Permanent magnet synchronous motor fault diagnosis method applied to wind power generation system

Abstract

Multi-source data of a rotor surface temperature value Tzz, a temperature value Dz of a stator coil, a resistance value of the stator coil, a voltage value I of the stator coil, a bearing vibration frequency and a bearing rotation speed of the permanent magnet synchronous motor are acquired, calculation accuracy is improved, a magnetic coefficient Tcd, a thermal short-circuit coefficient Dxs of the stator coil and a bearing wear vibration coefficient Zdxs are calculated respectively, and the stability of the permanent magnet synchronous motor is improved. And the fault of the permanent magnet synchronous motor is diagnosed through evaluation and analysis. A fault diagnosis recognition coefficient Sbx is obtained through comprehensive analysis and calculation, key fault parameters of the permanent magnet synchronous motor are comprehensively analyzed, and the fault diagnosis precision is remarkably improved; the fault diagnosis identification coefficient Sbx is analyzed and evaluated and is finally substituted into the unsupervised learning model; an efficient and reliable solution is provided for deep learning of fault diagnosis, operation monitoring and maintenance of the permanent magnet synchronous motor, and the method has important engineering application value and popularization significance.

Description

Technical Field

[0001] The present invention relates to the technical field of permanent magnet synchronous motor fault diagnosis, and in particular to a permanent magnet synchronous motor fault diagnosis method applied to a wind power generation system. Background Art

[0002] As a clean energy technology, wind power plays a vital role in the global energy transition. Permanent magnet synchronous motors (PMSMs) are widely used in wind power systems, particularly in direct-drive wind turbines, due to their high efficiency, high power density, excellent speed regulation, and reliability. However, PMSMs can fail during operation due to various reasons (such as mechanical wear, electrical faults, and environmental factors), impacting the normal operation of wind turbines and even causing downtime and economic losses.

[0003] Traditional motor fault diagnosis methods primarily rely on the analysis of single physical quantities, such as temperature, current, and resistance. While these methods can identify faults to a certain extent, due to the complex operating environment and diverse fault types of motors, the analysis of single physical quantities often fails to meet the high-precision fault diagnosis requirements under complex operating conditions. Furthermore, traditional methods rely on manual analysis of monitoring data, lacking a systematic and intelligent processing approach. This makes diagnostic results susceptible to human influence and lacks accuracy and robustness.

[0004] Based on this, a permanent magnet synchronous motor fault diagnosis method for wind power generation systems is proposed. Using an unsupervised learning model, the method is trained to automatically learn the fault diagnosis method, capturing important feature information within complex nonlinear relationships and significantly improving the accuracy and intelligence of fault diagnosis. Summary of the Invention

[0005] The object of the present invention is to provide a permanent magnet synchronous motor fault diagnosis method applied to a wind power generation system, so as to solve the problems raised in the above background technology.

[0006] The present invention is achieved through the following technical solutions:

[0007] A permanent magnet synchronous motor fault diagnosis method for a wind power generation system, the method comprising the following steps:

[0008] Step S1: Using a thermal imager to collect the rotor surface temperature Tzz and the stator coil temperature Dz of the permanent magnet synchronous motor, using a voltmeter and an ohmmeter to collect the stator coil resistance ΔR and the stator coil voltage I, using an oscilloscope and a vibration sensor to collect the bearing vibration frequency xd and the bearing speed Zs, and establish a data set;

[0009] Step S2: extracting the rotor surface temperature value Tzz from the data set, calculating and obtaining the rotor demagnetization coefficient Tcd, and evaluating and analyzing the rotor demagnetization fault, thereby generating a first screening result for permanent magnet synchronous motor fault diagnosis, forming a first qualified set of permanent magnet synchronous motors;

[0010] Step S3: extracting the temperature value Dz, resistance value ΔR, and voltage value I of the stator coil of the first qualified set of the permanent magnet synchronous motor from the data set, calculating and obtaining the thermal short-circuit coefficient Dxs of the stator coil, and evaluating and analyzing the stator winding short-circuit overheating fault, thereby generating a second screening result for permanent magnet synchronous motor fault diagnosis, forming a second qualified set of the permanent magnet synchronous motor;

