Motor defect detection method and device, electronic equipment, medium and program product
By integrating the multimodal data features of motor temperature, vibration, and sound, the problem of insufficient stability and accuracy in existing motor testing methods is solved, and efficient identification and accurate detection of internal defects in motors are achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- CHINA THREE GORGES CORPORATION
- Filing Date
- 2026-03-31
- Publication Date
- 2026-06-23
Smart Images
Figure CN122260104A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of motor testing technology, specifically to methods, devices, electronic equipment, media, and program products for detecting motor defects. Background Technology
[0002] As a core power device in industrial automation, energy, transportation, and equipment manufacturing, the reliability of electric motors directly affects the safety and production efficiency of the entire system. During long-term operation, factors such as load variations, mechanical wear, ambient temperature changes, and manufacturing or installation errors can easily lead to defects within the motor, including bearing wear, rotor imbalance, winding overheating, and structural loosening. Therefore, it is necessary to identify these defects to ensure safe motor operation.
[0003] In related technologies, the method for detecting motor defects relies on a single or limited number of sensing methods, such as using infrared sensors to monitor temperature changes on the surface or in localized areas of the motor to determine whether overheating is present. This method is difficult to fully reflect the complex internal operating state of the motor, resulting in insufficient stability and accuracy of the detection results. Summary of the Invention
[0004] This invention provides a method, apparatus, electronic device, medium, and program product for detecting defects in motors, in order to solve the problems of insufficient stability and accuracy of detection results in related technologies.
[0005] In a first aspect, the present invention provides a method for detecting defects in a motor, comprising: acquiring reference temperature data, reference vibration data, and reference sound data of a reference motor under various operating conditions; determining reference temperature characteristics, reference vibration characteristics, and reference sound characteristics based on the reference temperature data, reference vibration data, and reference sound data; the various operating conditions include normal operating conditions and abnormal operating conditions corresponding to various fault types; acquiring target temperature characteristics, target vibration characteristics, and target sound characteristics of a target motor under test; performing correlation analysis between the target temperature characteristics, target vibration characteristics, and target sound characteristics and their corresponding reference temperature characteristics, reference vibration characteristics, and reference sound characteristics to obtain temperature correlation coefficients, vibration correlation coefficients, and sound correlation coefficients between the target motor under test and the reference motor under each operating condition; summing the temperature correlation coefficients, vibration correlation coefficients, and sound correlation coefficients between the target motor under test and the reference motor under each operating condition to obtain a comprehensive comparison similarity between the target motor under test and the reference motor under each operating condition; and performing defect detection on the target motor under test based on the comprehensive comparison similarity between the target motor under test and the reference motor under each operating condition.
[0006] The present invention provides a method for detecting motor defects. It acquires reference temperature data, reference vibration data, and reference sound data of a reference motor under various operating conditions. Based on these reference temperature, vibration, and sound data, it determines reference temperature characteristics, reference vibration characteristics, and reference sound characteristics. This method overcomes the limitations of single-sensor data diagnosis, covers multiple types of defects, and provides a comparative basis for subsequent defect detection. The various operating conditions include normal operation and abnormal operation corresponding to various fault types, encompassing both normal state characteristics and characteristics of various fault states. The present invention acquires target temperature characteristics, target vibration characteristics, and target sound characteristics of the target motor under test. Correlation analysis is then performed between these target temperature characteristics, target vibration characteristics, and target sound characteristics and their corresponding reference temperature characteristics, reference vibration characteristics, and reference sound characteristics. This yields temperature correlation coefficients, vibration correlation coefficients, and sound correlation coefficients between the target motor under test and the reference motor under each operating condition. The matching degree of the three types of characteristics (temperature, vibration, and sound) is evaluated separately, avoiding interference between different modal data and ensuring the independence and accuracy of fault diagnosis results in each dimension. This invention sums the temperature, vibration, and sound correlation coefficients between the target motor under test and the reference motor under each operating state to obtain a comprehensive comparative similarity between the target motor under test and the reference motor under each operating state. By integrating multimodal correlation coefficients into a comprehensive similarity, this invention achieves effective fusion of multi-source information, preserving diagnostic information from each dimension while simplifying the decision-making logic. Based on the comprehensive comparative similarity between the target motor under test and the reference motor under each operating state, this invention performs defect detection on the target motor under test. Through the fusion of data features from multiple modalities, it improves the accuracy of defect detection in the target motor under test.
[0007] In one optional implementation, reference temperature data, reference vibration data, and reference sound data of a reference motor under various operating conditions are acquired. Based on the reference temperature data, reference vibration data, and reference sound data, reference temperature characteristics, reference vibration characteristics, and reference sound characteristics are determined. This includes: acquiring reference temperature data, reference vibration data, and reference sound data of the reference motor under normal operating conditions and abnormal operating conditions corresponding to various fault types; and performing multi-dimensional information processing on the reference temperature data, reference vibration data, and reference sound data to obtain the reference temperature characteristics, reference vibration characteristics, and reference sound characteristics.
[0008] In one optional implementation, the reference temperature data, reference vibration data, and reference sound data are subjected to multivariate information processing to obtain reference temperature features, reference vibration features, and reference sound features, including: extracting each frame of the reference temperature data, obtaining the feature vector of each frame of the image, and obtaining the reference temperature features; extracting the time-domain feature parameters reflecting the vibration amplitude change and wave characteristics in the reference vibration data, normalizing the time-domain feature parameters, and obtaining the reference vibration features; and extracting the sound signal feature vector of each frame of the sound data, averaging the sound signal feature vector of each frame of the sound data, and obtaining the reference sound features.
