Motor insulation diagnosis method and device based on multi-physics field data fusion

Abstract

The invention relates to the technical field of motor measurement, in particular to a motor insulation diagnosis method and device based on multi-physical field data fusion, and the method comprises the steps: collecting a multi-dimensional physical quantity signal related to insulation degradation; extracting a plurality of characteristic parameters representing the insulation state according to the multi-dimensional physical quantity signal; and inputting the plurality of characteristic parameters into a pre-constructed insulation health assessment model to output an insulation health index, and performing motor safety early warning under the condition that the insulation health index is greater than a preset index, the insulation health assessment model is constructed based on a pre-established mapping relation between the multi-dimensional characteristic parameters and the insulation health state. Therefore, the problems that the real health state of motor insulation cannot be reflected in time and the potential insulation breakdown risk cannot be early warned due to inaccurate insulation degradation identification caused by single general feature acquisition and one-sided diagnosis mode in related technologies are solved.

Description

Technical Field

[0001] This application relates to the field of motor measurement technology, and in particular to a method and device for motor insulation diagnosis based on multi-physics data fusion. Background Technology

[0002] During long-term operation, the insulation system of an electric motor is subjected to the combined effects of thermal aging, electrical stress, mechanical vibration, and humidity, which can lead to problems such as decreased insulation resistance, increased dielectric loss, and premature partial discharge.

[0003] In related technologies, insulation diagnostic methods mainly rely on insulation resistance testing, dielectric loss testing, or partial discharge detection. The degree of insulation degradation can be determined by measuring changes in insulation parameters, thereby assessing the insulation status of the motor.

[0004] However, related technologies generally suffer from problems such as single feature extraction and one-sided diagnostic methods in the insulation diagnosis process, which makes it impossible to accurately identify early insulation degradation. Moreover, the diagnostic results are easily affected by changes in operating conditions and environmental noise, resulting in unstable judgment of insulation deterioration characteristics. They cannot accurately reflect the actual health status of motor insulation and are difficult to warn of potential insulation breakdown risks in a timely manner, which urgently needs to be solved. Summary of the Invention

[0005] This application provides a method and apparatus for diagnosing motor insulation based on multi-physics data fusion, in order to solve the problem in related technologies that, due to the common single feature acquisition and one-sided diagnostic methods of insulation diagnosis, it is easy to lead to inaccurate identification of insulation degradation, thus failing to reflect the true health status of motor insulation and warn of potential insulation breakdown risks in a timely manner.

[0006] The first aspect of this application provides a method for diagnosing motor insulation based on multi-physics data fusion, comprising the following steps: acquiring multi-dimensional physical quantity signals related to insulation degradation; extracting multiple feature parameters characterizing the insulation state based on the multi-dimensional physical quantity signals; inputting the multiple feature parameters into a pre-constructed insulation health assessment model to output an insulation health index, and issuing a motor safety warning when the insulation health index is greater than a preset index, wherein the insulation health assessment model is constructed based on a pre-established mapping relationship between multi-dimensional feature parameters and insulation health state.

[0007] Through the above technical means, the embodiments of this application can obtain an insulation health index through multi-dimensional physical quantity signals and a pre-built insulation health assessment model, which can realize the quantitative assessment of the insulation status of the motor, identify early signs of deterioration, and issue timely safety warnings in conjunction with a graded early warning strategy. At the same time, by fusing and analyzing different types of physical signals, a comprehensive perception of the insulation system can be achieved, and data support can be provided for root cause analysis, thereby assisting maintenance personnel in carrying out targeted maintenance and operation optimization, and improving the reliability and safety of the motor.

[0008] Optionally, in one embodiment of this application, the acquisition of multi-dimensional physical quantity signals related to insulation degradation includes: acquiring multiple multi-source signals from partial discharge signals, dielectric property signals, cooling dielectric property signals, and operating condition and environmental signals; and generating the multi-dimensional physical quantity signals based on the multiple multi-source signals.

[0009] Through the above technical means, the embodiments of this application can obtain multi-dimensional physical quantity signals based on partial discharge signals, dielectric characteristic signals, cooling dielectric characteristic signals, operating conditions and environmental signals, which can comprehensively characterize the operating status and degradation characteristics of the motor insulation system, providing a reliable data foundation for subsequent feature extraction, insulation health assessment model analysis and early warning.

