A pumped storage power generation motor fault diagnosis method, system and device

Abstract

The application relates to the technical field of engine fault diagnosis, in particular to a pumped storage power generation motor fault diagnosis method, system and device, the method comprising the following steps: acquiring three-phase currents, power supply voltages and currents, bearing vibration signals and stator winding temperatures in a pumped storage power generation motor operation process; analyzing the difference between the power supply current and the rated current of the motor power supply, combining the fluctuation degree of the power supply current data and the zero value proportion in the power supply voltage and current to obtain a power supply voltage weight coefficient; obtaining a stator winding temperature weight coefficient according to the amplitude variation degree of the bearing vibration signal; obtaining a stator current weight coefficient through the difference of the three-phase currents of the stator winding, combining the power supply voltage, the stator winding temperature and the three-phase current at each moment to obtain a short-circuit fault discrimination value at each moment, and diagnosing the short-circuit fault of the pumped storage power generation motor. The application improves the accuracy of the pumped storage power generation motor fault diagnosis.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of engine fault diagnosis, in particular to a pumped storage power generation motor fault diagnosis method, system and device. BACKGROUND

[0002] When there is excess power in the power system, the pumped storage power generation motor can operate as a motor to convert electrical energy into potential energy of water for storage; when the power system has peak load, the pumped storage power generation motor can operate as a generator to generate electricity by releasing water, thereby adjusting the load and ensuring the stability of power supply.

[0003] As the core component of the pumped storage unit, the power generation motor has high speed, large single-pole capacity and frequent switching between pumping and power generation conditions, and is more prone to failure than conventional water turbine units. In the process of diagnosing the starting fault of the pumped storage power generation motor, the data change characteristics of the stator winding inter-phase short circuit fault and other faults are similar, and the stator winding inter-phase short circuit fault is often misjudged as other types of faults, resulting in low fault diagnosis accuracy. SUMMARY

[0004] To solve the above technical problems, the purpose of the present application is to provide a pumped storage power generation motor fault diagnosis method, system and device, and the technical solution adopted is as follows:

[0005] In a first aspect, the present application provides a pumped storage power generation motor fault diagnosis method, comprising the following steps:

[0006] Obtaining three-phase current, power supply voltage and current, bearing vibration signal and stator winding temperature during the operation of the pumped storage power generation motor;

[0007] Analyzing the difference between the power supply current at each time and the rated current of the motor power supply, combining the fluctuation degree of the power supply current data at multiple times before each time and the zero value proportion in the power supply voltage and current at multiple times before each time, to obtain the power supply voltage weight coefficient at each time;

[0008] According to the amplitude of the bearing vibration signal at each time and the change degree of the vibration signal amplitude at multiple times before each time, the stator winding temperature weight coefficient at each time is obtained;

[0009] By the difference between the stator winding three-phase current at each time and the maximum and minimum values in the three-phase current, the stator current weight coefficient at each time is obtained;

[0010] According to the three weight coefficients and in combination with the power supply voltage, the stator winding temperature and the three-phase current at each time, a short-circuit fault discrimination value at each time is obtained.

[0011] According to the short-circuit fault discrimination value, the short-circuit fault of the pumped storage generator motor is diagnosed.

[0012] Preferably, the calculation method of the power supply voltage weight coefficient at each time is as follows:

[0013] In the formula, S i represents the power supply voltage weight coefficient at the i th time; I i-1 represents the power supply current data collected at the i-1 th time; EI represents the rated current of the power supply; exp() represents the natural exponential function; A i represents the power supply current sequence at the i th time; D() represents the variance; g m,I represents the proportion of zero values in the power supply current data within m times before the i th time; g m,U represents the proportion of zero values in the power supply voltage data within m times before the i th time.

[0014] Preferably, the power supply currents at multiple times before the i th time are arranged in time sequence to form the power supply current sequence at the i th time.

[0015] Preferably, the calculation method of the stator winding temperature weight coefficient at each time is as follows:

[0016] In the formula, G i is the stator winding temperature weight coefficient at the i th time; Y i-1 represents the amplitude of the bearing vibration signal at the i-1 th time; P i represents the bearing vibration amplitude sequence at the i th time.