[0009] In one optional implementation, the target temperature characteristics, target vibration characteristics, and target sound characteristics of the target motor under test are obtained, including: collecting target temperature data, target vibration data, and target sound data of the target motor under test, and performing multivariate data processing on the target temperature data, target vibration data, and target sound data respectively to obtain the target temperature characteristics, target vibration characteristics, and target sound characteristics.
[0010] In one optional implementation, the target temperature feature, target vibration feature, and target sound feature are respectively correlated with the corresponding reference temperature feature, reference vibration feature, and reference sound feature to obtain the temperature correlation coefficient, vibration correlation coefficient, and sound correlation coefficient between the target motor under test and the reference motor in each operating state. This includes: performing Pearson correlation analysis on the target temperature feature and the reference temperature feature in each operating state to obtain the temperature correlation coefficient for each operating state; performing Pearson correlation analysis on the target vibration feature and the reference vibration feature in each operating state to obtain the vibration correlation coefficient for each operating state; and performing Pearson correlation analysis on the target sound feature and the reference sound feature in each operating state to obtain the sound correlation coefficient for each operating state.
[0011] In one optional implementation, defect detection is performed on the target motor under test based on the comprehensive comparison similarity between the target motor under test and the reference motor in each operating state, including: selecting the target operating state with the highest comprehensive comparison similarity among the comprehensive comparison similarities between the target motor under test and the reference motor in each operating state; using the target operating state as the operating state of the target motor under test, and performing defect detection on the target motor under test.
[0012] Secondly, the present invention provides a device for detecting motor defects, comprising: a reference feature determination module, used to acquire reference temperature data, reference vibration data, and reference sound data of a reference motor under various operating conditions, and to determine reference temperature features, reference vibration features, and reference sound features based on the reference temperature data, reference vibration data, and reference sound data; the various operating conditions include normal operating conditions and abnormal operating conditions corresponding to various fault types; a correlation analysis module, used to acquire target temperature features, target vibration features, and target sound features of a target motor under test, and to perform correlation analysis between the target temperature features, target vibration features, and target sound features and their corresponding reference temperature features, reference vibration features, and reference sound features, respectively, to obtain temperature correlation coefficients, vibration correlation coefficients, and sound correlation coefficients between the target motor under test and the reference motor under each operating condition; a comprehensive similarity determination module, used to sum the temperature correlation coefficients, vibration correlation coefficients, and sound correlation coefficients between the target motor under test and the reference motor under each operating condition, to obtain a comprehensive comparative similarity between the target motor under test and the reference motor under each operating condition; and a defect detection module, used to perform defect detection on the target motor under test based on the comprehensive comparative similarity between the target motor under test and the reference motor under each operating condition.
[0013] Thirdly, the present invention provides an electronic device, comprising: a memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to perform the motor defect detection method of the first aspect or any corresponding embodiment described above.
[0014] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to execute the method for detecting motor defects according to the first aspect or any corresponding embodiment described above.
[0015] Fifthly, the present invention provides a computer program product, including computer instructions for causing a computer to execute the method for detecting motor defects described in the first aspect or any corresponding embodiment. Attached Figure Description
[0016] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.
[0017] Figure 1This is a schematic diagram of an application scenario according to an embodiment of the present invention; Figure 2 This is a schematic flowchart of a first method for detecting motor defects according to an embodiment of the present invention; Figure 3 This is a schematic diagram of the structure of a motor defect detection device that integrates audiovisual light according to an embodiment of the present invention; Figure 4 This is a schematic diagram of a second process for detecting motor defects according to an embodiment of the present invention; Figure 5 This is a schematic diagram of the feature prototype determination process under normal conditions according to an embodiment of the present invention; Figure 6 This is a schematic diagram of the feature prototype determination process under abnormal conditions according to an embodiment of the present invention; Figure 7 This is a schematic diagram of the reference temperature characteristic determination process according to an embodiment of the present invention; Figure 8 This is a schematic diagram of the reference vibration characteristic determination process according to an embodiment of the present invention; Figure 9 This is a schematic diagram of the reference sound feature determination process according to an embodiment of the present invention; Figure 10 This is a schematic diagram of the feature comparison process according to an embodiment of the present invention; Figure 11 This is a structural block diagram of a motor defect detection device according to an embodiment of the present invention; Figure 12 This is a schematic diagram of the hardware structure of an electronic device according to an embodiment of the present invention. Detailed Implementation
[0018] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0019] It is understood that before using the technical solutions disclosed in the various embodiments of the present invention, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in the present invention and their authorization should be obtained in accordance with relevant laws and regulations through appropriate means.
[0020] As an optional application scenario of this invention, such as Figure 1 As shown, the motor defect detection system may include at least one terminal device and at least one server. Figure 1The system is illustrated in the example, which includes a computer 101, a mobile terminal 102, and a server 103, and the terminal devices such as the computer 101 and the mobile terminal 102 are connected to the server 103 through a network 110.
[0021] Specifically, the terminal device can be a smartphone, tablet, laptop, PDA, desktop computer, game console, smart TV, smart wearable device, in-vehicle terminal, VR (Virtual Reality) device, AR (Augmented Reality) device, etc. Server 103 can be a standalone physical server, a server cluster, a distributed system, or a cloud server providing cloud services. Network 110 can be a wired or wireless network, examples of which include, but are not limited to, the Internet, corporate intranet, local area network, wide area network, mobile communication network, and combinations thereof.
