Motor operation energy efficiency detection method and device

Abstract

The present disclosure provides a method and device for detecting motor energy efficiency, belonging to the field of motor detection technology. The method comprises: determining multiple normal samples and multiple abnormal samples of motor operating parameters based on a clustering algorithm; performing sample expansion on the multiple abnormal samples based on the sample characteristics of the multiple abnormal samples to obtain multiple expanded abnormal samples; training a state detection model based on the multiple normal samples and the multiple expanded abnormal samples, and detecting the motor operating state to be detected based on the trained state detection model. The method and device for detecting motor energy efficiency provided by the present disclosure can improve the accuracy of motor energy efficiency detection.

Description

Technical Field

[0001] The present disclosure belongs to the field of motor detection technology, and more specifically, relates to a method and device for detecting the energy efficiency of motor operation. Background Art

[0002] In modern industrial production and daily life, motors, as key devices that convert electrical energy into mechanical energy, are widely used in various scenarios. From the operation of large-scale factory machinery to the normal operation of household appliances, motors are everywhere. The operating status of motors directly affects the overall performance, production efficiency, and operational safety of the equipment.

[0003] Considering that the abnormal detection of motor operation depends on a large number of abnormal samples, but in practical applications the sample size of abnormal samples is insufficient, the existing motor operation energy efficiency detection method has the problem of low accuracy, which affects the stability of motor operation. Summary of the Invention

[0004] The purpose of the present disclosure is to provide a method and device for detecting the energy efficiency of a motor operation, so as to improve the accuracy of the detection of the energy efficiency of the motor operation.

[0005] According to a first aspect of the present disclosure, a method for detecting energy efficiency of a motor is provided, comprising:

[0006] Determine multiple normal samples and multiple abnormal samples of motor operating parameters based on a clustering algorithm;

[0007] performing sample expansion on the multiple abnormal samples according to the sample features of the multiple abnormal samples to obtain multiple expanded abnormal samples;

[0008] The state detection model is trained based on the multiple normal samples and the multiple expanded abnormal samples, and the motor operation energy efficiency is determined by detecting the motor operation state to be detected according to the trained state detection model.

[0009] According to a second aspect of the present disclosure, a motor energy efficiency detection device is provided, comprising:

[0010] A sample determination module, configured to determine a plurality of normal samples and a plurality of abnormal samples of motor operating parameters based on a clustering algorithm;

[0011] A sample expansion module, configured to expand the plurality of abnormal samples according to the sample features of the plurality of abnormal samples to obtain a plurality of expanded abnormal samples;

[0012] The detection model construction module is used to train the state detection model based on the multiple normal samples and the multiple expanded abnormal samples, and detect the motor operation state to be detected according to the trained state detection model to determine the motor operation energy efficiency.

[0013] According to a third aspect of an embodiment of the present disclosure, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of the above-mentioned motor operation energy efficiency detection method when executing the computer program.

[0014] According to a fourth aspect of the embodiments of the present disclosure, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned motor operation energy efficiency detection method are implemented.

[0015] The beneficial effects of the motor operation energy efficiency detection method and device provided by the embodiments of the present disclosure are:

[0016] The present disclosure uses a clustering algorithm to screen samples, which can accurately distinguish between normal and abnormal samples, classify motor operating parameters according to characteristics, and provide a reliable data basis for subsequent state detection. Compared with traditional manual judgment, it is more objective and accurate, and effectively avoids interference from human factors. At the same time, the present disclosure greatly enriches the diversity and quantity of abnormal data by expanding abnormal samples. In practice, abnormal samples are relatively scarce. After expansion, the state detection model can learn more potential fault modes, effectively improving the adaptability and fault diagnosis ability of the model. Finally, the present disclosure uses normal samples and expanded abnormal samples to train the model, which enables the model to learn more comprehensive and accurate motor operating state characteristics. When the model training is completed, when the operating state of the motor to be detected is detected, the operating state of the motor to be detected can be more accurately detected. Based on the operating state of the motor, the change in the motor operating energy efficiency can be accurately judged. Therefore, the present disclosure can improve the accuracy of motor operating energy efficiency detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0018] Figure 1 A flow chart of a method for detecting motor energy efficiency according to an embodiment of the present disclosure;

[0019] Figure 2This is a structural block diagram of a motor operation energy efficiency detection device provided by an embodiment of the present disclosure;

[0020] Figure 3 A schematic block diagram of an electronic device provided in one embodiment of the present disclosure. DETAILED DESCRIPTION

[0021] In the following description, specific details such as specific system structures and techniques are provided for purposes of illustration rather than limitation to facilitate a thorough understanding of the embodiments of the present disclosure. However, it will be apparent to those skilled in the art that the present disclosure may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid obscuring the description of the present disclosure with unnecessary detail.

[0022] In order to make the purpose, technical solutions and advantages of the present disclosure more clear, specific embodiments will be described below with reference to the accompanying drawings.

[0023] Please refer to Figure 1 , Figure 1 This is a flow chart of a method for detecting motor energy efficiency according to an embodiment of the present disclosure, the method comprising:

[0024] S101: Determine multiple normal samples and multiple abnormal samples of motor operating parameters based on a clustering algorithm.

[0025] In this embodiment, a clustering algorithm is an unsupervised learning algorithm used to divide data points in a dataset into different groups or clusters based on similarity. The clustering algorithm can group data points based on the similarity of the characteristics of the motor operating parameters. For example, the K-Means clustering algorithm can determine the cluster to which each data point belongs by calculating the distance between the data point and each cluster center.

[0026] Motor operating parameters are quantitative values that reflect the motor's operating status, including but not limited to motor temperature, noise, and vibration, as well as line voltage, current, power metering, and power quality. Changes in these parameters can help determine whether the motor is operating properly.

[0027] Normal samples are data samples consisting of the motor's operating parameters under normal operating conditions. The motor's operating parameters in normal samples should fall within the standard range for normal motor operation. For example, during normal operation, the motor's current fluctuates within a certain range of the rated current, and the temperature is within the normal operating temperature range.