[0017] Preferably, the amplitudes of the bearing vibration signals at multiple times before the i th time are arranged in time sequence as the bearing vibration amplitude sequence at the i th time.

[0018] Preferably, the calculation method of the stator current weight coefficient at each time is as follows:

[0019] V i = s i-1,max (s i-1,max -s i-1,min ); in the formula, V i is the stator current weight coefficient at the i th time; s i-1,max represents the maximum value of the three-phase current of the stator winding at the i-1 th time; s i-1,min represents the minimum value of the three-phase current of the stator winding at the i-1 th time.

[0020] Preferably, the calculation method of the short-circuit fault discrimination value at each time is as follows:

[0021]

[0022] wherein B i is the short-circuit fault discrimination value at the i-th time; ω i,1 , ω i,2 and ω i,3 are the normalized power supply voltage weight coefficient, the stator winding temperature weight coefficient and the stator current weight coefficient at the i-th time; t i-1 represents the stator winding temperature at the (i-1)-th time; t i,m represents the average value of the stator winding temperatures at the m times before the i-th time; relu() is a linear rectifier function; E i-1 represents the power supply voltage at the (i-1)-th time; E represents the rated voltage of the power supply; h() is a rectifier function; and σ is a constant to prevent the denominator from being zero.

[0023] Preferably, the diagnosing the short-circuit fault of the pumped storage generator motor according to the short-circuit fault discrimination value specifically comprises: when the short-circuit fault discrimination value is greater than a preset threshold value, the stator winding inter-phase short-circuit occurs at the corresponding time.

[0024] In a second aspect, the embodiments of the present application further provide a pumped storage generator motor fault diagnosis system, which comprises a memory, a processor and a computer program stored in the memory and running on the processor, and the processor implements the steps of the pumped storage generator motor fault diagnosis method according to any one of the above embodiments when executing the computer program.

[0025] In a third aspect, the embodiments of the present application further provide a pumped storage generator motor fault diagnosis device, wherein the device stores a computer program, and the computer program is executed by a processor to implement the pumped storage generator motor fault diagnosis method according to any one of the above embodiments.

[0026] As can be seen from the above, the pumped storage generator motor fault diagnosis method, system and device provided by the present application have at least the following beneficial effects:

[0027] According to the characteristics of the power supply voltage, the stator winding temperature and the three-phase current imbalance under different fault types, the present application constructs the power supply voltage weight coefficient, the stator winding temperature weight coefficient and the stator current weight coefficient, can judge the similarity degree of the data characteristics of the three types of data and the data characteristics that should be generated by the stator winding inter-phase short-circuit, and then gives the respective weights of the three types of data when judging whether the fault type is the stator winding inter-phase short-circuit, so that the interference of power supply abnormalities, bearing loss or overload operation is excluded in the fault diagnosis process, and the diagnosis result is more accurate. Attached Figure Description

[0028] To more clearly illustrate the technical solutions and advantages in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0029] Figure 1 A flowchart illustrating the steps of a fault diagnosis method for a pumped storage generator motor provided in this application. Detailed Implementation

[0030] To further illustrate the technical means and effects adopted by this application to achieve the intended purpose of the invention, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of a pumped-storage generator motor fault diagnosis method, system, and apparatus proposed in this application. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0031] Unless otherwise specified and limited, terms such as “comprising,” “including,” or any other variations thereof are intended to cover a non-exclusive inclusion, such that a circuit structure, article, or device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such an article or device. Without further limitation, an element defined by the phrase “comprising one…” does not exclude the presence of other identical elements in the article or device that includes said element. Furthermore, the term “and / or” as used herein includes any and all combinations of one or more of the associated listed items. All technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains.

[0032] The following description, in conjunction with the accompanying drawings, details the specific scheme of the fault diagnosis method, system, and device for pumped storage generator motors provided in this application.