[0022] During long-term operation, motors are prone to defects such as bearing wear, rotor imbalance, winding overheating, and structural loosening due to factors such as load variations, mechanical wear, ambient temperature changes, and manufacturing or installation errors. These defects are often concealed in their early stages, and if not detected in time, they can easily evolve into serious malfunctions, causing equipment downtime or even safety accidents. Therefore, effective and accurate detection of potential defects inside motors is of great significance.
[0023] In related technologies, motor defect detection techniques are mostly based on single or limited sensing methods. For example, infrared sensors are used to monitor temperature changes on the motor surface or in localized areas to determine if overheating is present; ultrasonic sensors are used to collect high-frequency acoustic signals generated during motor operation to identify friction, cracks, or structural anomalies; and vibration sensors or laser vibration measuring devices are used to detect motor vibration characteristics, thereby analyzing the operating status of mechanical components. While these motor defect detection technologies are effective in their respective application scenarios, due to the limited source of sensing information, they often only reflect one aspect of the motor's operating status.
[0024] This invention provides a method for detecting motor defects, which improves the accuracy of motor defect detection by comprehensively considering multiple features.
[0025] According to an embodiment of the present invention, a method for detecting motor defects is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.
[0026] This embodiment provides a method for detecting defects in electric motors, which can be used in computer equipment. Figure 2 This is a first flowchart of a method for detecting motor defects according to an embodiment of the present invention, as follows: Figure 2 As shown, the process includes the following steps: Step S201: Obtain reference temperature data, reference vibration data, and reference sound data of the reference motor under various operating conditions. Based on the reference temperature data, reference vibration data, and reference sound data, determine the reference temperature characteristics, reference vibration characteristics, and reference sound characteristics. The various operating conditions include normal operating conditions and abnormal operating conditions corresponding to various fault types.
[0027] The various operating states include normal operating state and abnormal operating state corresponding to various fault types; the normal operating state is the operating state in which the motor does not have any faults; various fault types can be set according to actual conditions. For example, various fault types include bearing wear, stator and rotor friction, loose internal structural connections, etc.; one operating state corresponds to one reference motor, and reference temperature data, reference vibration data and reference sound data of the reference motor under various operating states are collected.
[0028] In some alternative implementations, Figure 3 This is a schematic diagram of the structure of a motor defect detection device that integrates audiovisual and optical signals according to an embodiment of the present invention. Figure 3 The device includes a housing 301 to prevent external factors from affecting the experiment, an infrared temperature sensor 302 to acquire temperature data of the motor's outer surface, a multi-point laser vibration sensor 303 to acquire vibration data of the motor during operation, a motor and sensor mounting bracket 304 to fix the motor, a sound sensor 305 to acquire sound information of the motor during operation, a motor under test 306, which can be a reference motor or a target motor under test, and a multi-data processing system 307 for performing various data processing operations.
[0029] In some alternative implementations, according to Figure 3 The infrared temperature sensor 302 acquires reference temperature data, the multi-point laser vibration sensor 303 acquires reference vibration characteristics, and the sound sensor 305 acquires reference sound characteristics.
[0030] In some optional implementations, feature extraction is performed on the reference temperature data, reference vibration data, and reference sound data to obtain reference temperature features, reference vibration features, and reference sound features.
[0031] Step S202: Obtain the target temperature characteristics, target vibration characteristics, and target sound characteristics of the target motor under test. Perform correlation analysis between the target temperature characteristics, target vibration characteristics, and target sound characteristics and the corresponding reference temperature characteristics, reference vibration characteristics, and reference sound characteristics to obtain the temperature correlation coefficient, vibration correlation coefficient, and sound correlation coefficient between the target motor under test and the reference motor under each operating state.
[0032] Among them, the target motor under test is the motor that needs to be defect-detected; the target temperature feature is the temperature feature extracted by the same process as the reference feature under the current operating state of the target motor under test; the target vibration feature is the vibration feature extracted by the same process as the reference feature under the current operating state of the target motor under test; and the target sound feature is the sound feature extracted by the same process as the reference feature under the current operating state of the target motor under test.
[0033] In some optional implementations, correlation analysis is performed between the target temperature characteristics and the reference temperature characteristics under each operating state to obtain the temperature correlation coefficient between the target motor under test and the reference motor under each operating state; correlation analysis is performed between the target vibration characteristics and the reference vibration characteristics under each operating state to obtain the vibration correlation coefficient between the target motor under test and the reference motor under each operating state; correlation analysis is performed between the target sound characteristics and the reference sound characteristics under each operating state to obtain the sound correlation coefficient between the target motor under test and the reference motor under each operating state.
[0034] Step S203: Sum the temperature correlation coefficient, vibration correlation coefficient, and sound correlation coefficient between the target motor under test and the reference motor under each operating state to obtain the comprehensive comparison similarity between the target motor under test and the reference motor under each operating state.
[0035] For example, the temperature correlation coefficient, vibration correlation coefficient, and sound correlation coefficient between the target motor under test and the reference motor under normal operation are summed to obtain the comprehensive comparison similarity between the target motor under test and the reference motor under normal operation.
[0036] Step S204: Based on the comprehensive comparison similarity between the target motor under test and the reference motor under each operating state, perform defect detection on the target motor under test.
[0037] The greater the overall similarity between the target motor under test and the reference motor, the more similar their operating states are, thus enabling the identification of defects in the target motor under test.
