US20060071627A1

US20060071627A1 - Motor current reconstruction via DC bus current measurement

Info

Publication number: US20060071627A1
Application number: US10/402,107
Authority: US
Inventors: Eddy Ho; Toshio Takahashi
Original assignee: International Rectifier Corp USA
Current assignee: Infineon Technologies Americas Corp
Priority date: 2002-03-28
Filing date: 2003-03-27
Publication date: 2006-04-06
Also published as: EP1488504A2; TW200520362A; US20050206341A1; EP1488504B1; US7102327B2; JP4717038B2; JP2007288998A; WO2003084044A3; JP2005536973A; WO2003084044A2; EP1488504A4

Abstract

A technique for reconstructing phase currents based on measurements of a DC bus current. Non-observable regions of DC bus current samples to reconstruct phase currents are reduced in size by using two phase space vector modulation. The non-observable regions can be further reduced by omitting deadtime insertions for switch actuations when output current is higher than a given threshold. Voltage command vectors in non-observable areas can be formed by two additive vectors of differing phase and magnitude to obtain an observable DC bus current reflecting phase current. The additive vectors have the same combined time average value as that of the voltage command vector.

Description

RELATED APPLICATION

The application is based on and claims benefit of U.S. Provisional Application No. 60/368,860, filed on Mar. 28, 2002, entitled Motor Current Reconstruction Via DC Bus Current Measurement, to which a claim of priority is hereby made.

BACKGROUND OF THE INVENTION

1. Field of the Invention
The present invention relates generally to motor current feedback measurements, and relates more specifically to a computational reconstruction of motor current obtained through measurement of a DC bus current.
2. Description of Related Art
Inverters for three phase motor drives are well known in the industry. Typically, a DC bus supplies switched power to different phases of an AC motor. A design approach used to supply switching commands and sequences to the inverter involves the use of space vector modulation. For example, a switch vector plane is illustrated in FIG. 1 with specific switch states noted at the vertices of the hexagon.
With this type of motor control, it is desirable to accurately measure motor phase current to provide a high performance control. However, it is often difficult to accurately measure motor phase current over wide current and temperature ranges. For example, Hall effect sensors can be used, but are inherently bulky and costly. In a pulse width modulated (PWM) inverter drive system, motor phase current can be determined from measurement of the DC bus current when non-zero basic vectors are used. Each basic vector is assigned a specific time in a PWM cycle to generate the command voltage vector. However, if a basic vector is used only for a very short period of time, motor phase current cannot be directly determined from the DC bus current. This lack of observability of motor phase current is due to practical considerations in the implementation of the PWM inverter drive system. For example, time delays caused by A/D converter sample and hold times, slewing of voltage during turn on, and other delay factors prevent the effects of basic vectors used for a very short time from being observed.
In the space vector plane shown in FIG. 1A, the non-observable regions are illustrated as being located along the borders of the sections of the space vector plane. Without being able to observe motor phase currents during these control periods, it is difficult to achieve a robust and high performance motor drive.

SUMMARY OF THE INVENTION

The present invention provides an algorithm for the reconstruction of motor currents from measurement of DC bus current. The non-observable operation of motor phase current is restricted to a much smaller domain with the use of the reconstructing algorithm. 2-phase space vector modulation permits the minimum time for an observable effect of a basic vector to be decreased. In practical application, the time constraint related to non-observability is cut in half. By reducing this minimum time, the available time for measurement of phase current according to this technique is doubled. When the voltage vector angle is large than 30°, the zero vector 111 is used instead of 000. By using the different zero vector, a switched phase pulse time is maximized.
When 2-phase space vector modulation is used, and motor current exceeds a certain threshold level, dead time need not be inserted and the time constraint can be further reduced.
When command voltage falls inside the non-observable domains, the command voltage vector is formed from two vectors generated in two PWM periods. One generated vector is a voltage vector having a phase equal to 30° and a magnitude equal to two times the width of the non-observable section. Use of this vector insures the observability of two of the three motor phase currents. The second vector is added to form the resulting command voltage vector that falls inside the non-observable domain. The time average of the two combined vectors are equal to the time average of the command voltage vector. Using the combination of the two vectors permits the controller execution cycle to be reduced by half.

BRIEF DESCRIPTION OF THE DRAWINGS

The present invention is described in detail below, with reference to the accompanying drawings having appropriate reference numeral designators, in which:
FIG. 1A illustrates a voltage space vector plane with conventional non-observable zones;
FIG. 1B illustrates a modified voltage space vector plane according to the present invention;
FIG. 2 illustrates a reduced non-observable zone through 2-phase commutation;
FIG. 3 illustrates a current sampling technique according to the present invention; and
FIG. 4 illustrates the insertion of a known voltage vector to obtain a reference command voltage vector.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