[0010] Optionally, in one embodiment of this application, the method further includes: identifying the root cause and confidence level based on the fault feature pattern database and the plurality of feature parameters; and generating insulation health index status and root cause analysis recommendations based on the root cause and the confidence level.

[0011] Through the above technical means, the embodiments of this application can perform matching analysis on the collected multi-dimensional insulation characteristic parameters based on the fault characteristic mode database, which can identify the root cause of motor insulation degradation and its corresponding confidence level. By comparing the historical fault modes and the current characteristic deviation, it can accurately determine whether the insulation degradation is caused by partial discharge abnormality, high temperature aging, humidity intrusion or other factors, providing maintenance personnel with a clear source of fault and risk assessment, thereby guiding targeted maintenance measures and preventive interventions.

[0012] Optionally, in one embodiment of this application, the step of inputting the plurality of feature parameters into a pre-constructed insulation health assessment model to output an insulation health index includes: calculating the insulation health index based on the insulation health assessment model using a lightweight gradient boosting tree regression model and feature vectors obtained from the plurality of feature parameters, including average discharge quantity, number of discharges, dielectric loss factor, insulation resistance, coolant conductivity, and winding temperature.

[0013] Through the above technical means, the embodiments of this application can calculate the insulation health index based on the insulation health assessment model and the lightweight gradient boosting tree regression model, which can realize the quantitative assessment of the insulation status of the motor, efficiently integrate signals with different physical properties, accurately reflect the degree of insulation degradation, and realize early anomaly identification and health status classification warning.

[0014] Optionally, in one embodiment of this application, the step of providing motor safety warning includes: matching alarm categories according to the insulation health index; determining alarm actions and alarm objects according to the alarm categories; and issuing an alarm to the alarm object according to the alarm action.

[0015] Through the above technical means, the embodiments of this application can match alarm categories according to the insulation health index and trigger corresponding alarms, which can realize graded prompts for different degrees of insulation degradation, timely detect potential risks, and provide operation and maintenance personnel with clear processing priorities and decision-making basis, thereby guiding targeted maintenance and operation optimization, and improving the reliability and safety of motor operation.

[0016] A second aspect of this application provides a motor insulation diagnostic device based on multi-physics data fusion, comprising: an acquisition module for acquiring multi-dimensional physical quantity signals related to insulation degradation; an extraction module for extracting multiple feature parameters characterizing the insulation state based on the multi-dimensional physical quantity signals; and a diagnostic module for inputting the multiple feature parameters into a pre-constructed insulation health assessment model to output an insulation health index, and for issuing a motor safety warning when the insulation health index is greater than a preset index, wherein the insulation health assessment model is constructed based on a pre-established mapping relationship between the multi-dimensional feature parameters and the insulation health state.

[0017] Optionally, in one embodiment of this application, the acquisition module includes: an acquisition unit for acquiring multiple multi-source signals from partial discharge signals, dielectric property signals, cooling dielectric property signals, and operating condition and environmental signals; and a generation unit for generating the multi-dimensional physical quantity signals based on the multiple multi-source signals.

[0018] Optionally, in one embodiment of this application, it further includes: an identification module, used to identify the root cause and confidence level based on the fault feature pattern database and according to the plurality of feature parameters; and a generation module, used to generate insulation health index status and root cause analysis suggestions based on the root cause and the confidence level.

[0019] Optionally, in one embodiment of this application, the diagnostic module includes: a calculation unit, used to calculate the insulation health index based on the insulation health assessment model, using a lightweight gradient boosting tree regression model and the feature vectors obtained from the plurality of feature parameters, including average discharge quantity, number of discharges, dielectric loss factor, insulation resistance, coolant conductivity, and winding temperature.

[0020] Optionally, in one embodiment of this application, the diagnostic module includes: a matching unit, configured to match alarm categories according to the insulation health index; and an alarm unit, configured to determine alarm actions and alarm objects according to the alarm categories, and to send an alarm to the alarm objects according to the alarm actions.

[0021] A third aspect of this application provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor. The processor executes the program to implement the motor insulation diagnosis method based on multiphysics data fusion as described in the above embodiments.

[0022] A fourth aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method for diagnosing motor insulation based on multiphysics data fusion.

