Motor energy consumption monitoring method and device based on support vector machine algorithm
Through the motor energy consumption monitoring method based on the support vector machine algorithm, the problem of precise energy consumption monitoring under complex operating conditions is solved, high-precision energy consumption prediction and abnormal alarm are achieved, and the efficiency of energy consumption management is improved.
Patent Information
- Application Number
- CN202411497369.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-25
- Publication Date
- 2025-02-25
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The prior art is difficult to achieve precise motor energy consumption monitoring under complex operating conditions, especially under high loads or rapid changes in motor operating conditions, insufficient accuracy and response speed lead to failure of abnormal energy consumption monitoring.
The motor energy consumption monitoring method based on the support vector machine algorithm is adopted, and data is collected in real time through current and voltage sensors, and feature vector analysis is combined with the principal component analysis method and feature selection algorithm to organize the feature vector, input the support vector regression model for energy consumption prediction, and perform abnormal analysis and alarm.
It realizes accurate energy consumption monitoring and timely alarms under complex working conditions, improves the accuracy and efficiency of energy consumption management, and avoids the problem of abnormal energy consumption monitoring failure.
Smart Images
Figure CN119510839A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the technical field of motor energy consumption monitoring, and in particular relates to a motor energy consumption monitoring method and device based on a support vector machine algorithm. Background Art
[0002] At present, motor energy consumption monitoring technology has significant deficiencies in real-time, accuracy and adaptability. For example, existing technologies rely on traditional current and voltage measurement methods, which make it difficult to achieve accurate energy consumption predictions under high dynamic loads and rapidly changing conditions. In addition, when processing multi-dimensional feature data, existing technologies often fail to fully consider the correlation and importance between different features, resulting in improper feature selection, which affects the prediction effect. These deficiencies make motor energy consumption monitoring challenging in practical applications, especially in industrial environments that require high real-time and accuracy. Therefore, there is an urgent need for a method that can still achieve high-precision energy consumption monitoring under various working conditions, so as to improve the operating efficiency and maintenance management level of the motor, reduce energy consumption and operating costs, and thus meet the needs of modern industry for energy efficiency management. Summary of the invention
[0003] In view of the above-mentioned technical deficiencies, the purpose of the present invention is to propose a motor energy consumption monitoring method based on a support vector machine algorithm, aiming to solve the technical problem that the prior art cannot achieve accurate energy consumption monitoring under complex working conditions, especially under high load or rapid changes in motor operating conditions, due to insufficient accuracy and response speed leading to failure of abnormal energy consumption monitoring.
[0004] In order to solve the above technical problems, the present invention adopts the following technical solutions: The present invention provides a motor energy consumption monitoring method based on a support vector machine algorithm.
[0005] The method comprises:
[0006] Step S10: The current data and voltage data of the motor are collected in real time by the current sensor and the voltage sensor, the sampling frequency is set to 10kHz to 20kHz, and the instantaneous power data of the motor is calculated according to the formula P(t)=U(t)×I(t), where P(t) represents instantaneous power, U(t) represents real-time voltage, and I(t) represents real-time current;
[0007] Step S20: The current data, voltage data, instantaneous power data, speed data and ambient temperature data are sorted into feature vectors by principal component analysis. The feature vectors include the mean and variance of current and voltage, the maximum and minimum values of instantaneous power, and the change values of speed and temperature. After the most relevant features are selected by feature selection algorithm, the feature vectors are subjected to Z- sco r eStandardization is performed so that the mean of each feature is 0 and the standard deviation is 1, eliminating the scale differences of different data features;
[0008] Step S30: inputting the standardized feature vector into a support vector regression model based on a radial basis function kernel to predict the energy consumption of the motor, wherein the support vector regression model is trained using historical data, the training penalty parameter ranges from 0.1 to 10, and the kernel function parameter ranges from 0.001 to 0.1;
[0009] Step S40: Perform abnormal analysis on the motor energy consumption based on the predicted value of the motor energy consumption and the actual value of the motor energy consumption. If the difference between the predicted value of the motor energy consumption and the actual value of the energy consumption exceeds 10% of the set threshold, an abnormal energy consumption is indicated and an alarm is triggered.
