the manufacturing data, the equipment data and the purchasing data together as input data into the neural network model after completing the update of the neural network model.
In addition, the embodiment of the application also provides a nonvolatile computer storage medium, on which executable instructions are stored, and when the executable instructions are executed, the method for monitoring the manufacturing data of the IC carrier board based on cloud computing is realized.
Thus far, the technical solution of the present disclosure has been described in connection with the foregoing embodiments, but it is easily understood by those skilled in the art that the protective scope of the present disclosure is not limited to only these specific embodiments. The technical solutions in the above embodiments may be split and combined by those skilled in the art without departing from the technical principles of the present disclosure, and equivalent modifications or substitutions may be made to related technical features, which all fall within the scope of the present disclosure.

Claims (8)

1.一种基于云计算的IC载板制造数据监控方法,其特征在于,所述方法包括:1. A method for monitoring IC substrate manufacturing data based on cloud computing, characterized in that the method comprises: 通过制造线上预设的传感器,获取IC载板的制造数据;其中,制造数据包括:IC载板类型、制造速度、制造时间、制造数量;Obtaining manufacturing data of the IC substrate through sensors preset on the manufacturing line; wherein the manufacturing data includes: IC substrate type, manufacturing speed, manufacturing time, and manufacturing quantity; 通过IC载板数据记录服务器,获取IC载板对应制造设备的设备数据、采购数据和结果数据;其中,设备数据包括:工作状态、运行参数、故障信息,采购数据包括:采购原料种类、供应商名称、采购日期,结果数据包括:缺陷类型、缺陷率、合格率、尺寸精度;Obtain the equipment data, purchase data and result data of the manufacturing equipment corresponding to the IC substrate through the IC substrate data recording server; the equipment data includes: working status, operating parameters, fault information; the purchase data includes: type of purchased raw materials, supplier name, purchase date; the result data includes: defect type, defect rate, qualified rate, dimensional accuracy; 基于IC载板的IC载板类型、预设的传感器的位置信息和IC载板数据记录服务器的位置信息,确定对应的第一雾计算服务器和第二雾计算服务器;具体包括:Determine the corresponding first fog computing server and second fog computing server based on the IC substrate type of the IC substrate, the location information of the preset sensor and the location information of the IC substrate data recording server; specifically including: 基于IC载板的IC载板类型,从闲置的雾计算服务器集合中获取若干雾计算服务器;进而基于雾计算服务器的位置信息,从若干雾计算服务器中,选择与预设的传感器的位置信息和IC载板数据记录服务器的位置信息之间的直线距离均小于预设距离范围的两个雾计算服务器;其中,位置信息为经纬度信息;确定两个雾计算服务器中的任一为第一雾计算服务器,另一为第二雾计算服务器;Based on the IC substrate type of the IC substrate, a number of fog computing servers are obtained from the idle fog computing server set; then based on the location information of the fog computing servers, two fog computing servers whose straight-line distances from the preset sensor location information and the IC substrate data recording server are both less than a preset distance range are selected from the number of fog computing servers; wherein the location information is latitude and longitude information; and one of the two fog computing servers is determined to be a first fog computing server, and the other is determined to be a second fog computing server; 其中,存在预设数量个雾计算服务器,且预设数量大于100;第一雾计算服务器和第二雾计算服务器均具有预设服务类型,且预设服务类型与IC载板类型存在一对一关系,且一个预设服务类型对应若干雾计算服务器,雾计算服务器仅对应一个预设服务类型;There are a preset number of fog computing servers, and the preset number is greater than 100; the first fog computing server and the second fog computing server both have a preset service type, and there is a one-to-one relationship between the preset service type and the IC substrate type, and one preset service type corresponds to a plurality of fog computing servers, and the fog computing server corresponds to only one preset service type; 向第一雾计算服务器,上传IC载板的制造数据、IC载板对应制造设备的设备数据、采购数据和结果数据;实时向第二雾计算服务器,上传IC载板的制造数据、IC载板对应制造设备的设备数据和采购数据;Upload the manufacturing data of the IC substrate, the equipment data of the manufacturing equipment corresponding to the IC substrate, the procurement data and the result data to the first fog computing server; upload the