[0023] The fifth aspect of this application provides a vehicle including the above-described motor insulation diagnostic device, electronic device, or computer-readable storage medium based on multi-physics data fusion, for implementing the above-described motor insulation diagnostic method based on multi-physics data fusion.

[0024] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0025] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein: Figure 1 This is a flowchart of a motor insulation diagnosis method based on multiphysics data fusion provided in an embodiment of this application; Figure 2 This is a flowchart of a motor insulation diagnosis method based on multiphysics data fusion according to an embodiment of this application; Figure 3 This is a block diagram of a motor insulation diagnostic device based on multiphysics data fusion according to an embodiment of this application; Figure 4 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application.

[0026] Figure label: 10-Motor insulation diagnostic device based on multi-physics field data fusion; 100-Acquisition module, 200-Extraction module, 300-Diagnosis module; 401-Memory, 402-Processor, 403-Communication interface. Detailed Implementation

[0027] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0028] The following description, with reference to the accompanying drawings, illustrates a motor insulation diagnosis method and apparatus based on multi-physics data fusion, according to embodiments of this application. Addressing the technical problem mentioned in the background art—that related technologies generally rely on single-feature acquisition and one-sided diagnostic methods, easily leading to inaccurate identification of insulation degradation and thus failing to reflect the true health status of motor insulation and warn of potential insulation breakdown risks in a timely manner—this application provides a motor insulation diagnosis method based on multi-physics data fusion. In this method, multiple characteristic parameters representing the insulation state are extracted and input into a pre-constructed insulation health assessment model to output an insulation health index. Motor safety warnings are also set. This method allows for the fusion analysis of parameters with different physical properties, enabling a comprehensive perception of the insulation system's health status. This allows for early warning of insulation degradation and root cause analysis to identify possible degradation modes and fault sources. Simultaneously, it transforms the insulation state from qualitative judgment to quantitative assessment and sets graded warning strategies based on the health index, achieving precise responses to different degrees of insulation deterioration. This provides direct and effective decision support for maintenance personnel, guiding targeted maintenance and operational optimization, improving motor operational reliability, reducing fault risks, and extending equipment lifespan. This solves the problem that the limited acquisition of general characteristics and one-sided diagnostic methods of related technologies can easily lead to inaccurate identification of insulation degradation, thus failing to reflect the true health status of motor insulation and warn of potential insulation breakdown risks in a timely manner.

[0029] Specifically, Figure 1 This is a flowchart illustrating a method for diagnosing motor insulation based on multiphysics data fusion, provided in an embodiment of this application.

[0030] like Figure 1 As shown, the motor insulation diagnosis method based on multi-physics data fusion includes the following steps: In step S101, multi-dimensional physical quantity signals related to insulation degradation are acquired.

[0031] In the embodiments of this application, the multi-dimensional physical quantity signals may include electrical parameter signals such as phase voltage, phase current, and zero-sequence voltage that reflect the electrical characteristics of motor operation, or ultrasonic signals and ultra-high frequency partial discharge signals that reflect the characteristics of local insulation breakdown, as well as temperature signals and vibration signals that reflect the state of insulation under heat and stress. The acquisition methods include, but are not limited to, using voltage sensors, current sensors, high-frequency current transformers, high-speed data acquisition cards, etc.

[0032] The acquisition method and multi-dimensional physical quantity signals can be set by those skilled in the art according to the actual situation, and no specific restrictions are imposed here.

[0033] Optionally, in one embodiment of this application, the acquisition of multi-dimensional physical quantity signals related to insulation degradation includes: acquiring multiple multi-source signals from partial discharge signals, dielectric property signals, cooling dielectric property signals, and operating condition and environmental signals; and generating multi-dimensional physical quantity signals based on the multiple multi-source signals.

[0034] In some cases, PD (Partial Discharge) signals can be captured as nanosecond-level discharge pulses using high-frequency current transformers or capacitively coupled sensors, with sampling frequencies ≥100MHz. Dielectric characteristic signals can be acquired using integrated dielectric characteristic testing units to obtain the dielectric loss factor (Tanδ) and IR (Insulation Resistance). Cooling medium characteristic signals can be monitored in real time using a built-in coolant conductivity sensor to check the coolant conductivity and trace water content. Operating condition and environmental signals can be simultaneously acquired, such as motor winding temperature, motor operating voltage, and current, as auxiliary criteria.