[0011] Step S4: extracting the bearing vibration frequency xd and the bearing speed Zs of the second qualified set of the permanent magnet synchronous motor from the data set, calculating and obtaining the bearing wear vibration coefficient Zdxs, and evaluating and analyzing the abnormal bearing wear vibration fault, thereby generating a third screening result for permanent magnet synchronous motor fault diagnosis, constituting a third qualified set of the permanent magnet synchronous motor;

[0012] Step S5: By correlating the rotor demagnetization coefficient Tcd, the stator coil thermal short-circuit coefficient Dxs, and the bearing wear vibration coefficient Zdxs, a comprehensive calculation is performed to obtain a fault diagnosis identification coefficient Sbx;

[0013] Step S6: Based on the comprehensive evaluation fault diagnosis identification coefficient Sbx, the permanent magnet synchronous motor fault is diagnosed using a neural network model, and a correct diagnosis result is output.

[0014] Specifically, the step S2 includes:

[0015] By extracting the rotor surface temperature value Tzz from the data set and performing dimensionless processing, the rotor demagnetization coefficient Tcd is calculated using the following formula:

[0016]

[0017]

[0018] Where, T i represents the temperature value of the i-th monitoring point on the rotor surface, n represents the total number of monitoring points, T avg Indicates the average value of the rotor surface temperature, T max Indicates the maximum temperature of the rotor surface, D K Indicates the demagnetization parameters.

[0019] Specifically, step S2 further includes setting a first standard threshold Q and performing a comparative analysis with the rotor demagnetization coefficient Tcd, as follows:

[0020] When the rotor demagnetization coefficient Tcd is greater than the first standard threshold Q, it indicates a rotor demagnetization fault, triggering the first warning instruction, marking a first-level fault label, and generating the first screening result of the permanent magnet synchronous motor fault diagnosis;

[0021] When the rotor demagnetization coefficient Tcd ≤ the first standard threshold Q, it indicates that there is no rotor demagnetization fault, triggering the second early warning instruction and marking the first-level screening qualified label to form the first qualified set of the permanent magnet synchronous motor.

[0022] Specifically, step S3 specifically includes: extracting the temperature value Dz of the stator coil in the first qualified set of the permanent magnet synchronous motor in the data set, and calculating and obtaining the thermal short-circuit coefficient Dxs of the stator coil after dimensionless processing, and the formula is as follows:

[0023]

[0024] Where Dz j represents the temperature value of the jth monitoring point of the stator coil, m represents the total number of stator coils, Dz avg Indicates the average temperature of the stator coil, Dz max Indicates the maximum temperature value of the stator coil, Dz min Indicates the lowest temperature value of the stator coil, I indicates the stator coil voltage value, ΔR indicates the stator coil resistance value, C r Represents the cooling parameters of the stator coil.

[0025] Specifically, step S3 further includes setting a second standard threshold value P and performing a comparative analysis with the thermal short-circuit coefficient Dxs of the stator coil, as follows:

[0026] When the thermal short-circuit coefficient Dxs of the stator coil is greater than the second standard threshold value P, it indicates a stator winding short-circuit overheating fault, triggering the third early warning instruction, marking a secondary fault label, and generating the second screening result of the permanent magnet synchronous motor fault diagnosis;

[0027] When the thermal short-circuit coefficient Dxs of the stator coil is less than or equal to the second standard threshold value P, it indicates that there is no stator winding short-circuit overheating fault, triggering the fourth early warning instruction and marking the second-level screening qualified label, forming the second qualified set of the permanent magnet synchronous motor.

[0028] Specifically, step S4 specifically includes: extracting the bearing vibration frequency xd and the bearing speed Zs of the second qualified set of the permanent magnet synchronous motor from the data set, and calculating and obtaining the bearing wear vibration coefficient Zdxs after dimensionless processing, using the following formula:

[0029]

[0030] Where Zs uIndicates the u-th collected bearing speed, xd u represents the uth collected bearing vibration frequency, b represents the total number of collections, and w1 and w2 are both weight coefficients.