[0038] The motor defect detection method provided in this embodiment acquires reference temperature data, reference vibration data, and reference sound data of a reference motor under various operating conditions. Based on the reference temperature data, reference vibration data, and reference sound data, reference temperature characteristics, reference vibration characteristics, and reference sound characteristics are determined. This overcomes the limitations of single-sensor data diagnosis, covers multiple types of defects, and provides a comparative basis for subsequent defect detection. The multiple operating conditions include normal operating conditions and abnormal operating conditions corresponding to various fault types, encompassing both normal state characteristics and various fault state characteristics. This embodiment acquires target temperature characteristics, target vibration characteristics, and target sound characteristics of the target motor under test. Correlation analysis is performed between the target temperature characteristics, target vibration characteristics, and target sound characteristics and their corresponding reference temperature characteristics, reference vibration characteristics, and reference sound characteristics to obtain the temperature correlation coefficient, vibration correlation coefficient, and sound correlation coefficient between the target motor under test and the reference motor under each operating condition. The matching degree of the three types of characteristics (temperature, vibration, and sound) is evaluated separately to avoid interference between different modal data and ensure the independence and accuracy of fault diagnosis results in each dimension. This invention summarizes the temperature, vibration, and sound correlation coefficients between the target motor under test and the reference motor under each operating state to obtain a comprehensive comparative similarity between the target motor under test and the reference motor under each operating state. By integrating multimodal correlation coefficients into a comprehensive similarity, this invention achieves effective fusion of multi-source information, preserving diagnostic information from each dimension while simplifying the decision-making logic. Based on the comprehensive comparative similarity between the target motor under test and the reference motor under each operating state, this invention performs defect detection on the target motor under test. Through the fusion of data features from multiple modalities, the accuracy of defect detection in the target motor under test is improved.
[0039] This embodiment provides a method for detecting defects in electric motors, which can be used in computer equipment. Figure 4 This is a second flowchart of a method for detecting motor defects according to an embodiment of the present invention, as shown below. Figure 4 As shown, the process includes the following steps: Step S401: Obtain reference temperature data, reference vibration data, and reference sound data of the reference motor under various operating conditions. Based on the reference temperature data, reference vibration data, and reference sound data, determine the reference temperature characteristics, reference vibration characteristics, and reference sound characteristics. The various operating conditions include normal operating conditions and abnormal operating conditions corresponding to various fault types.
[0040] Specifically, step S401 includes: Step S4041: Collect reference temperature data, reference vibration data, and reference sound data of the reference motor under normal operating conditions and abnormal operating conditions corresponding to various fault types.
[0041] Specifically, the data collected includes reference temperature, reference vibration, and reference sound data of the reference motor under normal operating conditions; reference temperature, reference vibration, and reference sound data of the reference motor under bearing wear conditions; reference temperature, reference vibration, and reference sound data of the reference motor under stator-rotor friction conditions; and reference temperature, reference vibration, and reference sound data of the reference motor under loose internal structural connections.
[0042] Step S4042 involves performing multivariate information processing on the reference temperature data, reference vibration data, and reference sound data to obtain reference temperature characteristics, reference vibration characteristics, and reference sound characteristics.
[0043] In some alternative implementations, the reference motor in its normal state is mounted on a fixed bracket of the device, and the reference motor is operated under rated voltage and current. At the same time, reference temperature data, reference vibration data, and reference sound data are collected. The three types of data are processed separately to obtain the characteristic prototypes of different data, namely reference temperature characteristics, reference vibration characteristics, and reference sound characteristics.
[0044] For example, Figure 5 This is a schematic diagram of the process for determining the feature prototype under normal conditions according to an embodiment of the present invention. The temperature, sound and vibration information of the motor under normal conditions are obtained, and multi-source information processing is performed to obtain the temperature feature prototype, sound feature prototype and vibration feature prototype of the motor under normal conditions.
[0045] In some alternative implementations, a reference motor in an abnormal state (bearing wear, stator-rotor friction, loose internal structural connections) is mounted on a fixed bracket of the device, and the reference motor is operated under rated voltage and current. Temperature data, vibration data, and sound data are collected simultaneously to obtain temperature, sound, and vibration displacement information under abnormal conditions. The three types of data are processed separately to obtain the characteristic prototypes of different data, namely, reference temperature characteristics, reference vibration characteristics, and reference sound characteristics.
[0046] For example, Figure 6 This is a schematic diagram of the process for determining the feature prototype under abnormal conditions according to an embodiment of the present invention. The process involves acquiring the temperature, sound, and vibration information of the motor under abnormal conditions, performing multi-dimensional information processing, and obtaining the temperature feature prototype, sound feature prototype, and vibration feature prototype of the motor under abnormal conditions.
[0047] In some optional implementations, step S4042 above includes: Step a1: Extract each frame of the reference temperature data, obtain the feature vector of each frame, and obtain the reference temperature features.
[0048] The reference temperature data consists of video frame data collected by an infrared temperature sensor. Image preprocessing is performed, extracting each frame of the video data and cropping it to center the motor in the field of view. Feature extraction is then performed using the Histogram of Oriented Gradient (HOG) method to obtain the feature vector for each frame.