[0035] All sensor data can be synchronously acquired through a unified high-speed data acquisition card to ensure data consistency over time.

[0036] As a specific example, this embodiment of the application can use 100ms as a basic acquisition cycle, and synchronously acquire PD signals (sampling rate can be 100MHz), winding temperature, vibration signals, etc. in each cycle; furthermore, this embodiment of the application can start dielectric property measurement and calculation every 10 cycles to obtain the dielectric loss factor Tanδ and insulation resistance IR value; wherein, the coolant conductivity and trace water content sensors output a reading every 1 second, and all data are stamped with a unified timestamp to achieve time alignment and synchronous processing of multi-source data, thereby ensuring that different physical quantity signals can accurately correspond to the same operating time in the insulation state analysis and feature extraction process.

[0037] In step S102, multiple feature parameters characterizing the insulation state are extracted based on the multidimensional physical quantity signals.

[0038] As one possible approach, for PD signals, embodiments of this application can calculate the average discharge quantity (q) and the number of discharges (n) within one cycle; for dielectric loss factor Tanδ, insulation resistance IR, and coolant conductivity, their measured values ​​can be directly recorded.

[0039] Specifically, for PD feature extraction, embodiments of this application can extract statistical features such as discharge quantity (q), discharge phase (φ), and discharge frequency (n) from the PD pulse signal; for dielectric feature extraction, embodiments of this application can record insulation resistance (IR), dielectric loss factor (Tanδ), and their variation gradient; for coolant feature extraction, embodiments of this application can record the values ​​and trends of conductivity and trace water content; for auxiliary feature extraction, embodiments of this application can record the average value and peak value of temperature and vibration, etc.; these can be set by those skilled in the art according to actual conditions, and no specific limitations are made here.

[0040] In step S103, multiple feature parameters are input into a pre-built insulation health assessment model to output an insulation health index. If the insulation health index is greater than a preset index, a motor safety warning is issued. The insulation health assessment model is constructed based on a pre-established mapping relationship between multi-dimensional feature parameters and insulation health status.

[0041] In the embodiments of this application, the pre-constructed insulation health assessment model can employ a machine learning-based data fusion algorithm to establish a mapping relationship between multi-dimensional feature parameters and insulation health status. Under healthy motor conditions, a sufficient number of feature vector samples can be collected to establish a Gaussian distribution health model for each feature parameter. This allows for the quantification of the normal fluctuation range of each feature parameter. During motor operation, the degree of deviation from the insulation status is assessed by comparing the model with real-time features, thus achieving quantitative assessment of insulation health and early warning of degradation. The insulation health index can be a quantitative indicator obtained by fusing the deviations of multiple insulation feature parameters, and can be used to reflect the overall health status of the motor insulation system.

[0042] It can be noted that the preset index can be 90%, and the preset health index threshold can be set to 90%. It can also be set according to the specific motor type, operating conditions and insulation material characteristics, so as to achieve sensitive early warning and reliable judgment of insulation degradation in practical applications.

[0043] Optionally, in one embodiment of this application, multiple feature parameters are input into a pre-constructed insulation health assessment model to output an insulation health index, including: calculating the insulation health index based on the insulation health assessment model using a lightweight gradient boosting tree regression model and feature vectors obtained from multiple feature parameters, such as average discharge quantity, number of discharges, dielectric loss factor, insulation resistance, coolant conductivity, and winding temperature.

[0044] Among them, the lightweight gradient boosting tree regression model can be used to establish the mapping relationship between insulation feature parameters and insulation health index. It can generate multiple weak regression trees through iteration, and each tree is optimized based on the residual of the previous round, thereby gradually improving the overall prediction accuracy.

[0045] Specifically, the embodiments of this application can incorporate a LightGBM (Light Gradient Boosting Decision Tree) regression model, which can take the average discharge quantity q, the number of discharges n, the dielectric loss factor Tanδ, the insulation resistance IR, the coolant conductivity, and the winding temperature as inputs, and output an IHI (Insulation Health Index) of 0-100%.

[0046] For example, IHI=100% can indicate perfect insulation, while IHI=0% can indicate complete failure.