[0031] Specifically, step S4 further includes setting a third standard threshold value K and performing a comparative analysis with the bearing wear vibration coefficient Zdxs, as follows:

[0032] When the bearing wear vibration coefficient Zdxs is greater than the third standard threshold value K, it indicates an abnormal bearing wear vibration fault, triggering the fifth early warning instruction, marking a third-level fault label, and generating the third screening result of permanent magnet synchronous motor fault diagnosis;

[0033] When the bearing wear vibration coefficient Zdxs ≤ the third standard threshold K, it indicates that there is no abnormal bearing wear vibration fault, triggering the sixth early warning instruction, marking the third-level screening qualified label, and forming the third qualified set of the permanent magnet synchronous motor.

[0034] Specifically, step S5 includes obtaining the permanent magnet synchronous motor fault diagnosis identification coefficient Sbx through comprehensive calculation after dimensionless processing of the rotor demagnetization coefficient Tcd, the stator coil thermal short-circuit coefficient Dxs, and the bearing wear vibration coefficient Zdxs. The formula is as follows:

[0035] Sbx=F1*Tcd+F2*Dxs+F3*Zdxs;

[0036] Where F1, F2 and F3 are weight coefficients.

[0037] Specifically, the step S6 includes: presetting a fourth standard threshold G and performing a comparative analysis with the permanent magnet synchronous motor fault diagnosis identification coefficient Sbx, as follows:

[0038] When the permanent magnet synchronous motor fault diagnosis identification coefficient Sbx>the fourth standard threshold G, it indicates that the permanent magnet synchronous motor has a fault abnormality, and a permanent magnet synchronous motor fault abnormality diagnosis result is generated.

[0039] Compared with the prior art, the present invention has the following beneficial effects:

[0040] (1) This method for diagnosing permanent magnet synchronous motor faults in wind power generation systems combines multi-source data monitoring of permanent magnet synchronous motors with a fault screening process. It completes fault screening and classification in steps, from rotor demagnetization, stator winding short-circuit overheating to bearing wear and vibration, thus achieving standardization and systematization of the diagnostic process.

[0041] (2) This method for diagnosing permanent magnet synchronous motor faults in wind power generation systems uses thermal imagers, oscilloscopes, vibration sensors, voltmeters, and resistance meters to collect data on various physical quantities, including rotor surface temperature, stator coil temperature, stator voltage and resistance, bearing vibration frequency and speed. By calculating the rotor demagnetization coefficient Tcd, stator thermal short-circuit coefficient Dxs, and bearing wear vibration coefficient Zdxs, a comprehensive analysis of the key fault parameters of the permanent magnet synchronous motor is performed, significantly improving the accuracy of fault diagnosis.

[0042] (3) This method for diagnosing permanent magnet synchronous motor faults in wind power generation systems generates a first qualified set, a second qualified set, and a third qualified set in sequence through a step-by-step screening method. It can effectively locate the fault type and its severity, provide efficient technical support for fault management, and reduce the misdiagnosis rate and missed diagnosis rate.

[0043] (4) This method for diagnosing permanent magnet synchronous motor faults in wind power generation systems comprehensively calculates fault diagnosis identification coefficients, uses neural network technology to establish an unsupervised learning model and trains the method for diagnosing permanent magnet synchronous motor faults in wind power generation systems, automatically learns the fault diagnosis method, and outputs correct diagnostic results. This method is suitable for diagnosing permanent magnet synchronous motor faults in a variety of complex working conditions and has wider applicability and reliability. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only preferred embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0045] Figure 1 The present invention provides a flow chart of a method for diagnosing permanent magnet synchronous motor faults in a wind power generation system. DETAILED DESCRIPTION

[0046] In order to make the purpose, technical solutions and advantages of the present invention more apparent, exemplary embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments of the present invention, and it should be understood that the present invention is not limited to the exemplary embodiments described herein. Based on the embodiments of the present invention described in the present invention, all other embodiments obtained by those skilled in the art without creative work should fall within the scope of protection of the present invention.