[0033] Please see Figure 1 The document illustrates a flowchart of a fault diagnosis method for a pumped-storage generator motor according to an embodiment of this application, including the following steps:

[0034] Step 1: Obtain the three-phase current, power supply voltage and current, bearing vibration signal, and stator winding temperature during the operation of the pumped storage generator motor.

[0035] Pump storage unit plays a role in filling valley and peak regulation in power system, and it is generally started and stopped at least twice a day. In the actual application process, some pumped storage power stations require more frequent start and stop. Frequent start and stop will cause various faults of the generator motor. When the fault is relatively minor, the generator motor can still continue to run. As the degree of fault deepens, the generator motor may fail to start. Since the fault usually exists before the start-up failure occurs, the cause of the start-up failure can be determined by monitoring the data of the generator motor in real time during operation.

[0036] In the internal system of the pumped storage generator motor, voltage sensors, current sensors, vibration sensors and temperature sensors are installed to collect three-phase current (a phase, b phase, c phase), power voltage, power current, bearing vibration signal and stator winding temperature of the pumped storage generator motor in real time. In this embodiment, the frequency of data collection is 5 Hz.

[0037] Further, in this embodiment, the collected various data are respectively taken as inputs of the median filtering algorithm for denoising the data, wherein the median filtering algorithm is a known technology and the specific process is not described again.

[0038] Step two: analyze the difference between the power current of the previous adjacent time and the rated current of the motor power supply at each time, and obtain the power voltage weight coefficient of each time in combination with the fluctuation degree of the power current data of multiple times before each time and the proportion of zero values in the power voltage and current of multiple times before each time.

[0039] The causes of the start-up failure of the pumped storage generator motor generally include power supply abnormalities, mechanical damage (bearing damage, zero component damage) and circuit faults, wherein the circuit faults include stator winding inter-phase short circuit, stator winding inter-turn short circuit, excitation circuit short circuit, etc. Since the environment of the pumped storage power station is relatively humid, when water enters the stator winding, it is easy to cause insulation damage or direct short circuit of the stator winding, so that the stator winding inter-phase short circuit fault in the circuit fault becomes one of the common faults. When the stator winding inter-phase short circuit occurs, the unbalance of the three-phase circuit will make the generator motor unable to obtain sufficient starting torque, so it cannot be started. Therefore, when the pumped storage generator motor fails to start, it is necessary to diagnose whether it is caused by the stator winding inter-phase short circuit.

[0040] When the generator motor has a stator winding inter-phase short circuit fault, the current in the short-circuit phase of the stator winding will be much larger than that in the other two phases, resulting in unbalance of the three-phase current. Under the condition of stator winding inter-phase short circuit, the power supply needs to provide more current to meet the demand of the motor, which may cause the power supply voltage to drop. In addition, a large amount of heat will be generated by the short-circuit current when the stator winding inter-phase short circuit occurs, resulting in an increase in the temperature of the stator winding.

[0041] Although the above characteristics occur when the stator winding is short-circuited between phases, the above characteristics do not necessarily occur because of the short-circuit between the stator winding. For example, when the power supply voltage decreases, the power supply may have a fault; when the temperature of the stator winding increases, the generator motor may vibrate due to bearing damage, causing mechanical friction between the stator winding and adjacent parts, resulting in an increase in the temperature of the stator winding; and when the three-phase current of the stator winding is unbalanced, the generator motor may be overloaded.

[0042] When the power supply voltage decreases due to a power supply fault, the power supply current also decreases or abnormally fluctuates at the same time, and when the power supply is completely interrupted, the power supply voltage and the power supply current may be zero. When the power supply voltage decreases due to a short-circuit between the stator winding, the current in the short-circuit phase increases, which increases the power supply current.