[0047] Optionally, in one embodiment of this application, motor safety early warning includes: matching alarm categories according to insulation health index; determining alarm actions and alarm objects according to alarm categories; and sending an alarm to the alarm object according to the alarm action.

[0048] Furthermore, embodiments of this application can monitor online, inputting the extracted feature parameters into the trained model in real time to calculate the IHI value in real time.

[0049] As one possible implementation method, the embodiments of this application can set alarm thresholds, such as IHI>90% health, IHI<90% warning alarm, and IHI<80% danger alarm.

[0050] Meanwhile, after each warning is triggered, this embodiment of the application can record the feature vector pattern of the warning; if a certain pattern (for example, a significant increase in coolant conductivity always precedes a decrease in IHI) is found to occur frequently, this embodiment of the application can automatically increase the feature importance weight of coolant conductivity in the LightGBM model, thereby making subsequent warnings of coolant contamination more sensitive.

[0051] Optionally, in one embodiment of this application, the method further includes: identifying the root cause and confidence level based on a fault feature pattern database and multiple feature parameters; and generating insulation health index status and root cause analysis recommendations based on the root cause and confidence level.

[0052] In actual implementation, when the IHI value triggers an alarm, the embodiments of this application can initiate a root cause analysis process, which can infer the most likely cause of insulation degradation based on a fault characteristic mode database.

[0053] First, as shown in Table 1, the embodiments of this application can construct a fault characteristic mode library: based on historical data, experimental data, or physical knowledge, a corresponding relationship library is established between different degradation modes (such as corona aging, overheating aging, moisture absorption, and contamination) and changes in multiple characteristic parameters (such as a sharp increase in PD, an increase in Tanδ, a decrease in IR, and an increase in conductivity). Table 1 is a multi-parameter characteristic mode table for typical faults.

[0054] Table 1

[0055] Secondly, when an early warning occurs, this application embodiment can analyze which feature parameters have significantly changed and match them with the fault feature pattern library to calculate the matching degree with various degradation patterns. For example, when an alarm occurs, this application embodiment can calculate the cosine similarity between the current feature vector and each fault pattern in the pattern library, and select the fault pattern with the highest similarity as the root cause diagnosis result.

[0056] Finally, the embodiments of this application can output the most likely root cause of degradation and its confidence level, such as determining that the probability of partial discharge abnormality leading to insulation deterioration is 85%, or determining that the probability of long-term high-temperature operation causing insulation dielectric aging is 70%, thereby providing maintenance personnel with clear guidance on the cause of failure and risk quantification reference, and realizing targeted maintenance and preventive intervention.

[0057] like Figure 2 As shown below, a specific example will be used to further illustrate the motor insulation diagnosis method based on multi-physics data fusion according to the embodiments of this application; it may include the following steps: In step S201, multi-source signals are acquired synchronously.

[0058] First, the embodiments of this application can synchronously acquire multiple source signals during the operation of the motor, including but not limited to partial discharge signals, dielectric characteristic signals, cooling medium characteristic signals, and operating condition and environmental signals, etc.

[0059] In step S202, multi-dimensional feature extraction is performed.

[0060] Then, the embodiments of this application can preprocess and synchronize the collected signals, extract various feature parameters, and construct multi-source feature vectors.

[0061] In step S203, insulation health assessment and early warning are performed.

[0062] Next, the embodiments of this application can compare the data with samples in the health benchmark model database, use the insulation health assessment model to perform fusion analysis on each characteristic parameter, thereby calculating and outputting the insulation health index (IHI), and making early warning decisions based on the set threshold.

[0063] In step S204, root cause analysis is performed.

[0064] Furthermore, embodiments of this application can identify possible root causes of insulation degradation and their confidence levels by comparing fault feature pattern databases and combining multi-parameter pattern matching analysis.

[0065] In step S205, the Insulation Health Index (IHI) status and root cause analysis recommendations are output to provide a basis for operation and maintenance decisions and preventive maintenance.