[0028] Abnormal samples are data samples consisting of the corresponding operating parameters when the motor is faulty or operating abnormally. The values of the operating parameters in abnormal samples may exceed the normal standard range, or the relationship between the operating parameters may not conform to the rules of normal operation. For example, when a motor winding short circuits, the current will suddenly increase. The corresponding abnormal samples can record this abnormal current value and changes in other related parameters.

[0029] Specifically, in this embodiment, the motor operating parameter data over a period of time is first collected. The above data can be collected in real time by various sensors installed on the motor (such as current sensors, temperature sensors, acceleration sensors, etc.); then, the above data is used as input and processed by a clustering algorithm. The clustering algorithm will divide the above motor operating parameters into different clusters based on the similarity between the data.

[0030] S102: Expand the plurality of abnormal samples according to their sample features to obtain a plurality of expanded abnormal samples.

[0031] In this embodiment, the sample characteristics of the abnormal sample are various characteristics contained in the abnormal sample that can reflect the abnormal operating state of the motor. The above characteristics can be special values of a single motor operating parameter, abnormal relationships between motor operating parameters, or changing trends of motor operating parameters over time, etc.

[0032] Sample expansion involves generating more samples with similar characteristics to existing real abnormal samples through data expansion methods, thereby increasing the number and diversity of abnormal samples and providing richer data for subsequent model training. The data expansion method used in this embodiment can be a generative adversarial network.

[0033] This example first analyzes multiple existing abnormal samples to identify their common or representative sample features. It then uses these sample features and employs appropriate data augmentation methods to generate new samples. These newly generated samples share similar features with the existing samples, and are aggregated to ultimately obtain augmented abnormal samples.

[0034] Assume that this example has identified a set of abnormal motor operation samples, specifically motor bearing failures. The sample characteristics are primarily reflected in the motor's vibration acceleration parameters. While the amplitude of a normal motor's vibration acceleration is between 0 and 5 m / s², these abnormal samples have amplitudes between 10 and 20 m / s², and the vibration acceleration frequency peaks between 100 and 200 Hz.

[0035] To expand the sample, this embodiment can use methods such as data interpolation and random noise addition. For example, for the vibration acceleration amplitude, new values are randomly generated within the range of 10-20 m / s²; for the frequency peak, new frequency peak positions are generated between 100-200 Hz according to a certain probability distribution (such as a normal distribution).

[0036] Assume there are 10 original abnormal samples. Using the above method, each sample generates 3 new samples, resulting in 30 expanded abnormal samples. These expanded samples also reflect the abnormal characteristics of vibration acceleration amplitude and frequency peak when the motor bearing fails, providing richer data for subsequent state detection model training.

[0037] S103: Training a state detection model based on multiple normal samples and multiple expanded abnormal samples, and detecting the motor operating state to be detected according to the trained state detection model to determine the motor operating energy efficiency.

[0038] In this embodiment, the input set consists of multiple normal samples and multiple expanded abnormal samples, and the output is the corresponding motor operating state. The state detection model is a model used to identify the motor operating state and can be constructed based on machine learning or deep learning, such as a support vector machine or neural network. The state detection model learns the characteristics of normal and abnormal samples to establish a judgment criterion for distinguishing normal operating states from abnormal operating states. A trained state detection model is a state detection model that has been trained and, after testing and verification evaluation, has an accuracy greater than or equal to a preset threshold.

[0039] The motor operating state to be detected is the current state of the motor that needs to be judged in actual applications. The operating parameters of the motor are collected in real time through multiple sensors, and then the above parameters are input into the state detection model to determine whether the motor is in normal operation.

[0040] The large number of collected normal samples and expanded abnormal samples are used as training data and fed into the state detection model. During the training process, the state detection model adjusts its parameters (such as the weights and biases in the neural network) based on the characteristics of these samples, continuously learning the differences between normal and abnormal samples, thereby building a judgment model that can accurately distinguish between normal and abnormal operating states.

[0041] Once the state detection model has been trained to a certain level of accuracy and stability, it is considered a trained state detection model. Multiple sensors are used to obtain real-time operating parameters of the actual motor, which are then fed into the trained state detection model. Based on the learned characteristic patterns, the state detection model outputs a judgment indicating whether the motor's current operating status is normal or abnormal.

[0042] Training phase:

[0043] This example assumes that a multilayer perceptron (MLP) is used as the state detection model. 1,000 normal samples were collected, in which the motor current was between 95% and 105% of the rated current, the voltage was between 98% and 102% of the rated voltage, and the speed was stable within ±3% of the rated speed. Furthermore, 500 abnormal samples were expanded to cover the operating parameter characteristics of different fault types, including motor overload (e.g., current exceeding 120% of the rated current), winding short circuit (e.g., current rising sharply and three-phase current imbalance), and bearing fault (e.g., significant increase in vibration).

[0044] These normal and abnormal samples are divided into training and validation sets according to a specific ratio (e.g., 80% for training and 20% for validation). The training set is input into the MLP model, with the number of nodes in the input layer set to the same as the number of motor operating parameters (assuming there are five parameters, such as current, voltage, speed, temperature, and vibration). The model has two hidden layers, with 10 and 8 nodes per layer, respectively. The output layer has 1 node (indicating normal or abnormal judgment, with 0 representing normal and 1 representing abnormal). During training, the stochastic gradient descent algorithm is used to continuously adjust the model's weights and biases, continuously improving the model's prediction accuracy on the training set. After multiple iterations of training, the model is considered trained when its accuracy on the validation set reaches above 95%.

[0045] Detection phase:

[0046] For a running motor, multiple sensors installed on the motor collect real-time parameters such as current, voltage, speed, temperature, and vibration. Assume the collected parameters are: current is 110% of the rated current, voltage is 99% of the rated voltage, speed is 98% of the rated speed, temperature is 10°C higher than normal operating temperature, and vibration exceeds the normal range by twice. These parameters are input into the trained MLP model.