[0047] In the following description, numerous specific details are provided to provide a more thorough understanding of the present invention. However, it will be apparent to those skilled in the art that the present invention may be practiced without one or more of these details. In other instances, certain technical features well known in the art are not described to avoid confusion with the present invention.

[0048] It should be understood that the present invention can be implemented in different forms and should not be interpreted as being limited to the embodiments set forth herein. On the contrary, these embodiments are provided to make disclosure thorough and complete and to fully convey the scope of the present invention to those skilled in the art.

[0049] The purpose of the terms used herein is only to describe specific embodiments and is not intended to limit the present invention. When used herein, the singular forms "a", "an", and "the" are intended to include the plural forms, unless the context clearly indicates otherwise. It should also be understood that the terms "comprising" and / or "comprising", when used in this specification, determine the presence of the features, integers, steps, operations, elements and / or parts, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, parts and / or groups. When used herein, the term "and / or" includes any and all combinations of the relevant listed items.

[0050] In order to fully understand the present invention, a detailed structure will be provided in the following description to illustrate the technical solution proposed by the present invention. Optional embodiments of the present invention are described in detail below. However, in addition to these detailed descriptions, the present invention may also have other implementations.

[0051] See Figure 1 A method for diagnosing faults of a permanent magnet synchronous motor applied to a wind power generation system comprises the following steps:

[0052] Step S1: Using a thermal imager to collect the rotor surface temperature Tzz and the stator coil temperature Dz of the permanent magnet synchronous motor, using a voltmeter and an ohmmeter to collect the stator coil resistance ΔR and the stator coil voltage I, using an oscilloscope and a vibration sensor to collect the bearing vibration frequency xd and the bearing speed Zs, and establish a data set;

[0053] Step S2: extracting the rotor surface temperature value Tzz from the data set, calculating and obtaining the rotor demagnetization coefficient Tcd, and evaluating and analyzing the rotor demagnetization fault, thereby generating a first screening result for permanent magnet synchronous motor fault diagnosis, forming a first qualified set of permanent magnet synchronous motors;

[0054] Step S3: extracting the temperature value Dz, resistance value ΔR, and voltage value I of the stator coil of the first qualified set of the permanent magnet synchronous motor from the data set, calculating and obtaining the thermal short-circuit coefficient Dxs of the stator coil, and evaluating and analyzing the stator winding short-circuit overheating fault, thereby generating a second screening result for permanent magnet synchronous motor fault diagnosis, forming a second qualified set of the permanent magnet synchronous motor;

[0055] Step S4: extracting the bearing vibration frequency xd and the bearing speed Zs of the second qualified set of the permanent magnet synchronous motor from the data set, calculating and obtaining the bearing wear vibration coefficient Zdxs, and evaluating and analyzing the abnormal bearing wear vibration fault, thereby generating a third screening result for permanent magnet synchronous motor fault diagnosis, constituting a third qualified set of the permanent magnet synchronous motor;

[0056] Step S5: By correlating the rotor demagnetization coefficient Tcd, the stator coil thermal short-circuit coefficient Dxs, and the bearing wear vibration coefficient Zdxs, a comprehensive calculation is performed to obtain a fault diagnosis identification coefficient Sbx;

[0057] Step S6: Based on the comprehensive evaluation fault diagnosis identification coefficient Sbx, the permanent magnet synchronous motor fault is diagnosed using a neural network model, and a correct diagnosis result is output.