[0010] Preferably, in step S30,
[0011] The radial basis function kernel is:
[0012] K(x i , x) = exp(-γ||x i -x|| 2 )
[0013] Among them, K(x i , x) is the kernel function, γ is the parameter that controls the complexity of the model, x i and x are the support vector and input feature vector respectively, ||x i -x|| 2 is the square of the Euclidean distance between the two;
[0014] The support vector regression model formula is:
[0015]
[0016] Among them, f(x) is the predicted value of energy consumption, α i is the Lagrange multiplier, x i is the support vector, K(x i , x) is the above radial basis function kernel, b is the bias term, and ∈ is the adaptive error term.
[0017] Preferably, in step S20, the feature selection algorithm includes a feature selection method based on information gain, which preferentially selects the feature processing that makes the greatest contribution to energy consumption prediction.
[0018] Preferably, in step S10, the sampling frequency can be automatically adjusted according to the working state of the motor, and when the motor load is greater than a preset value, the sampling frequency is automatically increased to 20 kHz.
[0019] Preferably, in step S10, the instantaneous power data is smoothed by a sliding window method.
[0020] Preferably, in step S10, the current data and voltage data are pre-processed by a low-pass filter after being collected.
[0021] Preferably, in step S40, the alarm mode includes visual and sound prompts, which can simultaneously trigger light flashing and buzzer alarm when energy consumption is abnormal.
[0022] The present invention also provides a device, comprising:
[0023] A data acquisition module is used to collect the current data and voltage data of the motor in real time through a current sensor and a voltage sensor, the sampling frequency is set to 10kHz to 20kHz, and the instantaneous power data of the motor is calculated according to the formula P(t)=U(t)×I(t), where P(t) represents instantaneous power, U(t) represents real-time voltage, and I(t) represents real-time current;
[0024] A feature processing module is used to organize current data, voltage data, instantaneous power data, speed data and ambient temperature data into feature vectors by principal component analysis. The feature vectors include the mean and variance of current and voltage, the maximum and minimum values of instantaneous power, and the change values of speed and temperature. After the most relevant features are selected by the feature selection algorithm, the feature vectors are subjected to Z-score standardization processing so that the mean value of each feature is 0 and the standard deviation is 1, thereby eliminating the scale differences of different data features.
[0025] A prediction and analysis module, used for inputting the standardized feature vector into a support vector regression model based on a radial basis function kernel to predict the energy consumption of the motor, wherein the support vector regression model is trained using historical data, the training penalty parameter ranges from 0.1 to 10, and the kernel function parameter ranges from 0.001 to 0.1;
[0026] The anomaly detection module is used to analyze the abnormality of the motor energy consumption by combining the predicted value of the motor energy consumption with the actual value of the motor energy consumption. If the difference between the predicted value of the motor energy consumption and the actual value of the motor energy consumption exceeds 10% of the set threshold, it indicates that the energy consumption is abnormal and triggers an alarm;
[0027] The present invention also provides a motor energy consumption monitoring method and device based on a support vector machine algorithm, comprising:
[0028] A memory, a processor, and a motor energy consumption monitoring method program based on a support vector machine algorithm stored in the memory and executable on the processor. When the motor energy consumption monitoring method program based on a support vector machine algorithm is executed by the processor, the motor energy consumption monitoring method based on a support vector machine algorithm is implemented.
[0029] The present invention also provides a computer program product, including a motor energy consumption monitoring method program based on a support vector machine algorithm. When the motor energy consumption monitoring method program based on a support vector machine algorithm is executed by a processor, the motor energy consumption monitoring method based on a support vector machine algorithm is implemented.