[0047] The model calculated and output a value of 1, indicating that the motor was operating abnormally. Further analysis revealed that the abnormal characteristics of its current, temperature, and vibration values matched those of abnormal samples of overload and bearing failure in the training set. This suggests that the motor may be experiencing overload and bearing failure, necessitating timely maintenance and repair.

[0048] Therefore, the motor operating state is detected according to the trained state detection model to obtain the detection result of the motor operating state;

[0049] If the detection result of the motor operating state is normal operation, the motor operating energy efficiency is stable;

[0050] If the detection result of the motor operation state is abnormal operation, the fault type of the motor operation is determined, and based on the fault type, the motor operation energy efficiency is determined to be reduced.

[0051] When the motor operates normally, the motor's operating energy efficiency is better and is in a relatively stable state, and can operate efficiently; when the motor operates abnormally, the motor's operating energy efficiency decreases and the loss increases.

[0052] From the above, it can be concluded that the present disclosure is based on clustering algorithm to screen samples, which can accurately distinguish normal and abnormal samples, classify motor operating parameters according to characteristics, and provide a reliable data basis for subsequent state detection. Compared with traditional manual judgment, it is more objective and accurate, and effectively avoids the interference of human factors. At the same time, the present disclosure greatly enriches the diversity and quantity of abnormal data by expanding abnormal samples. In practice, abnormal samples are relatively scarce. After expansion, the state detection model can learn more potential fault modes, effectively improving the adaptability and fault diagnosis ability of the model. Finally, the present disclosure uses normal samples and expanded abnormal samples to train the model, which enables the model to learn more comprehensive and accurate motor operating state characteristics. When the model training is completed, when the operating state of the motor to be detected is detected, the operating state of the motor to be detected can be more accurately detected. Based on the operating state of the motor, the change of the motor operating energy efficiency can be accurately judged. Therefore, the present disclosure can improve the accuracy of motor operating energy efficiency detection.

[0053] In one embodiment of the present disclosure, the motor operating parameters include multiple types of operating parameters;

[0054] Multiple normal samples and multiple abnormal samples of motor operating parameters are determined based on the clustering algorithm, including:

[0055] Clustering is performed based on the parameter characteristics of each type of operating parameters to obtain clustering results corresponding to each type of operating parameters. The clustering results include a normal sample set and an abnormal sample set.

[0056] The normal sample sets corresponding to each type of operating parameters are aggregated to obtain multiple normal samples;

[0057] The abnormal sample sets corresponding to each type of operating parameters are aggregated to obtain multiple abnormal samples.

[0058] In this embodiment, the multiple operating parameters refer to motor operating parameters encompassing a variety of different properties, not just a single type. Each parameter type has its own unique characteristics and patterns of variation. Parameter characteristics are the characteristics and properties of each operating parameter type, including the parameter's value range, variation trend, and fluctuation pattern. For example, the current parameter characteristics may fluctuate within a small range around the rated current during normal operation, but may rise or fall sharply during a fault.

[0059] This embodiment uses a clustering algorithm to group each type of operating parameter. Each type of operating parameter includes normal operating parameters and abnormal operating parameters. The clustering algorithm can divide each type of operating parameter into different clusters based on the similarity between normal operating parameters and abnormal operating parameters, so that the data within the same cluster has high similarity, while the data between different clusters has large differences.

[0060] The normal sample set corresponding to each type of operating parameter is a set of samples of the normal operating state of the motor. In this sample set, the corresponding motor operating parameters are all within the normal range, which meets the characteristics of the normal operation of the motor.

[0061] The abnormal sample set corresponding to each type of operating parameter is a sample set when the motor is in an abnormal operating state. The motor operating parameters corresponding to this sample set deviate from the normal range and show abnormal or fault characteristics.

[0062] Specifically, the steps of this embodiment are as follows:

[0063] First, for each type of motor operating parameter (such as current, voltage, and speed), its parameter characteristics are analyzed separately and then processed using a clustering algorithm. After clustering, the data for each operating parameter type is divided into different groups. One group represents the sample set of normal motor operation, the normal sample set; the other group represents the sample set of abnormal motor operation, the abnormal sample set. For example, for the motor temperature parameter, the clustering algorithm classifies data within the normal temperature range as the normal sample set based on temperature fluctuations, while data outside the normal range, showing abnormal increases or decreases, is classified as the abnormal sample set.

[0064] Second, the normal sample sets obtained after clustering each operating parameter category are combined. Because each normal sample set contains only normal samples for that parameter category, through set operations, all normal samples can be combined to form a sample set containing information on the normal status of multiple motor operating parameters. This set is called multiple normal samples. For example, by combining the normal current sample set, the normal voltage sample set, and the normal speed sample set, a sample set can be obtained that comprehensively reflects the status of each parameter during normal motor operation.

[0065] Third, by combining the abnormal sample sets obtained after clustering each type of operating parameter, we can obtain a sample set containing information on abnormal conditions of multiple motor operating parameters, that is, multiple abnormal samples. For example, by combining the abnormal current sample set, abnormal temperature sample set, abnormal speed sample set, etc., we can form a sample set that comprehensively reflects various abnormal operating conditions of the motor.

[0066] Assume that the motor operating parameters include current, voltage and speed.

[0067] For current parameters, we collected current data over a period of time. The characteristic of this parameter is that it fluctuates between 95% and 105% of the rated current during normal operation. We clustered this current data using a hierarchical clustering algorithm, classifying data within the 95%-105% rated current range as a normal sample set and data outside this range as an abnormal sample set.

[0068] For voltage parameters, during normal operation, the voltage is between 98% and 102% of the rated voltage. Similarly, using the hierarchical clustering algorithm, voltage data within this range is classified as a normal sample set, and the rest as an abnormal sample set.