[0058] In this embodiment, a permanent magnet synchronous motor is positioned on a fault diagnosis test bench. Real-time monitoring of the permanent magnet synchronous motor's rotor surface temperature, stator coil temperature, stator coil voltage and resistance, bearing vibration frequency, and bearing speed is performed using a thermal imager, oscilloscope, vibration sensor, voltmeter, and resistance meter. Multi-source data, including the permanent magnet synchronous motor's rotor surface temperature Tzz, stator coil temperature Dz, stator coil resistance ΔR, stator coil voltage I, bearing vibration frequency xd, and bearing speed Zs, is collected to improve calculation accuracy. The magnetic coefficient Tcd, stator coil thermal short-circuit coefficient Dxs, and bearing wear vibration coefficient Zdxs are calculated, and faults in the permanent magnet synchronous motor are diagnosed through evaluation and analysis. A comprehensive analysis and calculation is then performed to obtain a fault diagnosis identification coefficient Sbx, which is then used to comprehensively analyze the key fault parameters of the permanent magnet synchronous motor, significantly improving fault diagnosis accuracy. The fault diagnosis identification coefficient Sbx is analyzed and evaluated and then substituted into an unsupervised learning model. It provides an efficient and reliable solution for fault diagnosis, operation monitoring and maintenance of deep learning permanent magnet synchronous motors, which has important engineering application value and promotion significance.

[0059] Specifically, the step S2 includes:

[0060] By extracting the rotor surface temperature value Tzz from the data set and performing dimensionless processing, the rotor demagnetization coefficient Tcd is calculated, which is the basis for effectively improving the accuracy of fault identification. The formula is as follows:

[0061]

[0062] Where, T i represents the temperature value of the i-th monitoring point on the rotor surface, n represents the total number of monitoring points, T avg Indicates the average value of the rotor surface temperature, T max Indicates the maximum temperature of the rotor surface, D K Indicates the demagnetization parameter, with common values ranging from -0.10% / °C to 0.13% / °C.

[0063] Specifically, step S2 further includes setting a first standard threshold Q and performing a comparative analysis with the rotor demagnetization coefficient Tcd, as follows:

[0064] When the rotor demagnetization coefficient Tcd is greater than the first standard threshold Q, it indicates a rotor demagnetization fault, triggering the first warning instruction, marking a first-level fault label, and generating the first screening result of the permanent magnet synchronous motor fault diagnosis;

[0065] When the rotor demagnetization coefficient Tcd ≤ the first standard threshold Q, it indicates that there is no rotor demagnetization fault, triggering the second early warning instruction and marking the first-level screening qualified label to form the first qualified set of the permanent magnet synchronous motor.

[0066] Specifically, step S3 specifically includes: extracting the temperature value Dz of the stator coil in the first qualified set of the permanent magnet synchronous motor in the data set, and calculating and obtaining the thermal short-circuit coefficient Dxs of the stator coil after dimensionless processing, and the formula is as follows:

[0067]

[0068] Where Dz j represents the temperature value of the jth monitoring point of the stator coil, m represents the total number of stator coils, Dz avg Indicates the average temperature of the stator coil, Dz max Indicates the maximum temperature value of the stator coil, Dz min Indicates the lowest temperature value of the stator coil, I indicates the stator coil voltage value, ΔR indicates the stator coil resistance value, C r Indicates the cooling parameters of the stator coil, and the commonly used value is 30-100W / ℃.

[0069] In this embodiment, the temperature value Dz of the stator coil of the first qualified set of the permanent magnet synchronous motor is dimensionlessly processed to obtain the thermal short-circuit coefficient Dxs of the stator coil, which effectively improves the recognition ability of complex motor fault diagnosis and meets the needs of permanent magnet synchronous motors for high-precision diagnosis under complex working conditions.

[0070] Specifically, step S3 further includes setting a second standard threshold value P and performing a comparative analysis with the thermal short-circuit coefficient Dxs of the stator coil, as follows:

[0071] When the thermal short-circuit coefficient Dxs of the stator coil is greater than the second standard threshold value P, it indicates a stator winding short-circuit overheating fault, triggering the third early warning instruction, marking a secondary fault label, and generating the second screening result of the permanent magnet synchronous motor fault diagnosis;

[0072] When the thermal short-circuit coefficient Dxs of the stator coil is less than or equal to the second standard threshold value P, it indicates that there is no stator winding short-circuit overheating fault, triggering the fourth early warning instruction and marking the second-level screening qualified label, forming the second qualified set of the permanent magnet synchronous motor.