[0030] The beneficial effect of the present invention is that compared with the prior art which is unable to realize accurate energy consumption monitoring under complex working conditions, especially under conditions of high load or rapid changes in motor working conditions, the technical problem of failure of abnormal energy consumption monitoring due to insufficient accuracy and response speed is achieved. The present invention introduces a support vector machine algorithm to realize accurate energy consumption monitoring and timely alarm under complex working conditions, thereby improving the accuracy and efficiency of energy consumption management. BRIEF DESCRIPTION OF THE DRAWINGS
[0031] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0032] Figure 1 The figure is a flow chart of a first embodiment of a method for monitoring motor energy consumption based on a support vector machine algorithm according to the present invention. DETAILED DESCRIPTION
[0033] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0034] Embodiment 1: Figure 1 , which is a flow chart of the first embodiment of the motor energy consumption monitoring method based on the support vector machine algorithm of the present invention, proposes the first embodiment of the motor energy consumption monitoring method based on the support vector machine algorithm of the present invention.
[0035] In a first embodiment, the method comprises:
[0036] Step S10: The current data and voltage data of the motor are collected in real time by the current sensor and the voltage sensor, the sampling frequency is set to 10kHz to 20kHz, and the instantaneous power data of the motor is calculated according to the formula P(t)=U(t)×I(t), where P(t) represents instantaneous power, U(t) represents real-time voltage, and I(t) represents real-time current;
[0037] It should be noted that the current and voltage are collected continuously and in real time, ensuring accurate recording of the motor's operating data under various operating conditions.
[0038] It should be understood that the selection of sampling frequency depends on the working state of the motor. Usually under normal load, the sampling frequency is 10kHz, while under high load or rapidly changing working conditions, the sampling frequency can be automatically adjusted to 20kHz to ensure data accuracy.
[0039] Step S20: The current data, voltage data, instantaneous power data, speed data and ambient temperature data are sorted into feature vectors by principal component analysis, wherein the feature vectors include the mean and variance of the current and voltage, the maximum and minimum values of the instantaneous power, and the change values of the speed and temperature. After the most relevant features are selected by the feature selection algorithm, the feature vectors are subjected to Z-score standardization processing so that the mean value of each feature is 0 and the standard deviation is 1, thereby eliminating the scale differences of different data features;
[0040] It should be noted that the principal component analysis (PCA) method not only simplifies the dimension of the data, but also retains key information that is useful for energy consumption prediction. This helps to reduce the impact of redundant features on model performance. In addition, the role of the feature selection algorithm is to prioritize the features that have the greatest impact on energy consumption prediction, ensuring that the model can predict and analyze more efficiently and accurately. The Z-score standardization process is to eliminate the dimensional differences between the features, so that the contributions of features of different scales to the results in model training are more balanced, and to prevent some features from causing deviations in the results due to excessively large or small values.
[0041] It should be understood that the combination of principal component analysis (PCA) and feature selection algorithm not only effectively reduces the redundancy of data, but also improves the processing efficiency of the model. By retaining key features, the consumption of computing resources can be reduced while avoiding overfitting, thereby improving the accuracy of energy consumption prediction. Z-score standardization does not change the distribution of data, but ensures that each feature has the same dimension by adjusting the mean and standard deviation of the feature. In this way, in the subsequent support vector machine algorithm training process, the model can process each feature more evenly, avoiding model deviations or errors caused by different data scales, thereby further improving the stability and accuracy of the prediction.