The present invention provides an algorithm to reconstruct 3-phase motor current information from measurement of a DC bus current supply. A voltage space vector plane 10, as illustrated in FIG. 1B, contains non-observable regions near sector borders. According to the present invention, a voltage space vector plane 11 is produced with reduced non-observable zones.
Referring to FIG. 2(a), a conventional 3-phase inverter provides a 3-phase voltage space vector PWM modulation. In FIG. 2(b), a same command voltage can be formed using a 2-phase voltage space vector PWM, as illustrated in commutation diagram 21. According to the 2-phase vector modulation, a minimum time constraint for non-observability is cut in half.
In a two level PWM inverter drive system, eight possible basic voltage vectors can be produced, and any desired command voltage vector can be formed by the eight basic voltage vectors. The desired command voltage vector is limited by the maximum output voltage of the inverter, as determined by the DC bus voltage level. In a PWM inverter drive system, motor phase current information can be determined from the DC bus current when non-zero basic vectors are used. Each basic vector is assigned a specific time in a PWM cycle to generate a command voltage vector. If the command voltage vector is used only for a very short period of time, the motor current cannot be observed from the DC bus current. The shortness of this time constraint results from time delays associated with A/D conversion, including sample and hold times, in addition to voltage slewing resulting from device turn on. It is this time constraint that forms the non-observable regions in the voltage space vector plane illustrated in FIG. 1.
Referring again to FIG. 2(a), a command voltage vector is shown in non-observable region of sector 1. In this instance, all three phases of the motor are PWM driven in a PWM cycle Tpwm. The total time T2 occurs in two different spots in PWM cycle Tpwm.
Referring now to FIG. 2(b), a non-observable region is reduced through the use of a 2-phase voltage space vector modulation. The same command voltage can be formed by the 2-phase PWM in FIG. 2(b), as is formed in the system of FIG. 2(a). However, in the 2-phase voltage space vector modulation, the non-observable time constraint period is cut in half. The total T2 time is localized in one spot. Accordingly, the available time for measurement of current is doubled. When the voltage angle is larger than 30°, the zero vector 111 is used instead of the zero vector 000 to maximize T1 time.
With the use of a 2-phase voltage space vector modulation, a further reduction in the time constraint can be achieved. When motor current is higher than a given threshold, the need to insert dead time is eliminated. Typically, the time constraint can be written as a minimum time Tmin as follows: $T \min = Td + T (ⅆ v / ⅆ t) + T (A / D)$ $where [\begin{matrix} Td = [\begin{matrix} Tdeadtime & abs (i) > Threshold \\ 0 & abs (i) < Threshold \end{matrix} \\ T (A / D) A / D converter sample / hold time \\ T (ⅆ v / ⅆ t) Power switching device slew time \end{matrix}$
Accordingly, when Td is equal to zero, Tmin is reduced accordingly.
Referring now to FIG. 3, the DC bus current is sampled three times every PWM cycle. In FIG. 3, samples idc1 and idc3 are taken from the same motor phase, but at different time instance. Current samples idc1 and idc3 are computed based on the equations shown in FIG. 3 to provide a timing synchronization with sample idc2.
Referring now to FIG. 4, the insertion of a known voltage vector is illustrated in diagram 40. The insertion of the voltage vector is used to form a command voltage vector Vref. When the command voltage is inside the non-observable sector bands, the command voltage vector is formed by two vectors generated in two PWM periods. Voltage vector V1 has a phase equal to 30° and a magnitude equal to two times the non-observable sector width A. By forming vector V1 according to these constraints, observation of two motor phase currents is insured. Vector V2 is added to vector V1 to form the resulting command voltage vector Vref. The time average of V1 plus V2 is equal to the time average of Vref, as illustrated in FIG. 4. By forming the command voltage vector with vectors V1 and V2, controller execution cycle is reduced by half when the command voltage enters the non-observable sector.
Although the present invention has been described in relation to particular embodiments thereof, many other variations and modifications and other uses will become apparent to those skilled in the art. It is preferred, therefore, that the present invention be limited not by the specific disclosure herein, but only by the appended claims.

Claims

1. A method for reducing a non-observable region in a PWM inverter drive system, comprising:

forming a command voltage using two phase space vector modulation;

increasing a time spent on any given basic vector to be above a specified threshold; and

localizing an amount of time spent on any given basic vector, such that an available current measurement time is increased, whereby the non-observable regions are reduced.

2. The method according to claim 1, further comprising using an alternate zero vector when a voltage angle is larger than 30° to maximize an available observation interval.

3. The method according to claim 2, wherein zero vector 111 is used as the alternate zero vector.

4. The method according to claim 1, further comprising eliminating a deadtime insertion when motor current is higher than a given threshold, thereby reducing a time period of the non-observable regions.

5. The method according to claim 1, further comprising sampling a DC bus current at least three times in each PWM cycle.

6. The method according to claim 5, further comprising:

defining a time interval over which DC bus current samples are obtained during a PWM cycle; and

spacing the DC bus current sample within the defined interval to permit output phase current reconstruction in at least two phases.

7. A method for obtaining phase current in a power inverter by measuring DC bus current, comprising:

determining a non-observable sector having a width;

forming a first voltage vector with an observable phase angle and a magnitude being greater than the non-observable sector width when a command voltage vector is in the non-observable sector;

forming a second voltage vector having a phase and magnitude such that said command voltage vector results from summing said first and second voltage vectors, such that a time average of the sum of the first and second voltage vectors is approximately equal to a time average of the command voltage vector.

8. The method according to claim 7, wherein the non-observable sector width is related to a DC bus current sample time lag.

9. The method according to claim 8, wherein the non-observable sector width A is given by the equation

A = \frac{T_{\min}}{T_{pwm}} \times \frac{π}{\sqrt{3}}

wherein T_minis the minimum time required to obtain a DC bus current sample and T_pwmis a PWM cycle time interval.

10. A processor programmable to produce representations of phase output current based on DC bus current samples in accordance with the method of claim 7.

11. A program code for execution by a processor to provide representations of phase current reconstructed from measuring DC bus current in an inverter, comprising instructions for operating the processor in accordance with the method of claim 7.

12. A method for obtaining phase current in a power inverter from DC bus current, comprising:

forming a command voltage vector using two phase space vector modulation;

arranging a combination of basic voltage vectors to produce the command voltage vector with a non-observable region having a reduced width; and

when the command voltage vector is in the non-observable region:

forming a first voltage vector in an observable region to have a magnitude greater than the width;

forming a second voltage vector to add to the first voltage vector;

adding the first and second voltage vectors to form a third voltage vector having approximately a same phase and magnitude as the command voltage, such that a time average of the sum of the third voltage vector is approximately the same as a time average of the command voltage vector.