[0066] According to the multi-physics data fusion-based motor insulation diagnosis method proposed in this application, multiple characteristic parameters representing the insulation state are extracted and input into a pre-constructed insulation health assessment model to output an insulation health index and set motor safety warnings. This method can perform fusion analysis on parameters with different physical properties, enabling a comprehensive perception of the insulation system's health status. This allows for early warning of insulation degradation, root cause analysis, and identification of possible degradation modes and fault sources. Simultaneously, it transforms the insulation state from qualitative judgment to quantitative assessment and sets graded warning strategies based on the health index, achieving precise responses to different degrees of insulation deterioration. This provides direct and effective decision support for maintenance personnel, guiding targeted maintenance and operational optimization, improving motor reliability, reducing fault risks, and extending equipment lifespan.

[0067] Next, referring to the accompanying drawings, we describe the motor insulation diagnostic device based on multi-physics data fusion proposed according to the embodiments of this application.

[0068] Figure 3 This is a block diagram of a motor insulation diagnostic device based on multi-physics data fusion according to an embodiment of this application.

[0069] like Figure 3 As shown, the motor insulation diagnostic device 10 based on multi-physics data fusion includes: an acquisition module 100, an extraction module 200, and a diagnostic module 300.

[0070] The acquisition module 100 is used to acquire multi-dimensional physical quantity signals related to insulation degradation.

[0071] The extraction module 200 is used to extract multiple feature parameters characterizing the insulation state based on multi-dimensional physical quantity signals.

[0072] The diagnostic module 300 is used to input multiple feature parameters into a pre-built insulation health assessment model to output an insulation health index. When the insulation health index is greater than a preset index, a motor safety warning is issued. The insulation health assessment model is constructed based on a pre-established mapping relationship between multi-dimensional feature parameters and insulation health status.

[0073] Optionally, in one embodiment of this application, the acquisition module 100 includes: an acquisition unit and a generation unit.

[0074] The acquisition unit is used to acquire multiple multi-source signals, including partial discharge signals, dielectric property signals, cooling dielectric property signals, and operating condition and environmental signals.

[0075] The generation unit is used to generate multi-dimensional physical quantity signals based on multiple multi-source signals.

[0076] Optionally, in one embodiment of this application, it further includes an identification module and a generation module.

[0077] The identification module is used to identify the root cause and confidence level based on a fault feature pattern database and multiple feature parameters.

[0078] The generation module is used to generate insulation health index status and root cause analysis recommendations based on root causes and confidence levels.

[0079] Optionally, in one embodiment of this application, the diagnostic module 300 includes a calculation unit.

[0080] The calculation unit is used to calculate the insulation health index based on the insulation health assessment model, using a lightweight gradient boosting tree regression model and feature vectors obtained from multiple feature parameters, such as average discharge quantity, discharge number, dielectric loss factor, insulation resistance, coolant conductivity, and winding temperature.

[0081] Optionally, in one embodiment of this application, the diagnostic module includes a matching unit and an alarm unit.

[0082] The matching unit is used to match alarm categories based on the insulation health index.

[0083] The alarm unit is used to determine the alarm action and alarm object according to the alarm category, and to send an alarm to the alarm object according to the alarm action.

[0084] It should be noted that the foregoing explanation of the embodiment of the motor insulation diagnosis method based on multi-physics field data fusion also applies to the motor insulation diagnosis device based on multi-physics field data fusion in this embodiment, and will not be repeated here.

[0085] According to the multi-physics data fusion-based motor insulation diagnostic device proposed in this application, multiple characteristic parameters representing the insulation state are extracted and input into a pre-constructed insulation health assessment model to output an insulation health index and set motor safety warnings. This device can perform fusion analysis on parameters with different physical properties, enabling comprehensive perception of the insulation system's health status. It provides early warnings of early insulation degradation, performs root cause analysis, and identifies possible degradation modes and fault sources. Simultaneously, it transforms the insulation state from qualitative judgment to quantitative assessment and sets graded warning strategies based on the health index, achieving precise responses to different degrees of insulation deterioration. This provides direct and effective decision support for maintenance personnel, guiding targeted maintenance and operational optimization, improving motor operational reliability, reducing fault risks, and extending equipment lifespan.

[0086] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device may include: The memory 401, the processor 402, and the computer program stored on the memory 401 and capable of running on the processor 402.

[0087] When the processor 402 executes the program, it implements the motor insulation diagnosis method based on multi-physics data fusion provided in the above embodiments.

[0088] Furthermore, electronic devices also include: Communication interface 403 is used for communication between memory 401 and processor 402.