manufacturing data of the IC substrate, the equipment data of the manufacturing equipment corresponding to the IC substrate and the procurement data to the second fog computing server in real time; 通过第一雾计算服务器,将预设时间段内IC载板对应的制造数据、IC载板对应制造设备的设备数据、采购数据和结果数据,上传至云计算终端;通过预设时间段内的IC载板的制造数据、IC载板对应制造设备的设备数据、采购数据和结果数据,训练云计算终端内部的初始神经网络模型,进而获得训练好的神经网络模型,进而获得训练好的神经网络模型的模型参数;Upload the manufacturing data corresponding to the IC substrate within a preset time period, the equipment data of the manufacturing equipment corresponding to the IC substrate, the procurement data and the result data to the cloud computing terminal through the first fog computing server; train the initial neural network model inside the cloud computing terminal through the manufacturing data of the IC substrate within the preset time period, the equipment data of the manufacturing equipment corresponding to the IC substrate, the procurement data and the result data, and then obtain the trained neural network model, and then obtain the model parameters of the trained neural network model; 通过云计算终端,将模型参数下发至第二雾计算服务器,使第二雾计算服务器通过模型参数更新内部的神经网络模型;并将实时获得的IC载板的制造数据、IC载板对应制造设备的设备数据和采购数据输入神经网络模型,获得预测结果数据。Through the cloud computing terminal, the model parameters are sent to the second fog computing server, so that the second fog computing server updates the internal neural network model through the model parameters; and the real-time manufacturing data of the IC substrate, the equipment data of the manufacturing equipment corresponding to the IC substrate, and the procurement data are input into the neural network model to obtain the prediction result data. 2.根据权利要求1所述的基于云计算的IC载板制造数据监控方法,其特征在于,通过IC载板数据记录服务器,获取IC载板对应制造设备的设备数据、采购数据和结果数据,具体包括:2. The IC substrate manufacturing data monitoring method based on cloud computing according to claim 1 is characterized in that the device data, procurement data and result data of the manufacturing equipment corresponding to the IC substrate are obtained through the IC substrate data recording server, specifically including: 通过IC载板数据记录服务器的设备数据上传界面获取IC载板对应制造设备的设备数据;Obtain the device data of the manufacturing device corresponding to the IC substrate through the device data upload interface of the IC substrate data recording server; 通过与IC载板数据记录服务器建立通信连接的采购上传终端,获取采购数据;通过与IC载板数据记录服务器建立通信连接的检测终端获取结果数据。The purchasing data is obtained through a purchasing upload terminal that establishes a communication connection with the IC substrate data recording server; and the result data is obtained through a detection terminal that establishes a communication connection with the IC substrate data recording server. 3.根据权利要求1所述的基于云计算的IC载板制造数据监控方法,其特征在于,第一雾计算服务器和第二雾计算服务器均包括新增数据上传接口,用于获取IC载板的新增参与数据;3. The IC substrate manufacturing data monitoring method based on cloud computing according to claim 1, characterized in that the first fog computing server and the second fog computing server both include a new data upload interface for obtaining the new participation data of the IC substrate; 在第一雾计算服务器获取到新增参与数据后,将新增参与数据与IC载板的制造数据、IC载板对应制造设备的设备数据、采购数据和结果数据一起上传至云计算终端;After the first fog computing server obtains the newly added participation data, the newly added participation data is uploaded to the cloud computing terminal together with the manufacturing data of the IC substrate, the equipment data of the manufacturing equipment corresponding to the IC substrate, the procurement data and the result data; 进而再次训练初始神经网络模型,获得训练好的神经网络模型的模型参数;Then, the initial neural network model is trained again to obtain the model parameters of the trained neural network model; 在第二雾计算服务器获取到新增参与数据对应的模型参数后,更新神经网络模型;在完成神经网络模型的更新后,将新增参与数据与IC载板的制造数据、IC载板对应制造设备的设备数据、采购数据一起作为输入数据,输入神经网络模型。After the second fog computing server obtains the model parameters corresponding to the newly added participating data, it updates the neural network model; after completing the update of the neural network model, the newly added participating data, together with the manufacturing data of the IC substrate, the equipment data of the manufacturing equipment corresponding to the IC substrate, and the procurement data are used as input data and input into the neural network model. 4.