[0042] For example, suppose the collected data of the motor at a certain moment is as follows:
[0043] Current data(A) Voltage data(V) Instantaneous power (W) Speed data (rpm) Ambient temperature (℃) 12 220 2640 1450 30 13 221 2873 1452 31 15 222 3330 1455 30 14 220 3080 1450 29 13 223 2899 1453 30
[0044] Through principal component analysis (PCA), these data are first converted into feature vectors. The feature vector may include the following statistical information: current mean: 13.4A, voltage mean: 221.2V, instantaneous power maximum: 3330W, minimum: 2640W, speed change: 5rpm (maximum 1455rpm, minimum 1450rpm), temperature change: 2℃ (maximum 31℃, minimum 29℃). After the feature selection algorithm, the features that have the greatest impact on the prediction of motor energy consumption may be screened out, such as the maximum and minimum values of instantaneous power, and the mean values of current, voltage, and speed changes. Then, these features are Z-score standardized. Assuming that the mean and standard deviation of the features are: the mean current is 13.4A, the standard deviation is 1.1A, the mean voltage is 221.2V, the standard deviation is 1.2V, the mean instantaneous power is 2984.4W, the standard deviation is 244.7W, the mean speed change value is 4rpm, the standard deviation is 2rpm, the mean temperature change value is 1°C, the standard deviation is 0.5°C, the features after Z-score standardization can be expressed as follows: the standardized Z-score value of current: (13.4-13.4) / 1.1=0, the standardized Z-score value of voltage: (221.2-221.2) / 1.2=0, the standardized Z-score value of instantaneous power: (3330-2984.4) / 244.7=1.41. Through this standardization, all features will be normalized to have the same mean and standard deviation, thereby eliminating the scale differences between different features, allowing the model to process these features more balanced during training and avoiding unnecessary deviations in the model due to excessively large or small values of certain features.
[0045] Therefore, it should be understood that this step is intended to optimize the input data of the model so that each feature can have a balanced effect on the prediction results of the model, thereby improving the accuracy and stability of the motor energy consumption prediction.
[0046] Step S30: inputting the standardized feature vector into a support vector regression model based on a radial basis function kernel to predict the energy consumption of the motor, wherein the support vector regression model is trained using historical data, the training penalty parameter ranges from 0.1 to 10, and the kernel function parameter ranges from 0.001 to 0.1;
[0047] It should be noted that the radial basis function kernel (RBF kernel) is a commonly used kernel function that can handle nonlinear relationships well and is particularly suitable for complex motor energy consumption data prediction. When training a support vector regression model, the penalty parameter controls the model's tolerance to errors in the training data, while the kernel function parameters determine the influence range of the support vector.
[0048] It should be understood that in the actual training process, the specific execution steps may be:
[0049] (1) Training data: The model is trained using past motor energy consumption data (including standardized feature vectors and corresponding actual energy consumption). Historical data may include thousands of sets of features and energy consumption values under different operating conditions.
[0050] (2) Kernel function application: Through the radial basis function kernel (RBF kernel), the support vector regression model can capture the nonlinear relationship between input features and motor energy consumption. For example, the energy consumption variation of the motor under different load and temperature conditions can be modeled by the kernel function.
[0051] (3) Error control: The penalty parameter C is used to control the model’s tolerance for incorrect predictions. In this example, the penalty parameter C = 1.0 means that the model can tolerate some errors when the prediction error is small, but will make larger adjustments to the model when the error exceeds a certain threshold.
[0052] (4) Influence of support vectors: The kernel function parameter γ = 0.01 determines the influence range of each support vector on the overall prediction result. If γ is large, the influence range of each support vector is small, which is suitable for processing complex data structures; if γ is small, the influence range of the support vector is wider, which is suitable for processing smoother relationships.
[0053] Step S40: Perform abnormal analysis on the motor energy consumption based on the predicted value of the motor energy consumption and the actual value of the motor energy consumption. If the difference between the predicted value of the motor energy consumption and the actual value of the energy consumption exceeds 10% of the set threshold, an abnormal energy consumption is indicated and an alarm is triggered.
[0054] It should be noted that the threshold setting can be adjusted according to the specific operating conditions of the motor. 10% is a commonly used default value, which is used to effectively detect abnormal conditions under most working conditions. For specific industrial scenarios, the threshold can be flexibly set according to the sensitivity and safety requirements of the equipment.
[0055] It is understandable that the triggering of the alarm is not limited to a single method. When the energy consumption is abnormal, it can be reminded in multiple forms such as visual (such as flashing indicator lights) and sound (such as buzzer alarms). In addition, the system can also record the alarm information in the log or transmit it to the maintenance personnel through the network so that timely measures can be taken.