[0049] Specifically, the HOG feature extraction method involves the following steps: calculating the gradient value of each pixel in the image to obtain the gradient intensity and direction; calculating the gradient histogram, dividing the image into several 16×16 pixel cells, and statistically analyzing the feature descriptors of each cell, with each descriptor having a dimension of 1 and 9 feature values; normalizing the feature descriptors of all cells and concatenating them to obtain the feature vector of the image. Finally, averaging the feature vectors of each frame to obtain the prototype temperature feature (baseline temperature feature) under normal motor operation. δ 1. Temperature characteristics prototype (reference temperature characteristics) of the motor under abnormal operating conditions (bearing wear, stator-rotor friction, loose internal structural connections). δ 2, δ 3, and δ 4.
[0050] For example, Figure 7 This is a schematic diagram of the reference temperature feature determination process according to an embodiment of the present invention, including temperature information acquisition, image preprocessing (including single-frame image extraction and image cropping), HOG feature extraction, and obtaining a temperature feature prototype. δ 1, δ 2, δ 3, and δ 4.
[0051] Step a2: Extract time-domain feature parameters from the reference vibration data that reflect the changes in vibration amplitude and wave characteristics, and normalize the time-domain feature parameters to obtain the reference vibration characteristics.
[0052] The vibration displacement signal generated during the operation of the reference motor is acquired through a vibration sensor and continuously sampled at a preset sampling frequency of 1000 times per second to form raw vibration data. The raw vibration data is preprocessed, including removing DC components, noise suppression, and signal normalization, to reduce the impact of environmental noise and measurement errors on the vibration signal and improve signal quality. Based on the preprocessed vibration signal, time-domain feature parameters reflecting the changes in vibration amplitude and fluctuation characteristics are extracted. These time-domain feature parameters include root mean square value, peak value, peak-to-peak value, variance, kurtosis, and skewness. After normalization, vibration characteristic prototypes α1 under normal motor conditions and α2, α3, and α4 under abnormal motor conditions are obtained.
[0053] For example, Figure 8 This is a schematic diagram of the reference vibration feature determination process according to an embodiment of the present invention. Vibration information is acquired, and vibration features are extracted, including root mean square and variance, peak value and peak-to-peak value, kurtosis and skewness, to obtain vibration feature prototypes (reference vibration features) α1, α2, α3, and α4.
[0054] Step a3: Extract the sound signal feature vector of each frame of sound in the reference sound data, and calculate the average value of the sound signal feature vector of each frame of sound to obtain the reference sound features.
[0055] The system collects sound information from a reference motor during its operating state using a sound sensor. Since the motor typically covers a wide frequency range from audible to ultrasonic during operation, the sound acquisition device samples sound frequencies from 20Hz to 100kHz. To ensure sampling accuracy, 10,000 samples are taken per second. The frame length for processing the sound signal is set to 30ms, with a frame shift of 15ms. Sound signal features are acquired, including the chromagram, the log-Mel spectrogram, and the Mel-frequency cepstral coefficients (MFCCs). Each frame's chromagram has 12 feature values, the log-Mel spectrogram has 128 feature values, and the MFCCs have 40 feature values. These are sequentially extended and combined to ensure that each frame's sound feature vector has a dimension of 1 and 180 feature values (12 + 128 + 40). The average value of the feature vector corresponding to each frame of sound is calculated to obtain the sound feature prototype β1 under normal motor conditions and the sound feature prototypes β2, β3, and β4 under abnormal motor conditions.
[0056] For example, Figure 9 This is a schematic diagram of the baseline sound feature determination process according to an embodiment of the present invention. The sound information is obtained from the Huqiu (a type of sound profile), and the sound feature extraction includes energy spectrum, log-Mel spectrum and Mel frequency cepstral coefficients, to obtain the sound feature prototypes (baseline sound features) β1, β2, β3 and β4.
[0057] Step S402: Obtain the target temperature characteristics, target vibration characteristics, and target sound characteristics of the target motor under test. Perform correlation analysis between the target temperature characteristics, target vibration characteristics, and target sound characteristics and the corresponding reference temperature characteristics, reference vibration characteristics, and reference sound characteristics to obtain the temperature correlation coefficient, vibration correlation coefficient, and sound correlation coefficient between the target motor under test and the reference motor under each operating state.
[0058] Specifically, step S402 includes: Step S4021: Collect target temperature data, target vibration data, and target sound data of the target motor under test. Perform multivariate data processing on the target temperature data, target vibration data, and target sound data respectively to obtain target temperature characteristics, target vibration characteristics, and target sound characteristics.
[0059] The process involves mounting the target motor on a fixed bracket and operating it under rated voltage and current. Simultaneously, target temperature data, target vibration data, and target sound data are collected. The target temperature data, target vibration data, and target sound data are then processed separately to obtain target temperature characteristics, target vibration characteristics, and target sound characteristics.
[0060] In some optional implementations, feature extraction is performed on the target temperature data, target vibration data, and target sound data to obtain target temperature features, target vibration features, and target sound features.
[0061] Step S4022: Perform Pearson correlation analysis on the target temperature characteristics and the reference temperature characteristics under each operating condition to obtain the temperature correlation coefficient corresponding to each operating condition.
[0062] For example, the formula for determining the temperature correlation coefficient corresponding to each operating state is as follows:
[0063] in, Target temperature characteristics X With the m The temperature correlation coefficient between the reference temperature characteristics under various operating conditions, where cov is the covariance. The standard deviation of the target temperature characteristic. For the first m Reference temperature characteristics under various operating conditions The standard deviation, when m= 1 o'clock ， The running status is normal operating status, when m= 2 o'clock ， The operating state is the bearing wear operating state, when m= 3 o'clock ， The operating state is the stator-rotor friction operation state, when m= 4 o'clock ， The operating status is that the internal structural connections are loose.