根据权利要求1所述的基于云计算的IC载板制造数据监控方法,其特征在于,在将实时获得的IC载板的制造数据、IC载板对应制造设备的设备数据和采购数据输入神经网络模型,获得预测结果数据之后,所述方法还包括:4. The method for monitoring IC substrate manufacturing data based on cloud computing according to claim 1 is characterized in that after inputting the real-time manufacturing data of the IC substrate, the equipment data of the manufacturing equipment corresponding to the IC substrate and the procurement data into the neural network model to obtain the prediction result data, the method further comprises: 将预测结果数据发送至预设检测终端。The prediction result data is sent to the preset detection terminal. 5.一种基于云计算的IC载板制造数据监控系统,其特征在于,所述系统包括:5. A cloud computing-based IC substrate manufacturing data monitoring system, characterized in that the system comprises: 制造线上预设的传感器,用于获取IC载板的制造数据;其中,制造数据包括:IC载板类型、制造速度、制造时间、制造数量;The sensors preset on the manufacturing line are used to obtain the manufacturing data of the IC substrate; wherein the manufacturing data includes: the type of IC substrate, the manufacturing speed, the manufacturing time, and the manufacturing quantity; IC载板数据记录服务器,用于获取IC载板对应制造设备的设备数据、采购数据和结果数据;其中,设备数据包括:工作状态、运行参数、故障信息,采购数据包括:采购原料种类、供应商名称、采购日期,结果数据包括:缺陷类型、缺陷率、合格率、尺寸精度;IC substrate data recording server, used to obtain equipment data, procurement data and result data of manufacturing equipment corresponding to IC substrate; wherein equipment data includes: working status, operating parameters, fault information; procurement data includes: type of purchased raw materials, supplier name, purchase date; result data includes: defect type, defect rate, qualified rate, dimensional accuracy; 确定模块,用于基于IC载板的IC载板类型、预设的传感器的位置信息和IC载板数据记录服务器的位置信息,确定对应的第一雾计算服务器和第二雾计算服务器;向第一雾计算服务器,上传IC载板的制造数据、IC载板对应制造设备的设备数据、采购数据和结果数据;实时向第二雾计算服务器,上传IC载板的制造数据、IC载板对应制造设备的设备数据和采购数据;A determination module is used to determine the corresponding first fog computing server and second fog computing server based on the IC substrate type of the IC substrate, the location information of the preset sensor and the location information of the IC substrate data recording server; upload the manufacturing data of the IC substrate, the equipment data of the manufacturing equipment corresponding to the IC substrate, the procurement data and the result data to the first fog computing server; upload the manufacturing data of the IC substrate, the equipment data and the procurement data of the manufacturing equipment corresponding to the IC substrate to the second fog computing server in real time; 确定模块包括确定单元,用于基于IC载板的IC载板类型,从闲置的雾计算服务器集合中获取若干雾计算服务器;进而基于雾计算服务器的位置信息,从若干雾计算服务器中,选择与预设的传感器的位置信息和IC载板数据记录服务器的位置信息之间的直线距离均小于预设距离范围的两个雾计算服务器;其中,位置信息为经纬度信息;确定两个雾计算服务器中的任一为第一雾计算服务器,另一为第二雾计算服务器;The determination module includes a determination unit, which is used to obtain a number of fog computing servers from an idle fog computing server set based on the IC substrate type of the IC substrate; and then select, from the number of fog computing servers, two fog computing servers whose straight-line distances from the preset sensor location information and the IC substrate data recording server are both less than a preset distance range based on the location information of the fog computing servers; wherein the location information is longitude and latitude information; and determine that either of the two fog computing servers is a first fog computing server and the other is a second fog computing server; 其中,存在预设数量个雾计算服务器,且预设数量大于100;第一雾计算服务器和第二雾计算服务器均具有预设服务类型,且预设服务类型与IC载板类型存在一对一关系,且一个预设服务类型对应若干雾计算服务器,雾计算服务器仅对应一个预设服务类型;There are a preset number of fog computing servers, and the preset number is greater than 100; the first fog computing server and the second fog computing server both have a preset service type, and there is a one-to-one relationship between the preset service type and the IC substrate type, and one preset service type corresponds to a plurality of fog computing servers, and the fog computing server corresponds to only one preset service type; 第一雾计算服务器,用于将预设时间段内IC载板对应的制造数据、设备数据、采购数据和结果数据,上传至云计算终端;The first fog computing server is used to upload manufacturing data, equipment data, procurement data and result data corresponding to the IC substrate within a preset time period to the cloud computing terminal; 