Motor drive optimization management system based on data analysis

Abstract

The present invention relates to the field of big data technology, and in particular to a motor drive optimization management system based on data analysis. The present invention collects motor operating parameters and environmental data in real time, combines historical data, predicts motor operating efficiency, and then constructs a relationship model to optimize the prediction results, and analyzes the impact of environmental factors on motor health; the system also includes an adjustment module for calculating the optimized output power based on the actual input power and the predicted operating efficiency, and formulating an adjustment strategy after comparing with the target output power to improve motor efficiency and system stability. The present invention realizes efficient operation of the motor, reduces energy consumption, and extends the life of the motor.

Description

Technical Field

[0001] The present invention relates to the field of big data technology, and in particular to a motor drive optimization management system based on data analysis. Background Art

[0002] With the rise of Industry 4.0 and smart manufacturing, the automation and intelligence level of the production process is constantly improving. As an important part of the smart factory, the motor drive system needs to be closely linked with the upper control system (such as PLC, DCS, etc.) to meet the precise control requirements of complex production processes.

[0003] The patent document with publication number CN109910918A discloses an optimization method and system for the energy management strategy of a hybrid train with an internal combustion generator set and a supercapacitor, including: an energy management system, a hybrid power system, an automatic driving system, and a traction system; the automatic driving system calculates the actual traction force Ft* required when the train is running and transmits it to the traction system; the traction system transmits the actual required traction force to the traction motor to generate axle traction force acting on the movement of the train body; the energy management system makes reasonable planning based on the movement state of the train on different lines and the energy state actually required by the hybrid power system, so that the hybrid power system works in the optimal state. The hybrid power system provides energy for the traction system of the train and sends its own status information to the energy management system.

[0004] It can be seen that the following problems exist: in the prior art, since supercapacitors are energy storage devices, their charge and discharge cycle life is limited, and as the number of uses increases, the efficiency decreases and the service life is short. Summary of the invention

[0005] To this end, the present invention provides a motor drive optimization management system based on data analysis to overcome the problem in the prior art that supercapacitors, as energy storage devices, have limited charge and discharge cycle life, which leads to reduced efficiency and short service life as the number of uses increases.

[0006] To achieve the above object, the present invention provides a motor drive optimization management system based on data analysis, comprising:

[0007] A collection module is used to collect the current, voltage, temperature and speed of the motor in real time to obtain real-time data, obtain corresponding historical data according to the real-time data, and collect the load data of the ball mill and the surrounding environmental data, the load data includes raw material humidity, raw material hardness and feed amount, and the environmental data includes humidity, temperature and dust amount;

[0008] An analysis module, connected to the acquisition module, for predicting the operating efficiency of the motor according to the real-time data and the historical data to obtain a predicted operating efficiency;

[0009] A prediction module connected to the analysis module, constructing a relationship model according to the raw material humidity, the raw material hardness, the feed amount and the predicted operation efficiency to optimize the predicted operation efficiency to obtain the optimized operation efficiency, and analyzing the influence of the humidity, the temperature and the dust amount on the optimized operation efficiency to obtain the motor health index;

[0010] An adjustment module is connected to the prediction module, calculates the actual input power according to the current and the voltage, calculates the optimized output power according to the actual input power and the optimized operating efficiency, compares the optimized output power with a preset target output power to obtain a comparison result, and formulates an adjustment strategy according to the comparison result and the motor health index.

[0011] Furthermore, the analysis module includes:

[0012] A first data preprocessing unit, used for cleaning, converting and normalizing the real-time data and the historical data to obtain a first processing result;

[0013] a first feature extraction unit connected to the first data preprocessing unit, for extracting harmonic components of current, stability of voltage, distribution of temperature and rotation speed fluctuation from the first processing result to obtain a first feature result;

[0014] A model building unit is connected to the first feature extraction unit and is used to build a prediction model according to the first feature result to predict the prediction operation efficiency.

[0015] Furthermore, the model building unit includes:

[0016] A model training subunit, used for training the prediction model according to the feature result and a part of the historical data to obtain a training model;

[0017] A model verification subunit, connected to the model training subunit, for verifying the training model according to another part of the historical data to obtain a verification model;

[0018] The model optimization subunit is connected to the model verification subunit and is used to optimize the verification model to predict the prediction operation efficiency.

[0019] Furthermore, the prediction module includes:

[0020] A data integration unit, for integrating the raw material moisture, the raw material hardness, the feed amount and the predicted operation efficiency into a data set;

[0021] a second feature extraction unit connected to the data integration unit, for extracting the raw material hardness grade, feed amount distribution and feed rate of the data set to obtain a second feature result;

[0022] A model training unit is connected to the second feature extraction unit, and is used to construct a second prediction model using the second feature result as an input parameter of the model and train the second prediction model to predict the optimized operation efficiency.