[0056] It should be understood that the difference between the predicted and actual energy consumption may not only be caused by changes in motor load or operating conditions, but may also indicate potential equipment failure or maintenance needs. Therefore, timely abnormality analysis and alarm triggering can effectively prevent further damage to the equipment and help maintenance personnel intervene in advance, thereby extending the life of the motor and reducing operating costs.
[0057] For example, suppose the system predicts that the motor energy consumption is 2500W, while the actual measured energy consumption is 2800W, with a difference of about 12%, exceeding the set threshold of 10%. In this case, the system will trigger an abnormal alarm, indicating that the equipment may have a high energy consumption problem, and maintenance personnel can further check the operating status of the motor to prevent potential failures.
[0058] In the second embodiment provided by the present invention, in step S30,
[0059] The radial basis function kernel is:
[0060] K(x i , x) = exp(-γ||x i -x|| 2 )
[0061] Among them, K(x i , x) is the kernel function, γ is the parameter that controls the complexity of the model, x i and x are the support vector and input feature vector respectively, ||x i -x|| 2 is the square of the Euclidean distance between the two;
[0062] The support vector regression model formula is:
[0063]
[0064] Among them, f(x) is the predicted value of energy consumption, α i is the Lagrange multiplier, x i is the support vector, K(x i , x) is the above radial basis function kernel, b is the bias term, and ∈ is the adaptive error term.
[0065] It should be understood that the combination of this kernel function and the prediction model allows SVR to handle nonlinear problems by mapping the data into a higher dimensional space where linear methods can be used to solve nonlinear problems in the original space. In the application of motor energy consumption prediction, this enables the model to accurately predict the energy consumption of the motor based on its various operating parameters (such as current, voltage, speed, etc.), even if these relationships are nonlinear in the original space. By precisely adjusting these parameters, we can optimize the model to adapt to specific application scenarios, such as different conditions and environments where the motor operates, thereby improving the accuracy of the prediction and the reliability of the model.
[0066] For example, suppose there is the following sample data of motor operating parameters and energy consumption data:
[0067] Current (A) Voltage (V) Speed (rpm) Temperature(℃) Actual energy consumption (W) 12 220 1450 30 2800 13 221 1452 31 2900 15 222 1455 30 3200 14 220 1450 29 3000 13 223 1453 30 2950
[0068] The support vector regression model is used to predict the energy consumption of the motor under specific conditions. In this case, the RBF kernel function maps these parameters (current, voltage, speed, temperature) from the original low-dimensional space to the high-dimensional space, making these nonlinear relationships linear in the high-dimensional space. Through this mapping, the SVR model can effectively fit these complex nonlinear relationships and thus make accurate predictions of energy consumption. After that, by training the SVR model, setting the penalty parameter C = 1.0 and the kernel function parameter γ = 0.01, the following predictions are obtained:
[0069] Current (A) Voltage (V) Speed (rpm) Temperature(℃) Actual energy consumption (W) Predicted energy consumption (W) 12 220 1450 30 2800 2785 13 221 1452 31 2900 2890 15 222 1455 30 3200 3185 14 220 1450 29 3000 2995 13 223 1453 30 2950 2940
[0070] As can be seen from the table, the error between the predicted value and the actual energy consumption is very small, indicating that the SVR model successfully captures the nonlinear relationship between current, voltage, speed and temperature through the RBF kernel. In this case, if the difference between the energy consumption value predicted by the model and the actual energy consumption value exceeds 10%, for example, the actual energy consumption at a certain moment is 3200W, and the energy consumption predicted by the model is 2800W, and the difference reaches 12.5%, the system will trigger an alarm, indicating that the device may be in an abnormal state. This abnormal analysis and alarm function further improves the safety and reliability of the system. Therefore, the SVR model combined with the RBF kernel function can not only handle complex nonlinear relationships, but also make accurate energy consumption predictions based on various operating parameters of the motor, thereby providing strong support for motor operation optimization.