[0064] Step S4023: Perform Pearson correlation analysis on the target vibration characteristics and the reference vibration characteristics under each operating condition to obtain the vibration correlation coefficient corresponding to each operating condition.
[0065]
[0066] in, Target vibration characteristics Y With the m The vibration correlation coefficient between the reference vibration characteristics under different operating conditions, where cov is the covariance. The standard deviation of the target vibration characteristics, For the first m Reference vibration characteristics under various operating conditions The standard deviation, when m= 1 o'clock ， The running status is normal operating status, when m= 2 o'clock ， The operating state is the bearing wear operating state, when m= 3 o'clock ， The operating state is the stator-rotor friction operation state, when m= 4 o'clock ， The operating status is that the internal structural connections are loose.
[0067] Step S4024: Perform Pearson correlation analysis on the target sound features and the baseline sound features under each operating state to obtain the sound correlation coefficient corresponding to each operating state.
[0068]
[0069] in, Target sound features Z With the m The sound correlation coefficient between the baseline sound features under different operating conditions, where cov is the covariance. The standard deviation of the target sound features For the first m Reference sound characteristics under various operating conditions The standard deviation, when m= 1 o'clock ， The running status is normal operating status, when m= 2 o'clock ， The operating state is the bearing wear operating state, when m= 3 o'clock ， The operating state is the stator-rotor friction operation state, when m= 4 o'clock ， The operating status is that the internal structural connections are loose.
[0070] Step S403: Sum the temperature correlation coefficient, vibration correlation coefficient, and sound correlation coefficient between the target motor under test and the reference motor under each operating condition to obtain the comprehensive comparison similarity between the target motor under test and the reference motor under each operating condition. For details, please refer to... Figure 2 Step S203 of the illustrated embodiment will not be described again here.
[0071] Step S404: Based on the comprehensive comparison similarity between the target motor under test and the reference motor under each operating state, perform defect detection on the target motor under test.
[0072] Specifically, step S404 includes: Step S4041: Select the target operating state with the highest comprehensive comparison similarity among the comprehensive comparison similarity between the target motor under test and the reference motor in each operating state.
[0073] For example, the formula for determining the overall comparison similarity is:
[0074] in, The overall similarity between the target motor under test and the reference motor under normal operating conditions is calculated. The temperature correlation coefficient between the target motor under test and the reference motor under normal operating conditions. The vibration correlation coefficient is the relationship between the target motor under test and the reference motor under normal operating conditions. The acoustic correlation coefficient between the target motor under test and the reference motor under normal operating conditions; The overall similarity between the target motor under test and a reference motor in a bearing-wear operating state is determined by comparison. The temperature correlation coefficient between the target motor under test and the reference motor under bearing wear operating conditions. The vibration correlation coefficient between the target motor under test and the reference motor under bearing wear operating conditions. The acoustic correlation coefficient between the target motor under test and the reference motor under bearing wear operating conditions; The comprehensive comparison similarity between the target motor under test and the reference motor under stator-rotor friction operation is determined. The temperature correlation coefficient between the target motor under test and the reference motor under stator-rotor frictional operation is given. The vibration correlation coefficient between the target motor under test and the reference motor under stator-rotor frictional operation is given. The acoustic correlation coefficient between the target motor under test and the reference motor under stator-rotor frictional operation; The overall similarity between the target motor under test and a reference motor operating in a state of loose internal structural connections is used for comparison. The temperature correlation coefficient between the target motor under test and the reference motor in a loosely connected internal structure operating state. The vibration correlation coefficient is defined as the relationship between the target motor under test and the reference motor in a loosely connected internal structure operating state. The sound correlation coefficient between the target motor under test and the reference motor in a loosely connected internal structure operating state.
[0075] Step S4042: The target operating state is taken as the operating state of the target motor under test, and defect detection is performed on the target motor under test.
[0076] In some alternative implementations, the magnitude of the overall similarity is compared. The greater the similarity, the more the target test motor tends to be in a certain state, thereby identifying the result of defect detection.
[0077] For example, Figure 10 This is a schematic diagram of the feature comparison process according to an embodiment of the present invention. The temperature, sound and vibration information of the test motor are obtained, multi-source information processing is performed to obtain temperature, sound and vibration features, and the temperature features, sound features and vibration features are compared with feature prototypes under normal / abnormal conditions. Based on the comprehensive comparison similarity, the defect detection results are identified.
[0078] The motor defect detection method provided in this embodiment integrates multimodal sensing information such as infrared temperature, sound, and laser vibration displacement. It comprehensively analyzes the motor's operating status in a detection environment isolated from external interference, and identifies defects based on the correlation comparison of normal and abnormal state characteristic prototypes. This fully utilizes the complementary advantages between different physical quantities, effectively improving the accuracy and stability of detecting internal motor defects such as bearing wear, stator-rotor friction, and structural loosening. Compared to existing single-signal or simple superposition detection methods, this embodiment reduces the probability of false positives and false negatives, and has higher sensitivity for identifying early and latent defects. It is suitable for online monitoring of motor operating status and intelligent defect detection.
[0079] This embodiment also provides a device for detecting motor defects, which is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.
[0080] This embodiment provides a device for detecting defects in motors, such as... Figure 11 As shown, it includes: The reference feature determination module 1101 is used to acquire reference temperature data, reference vibration data, and reference sound data of the reference motor under various operating conditions, and to determine the reference temperature features, reference vibration features, and reference sound features based on the reference temperature data, reference vibration data, and reference sound data; the various operating conditions include normal operating conditions and abnormal operating conditions corresponding to various fault types.