[0023] Furthermore, the prediction module also includes:

[0024] a second data preprocessing unit, configured to filter, denoise and normalize the humidity, the temperature, the dust amount and the optimized operation efficiency to obtain a second processing result;

[0025] a degree impact analysis unit, used for analyzing the relationship between the humidity, the temperature and the amount of dust on the optimized operation efficiency to obtain an analysis result;

[0026] a third feature extraction unit connected to the second data preprocessing unit, for extracting the humidity level, the temperature range, and the dust volume threshold of the second processing result to obtain a third feature result;

[0027] A health index calculation unit is connected to the degree impact analysis unit and the third feature weighting unit respectively, and is used to calculate the motor health index according to the analysis result and the third feature result.

[0028] Furthermore, the impact degree analysis unit includes:

[0029] A humidity impact subunit, used for analyzing the impact of the humidity on the optimized operation efficiency to obtain a first analysis result;

[0030] a temperature impact subunit, used for analyzing the impact of the temperature on the optimized operation efficiency to obtain a second analysis result;

[0031] a dust amount impact subunit, used for analyzing the impact of the dust amount on the optimized operation efficiency to obtain a third analysis result;

[0032] a factor interaction subunit, used for analyzing the interaction among the temperature, the humidity and the dust amount to obtain a fourth analysis result;

[0033] The degree ranking subunit is respectively connected to the humidity impact subunit, the temperature impact subunit, the dust amount impact subunit and the factor interaction impact subunit, and calculates the impact degrees of the temperature, the humidity and the dust amount according to the first analysis result, the second analysis result, the third analysis result and the fourth analysis result to obtain an impact score, and sets a priority according to the impact score.

[0034] Furthermore, the adjustment module includes:

[0035] A power factor calculation unit, used for measuring a phase difference according to the voltage and the current to obtain a power factor;

[0036] an input power calculation unit, connected to the power factor calculation unit, and calculating the actual input power according to the power factor, the current and the voltage;

[0037] An output power calculation unit is connected to the input power calculation unit and calculates the optimized output power according to the actual input power and the optimized operating efficiency.

[0038] Furthermore, the adjustment module also includes:

[0039] A target output power setting unit, used to set the target output power;

[0040] a power comparison unit connected to the target output power setting unit, for comparing the optimized output power with the target output power to obtain a comparison result;

[0041] An adjustment strategy formulation unit is connected to the power comparison unit and formulates the adjustment strategy according to the comparison result and the motor health index.

[0042] Furthermore, the power comparison unit comprises:

[0043] A target power receiving subunit, used for receiving the target output power;

[0044] A comparison calculation subunit is connected to the target power receiving subunit, and is used to compare the actual output power with the target output power to determine whether there is a power deviation in the actual output efficiency, wherein:

[0045] If the actual output power is greater than or equal to the target output power, then there is no deviation in the actual output power;

[0046] If the actual output power is less than the target output power, then there is a deviation in the actual output power.

[0047] Furthermore, the adjustment strategy formulation unit includes:

[0048] An operating point optimization subunit, for adjusting the operating point of the motor to a target efficiency point when the actual operating point of the motor deviates from the highest efficiency point;

[0049] The health management subunit is used to change the operating parameters of the motor when the motor health index is lower than a preset safety health index.

[0050] Compared with the prior art, the beneficial effect of the present invention is that, through the real-time data collection and analysis of the acquisition module, the system can accurately understand the current working state of the motor. Based on historical data and real-time data, the analysis module can predict the operating efficiency of the motor and optimize the working parameters of the motor. The adjustment module adjusts the operating state of the motor according to the comparison result of the actual input power and the optimized output power to reduce unnecessary energy consumption. By building a relationship model based on environmental data and load conditions, the service life of the motor can be predicted more accurately. By optimizing the working parameters of the motor, the system can reduce the loss of reactive power, thereby reducing overall energy consumption.

[0051] In particular, the data preprocessing unit improves the data quality by cleaning, converting and normalizing real-time data and historical data. The feature results make data analysis closer to the actual working conditions of the motor by extracting current harmonic components, voltage stability, temperature distribution and speed fluctuation. The model building unit uses the extracted feature results to build a prediction model, which can accurately predict the operating efficiency of the motor.

[0052] In particular, the process of the model training subunit and the model verification subunit helps to improve the generalization ability of the model when facing new data, ensuring that the model can stably predict the motor operating efficiency. The optimization subunit further enhances the generalization ability of the model by reducing the number of features and dealing with data imbalance.

[0053] In particular, the data integration unit can reduce the time and complexity of data processing and improve data quality by integrating the data into one data set. The feature extraction of the second feature extraction unit and the model training of the model training unit realize efficient conversion from raw data to prediction results, which not only improves production efficiency, but also helps enterprises reduce costs, improve product quality and enhance market competitiveness.