[0073] In this embodiment, by comparing and analyzing the thermal short-circuit coefficient Dxs of the stator coil, it is evaluated whether the permanent magnet synchronous motor has a stator winding short-circuit overheating fault. After the evaluation, a secondary fault screening is performed, effectively ensuring the efficiency of fault diagnosis.

[0074] Specifically, step S4 specifically includes: extracting the bearing vibration frequency xd and the bearing speed Zs of the second qualified set of the permanent magnet synchronous motor from the data set, and calculating and obtaining the bearing wear vibration coefficient Zdxs after dimensionless processing, using the following formula:

[0075]

[0076] Where Zs u Indicates the u-th collected bearing speed, xd u represents the u-th collected bearing vibration frequency, b represents the total number of collections, w1 and w2 are both weight coefficients, 0<w1<1, 0<w2<1, and w1+w2=1.

[0077] In this embodiment, the bearing wear vibration coefficient Zdxs is calculated by the bearing vibration frequency xd and bearing speed Zs of the second qualified set of the permanent magnet synchronous motor, which provides data support for the judgment of abnormal bearing wear vibration fault of the permanent magnet synchronous motor and significantly improves the accuracy of fault diagnosis.

[0078] Specifically, step S4 further includes setting a third standard threshold value K and performing a comparative analysis with the bearing wear vibration coefficient Zdxs, as follows:

[0079] When the bearing wear vibration coefficient Zdxs is greater than the third standard threshold value K, it indicates an abnormal bearing wear vibration fault, triggering the fifth early warning instruction, marking a third-level fault label, and generating the third screening result of permanent magnet synchronous motor fault diagnosis;

[0080] When the bearing wear vibration coefficient Zdxs ≤ the third standard threshold K, it indicates that there is no abnormal bearing wear vibration fault, triggering the sixth early warning instruction, marking the third-level screening qualified label, and forming the third qualified set of the permanent magnet synchronous motor.

[0081] In this embodiment, by analyzing and evaluating the bearing wear vibration coefficient Zdxs, it is determined whether the permanent magnet synchronous motor has an abnormal bearing wear vibration fault. After the evaluation, a three-level screening of the fault is performed, providing efficient technical support for fault management.

[0082] Specifically, step S5 includes obtaining the permanent magnet synchronous motor fault diagnosis identification coefficient Sbx through comprehensive calculation after dimensionless processing of the rotor demagnetization coefficient Tcd, the stator coil thermal short-circuit coefficient Dxs, and the bearing wear vibration coefficient Zdxs. The formula is as follows:

[0083] Sbx=F1*Tcd+F2*Dxs+F3*Zdxs;

[0084] Wherein, F1, F2 and F3 are weight coefficients, 0<F1<1, 0<F2<1, 0<F3<1, and F1+F2+F3=1.

[0085] Specifically, the step S6 includes: presetting a fourth standard threshold G and performing a comparative analysis with the permanent magnet synchronous motor fault diagnosis identification coefficient Sbx, as follows:

[0086] When the permanent magnet synchronous motor fault diagnosis identification coefficient Sbx>the fourth standard threshold G, it indicates that the permanent magnet synchronous motor has a fault abnormality, and a permanent magnet synchronous motor fault abnormality diagnosis result is generated.

[0087] The permanent magnet synchronous motor fault diagnosis identification coefficient Sbx>the fourth standard threshold G indicates that the permanent magnet synchronous motor has no fault, and a permanent magnet synchronous motor no-fault diagnosis result is generated.

[0088] In this embodiment, in the previous steps, the rotor demagnetization coefficient (Tcd), stator coil thermal short-circuit coefficient (Dxs) and bearing wear vibration coefficient (Zdxs) are obtained by extracting various fault characteristics, and these characteristics are correlated and calculated to obtain the fault diagnosis identification coefficient (Sbx).