[0069] For the speed parameter, the speed is stable within ±3% of the rated speed during normal operation. Through clustering, the speed data that falls within this range is classified as the normal sample set, and those that exceed the range are classified as the abnormal sample set.

[0070] Next, the normal samples of current, voltage, and speed are combined to generate multiple normal samples, which comprehensively reflect the current, voltage, and speed states of the motor during normal operation. The abnormal samples of current, voltage, and speed are combined to generate multiple abnormal samples, which cover various abnormalities in the motor's current, voltage, and speed. For example, an abnormal sample may include information about different types of abnormal conditions, such as excessive current, low voltage, and unstable speed.

[0071] As can be seen from the above, this embodiment can systematically analyze multiple types of motor operating parameters and accurately distinguish between normal and abnormal motor operating conditions through clustering. This embodiment not only improves the accuracy and efficiency of fault detection, but also provides reliable data support for subsequent motor maintenance and management. In addition, this method avoids the limitations of traditional methods that rely on manual experience and judgment, and realizes automated and intelligent detection of motor operating conditions, which is of great significance for ensuring stable motor operation and preventing potential failures.

[0072] In one embodiment of the present disclosure, clustering processing is performed based on the parameter characteristics of each type of operating parameters to obtain clustering results corresponding to each type of operating parameters, including:

[0073] Determine multiple cluster centers;

[0074] Determining the distance between each type of operating parameter and the operating parameters of the multiple cluster centers based on the first distance measurement method to obtain multiple first distances;

[0075] A clustering result corresponding to each type of operating parameter is determined based on the multiple first distances.

[0076] In this embodiment, the cluster center is the representative point of each cluster. In the data space, the cluster center can be regarded as a data point, and its coordinate value represents the average feature or typical feature of the cluster data.

[0077] The first distance measurement method is a calculation formula for measuring the degree of difference between two data points. In this embodiment, the first distance measurement method is used to measure the difference between each type of operating parameter of the motor and the operating parameter of the cluster center.

[0078] Assume the motor has Class running parameters are For each type of operating parameters , the value in a certain period of time is , is the number of samples, and the corresponding parameter value of the cluster center is .

[0079] First, calculate the sum of the squares of the Euclidean distances between each type of operating parameter and the cluster center. Class operating parameters, the calculation formula of Euclidean distance is:

[0080]

[0081] in, Indicates the Class operating parameters The sample value of Indicates the Class operating parameters The value of the cluster center.

[0082] Considering the different importance of different types of operating parameters to the judgment of the motor operating status, weights are set for each type of operating parameter. , The weight setting can be determined based on the actual operation of the motor and experience. For example, the current parameter is more sensitive to motor faults, and its weight can be set relatively high.

[0083] At the same time, considering the correlation between motor operating parameters, the correlation coefficient adjustment term is introduced. The average correlation coefficient of the class operating parameter with all other class operating parameters , and the average correlation coefficient of the corresponding parameters of the cluster center Correlation coefficient The calculation formula is:

[0084]

[0085] in, Indicates the Motor operating parameters of the class, Indicates the Motor operating parameters of the class , represents the number of samples, Indicates the Class operating parameters Sample values, Indicates the Class operating parameters Sample values, Indicates the The mean of the sample values of the class running parameter, Indicates the The mean of the sample values of the class run parameter.

[0086] The calculation formula of the first distance metric as follows:

[0087]

[0088] in, represents the adjustment coefficient, , used to measure the impact of the Euclidean distance and correlation coefficient adjustment terms. When it is close to 1, it focuses more on the influence of Euclidean distance; when When it is close to 0, the correlation coefficient adjustment term has a greater effect.

[0089] In this embodiment, the weight is set , the calculation formula of the first distance metric can differentiate the importance of judging the motor operating status according to different operating parameters. For example, when judging whether the motor is overloaded, the current parameter is more critical than the temperature parameter. Therefore, a larger weight can be set for the current parameter so that the first distance metric can better reflect the characteristics related to overload. The correlation coefficient adjustment item is introduced to take into account that the motor operating parameters do not exist in isolation, but are interrelated. For example, when the motor load increases, the current and speed usually show a certain correlation change. By comparing the correlation coefficient difference between the operating parameters and the corresponding parameters of the cluster center, the similarity between the sample and the cluster center can be more comprehensively measured, thereby improving the accuracy of clustering. Adjustment coefficient The existence of can flexibly adjust the relative importance of Euclidean distance and correlation coefficient adjustment items in distance measurement according to actual conditions. In the case of strong correlation between motor operating parameters, it can be appropriately reduced. When the parameter correlation is weak, increase To highlight the influence of Euclidean distance.

[0090] For example, weight The setting of is based on the prior knowledge of the importance of different operating parameters. For example, the importance of current parameter to the motor operating status judgment is greater than that of temperature parameter, and the importance of temperature parameter to the motor operating status judgment is greater than that of speed parameter, so the weight of current parameter is set to , the weight of the temperature parameter is , the weight of the speed parameter is This weight distribution allows the first distance metric to more reasonably reflect the contribution of each parameter to the overall distance. Large deviations in the current parameter will have a greater impact on the distance calculation due to its larger weight, which is consistent with the fact that current parameters are more critical for determining the motor's operating status in real-world situations.

[0091] The sum of the squares of the Euclidean distances between each type of operating parameter and the cluster center measures the degree of dispersion of the sample points from the cluster center in each dimension of the motor operating parameter. Taking the current parameter as an example, the smaller the sum of the squares of the Euclidean distances, the closer the current parameter values of the sample are to the current values of the cluster center overall, that is, the higher the similarity of the sample with the cluster center in the current dimension. The Euclidean distance itself has good mathematical properties and is an intuitive distance measurement method that can accurately reflect the geometric distance between two points in space. Among the multi-dimensional parameters of motor operating parameters such as current, temperature, and speed, the Euclidean distance can comprehensively consider the differences in each dimension, thereby providing a comprehensive measurement standard for the distance between the sample and the cluster center.