[0071] The present invention provides a motor energy consumption monitoring method device based on a support vector machine algorithm, which adopts a motor energy consumption monitoring method based on a support vector machine algorithm in the above embodiment, and can solve the technical problem of a motor energy consumption monitoring method based on a support vector machine algorithm. Compared with the prior art, the beneficial effects of the motor energy consumption monitoring method device based on a support vector machine algorithm provided by the present invention are the same as the beneficial effects of the motor energy consumption monitoring method based on a support vector machine algorithm provided by the above embodiment, and the other technical features of the motor energy consumption monitoring method device based on a support vector machine algorithm are the same as the features disclosed in the above embodiment method, which will not be repeated here.
[0072] The present invention provides a motor energy consumption monitoring method and device based on a support vector machine algorithm. The motor energy consumption monitoring method and device based on a support vector machine algorithm include: at least one processor; and a memory connected to the at least one processor in communication; wherein the memory stores instructions that can be executed by at least one processor, and the instructions are executed by at least one processor, so that at least one processor can execute the motor energy consumption monitoring method based on the support vector machine algorithm in the above-mentioned embodiment 1. The motor energy consumption monitoring method and device based on the support vector machine algorithm in the embodiment of the present invention may include but is not limited to mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. A motor energy consumption monitoring method and device based on a support vector machine algorithm is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention. A motor energy consumption monitoring method and device based on a support vector machine algorithm may include a processing device 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of a motor energy consumption monitoring method and device based on a support vector machine algorithm are also stored. The processing device 1001, ROM1002, and RAM1004 are connected to each other via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 1003 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 1009. The communication device 1009 can allow a motor energy consumption monitoring method device based on a support vector machine algorithm to communicate wirelessly or wired with other devices to exchange data. Although the figure shows a motor energy consumption monitoring method device based on a support vector machine algorithm with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems may be implemented or have alternatively.
[0073] The present invention also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of a motor energy consumption monitoring method based on a support vector machine algorithm as described above. The computer program product provided by the present invention can solve the technical problem of a motor energy consumption monitoring method based on a support vector machine algorithm. Compared with the prior art, the beneficial effects of the computer program product provided by the present invention are the same as the beneficial effects of a motor energy consumption monitoring method based on a support vector machine algorithm provided in the above embodiment, which will not be repeated here.
[0074] In particular, according to the embodiments disclosed in the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present invention include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through a communication device, or installed from the storage device 1003, or installed from the ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present invention are executed.
[0075] It should be understood that the various parts disclosed in the present invention can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.
[0076] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.
Claims
1. A motor energy consumption monitoring method based on support vector machine algorithm, characterized in that: The method comprises: Step S10: The current data and voltage data of the motor are collected in real time by the current sensor and the voltage sensor, the sampling frequency is set to 10kHz to 20kHz, and the instantaneous power data of the motor is calculated according to the formula P(t)=U(t)×I(t), where P(t) represents instantaneous power, U(t) represents real-time voltage, and I(t) represents real-time current; Step S20: sorting the current data, voltage data, instantaneous power data, speed data and ambient temperature data into a feature vector by principal component analysis, wherein the feature vector includes the mean value, variance, maximum value, minimum value of instantaneous power and change value of speed and temperature of the current and voltage, and performing Z-score normalization on the feature vector after selecting the most relevant features by feature selection algorithm; Step S30: inputting the standardized feature vector into a support vector regression model based on a radial basis function kernel to predict the energy consumption of the motor, wherein the support vector regression model is trained using historical data, the training penalty parameter ranges from 0.1 to 10, and the kernel function parameter ranges from 0.001 to 0.1; Step S40: Perform abnormal analysis on the motor energy consumption based on the predicted value of the motor energy consumption and the actual value of the motor energy consumption. If the difference between the predicted value of the motor energy consumption and the actual value of the energy consumption exceeds 10% of the set threshold, an abnormal energy consumption is indicated and an alarm is triggered.