[0043] Therefore, based on the above characteristics, the difference between the power supply current at each time and the rated current of the motor power supply is analyzed, the fluctuation degree of the power supply current data, and the proportion of zero values in the power supply voltage and current are combined to construct a power supply voltage weight coefficient. In this embodiment, the calculation formula of the power supply voltage weight coefficient at each time is:

[0044] In the formula, S i represents the power supply voltage weight coefficient at the i-th time; I i-1 represents the power supply current data collected at the (i-1)-th time; EI represents the rated current of the power supply; exp() represents the natural exponential function; A i represents the power supply current sequence at the i-th time, in this embodiment, the power supply currents at the m times before the i-th time are arranged in time sequence to form the power supply current sequence at the i-th time, where m is 20 in this embodiment; D() represents the variance; g m,I represents the proportion of zero values in the power supply current data at the m times before the i-th time; g m,U represents the proportion of zero values in the power supply voltage data at the m times before the i-th time.

[0045] When the value of exp(I i-1 -EI) is larger, it indicates that the power supply current at the (i-1)-th time is larger than the rated current, and further indicates that the power supply voltage decrease is more likely to be caused by the short-circuit between the stator winding; when D(A i ) is smaller, it indicates that the power supply current in the recent period of time is more similar, and further indicates that the power supply current in the recent period of time is less likely to abnormally fluctuate, and the reason for the decrease in the power supply voltage is more likely to be the short-circuit between the stator winding; if g m,I , g m,UThe smaller the proportion of zero values in the power current data and the power voltage data in the near period of time is, the less likely the power voltage drop is caused by a power failure.

[0046] Step three: obtaining the stator winding temperature weight coefficient of each time according to the amplitude of the bearing vibration signal of the previous adjacent time and the change degree of the vibration signal amplitudes of the plurality of times before each time.

[0047] Further, when the reason for the rise of the stator winding temperature is bearing damage, the strength of the vibration signal at the bearing will become larger, and the vibration signal in the near period of time will have a large difference with the vibration signal in the previous period of time; when the reason for the rise of the stator winding temperature is the inter-phase short circuit of the stator winding, the vibration signal at the bearing will not usually change.

[0048] Therefore, the change degree of the amplitude of the bearing vibration signal is analyzed, and then the stator winding temperature weight coefficient of each time is obtained, which is used to represent the possibility that the reason for the rise of the stator winding temperature is the inter-phase short circuit of the stator winding. In the embodiment, the calculation formula of the stator winding temperature weight coefficient of each time is as follows:

[0049] In the formula, G i is the stator winding temperature weight coefficient of the i th time; Y i-1 represents the amplitude of the bearing vibration signal of the i-1 th time; P i represents the bearing vibration amplitude sequence of the i th time, in the embodiment, the amplitudes of the bearing vibration signals of the 20 times before the i th time are arranged in time sequence as the bearing vibration amplitude sequence of the i th time.

[0050] It can be understood that the smaller the value of Y i-1 is, the weaker the strength of the bearing vibration signal of the i-1 th time is, and then it is more likely that the reason for the rise of the stator winding temperature is the inter-phase short circuit of the stator winding; the smaller D(P i is, the more similar the bearing vibration signals in the near period of time are, and then it is more likely that the reason for the rise of the stator winding temperature is caused by the inter-phase short circuit of the stator winding.

[0051] Step four: obtaining the stator current weight coefficient of each time through the stator winding three-phase current of the previous adjacent time and the difference between the maximum value and the minimum value in the three-phase current.

[0052] Further, when the reason for the three-phase current imbalance of the stator winding is because of overload operation, the phase currents of the stator winding will not exceed the rated current too much, and the imbalance degree of the three-phase current is relatively small. When the reason for the three-phase current imbalance of the stator winding is because of the inter-phase short circuit of the stator winding, a large circulating current will flow in the shorted coil, and the three-phase current will be seriously imbalanced.

[0053] Based on the above characteristics, the difference between the maximum value and the minimum value in the three-phase current of the stator winding at each moment is analyzed, and then the stator current weight coefficient at each moment is obtained. In this embodiment, the specific calculation formula is:

[0054] V i = s i-1,max (s i-1,max -s i-1,min ); in the formula, V i is the stator current weight coefficient at the i th moment; s i-1,max represents the maximum value in the three-phase current of the stator winding at the (i-1) th moment; s i-1,min represents the minimum value in the three-phase current of the stator winding at the (i-1) th moment.