[0092] The correlation coefficient measures the linear correlation between different operating parameters. During motor operation, different parameters often have certain correlations. For example, current and temperature may have a certain positive correlation due to factors such as heat generation caused by the motor's internal resistance. By calculating the average correlation coefficient and the average correlation coefficient of the parameters corresponding to the cluster centers, we can consider the impact of the mutual relationship between the parameters on the distance metric. When the correlation between the parameters of a sample differs significantly from the correlation between the parameters of the cluster centers, the correlation coefficient adjustment term will increase the first distance metric accordingly. For example, if the correlation between the current and temperature of a sample is significantly different from the correlation between the current and temperature of the cluster center, this indicates that the sample's operating mode is significantly different from the typical mode represented by the cluster center. The correlation coefficient adjustment term can more keenly capture this difference, thereby improving the first distance metric's ability to identify sample anomalies or differences. Therefore, the combination of Euclidean distance and correlation coefficient can improve the reliability and accuracy of motor operating status judgment.

[0093] The adjustment coefficient balances the proportion of the weighted Euclidean distance and the correlation coefficient adjustment item in the entire distance metric. By adjusting the value of the adjustment coefficient, the performance of the first distance measurement formula can be optimized according to the data characteristics of the motor operating parameters and the actual operating scenario of the motor. For example, when the distribution of the motor operating parameter data is mainly affected by the discrete degree of the parameter value itself, and the correlation between the motor operating parameters is relatively stable, the importance of the Euclidean distance part in the first distance metric can be appropriately increased; on the contrary, when the correlation change between the motor operating parameters is more critical to the abnormality detection of each sample point, the role of the correlation coefficient adjustment item should be highlighted. The above-mentioned dynamic adjustment of the adjustment coefficient based on the actual situation of the motor operation can adapt to different application scenarios and improve the reliability of the judgment of the motor operating status.

[0094] This embodiment uses a first distance metric to calculate the distance between each type of operating parameter and the operating parameters of multiple cluster centers. The resulting series of distance values are multiple first distances. The clustering results are the result of dividing the data points into different clusters after processing by the clustering algorithm. In clustering motor operating parameters, the clustering results indicate which operating parameters belong to the normal sample set and which belong to the abnormal sample set.

[0095] As can be seen from the above, the determination of multiple cluster centers in this embodiment provides a benchmark for subsequent distance calculations, ensuring the diversity and representativeness of the clusters. This embodiment uses the first distance metric to accurately calculate the distance between each type of operating parameter and the cluster center, making the clustering results more closely aligned with the actual data distribution. Ultimately, the clustering results determined based on the first distance not only help identify similarities and differences between parameters but also provide strong support for subsequent applications such as pattern recognition and fault diagnosis, greatly enhancing data-driven decision-making capabilities.

[0096] In one embodiment of the present disclosure, sample expansion is performed on the plurality of abnormal samples according to the sample features of the plurality of abnormal samples to obtain a plurality of expanded abnormal samples, including:

[0097] Input multiple abnormal samples into the target generative adversarial network model to obtain multiple expanded abnormal samples;

[0098] Among them, the target generative adversarial network model learns the sample features of multiple abnormal samples.

[0099] In this embodiment, the target Generative Adversarial Network (GAN) model is a pre-trained GAN model. This embodiment uses the target GAN model to generate new samples (i.e., expanded abnormal samples) based on existing abnormal samples. These new samples have similar characteristics to the original abnormal samples, thereby increasing the number and diversity of abnormal samples, facilitating more comprehensive training of subsequent applications such as state detection models.

[0100] In this embodiment, multiple samples of motor abnormalities are collected and fed into a pre-built target GAN model. Based on the learned characteristics of these abnormal samples, the model generates new data with similar characteristics to the original abnormal samples. These newly generated data are called expanded abnormal samples.

[0101] During GAN model training, the generator attempts to capture the various characteristics exhibited by multiple anomalous samples, such as the data's numerical range, changing trends, and the correlations between different parameters. The discriminator helps guide the generator to better learn these characteristics. By continuously determining the differences between generated data and real anomalous samples, it prompts the generator to make continuous adjustments, ultimately enabling the generator to generate data that matches the characteristics of anomalous samples, thereby achieving the goal of learning and mastering these characteristics.

[0102] As can be seen from the above, this embodiment leverages the learning capabilities of the GAN model to accurately capture and reproduce the complex features of abnormal samples, thereby generating high-quality expanded samples. This not only significantly enriches the abnormal sample dataset and enhances the model's generalization capabilities, but also effectively alleviates the training challenges caused by the scarcity of abnormal samples. Furthermore, the expanded abnormal sample set provides a more solid data foundation for subsequent tasks such as anomaly detection and classification, improving the performance and accuracy of the overall system and possessing significant practical application value.

[0103] In one embodiment of the present disclosure, a generative adversarial network model includes a generator and a discriminator;

[0104] The motor operation energy efficiency detection method further includes:

[0105] The generator is trained based on the historical abnormal sample set to obtain a trained generator;

[0106] Input the random noise vector into the trained generator to obtain the first anomaly data set;

[0107] Training the discriminator based on the historical abnormal sample set and the first abnormal data set to obtain a trained discriminator;

[0108] Determine the target generative adversarial network model based on the trained generator and the trained discriminator.

[0109] In one embodiment of the present disclosure, the motor operation energy efficiency detection method further includes:

[0110] Determining a confidence level for the first anomaly data set based on the discriminator;

[0111] If the confidence is greater than the first threshold, the parameters of the generator are retained;

[0112] If the confidence is less than or equal to the first threshold, the parameters of the generator are updated.

[0113] In this embodiment, the GAN model is a deep learning model architecture consisting of two parts: a generator and a discriminator. The generator aims to generate data with a distribution similar to real data, while the discriminator is responsible for distinguishing whether the input data comes from a real dataset or is generated by the generator. The two are trained through a competitive and continuous game, making the data generated by the generator increasingly similar to real data.