[0081] The correlation analysis module 1102 is used to acquire the target temperature characteristics, target vibration characteristics, and target sound characteristics of the target motor under test. The target temperature characteristics, target vibration characteristics, and target sound characteristics are then correlated with the corresponding reference temperature characteristics, reference vibration characteristics, and reference sound characteristics to obtain the temperature correlation coefficient, vibration correlation coefficient, and sound correlation coefficient between the target motor under test and the reference motor under each operating state.
[0082] The comprehensive similarity determination module 1103 is used to sum the temperature correlation coefficient, vibration correlation coefficient and sound correlation coefficient between the target motor under test and the reference motor under each operating state to obtain the comprehensive comparison similarity between the target motor under test and the reference motor under each operating state.
[0083] The defect detection module 1104 is used to detect defects in the target motor under test based on the comprehensive comparison similarity between the target motor under test and the reference motor under each operating state.
[0084] In some optional implementations, the reference feature determination module 1101 includes: The historical data acquisition unit is used to collect reference temperature data, reference vibration data, and reference sound data of the reference motor under normal operating conditions and abnormal operating conditions corresponding to various fault types.
[0085] The data processing unit is used to perform multi-source information processing on the reference temperature data, reference vibration data, and reference sound data to obtain reference temperature characteristics, reference vibration characteristics, and reference sound characteristics.
[0086] In some optional implementations, the data processing unit includes: The reference temperature feature determination subunit is used to extract each frame of the reference temperature data, obtain the feature vector of each frame, and obtain the reference temperature features.
[0087] The reference vibration characteristic determination sub-unit is used to extract time-domain characteristic parameters reflecting vibration amplitude changes and wave characteristics from the reference vibration data, and to normalize the time-domain characteristic parameters to obtain the reference vibration characteristics.
[0088] The reference sound feature determination subunit is used to extract the sound signal feature vector of each frame of sound in the reference sound data, and to calculate the average value of the sound signal feature vector of each frame of sound to obtain the reference sound features.
[0089] In some optional implementations, the correlation analysis module 1102 includes: The test data acquisition unit is used to acquire target temperature data, target vibration data, and target sound data of the target motor under test. It performs multivariate data processing on the target temperature data, target vibration data, and target sound data to obtain target temperature characteristics, target vibration characteristics, and target sound characteristics.
[0090] The temperature correlation coefficient determination unit is used to perform Pearson correlation analysis on the target temperature characteristics and the reference temperature characteristics under each operating condition to obtain the temperature correlation coefficient corresponding to each operating condition.
[0091] The vibration correlation coefficient determination unit is used to perform Pearson correlation analysis on the target vibration characteristics and the reference vibration characteristics under each operating condition to obtain the vibration correlation coefficient corresponding to each operating condition.
[0092] The sound correlation coefficient determination unit is used to perform Pearson correlation analysis on the target sound features and the reference sound features under each operating state to obtain the sound correlation coefficient corresponding to each operating state.
[0093] In some alternative implementations, the defect detection module 1104 includes: The target operating state determination unit is used to select the target operating state with the highest comprehensive comparison similarity among the comprehensive comparison similarity between the target motor under test and the reference motor in each operating state.
[0094] The defect detection unit is used to take the target operating state as the operating state of the target motor under test and perform defect detection on the target motor under test.
[0095] The motor defect detection device provided in this embodiment of the invention can execute the motor defect detection method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects for executing the method. Further functional descriptions of the various modules and units described above are the same as in the corresponding embodiments described above, and will not be repeated here.
[0096] Figure 12 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention.
[0097] The following is a detailed reference. Figure 12The diagram illustrates a structural schematic suitable for implementing an electronic device according to embodiments of the present invention. The electronic device may include a processor (e.g., a central processing unit, graphics processor, etc.) 1201, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 1202 or a program loaded from memory 1208 into random access memory (RAM) 1203. The RAM 1203 also stores various programs and data required for the operation of the electronic device. The processor 1201, ROM 1202, and RAM 1203 are interconnected via a bus 1204. An input / output (I / O) interface 1205 is also connected to the bus 1204.
[0098] Typically, the following devices can be connected to I / O interface 1205: input devices 1206 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 1207 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; memory devices 1208 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1209. Communication device 1209 allows electronic devices to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 12 Electronic devices with various devices are shown, but it should be understood that it is not required to implement or have all of the devices shown, and more or fewer devices may be implemented or have instead.
[0099] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 1209, or installed from a memory 1208, or installed from a ROM 1202. When the computer program is executed by the processor 1201, it performs the functions defined in the motor defect detection method of the embodiments of the present invention.
[0100] Figure 12 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments of the present invention.
[0101] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code. When the software or computer code is accessed and executed by the computer, processor, or hardware, the method for detecting motor defects shown in the above embodiments is implemented.
[0102] A portion of this invention can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to the invention through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.
[0103] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.