[0055] It can be understood that the greater the value of s i-1,max , that is, the greater the maximum value in the three-phase current at the (i-1) th moment, the greater the possibility that the reason for the three-phase circuit imbalance of the stator winding is the inter-phase short circuit of the stator winding; the greater the value of (s i-1,max -s i-1,min ), that is, the higher the three-phase current imbalance degree of the stator winding at the (i-1) th moment, the greater the current difference, and the greater the possibility that the reason for the three-phase circuit imbalance of the stator winding is the inter-phase short circuit of the stator winding.

[0056] Step five: obtaining the short circuit fault discrimination value at each moment according to the three weight coefficients and combining the power supply voltage, the stator winding temperature, and the three-phase current at each moment.

[0057] Further, the short circuit fault discrimination value is constructed according to the power supply voltage weight coefficient, the stator winding temperature weight coefficient, and the stator current weight coefficient at each moment. In this embodiment, the specific calculation formula of the short circuit fault discrimination value at each moment is:

[0058]

[0059] Wherein, B i is the short circuit fault discrimination value at the i th moment; ω i,1 , ω i,2 , and ω i,3 are the normalized power supply voltage weight coefficient, the stator winding temperature weight coefficient, and the stator current weight coefficient at the i th moment, wherein, ωi,1 = tanh(S i ), ω i,2 = tanh(G i ), ω i,3 = tanh(V i ); tanh() is a hyperbolic tangent function for normalizing input data; t i-1 represents the stator winding temperature at the i-1th moment; t i,n represents the average value of the stator winding temperature at the m moments before the ith moment; relu() is a linear rectifier function; E i-1 represents the power supply voltage at the i-1th moment; E represents the rated voltage of the power supply; h() is a rectifier function, and its expression is σ is a constant to prevent the denominator from being zero, which can be any positive number less than 0.1, and in this embodiment, the value is 0.01.

[0060] It can be understood that the more unbalanced the three-phase current at the i-1th moment, the higher the stator winding temperature, and the smaller the power supply voltage, the more likely it is that the starting failure at the ith moment is caused by the stator winding inter-phase short circuit.

[0061] Step six: diagnosing the short circuit fault of the pumped storage generator motor according to the short circuit fault discrimination value.

[0062] Further, according to the short circuit fault discrimination value at each moment, the short circuit fault in the operation process of the pumped storage generator motor is diagnosed and analyzed. Specifically, in this embodiment, when the short circuit fault discrimination value is greater than the threshold value z, the stator winding inter-phase short circuit occurs at the corresponding moment. In this embodiment, z is 3, and the implementer can determine it according to the actual situation.

[0063] Based on the same inventive concept as the above method, the embodiments of the present application also provide a pumped storage generator motor fault diagnosis system, which comprises a memory, a processor, and a computer program stored in the memory and running on the processor, and the processor implements the steps of any one of the above pumped storage generator motor fault diagnosis methods when executing the computer program.

[0064] Meanwhile, the embodiments of the present application also provide a pumped storage generator motor fault diagnosis device, and the device stores a computer program, and the computer program is executed by the processor to implement any one of the above pumped storage generator motor fault diagnosis methods.

[0065] It can be understood that the above-mentioned embodiments of the application are only for description, and do not represent the advantages and disadvantages of the embodiments. And the above describes specific embodiments of the specification. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are also possible or can be advantageous.

[0066] Each of the embodiments in the specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other. Each embodiment focuses on the difference from other embodiments.

[0067] The above is only an embodiment of the application, and is not used to limit the scope of the application. Any equivalent structure or equivalent process transformation using the content of the specification and the drawings, or direct or indirect application in other related technical fields, is also included in the protection scope of the application.