[0114] The generator receives a random noise vector as input and, through its internal neural network structure and parameter transformations, outputs data that simulates the characteristics of a historical anomaly sample set. The discriminator takes as input a historical anomaly sample set (i.e., real data) or a simulated historical anomaly sample set generated by the generator. After processing it through its own network structure, it outputs a probability value indicating the likelihood that the input data is real data.

[0115] The historical abnormal sample set is a data set of operating parameters collected in the past that can represent abnormal operating conditions of the motor. These samples contain parameter conditions corresponding to various fault types, such as the values of current, voltage, temperature, vibration and other parameters under different faults. They are an important basis for training the GAN model.

[0116] The random noise vector is a set of numerical vectors randomly sampled from a specific distribution (such as the normal distribution or uniform distribution). It serves as the generator's input and provides a random basis for generating different data. The first abnormal data set is a parameter data set generated by the trained generator based on the input random noise vector, simulating abnormal motor operating conditions. This data set is generated by the generator based on the learned characteristics of historical abnormal samples.

[0117] The confidence value is the probability value that the discriminator determines that the data in the first abnormal data set is real data, which reflects the degree of recognition of the discriminator on the data generated by the generator. The higher the probability, the closer the discriminator believes the data is to the real abnormal sample data.

[0118] The first threshold is a pre-set probability threshold used to determine whether the quality of the data generated by the generator meets the requirements. When the confidence level given by the discriminator is higher than this threshold, the data generated by the generator is considered to be relatively satisfactory; otherwise, the data generated by the generator is considered to need improvement.

[0119] Specifically, the steps of this embodiment are as follows:

[0120] First, the historical abnormal sample set (i.e., abnormal motor operation parameter data) is provided to the generator, allowing the generator to learn the characteristics, distribution patterns, and other information of this data. By continuously adjusting its own neural network parameters (such as weights, biases, etc.), the generator can generate data similar to the characteristics of historical abnormal samples based on the input random noise vector. After a certain number of rounds of training, the result is a trained generator.

[0121] Second, after the generator is trained, multiple random noise vectors are randomly extracted from the set distribution (such as the normal distribution), and then these vectors are input into the trained generator one by one. The generator processes each input random noise vector according to the previously learned historical abnormal sample characteristics and outputs the corresponding parameter data of the simulated abnormal operating state of the motor. These output data sets together constitute the first abnormal data set.

[0122] Third, the historical anomaly sample set (i.e., real anomaly sample data) is mixed with the data from the first anomaly dataset generated by the generator and then fed into the discriminator. The discriminator learns from this data and adjusts its parameters to accurately distinguish between real anomaly sample data and data generated by the generator. After a certain training process, a trained discriminator is obtained that can make good judgments.

[0123] Fourth, after the generator and discriminator are trained separately, they are combined to form the target GAN model. This model has the ability to generate simulated motor abnormal operating state data and determine the authenticity of this data. The target GAN model can then be used to expand the number of motor abnormal operation samples and other operations.

[0124] The data in the first anomaly data set are input into the trained discriminator one by one. The discriminator will output a probability value for each input data. This probability value is the confidence of the discriminator that the data is a real anomaly sample data, reflecting the discriminator's judgment on the quality of the data generated by the generator.

[0125] The confidence calculation formula is:

[0126]

[0127] in, Indicates that the last layer of the discriminator neural network is input to the sample The linear combination output of , represents the weight vector, represents the input data vector, Indicates bias, Indicates transpose.

[0128] A first threshold is set in advance, for example, 0.9. If the confidence output by the discriminator for a certain data in the first anomaly data set is greater than this threshold, it means that the data generated by the generator is of relatively high quality and closer to the real anomaly sample data. At this time, the existing parameters of the generator are temporarily kept unchanged because the current generator's performance meets the expected requirements.

[0129] If the confidence level of the discriminator's output for a certain data in the first abnormal data set is less than or equal to a pre-set first threshold, it means that the data generated by the generator is still different from the real abnormal sample data and the quality is not ideal. Therefore, the parameters of the generator need to be updated and adjusted. For example, through the backpropagation algorithm, the neural network weights, bias and other parameters of the generator are changed according to the feedback from the discriminator, in the hope that the generator can generate better quality data in the future.

[0130] From the above, it can be concluded that this embodiment trains the generator based on the historical abnormal sample set and generates the first abnormal data set in combination with the random noise vector. This method effectively simulates the abnormal state in the operation of the motor and enhances the generalization ability of the model. It not only improves the detection sensitivity of unknown abnormal situations, but also reduces the false alarm rate. Secondly, the discriminator is trained in combination with the historical abnormal sample set and the generated first abnormal data set, so that the discriminator can more accurately identify real abnormalities and simulated abnormalities, thereby improving the accuracy of motor operation energy efficiency detection. In addition, this embodiment introduces a confidence judgment mechanism to dynamically adjust the parameters of the generator, thereby ensuring the continuous optimization of the GAN model, and the adaptive adjustment strategy further improves the stability and reliability of the model.

[0131] In one embodiment of the present disclosure, the motor operation energy efficiency detection method further includes:

[0132] Based on the results of the state detection, the motor operation state is warned to obtain the warning result;

[0133] Remotely report warning results.

[0134] In this embodiment, the state detection result is a judgment conclusion obtained after analyzing the motor operating parameters through the state detection model, indicating whether the motor is currently in a normal operating state or an abnormal situation exists.

[0135] Motor status warnings are based on status detection results. When an abnormality is detected in the motor's operating state, a corresponding warning mechanism is activated, alerting relevant personnel or systems to the motor's operating status, reminding them to pay attention to the motor's operating status so that timely measures can be taken. Warnings can be implemented in various ways, such as sound prompts, flashing lights, and push notifications.