云计算终端,用于通过预设时间段内的IC载板的制造数据、IC载板对应制造设备的设备数据、采购数据和结果数据,训练云计算终端内部的初始神经网络模型,进而获得训练好的神经网络模型,进而获得训练好的神经网络模型的模型参数;通过云计算终端,将模型参数下发至第二雾计算服务器;The cloud computing terminal is used to train the initial neural network model inside the cloud computing terminal through the manufacturing data of the IC substrate within a preset time period, the equipment data of the manufacturing equipment corresponding to the IC substrate, the procurement data and the result data, thereby obtaining the trained neural network model, and then obtaining the model parameters of the trained neural network model; the model parameters are sent to the second fog computing server through the cloud computing terminal; 第二雾计算服务器,用于通过模型参数更新内部的神经网络模型;并将实时获得的IC载板的制造数据、IC载板对应制造设备的设备数据和采购数据输入神经网络模型,获得预测结果数据。The second fog computing server is used to update the internal neural network model through model parameters; and input the real-time manufacturing data of the IC substrate, the equipment data of the manufacturing equipment corresponding to the IC substrate, and the procurement data into the neural network model to obtain prediction result data. 6.根据权利要求5所述的基于云计算的IC载板制造数据监控系统,其特征在于,IC载板数据记录服务器包括设备数据上传界面和通信连接组件;6. The cloud computing-based IC substrate manufacturing data monitoring system according to claim 5, characterized in that the IC substrate data recording server includes a device data upload interface and a communication connection component; 设备数据上传界面,用于获取IC载板对应制造设备的设备数据;The device data upload interface is used to obtain the device data of the manufacturing equipment corresponding to the IC substrate; 通信连接组件,用于与采购上传终端建立通信连接,获取采购数据;与检测终端建立通信连接,获取结果数据。The communication connection component is used to establish a communication connection with the procurement upload terminal to obtain procurement data; and to establish a communication connection with the detection terminal to obtain result data. 7.根据权利要求5所述的基于云计算的IC载板制造数据监控系统,其特征在于,第一雾计算服务器和第二雾计算服务器均包括新增数据上传接口,用于获取IC载板的新增参与数据;7. The IC substrate manufacturing data monitoring system based on cloud computing according to claim 5, characterized in that the first fog computing server and the second fog computing server both include a new data upload interface for obtaining the new participation data of the IC substrate; 第一雾计算服务器,还用于在第一雾计算服务器获取到新增参与数据后,将新增参与数据与IC载板的制造数据、IC载板对应制造设备的设备数据、采购数据和结果数据一起上传至云计算终端;进而再次训练初始神经网络模型,获得训练好的神经网络模型的模型参数;The first fog computing server is further used to upload the newly added participation data together with the manufacturing data of the IC substrate, the equipment data of the manufacturing equipment corresponding to the IC substrate, the procurement data and the result data to the cloud computing terminal after the first fog computing server obtains the newly added participation data; and then train the initial neural network model again to obtain the model parameters of the trained neural network model; 第二雾计算服务器,还用于在获取到新增参与数据对应的模型参数后,更新神经网络模型;在完成神经网络模型的更新后,将新增参与数据与IC载板的制造数据、IC载板对应制造设备的设备数据、采购数据一起作为输入数据,输入神经网络模型。The second fog computing server is also used to update the neural network model after obtaining the model parameters corresponding to the newly added participating data; after completing the update of the neural network model, the newly added participating data is input into the neural network model together with the manufacturing data of the IC substrate, the equipment data of the manufacturing equipment corresponding to the IC substrate, and the procurement data. 8.一种非易失性计算机存储介质,其特征在于,其上存储有计算机指令,所述计算机指令在被执行时实现如权利要求1-4任一项所述的一种基于云计算的IC载板制造数据监控方法。8. A non-volatile computer storage medium, characterized in that computer instructions are stored thereon, and when the computer instructions are executed, they implement a cloud computing-based IC substrate manufacturing data monitoring method as described in any one of claims 1 to 4.
CN202411131895.2A 2024-08-19 2024-08-19 IC substrate manufacturing data monitoring method, system and medium based on cloud computing Active CN118656271B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202411131895.2A CN118656271B (en) 2024-08-19 2024-08-19 IC substrate manufacturing data monitoring method, system and medium based on cloud computing