[0089] This coefficient serves as input data for the neural network model's discrimination. The neural network model consists of an input layer, hidden layers, and an output layer. The input layer receives the fault identification coefficient (Sbx). The hidden layer then propagates the information forward through each layer of the network. Each node processes the information using an activation function (such as ReLU or Sigmoid), passing it layer by layer until it reaches the output layer, which provides the fault diagnosis results.

[0090] In this embodiment, by comprehensively calculating the fault diagnosis identification coefficient Sbx, this method supports the output of diversified diagnostic results such as fault trend analysis, fault warning prompts and fault category identification, which facilitates further formulation of maintenance strategies and provides comprehensive protection for the reliability and stability of motor operation.

[0091] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A permanent magnet synchronous motor fault diagnosis method applied to a wind power generation system, characterized in that: The method comprises the following steps: Step S1: Using a thermal imager to collect the rotor surface temperature Tzz and the stator coil temperature Dz of the permanent magnet synchronous motor, using a voltmeter and an ohmmeter to collect the stator coil resistance ΔR and the stator coil voltage I, using an oscilloscope and a vibration sensor to collect the bearing vibration frequency xd and the bearing speed Zs, and establish a data set; Step S2: extracting the rotor surface temperature value Tzz from the data set, calculating and obtaining the rotor demagnetization coefficient Tcd, and evaluating and analyzing the rotor demagnetization fault, thereby generating a first screening result for permanent magnet synchronous motor fault diagnosis, forming a first qualified set of permanent magnet synchronous motors; Step S3: extracting the temperature value Dz, resistance value ΔR, and voltage value I of the stator coil of the first qualified set of the permanent magnet synchronous motor from the data set, calculating and obtaining the thermal short-circuit coefficient Dxs of the stator coil, and evaluating and analyzing the stator winding short-circuit overheating fault, thereby generating a second screening result for permanent magnet synchronous motor fault diagnosis, forming a second qualified set of the permanent magnet synchronous motor; Step S4: extracting the bearing vibration frequency xd and the bearing speed Zs of the second qualified set of the permanent magnet synchronous motor from the data set, calculating and obtaining the bearing wear vibration coefficient Zdxs, and evaluating and analyzing the abnormal bearing wear vibration fault, thereby generating a third screening result for permanent magnet synchronous motor fault diagnosis, constituting a third qualified set of the permanent magnet synchronous motor; Step S5: By correlating the rotor demagnetization coefficient Tcd, the stator coil thermal short-circuit coefficient Dxs, and the bearing wear vibration coefficient Zdxs, a comprehensive calculation is performed to obtain a fault diagnosis identification coefficient Sbx; Step S6: Based on the comprehensive evaluation fault diagnosis identification coefficient Sbx, the permanent magnet synchronous motor fault is diagnosed using a neural network model, and a correct diagnosis result is output.

2. A permanent magnet synchronous motor fault diagnosis method for a wind power generation system according to claim 1, characterized in that: The step S2 specifically includes: By extracting the rotor surface temperature value Tzz from the data set and performing dimensionless processing, the rotor demagnetization coefficient Tcd is calculated using the following formula: Where, T i represents the temperature value of the i-th monitoring point on the rotor surface, n represents the total number of monitoring points, T avg Indicates the average value of the rotor surface temperature, T ,ax Indicates the maximum temperature of the rotor surface, D K Indicates the demagnetization parameters.

3. A permanent magnet synchronous motor fault diagnosis method for a wind power generation system according to claim 2, characterized in that: The step S2 further includes setting a first standard threshold Q and performing a comparative analysis with the rotor demagnetization coefficient Tcd, as follows: When the rotor demagnetization coefficient Tcd is greater than the first standard threshold Q, it indicates a rotor demagnetization fault, triggering the first warning instruction, marking a first-level fault label, and generating the first screening result of the permanent magnet synchronous motor fault diagnosis; When the rotor demagnetization coefficient Tcd ≤ the first standard threshold Q, it indicates that there is no rotor demagnetization fault, triggering the second early warning instruction and marking the first-level screening qualified label to form the first qualified set of the permanent magnet synchronous motor.