[0136] The warning result is the final output after the warning process. It contains detailed information about the abnormal state of the motor, such as the time when the abnormality occurred, the type of abnormality, and the possible impact.

[0137] Remote reporting utilizes network communication technology to transmit warning results from the motor's local location to a remote server, monitoring center, or other receiving end. This allows operators to obtain timely information about motor anomalies, enabling remote monitoring and management, even when they are not physically present.

[0138] After the condition detection model analyzes the motor's operating parameters, it generates a condition detection result. If the result indicates abnormal motor operation, the system initiates an early warning process based on pre-set warning rules. Once the warning result is generated, the system uses a network communication module to transmit the warning result to a remote destination. This destination can be a company's remote monitoring center or a maintenance personnel's mobile app. Remote reporting allows relevant personnel to be immediately informed of motor anomalies, enabling them to respond promptly even when they are remote, such as by arranging for on-site maintenance personnel to inspect the motor.

[0139] As can be seen from the above, this embodiment effectively avoids unexpected downtime and ensures production continuity by monitoring motor status in real time and providing timely warnings of potential faults. The remote reporting function enables the operations and maintenance team to respond quickly, regardless of geographic location. They can obtain motor status information immediately and take maintenance measures to ensure safe and stable operation of the motor, thereby improving operations and maintenance efficiency.

[0140] Corresponding to the motor operation energy efficiency detection method of the above embodiment, Figure 2 This is a structural block diagram of a motor energy efficiency detection device provided by an embodiment of the present disclosure. For ease of explanation, only the parts related to the embodiment of the present disclosure are shown. Figure 2 The motor operation energy efficiency detection device 20 includes: a sample determination module 21, a sample expansion module 22 and a detection model construction module 23.

[0141] The sample determination module 21 is configured to determine a plurality of normal samples and a plurality of abnormal samples of the motor operating parameters based on a clustering algorithm;

[0142] A sample expansion module 22 is configured to expand the plurality of abnormal samples according to the sample features of the plurality of abnormal samples to obtain a plurality of expanded abnormal samples;

[0143] The detection model building module 23 is used to train the state detection model based on multiple normal samples and multiple expanded abnormal samples, and detect the motor operating state to be detected according to the trained state detection model.

[0144] In one embodiment of the present disclosure, the motor operating parameters include multiple types of operating parameters;

[0145] The sample determination module 21 is specifically configured to:

[0146] Clustering is performed based on the parameter characteristics of each type of operating parameters to obtain clustering results corresponding to each type of operating parameters. The clustering results include a normal sample set and an abnormal sample set.

[0147] The normal sample sets corresponding to each type of operating parameters are aggregated to obtain multiple normal samples;

[0148] The abnormal sample sets corresponding to each type of operating parameters are aggregated to obtain multiple abnormal samples.

[0149] In one embodiment of the present disclosure, the sample determination module 21 is further configured to:

[0150] Determine multiple cluster centers;

[0151] Determining the distance between each type of operating parameter and the operating parameters of the multiple cluster centers based on the first distance measurement method to obtain multiple first distances;

[0152] A clustering result corresponding to each type of operating parameter is determined based on the multiple first distances.

[0153] In one embodiment of the present disclosure, the sample expansion module 22 is specifically configured to:

[0154] Input multiple abnormal samples into the target generative adversarial network model to obtain multiple expanded abnormal samples;

[0155] Among them, the target generative adversarial network model learns the sample features of multiple abnormal samples.

[0156] In one embodiment of the present disclosure, a generative adversarial network model includes a generator and a discriminator;

[0157] The motor operation energy efficiency detection device 20 further includes: a sample expansion model construction module;

[0158] The sample expansion model construction module is used to train the generator based on the historical abnormal sample set to obtain a trained generator;

[0159] Input the random noise vector into the trained generator to obtain the first anomaly data set;

[0160] Training the discriminator based on the historical abnormal sample set and the first abnormal data set to obtain a trained discriminator;

[0161] Determine the target generative adversarial network model based on the trained generator and the trained discriminator.

[0162] In one embodiment of the present disclosure, the motor operation energy efficiency detection device 20 further includes: a parameter updating module;

[0163] a parameter updating module, configured to determine a confidence level for the first abnormal data set based on the discriminator;

[0164] If the confidence is greater than the first threshold, the parameters of the generator are retained;

[0165] If the confidence is less than or equal to the first threshold, the parameters of the generator are updated.

[0166] In one embodiment of the present disclosure, the motor operation energy efficiency detection device 20 further includes: an early warning module;

[0167] An early warning module is used to issue an early warning of the motor operation status based on the result of the status detection and obtain an early warning result;

[0168] Remotely report warning results.

[0169] See also Figure 3 , Figure 3 This is a schematic block diagram of an electronic device provided by an embodiment of the present disclosure. Figure 3 The electronic device 300 in the embodiment shown may include: one or more processors 301, one or more input devices 302, one or more output devices 303, and one or more memories 304. The processors 301, input devices 302, output devices 303, and memories 304 communicate with each other via a communication bus 305. The memory 304 is used to store computer programs, which include program instructions. The processor 301 is used to execute the program instructions stored in the memory 304. The processor 301 is configured to call the program instructions to execute the functions of the modules / units in the above-mentioned device embodiments, such as Figure 2 The functions of modules 21 to 23 are shown.

[0170] It should be understood that in the embodiments of the present disclosure, the processor 301 may be a central processing unit (CPU), or may be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0171] The input device 302 may include a touchpad, a fingerprint collection sensor (for collecting user fingerprint information and fingerprint direction information), a microphone, etc. The output device 303 may include a display (LCD, etc.), a speaker, etc.

[0172] The memory 304 may include a read-only memory and a random access memory, and provides instructions and data to the processor 301. A portion of the memory 304 may also include a non-volatile random access memory. For example, the memory 304 may also store information about the device type.