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202411131895.2A CN118656271B (en) 2024-08-19 2024-08-19 IC substrate manufacturing data monitoring method, system and medium based on cloud computing

Publications (2)

Publication Number Publication Date
CN118656271A CN118656271A (en) 2024-09-17
CN118656271B true CN118656271B (en) 2024-11-29

Family

ID=92697693

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202411131895.2A Active CN118656271B (en) 2024-08-19 2024-08-19 IC substrate manufacturing data monitoring method, system and medium based on cloud computing

Country Status (1)

Country Link
CN (1) CN118656271B (en)

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113660336A (en) * 2018-03-30 2021-11-16 北京忆芯科技有限公司 Cloud computing and fog computing system using KV storage device
CN115443641A (en) * 2020-03-26 2022-12-06 斯纳普公司 Combine first UI content into second UI

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN204155126U (en) * 2014-09-26 2015-02-11 广东电网有限责任公司佛山供电局 A kind of intelligent substation supervising device
CN116996577A (en) * 2023-08-14 2023-11-03 南方电网数字平台科技(广东)有限公司 Mist computing resource pre-allocation method, device, equipment and medium for electric power system
CN118409713B (en) * 2024-07-01 2024-09-13 清河电子科技(山东)有限责任公司 IC carrier production information processing method, system, electronic equipment and medium

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113660336A (en) * 2018-03-30 2021-11-16 北京忆芯科技有限公司 Cloud computing and fog computing system using KV storage device
CN115443641A (en) * 2020-03-26 2022-12-06 斯纳普公司 Combine first UI content into second UI

Also Published As

Publication number Publication date
CN118656271A (en) 2024-09-17

Similar Documents

Publication Publication Date Title
US6944521B2 (en) Method of providing board packaging line program
US9807920B2 (en) Electronic component mounting system
CN105760555B (en) A kind of filter stick formation analysis of processing quality and traceability system and its method
JP2006279072A (en) Semiconductor device manufacture management system
CN115438493B (en) Digital twinning-based PCB manufacturing process debugging system, method and processing equipment
CN105278490A (en) A platform and method for manufacturing optimization
CN109471142B (en) A working track identification method based on RTK differential positioning
KR100486032B1 (en) Degradation diagnosis method, degradation diagnosis intermediation device, degradation diagnosis device and computer-readable recording medium storing degradation dianosis program
CN101266484B (en) Process management method and manufacturing method of electronic device
JP2008090837A (en) System and method for remote diagnostics of device
CN106327082A (en) Medical equipment measurement, detection and quality control platform based on internet cloud computing
US9153502B2 (en) Semiconductor chip testing method and semiconductor chip testing device
CN110519982A (en) Pasting method, device, electronic equipment and storage medium
CN118656271B (en) IC substrate manufacturing data monitoring method, system and medium based on cloud computing
CN109693459B (en) Information processing method and device
US8552867B2 (en) Radio frequency identification for collecting stage-by-stage manufacturing and/or post-manufacturing information associated with a circuit board
CN109879233A (en) A kind of refueling nozzle calibrating Message Entry System and method based on GPS positioning
RU2593446C1 (en) Method for automatic control of metrological characteristics of measuring devices of mass of oil or liquid oil products during tempering at fuel bases
CN114218430A (en) Remote cooperative equipment operation and maintenance system, method and device
CN106569121A (en) Method for calibrating voltage and current accuracy of power management IC
CN109102357A (en) A kind of method for pushing based on Articles detecting, device and terminal
Sower Statistical process control for managers
JP2012204455A (en) Mounting failure analysis system and process abnormality monitoring system
JPH04287274A (en) Quality information management system for electronic devices equipped with printed circuit boards
CN102116826A (en) System and method for measuring voltage of pin of electronic component

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant
点击 这是indexloc提供的php浏览器服务,不要输入任何密码和下载