Claims
1. A method for detecting defects in an electric motor, characterized in that, The method includes: The system acquires reference temperature data, reference vibration data, and reference sound data of a reference motor under various operating conditions. Based on the reference temperature data, reference vibration data, and reference sound data, it determines the reference temperature characteristics, reference vibration characteristics, and reference sound characteristics. The various operating conditions include normal operating conditions and abnormal operating conditions corresponding to various fault types. The target temperature characteristics, target vibration characteristics, and target sound characteristics of the target motor under test are obtained. Correlation analysis is performed between the target temperature characteristics, target vibration characteristics, and target sound characteristics and the corresponding reference temperature characteristics, reference vibration characteristics, and reference sound characteristics, respectively, to obtain the temperature correlation coefficient, vibration correlation coefficient, and sound correlation coefficient between the target motor under test and the reference motor in each of the operating states. The temperature correlation coefficient, vibration correlation coefficient, and sound correlation coefficient between the target motor under test and the reference motor under each of the operating states are summed to obtain the comprehensive comparison similarity between the target motor under test and the reference motor under each of the operating states. Defect detection is performed on the target motor under test based on the comprehensive comparison similarity between the target motor under test and the reference motor in each of the operating states.
2. The method according to claim 1, characterized in that, The process of acquiring reference temperature data, reference vibration data, and reference sound data of a reference motor under various operating conditions, and determining reference temperature characteristics, reference vibration characteristics, and reference sound characteristics based on the reference temperature data, reference vibration data, and reference sound data, includes: Collect the reference temperature data, reference vibration data, and reference sound data of the reference motor under the normal operating state and the abnormal operating state corresponding to various fault types; The reference temperature data, the reference vibration data, and the reference sound data are processed using multi-source information processing to obtain the reference temperature features, the reference vibration features, and the reference sound features.
3. The method according to claim 2, characterized in that, The reference temperature data, reference vibration data, and reference sound data are processed using multi-source information processing to obtain the reference temperature features, reference vibration features, and reference sound features, including: Extract each frame of the reference temperature data, obtain the feature vector of each frame of the image, and obtain the reference temperature features; Extract time-domain feature parameters reflecting vibration amplitude changes and wave characteristics from the reference vibration data, and normalize the time-domain feature parameters to obtain the reference vibration characteristics; Extract the sound signal feature vector of each frame of sound in the reference sound data, and calculate the average value of the sound signal feature vector of each frame of sound to obtain the reference sound features.
4. The method according to any one of claims 1 to 3, characterized in that, The acquisition of the target temperature characteristics, target vibration characteristics, and target sound characteristics of the target motor under test includes: The target temperature data, target vibration data, and target sound data of the target motor under test are collected. Multivariate data processing is performed on the target temperature data, the target vibration data, and the target sound data to obtain the target temperature characteristics, the target vibration characteristics, and the target sound characteristics.
5. The method according to any one of claims 1 to 3, characterized in that, The step of performing correlation analysis between the target temperature feature, the target vibration feature, and the target sound feature and the corresponding reference temperature feature, reference vibration feature, and reference sound feature, respectively, to obtain the temperature correlation coefficient, vibration correlation coefficient, and sound correlation coefficient between the target motor under test and the reference motor in each of the operating states, includes: Pearson correlation analysis was performed on the target temperature characteristics and the reference temperature characteristics under each of the operating states to obtain the temperature correlation coefficients corresponding to each of the operating states. Pearson correlation analysis was performed on the target vibration characteristics and the reference vibration characteristics under each of the operating states to obtain the vibration correlation coefficient corresponding to each of the operating states; Pearson correlation analysis is performed on the target sound features and the reference sound features in each of the operating states to obtain the sound correlation coefficient corresponding to each of the operating states.
6. The method according to any one of claims 1 to 3, characterized in that, The step of performing defect detection on the target motor under test based on the comprehensive comparison similarity between the target motor under test and the reference motor in each of the operating states includes: Among the comprehensive comparison similarity between the target motor under test and the reference motor in each of the operating states, the target operating state with the largest comprehensive comparison similarity is selected; The target operating state is used as the operating state of the target motor under test, and defect detection is performed on the target motor under test.
7. A device for detecting defects in an electric motor, characterized in that, The device includes: The reference feature determination module is used to acquire reference temperature data, reference vibration data, and reference sound data of the reference motor under various operating conditions, and to determine reference temperature features, reference vibration features, and reference sound features based on the reference temperature data, the reference vibration data, and the reference sound data; the various operating conditions include normal operating conditions and abnormal operating conditions corresponding to various fault types. The correlation analysis module is used to acquire the target temperature characteristics, target vibration characteristics, and target sound characteristics of the target motor under test, and to perform correlation analysis between the target temperature characteristics, target vibration characteristics, and target sound characteristics and the corresponding reference temperature characteristics, reference vibration characteristics, and reference sound characteristics, respectively, to obtain the temperature correlation coefficient, vibration correlation coefficient, and sound correlation coefficient between the target motor under test and the reference motor in each of the operating states. The comprehensive similarity determination module is used to sum the temperature correlation coefficient, vibration correlation coefficient and sound correlation coefficient between the target motor under test and the reference motor in each of the operating states to obtain the comprehensive comparison similarity between the target motor under test and the reference motor in each of the operating states. The defect detection module is used to detect defects in the target motor under test based on the comprehensive comparison similarity between the target motor under test and the reference motor in each of the operating states.
8. An electronic device, characterized in that, include: The device includes a memory and a processor, which are communicatively connected to each other. The memory stores computer instructions, and the processor executes the computer instructions to perform the method for detecting motor defects according to any one of claims 1 to 6.
9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to perform the method for detecting motor defects according to any one of claims 1 to 6.
10. A computer program product, characterized in that, Includes computer instructions for causing a computer to execute the method for detecting motor defects according to any one of claims 1 to 6.