[0173] In a specific implementation, the processor 301, input device 302, and output device 303 described in the embodiments of the present disclosure can execute the implementation methods described in the first and second embodiments of the motor operation energy efficiency detection method provided in the embodiments of the present disclosure, and can also execute the implementation methods of the electronic device described in the embodiments of the present disclosure, which will not be repeated here.

[0174] In another embodiment of the present disclosure, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program. The computer program includes program instructions. When the program instructions are executed by a processor, all or part of the process of the method in the above embodiment is implemented. The computer program can also be used to instruct related hardware to complete the process. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of each of the above method embodiments are implemented. The computer program includes computer program code, which can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium can include: any entity or device capable of carrying computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium.

[0175] The computer-readable storage medium can be an internal storage unit of the electronic device in any of the aforementioned embodiments, such as a hard disk or memory of the electronic device. The computer-readable storage medium can also be an external storage device of the electronic device, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a flash memory card, etc. Furthermore, the computer-readable storage medium can include both an internal storage unit of the electronic device and an external storage device. The computer-readable storage medium is used to store computer programs and other programs and data required by the electronic device. The computer-readable storage medium can also be used to temporarily store data that has been output or is about to be output.

[0176] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the above description has generally described the composition and steps of each example according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this disclosure.

[0177] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the electronic devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0178] In the several embodiments provided in this application, it should be understood that the disclosed electronic devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces or units, or can be an electrical, mechanical or other form of connection.

[0179] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, i.e., they may be located in one place or distributed across multiple network units. Some or all of these units may be selected based on actual needs to achieve the objectives of the embodiments of the present disclosure.

[0180] In addition, the functional units in the various embodiments of the present disclosure may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0181] The above are only specific embodiments of the present disclosure, but the scope of protection of the present disclosure is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or replacements within the technical scope disclosed in this disclosure, and such modifications or replacements should be included in the scope of protection of the present disclosure. Therefore, the scope of protection of the present disclosure should be based on the scope of protection of the claims.

Claims

1. A method for detecting motor energy efficiency, characterized in that: include: Determine multiple cluster centers; Determine the distance between each type of operating parameter and the operating parameters of the multiple cluster centers based on a first distance measurement method to obtain multiple first distances; wherein the motor operating parameters include multiple types of operating parameters; The calculation formula of the first distance measurement method is: in, is the first distance, is the number of types of motor operating parameters, For the Class running parameters, is the weight, , is the adjustment coefficient, For the Euclidean distance of class operating parameters, For the The average correlation coefficient of the class operating parameters with all other class operating parameters, is the average correlation coefficient of the parameters corresponding to the cluster centers; Determining a clustering result corresponding to each type of operating parameter based on the multiple first distances; wherein the clustering result includes a normal sample set and an abnormal sample set; The normal sample sets corresponding to each type of operating parameters are aggregated to obtain multiple normal samples; The abnormal sample sets corresponding to each type of operating parameters are aggregated to obtain multiple abnormal samples; performing sample expansion on the multiple abnormal samples according to the sample features of the multiple abnormal samples to obtain multiple expanded abnormal samples; The state detection model is trained based on the multiple normal samples and the multiple expanded abnormal samples, and the motor operation energy efficiency is determined by detecting the motor operation state to be detected according to the trained state detection model.

2. The motor operation energy efficiency detection method according to claim 1, characterized in that: The step of expanding the plurality of abnormal samples according to the sample features of the plurality of abnormal samples to obtain a plurality of expanded abnormal samples includes: Inputting the multiple abnormal samples into a target generative adversarial network model to obtain the multiple expanded abnormal samples; The target generative adversarial network model learns the sample features of the multiple abnormal samples.

3. The motor operation energy efficiency detection method according to claim 2, characterized in that: The generative adversarial network model includes a generator and a discriminator; The motor operation energy efficiency detection method further includes: Training the generator based on a historical abnormal sample set to obtain a trained generator; Input the random noise vector into the trained generator to obtain the first anomaly data set; Training the discriminator based on the historical abnormal sample set and the first abnormal data set to obtain a trained discriminator; A target generative adversarial network model is determined based on the trained generator and the trained discriminator.

4. The motor operation energy efficiency detection method according to claim 3, characterized in that: Also includes: determining a confidence level for the first anomaly data set based on the discriminator; If the confidence level is greater than a first threshold, retaining the parameters of the generator; If the confidence is less than or equal to a first threshold, the parameters of the generator are updated.

5. The motor operation energy efficiency detection method according to claim 1, characterized in that: Also includes: Based on the results of the state detection, the motor operation state is warned to obtain the warning result; Remotely report the warning results.

6. A motor operation energy efficiency detection device, characterized in that: include: A sample determination module, used to determine multiple cluster centers; Determine the distance between each type of operating parameter and the operating parameters of the multiple cluster centers based on a first distance measurement method to obtain multiple first distances; wherein the motor operating parameters include multiple types of operating parameters; The calculation formula of the first distance measurement method is: in, is the first distance, is the number of types of motor operating parameters, For the Class running parameters, is the weight, , is the adjustment coefficient, For the Euclidean distance of class operating parameters, For the The average correlation coefficient of the class operating parameters with all other class operating parameters, is the average correlation coefficient of the parameters corresponding to the cluster centers; Determining a clustering result corresponding to each type of operating parameter based on the multiple first distances; wherein the clustering result includes a normal sample set and an abnormal sample set; The normal sample sets corresponding to each type of operating parameters are aggregated to obtain multiple normal samples; The abnormal sample sets corresponding to each type of operating parameters are aggregated to obtain multiple abnormal samples; A sample expansion module, configured to expand the plurality of abnormal samples according to the sample features of the plurality of abnormal samples to obtain a plurality of expanded abnormal samples; The detection model construction module is used to train the state detection model based on the multiple normal samples and the multiple expanded abnormal samples, and to detect the motor operation state to be detected according to the trained state detection model to determine the motor operation energy efficiency.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images