4. A permanent magnet synchronous motor fault diagnosis method for a wind power generation system according to claim 3, characterized in that: The step S3 specifically includes: extracting the temperature value Dz of the stator coil in the first qualified set of the permanent magnet synchronous motor in the data set, and calculating and obtaining the thermal short-circuit coefficient Dxs of the stator coil after dimensionless processing, and the formula is as follows: Where Dz j represents the temperature value of the jth monitoring point of the stator coil, m represents the total number of stator coils, Dz avg Indicates the average temperature of the stator coil, Dz max Indicates the maximum temperature value of the stator coil, Dz min Indicates the lowest temperature value of the stator coil, I indicates the stator coil voltage value, ΔR indicates the stator coil resistance value, C r Represents the cooling parameters of the stator coil.

5. A permanent magnet synchronous motor fault diagnosis method for a wind power generation system according to claim 4, characterized in that: The step S3 further includes setting a second standard threshold value P and performing a comparative analysis with the thermal short-circuit coefficient Dxs of the stator coil, as follows: When the thermal short-circuit coefficient Dxs of the stator coil is greater than the second standard threshold value P, it indicates a stator winding short-circuit overheating fault, triggering the third early warning instruction, marking a secondary fault label, and generating the second screening result of the permanent magnet synchronous motor fault diagnosis; When the thermal short-circuit coefficient Dxs of the stator coil is less than or equal to the second standard threshold value P, it indicates that there is no stator winding short-circuit overheating fault, triggering the fourth early warning instruction and marking the second-level screening qualified label, forming the second qualified set of the permanent magnet synchronous motor.

6. A permanent magnet synchronous motor fault diagnosis method for a wind power generation system according to claim 5, characterized in that: The step S4 specifically includes: extracting the bearing vibration frequency xd and the bearing speed Zs of the second qualified set of the permanent magnet synchronous motor from the data set, and calculating and obtaining the bearing wear vibration coefficient Zdxs after dimensionless processing, using the following formula: Where Zs u Indicates the u-th collected bearing speed, xd u represents the uth collected bearing vibration frequency, b represents the total number of collections, and w1 and w2 are both weight coefficients.

7. A permanent magnet synchronous motor fault diagnosis method for a wind power generation system according to claim 6, characterized in that: The step S4 further includes setting a third standard threshold value K and performing a comparative analysis with the bearing wear vibration coefficient Zdxs, as follows: When the bearing wear vibration coefficient Zdxs is greater than the third standard threshold value K, it indicates an abnormal bearing wear vibration fault, triggering the fifth early warning instruction, marking a third-level fault label, and generating the third screening result of permanent magnet synchronous motor fault diagnosis; When the bearing wear vibration coefficient Zdxs ≤ the third standard threshold K, it indicates that there is no abnormal bearing wear vibration fault, triggering the sixth early warning instruction, marking the third-level screening qualified label, and forming the third qualified set of the permanent magnet synchronous motor.

8. A permanent magnet synchronous motor fault diagnosis method for a wind power generation system according to claim 7, characterized in that: The step S5 specifically includes obtaining the permanent magnet synchronous motor fault diagnosis identification coefficient Sbx by comprehensive calculation through dimensionless processing of the rotor demagnetization coefficient Tcd, the stator coil thermal short-circuit coefficient Dxs, and the bearing wear vibration coefficient Zdxs. The formula is as follows: Sbx=F1*Tcd+F2*Dxs+F3*Zdxs; Where F1, F2 and F3 are weight coefficients.

9. A permanent magnet synchronous motor fault diagnosis method for a wind power generation system according to claim 8, characterized in that: The step S6 specifically includes: presetting a fourth standard threshold G and performing a comparative analysis with the permanent magnet synchronous motor fault diagnosis identification coefficient Sbx, as follows: When the permanent magnet synchronous motor fault diagnosis identification coefficient Sbx>the fourth standard threshold G, it indicates that the permanent magnet synchronous motor has a fault abnormality, and a permanent magnet synchronous motor fault abnormality diagnosis result is generated.

Images