[0089] The memory 401 is used to store computer programs that can run on the processor 402.

[0090] Memory 401 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0091] If the memory 401, processor 402, and communication interface 403 are implemented independently, then the communication interface 403, memory 401, and processor 402 can be interconnected via a bus to complete communication between them. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of representation, Figure 4 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0092] Optionally, in a specific implementation, if the memory 401, processor 402, and communication interface 403 are integrated on a single chip, then the memory 401, processor 402, and communication interface 403 can communicate with each other through an internal interface.

[0093] Processor 402 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0094] This embodiment also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method for diagnosing motor insulation based on multi-physics data fusion.

[0095] This application also provides a vehicle, including the above-mentioned motor insulation diagnostic device based on multi-physics data fusion, or electronic device, or computer-readable storage medium, to implement the motor insulation diagnostic method based on multi-physics data fusion provided in this application.

[0096] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0097] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0098] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0099] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0100] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, it can be implemented using any one or more of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0101] Those skilled in the art will understand that all or part of the steps of the methods described in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it includes one or a combination of the steps of the method embodiments.

[0102] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0103] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. A method for diagnosing motor insulation based on multi-physics data fusion, characterized in that, Includes the following steps: Acquire multi-dimensional physical quantity signals related to insulation degradation; Multiple feature parameters characterizing the insulation state are extracted based on the multidimensional physical quantity signals; The multiple feature parameters are input into a pre-built insulation health assessment model to output an insulation health index. If the insulation health index is greater than a preset index, a motor safety warning is issued. The insulation health assessment model is constructed based on a pre-established mapping relationship between multi-dimensional feature parameters and insulation health status.

2. The method according to claim 1, characterized in that, The acquisition of multi-dimensional physical quantity signals related to insulation degradation includes: It collects multiple multi-source signals from partial discharge signals, dielectric property signals, cooling dielectric property signals, and operating condition and environmental signals; The multidimensional physical quantity signal is generated based on the multiple multi-source signals.

3. The method according to claim 1, characterized in that, Also includes: Based on the fault feature pattern database, the root cause and confidence level are identified according to the multiple feature parameters; Based on the stated root cause and the stated confidence level, an insulation health index status and root cause analysis recommendations are generated.

4. The method according to claim 1, characterized in that, The step of inputting the multiple feature parameters into a pre-built insulation health assessment model to output an insulation health index includes: Based on the insulation health assessment model, the insulation health index is calculated using a lightweight gradient boosting tree regression model and the feature vectors obtained from the multiple feature parameters, including average discharge quantity, discharge number, dielectric loss factor, insulation resistance, coolant conductivity, and winding temperature.

5. The method according to claim 1, characterized in that, The aforementioned motor safety warning includes: Alarm categories are matched based on the insulation health index. The alarm action and alarm object are determined according to the alarm category, and an alarm is sent to the alarm object according to the alarm action.

6. A motor insulation diagnostic device based on multi-physics data fusion, characterized in that, include: The acquisition module is used to acquire multi-dimensional physical quantity signals related to insulation degradation; The extraction module is used to extract multiple feature parameters characterizing the insulation state based on the multi-dimensional physical quantity signals; The diagnostic module is used to input the multiple feature parameters into a pre-built insulation health assessment model to output an insulation health index, and to issue a motor safety warning when the insulation health index is greater than a preset index. The insulation health assessment model is constructed based on a pre-established mapping relationship between multi-dimensional feature parameters and insulation health status.

7. The apparatus according to claim 6, characterized in that, The acquisition module includes: The acquisition unit is used to acquire multiple multi-source signals, including partial discharge signals, dielectric property signals, cooling dielectric property signals, and operating condition and environmental signals. The generation unit is used to generate the multidimensional physical quantity signal based on the plurality of multi-source signals.

8. An electronic device, characterized in that, include: The memory, the processor, and the computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the motor insulation diagnosis method based on multiphysics data fusion as described in any one of claims 1-5.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to implement the motor insulation diagnosis method based on multiphysics data fusion as described in any one of claims 1-5.

10. A vehicle, characterized in that, The vehicle includes the motor insulation diagnostic device based on multiphysics data fusion as described in claims 6-7, or the electronic device as described in claim 8, or the computer-readable storage medium as described in claim 9.

Images