2. The motor energy consumption monitoring method based on the support vector machine algorithm according to claim 1 is characterized in that: In the step S30, The radial basis function kernel is: K(x i ,x)=exp(-γ||x i -x|| 2 ) Among them, K(x i ,x) is the kernel function, γ is the parameter that controls the complexity of the model, x i and x are the support vector and input feature vector respectively, ||x i -x|| 2 is the square of the Euclidean distance between the two; The support vector regression model formula is: Among them, f(x) is the predicted value of energy consumption, α i is the Lagrange multiplier, x i is the support vector, b is the bias term, ∈ is the adaptive error term, i represents the index of the support vector, and n is the total number of support vectors.
3. The motor energy consumption monitoring method based on support vector machine algorithm according to claim 1 is characterized in that: In step S20, the feature selection algorithm includes a feature selection method based on information gain, which preferentially selects the feature processing that makes the greatest contribution to energy consumption prediction.
4. The motor energy consumption monitoring method based on support vector machine algorithm according to claim 1 is characterized in that: In step S10, the sampling frequency can be automatically adjusted according to the working state of the motor. When the motor load is greater than a preset value, the sampling frequency is automatically increased to 20 kHz.
5. The motor energy consumption monitoring method based on support vector machine algorithm according to claim 1 is characterized in that: In the step S10, the instantaneous power data is smoothed by a sliding window method.
6. The motor energy consumption monitoring method based on support vector machine algorithm according to claim 1 is characterized in that: In the step S10, the current data and the voltage data are pre-processed by a low-pass filter after being collected.
7. The motor energy consumption monitoring method based on support vector machine algorithm according to claim 1 is characterized in that: In step S40, the alarm mode includes visual and sound prompts, which can simultaneously trigger light flashing and buzzer alarm when energy consumption is abnormal.
8. A motor energy consumption monitoring method and device based on support vector machine algorithm, characterized in that: The device comprises: A data acquisition module is used to collect the current data and voltage data of the motor in real time through a current sensor and a voltage sensor, the sampling frequency is set to 10kHz to 20kHz, and the instantaneous power data of the motor is calculated according to the formula P(t)=U(t)×I(t), where P(t) represents instantaneous power, U(t) represents real-time voltage, and I(t) represents real-time current; A feature processing module is used to organize current data, voltage data, instantaneous power data, speed data and ambient temperature data into feature vectors by principal component analysis. The feature vectors include the mean and variance of current and voltage, the maximum and minimum values of instantaneous power, and the change values of speed and temperature. After the most relevant features are selected by the feature selection algorithm, the feature vectors are subjected to Z-score standardization processing so that the mean value of each feature is 0 and the standard deviation is 1, thereby eliminating the scale differences of different data features. A prediction and analysis module, used for inputting the standardized feature vector into a support vector regression model based on a radial basis function kernel to predict the energy consumption of the motor, wherein the support vector regression model is trained using historical data, the training penalty parameter ranges from 0.1 to 10, and the kernel function parameter ranges from 0.001 to 0.1; The anomaly detection module is used to perform abnormal analysis of the motor energy consumption by combining the predicted value of the motor energy consumption and the actual value of the motor energy consumption. If the difference between the predicted value of the motor energy consumption and the actual value of the motor energy consumption exceeds 10% of the set threshold, an energy consumption abnormality is prompted and an alarm is triggered.
9. A motor energy consumption monitoring device based on support vector machine algorithm, characterized in that: The device comprises: A memory, a processor, and a motor energy consumption monitoring method program based on a support vector machine algorithm stored in the memory and executable on the processor. When the motor energy consumption monitoring method program based on a support vector machine algorithm is executed by the processor, the motor energy consumption monitoring method based on a support vector machine algorithm is implemented.
10. A computer program product, characterized in that The computer program product includes a motor energy consumption monitoring program based on a support vector machine algorithm. When the motor energy consumption monitoring method program based on a support vector machine algorithm is executed by a processor, the motor energy consumption monitoring method based on a support vector machine algorithm is implemented.