Claims

1. A pumped storage power generation motor failure diagnosis method characterized by, The method comprises the following steps: obtaining three-phase current, power supply voltage and current, bearing vibration signal, and stator winding temperature during the operation of the pumped storage power generation motor; analyzing the difference between the power supply current at each time and the rated current of the motor power supply, combining the fluctuation degree of the power supply current data at multiple times before each time and the proportion of zero values in the power supply voltage and current at multiple times before each time, and obtaining the power supply voltage weight coefficient at each time; obtaining the stator winding temperature weight coefficient at each time according to the amplitude of the bearing vibration signal at the previous adjacent time of each time and the change degree of the vibration signal amplitude at multiple times before each time; obtaining the stator current weight coefficient at each time through the difference between the stator winding three-phase current at the previous adjacent time of each time and the maximum and minimum values in the three-phase current; obtaining the short-circuit fault discrimination value at each time according to the three weight coefficients and combining the power supply voltage, stator winding temperature, and three-phase current at each time; diagnosing the short-circuit fault of the pumped storage power generation motor according to the short-circuit fault discrimination value.

2. A pumped storage power generating motor fault diagnostic method according to claim 1, characterized by, The calculation method of the power supply voltage weight coefficient at each time is: where S i represents the power voltage weight coefficient at the i th moment; I i-1 represents the power current data collected at the i-1 th moment; EI represents the rated current of the power supply; exp() represents the natural exponential function; A i represents the power current sequence at the i th moment; D() represents the variance; g m,I represents the proportion of zero values in the power current data within m moments before the i th moment; g m,U represents the proportion of zero values in the power voltage data within m moments before the i th moment.

3. A pumped storage power generating motor fault diagnostic method according to claim 2, characterized by, arranging the power supply currents at multiple times before the i th time in time sequence to form a power supply current sequence at the i th time.

4. A pumped storage power generating motor fault diagnostic method according to claim 1, characterized by, The calculation method of the stator winding temperature weight coefficient at each time is: wherein G i is the stator winding temperature weight coefficient at the i th moment; Y i-1 represents the amplitude of the bearing vibration signal at the i-1 th moment; P i represents the bearing vibration amplitude sequence at the i th moment.

5. A pumped storage power generating motor fault diagnostic method according to claim 4, characterized by, arranging the amplitudes of the bearing vibration signals at multiple times before the i th time in time sequence as a bearing vibration amplitude sequence at the i th time.

6. A pumped storage power generating motor fault diagnostic method as set forth in claim 1, characterized by, The calculation method of the stator current weight coefficient at each time is: V i = s i-1,max (s i-1,max -s i-1,min ); in the formula, V i is the stator current weight coefficient at the i th moment; s i-1,max represents the maximum value of the three-phase current of the stator winding at the i-1 th moment; s i-1,min represents the minimum value of the three-phase current of the stator winding at the i-1 th moment.

7. A pumped storage power generating motor fault diagnostic method as set forth in claim 1, characterized by, The calculation method of the short-circuit fault discrimination value at each time is: wherein B i is the short-circuit fault discrimination value at the i-th moment; ω i,1 , ω i,2 , and ω i,3 are the normalized power supply voltage weight coefficient, stator winding temperature weight coefficient, and stator current weight coefficient at the i-th moment, respectively; t i-1 represents the stator winding temperature at the i-1-th moment; t i,m represents the average value of the stator winding temperatures at the m moments before the i-th moment; relu() is a linear rectification function; E i-1 represents the power supply voltage at the i-1-th moment; E represents the rated voltage of the power supply; h() is a rectification function; and σ is a constant to prevent the denominator from being zero.

8. A pumped storage power generating motor fault diagnostic method as set forth in claim 1, characterized by, When the short-circuit fault discrimination value is greater than a preset threshold, the stator winding inter-phase short-circuit occurs at the corresponding time.

9. A pumped storage power generation motor failure diagnosis system comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized by, The processor executes the computer program to realize the steps of the pumped storage power generation motor fault diagnosis method according to any one of claims 1-8.

10. A pumped storage power generation motor failure diagnosis device, in which a computer program is stored, characterized by, The computer program is executed by the processor to realize the pumped storage power generation motor fault diagnosis method according to any one of claims 1-8.

Images