[0054] In particular, the second preprocessing unit improves the quality and accuracy of the data through filtering, denoising and normalization. The degree impact analysis unit can identify which environmental factors have the greatest impact on the motor operating efficiency by analyzing the relationship between humidity, temperature and dust volume and optimizing operating efficiency. This helps to formulate targeted maintenance strategies to maximize the efficiency of the motor. The third feature extraction unit helps to reduce the complexity of the data by extracting key features. The health index calculation unit can provide a standardized evaluation of the health status of the motor by calculating the health index, which helps to improve the management level of the entire motor group.

[0055] In particular, the humidity impact subunit helps to identify and quantify the impact of humidity changes on motor operating efficiency, so as to control and adjust humidity in a targeted manner to improve motor efficiency. The temperature impact subunit can evaluate the impact of ambient temperature on motor performance, so as to take measures to optimize temperature conditions during design or operation to improve motor efficiency and reliability. The dust volume impact subunit can analyze the impact of dust volume on motor operating efficiency and take corresponding cleaning and protection measures to reduce the negative impact of dust on motor performance. The factor interaction subunit helps to reveal the interaction between environmental factors such as humidity, temperature and dust volume, and provide a basis for comprehensive optimization of the motor operating environment. The degree ranking subunit calculates the impact score of each influencing factor on the motor operating efficiency based on the analysis results of each influencing factor, and provides a quantitative basis for formulating optimization strategies. It helps to determine which factors have the most significant impact on motor efficiency, so as to formulate targeted priority strategies and improve the efficiency and effectiveness of optimization measures.

[0056] In particular, the power factor calculation unit can timely discover efficiency problems in the operation of the motor by monitoring the power factor in real time. The input power calculation unit can adjust the load of the motor by calculating the actual output power to ensure that the motor operates at the optimal working point, thereby improving the overall operating efficiency. The output power calculation unit helps to determine the ideal working point of the motor in an optimized state, thereby improving the working efficiency and stability of the motor.

[0057] In particular, the target output power setting unit helps to clarify the target of motor operation, ensure that the motor operates in the high-efficiency area, and improve the overall operating efficiency. By setting a reasonable power target, the motor can be avoided from overload or underload operation and the life of the motor can be extended. The power unit can monitor the motor operating status in real time, and by comparing the actual output power with the target output power, promptly discover and solve problems in the motor operation. It helps to ensure that the motor always operates at the optimal efficiency point and reduce energy waste. The adjustment strategy unit formulates targeted adjustment strategies based on the comparison results and the motor health index to optimize the motor operating parameters.

[0058] In particular, by comparing the actual output power with the target output power in real time, the power comparison unit can timely detect and correct the power deviation, thereby improving the operating efficiency of the motor. By keeping the motor running in an optimized power output state, the power comparison unit helps to reduce the wear of the motor caused by long-term operation in a non-optimized state, thereby extending the service life of the motor.

[0059] In particular, through the Susonghu working point optimization subunit, the motor can always operate near the optimal efficiency point during its operating cycle, which can reduce energy consumption, reduce operating costs, and improve overall energy efficiency. The health management subunit can monitor the health status of the motor in real time and adjust the operating parameters in time when the motor health index is lower than the preset safety health index, thereby extending the service life of the motor. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 A schematic diagram of the structure of a motor drive optimization management system based on data analysis provided by an embodiment of the present invention;

[0061] Figure 2 A schematic diagram of the structure of an analysis module in a motor drive optimization management system based on data analysis provided by an embodiment of the present invention;

[0062] Figure 3 A schematic diagram of the structure of a prediction module in a motor drive optimization management system based on data analysis provided by an embodiment of the present invention;

[0063] Figure 4 A schematic diagram of the structure of an adjustment module in a motor drive optimization management system based on data analysis provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0064] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0065] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0066] It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside" and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the drawings. This is merely for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.

[0067] In addition, it should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0068] See also Figure 1 As shown, the motor drive optimization management system based on data analysis provided by the embodiment of the present invention includes:

[0069] The acquisition module 10 is used to acquire the current, voltage, temperature and speed of the motor in real time to obtain real-time data, obtain corresponding historical data according to the real-time data, and also to acquire the load data of the ball mill and the surrounding environmental data, wherein the load data includes raw material humidity, raw material hardness and feed amount, and the environmental data includes humidity, temperature and dust amount;

[0070] The analysis module 20 is connected to the acquisition module 10, and is used to predict the operating efficiency of the motor according to the real-time data and the historical data to obtain the predicted operating efficiency; to build a relationship model according to the raw material humidity, the raw material hardness, the feed amount and the predicted operating efficiency to optimize the predicted operating efficiency to obtain the optimized operating efficiency; and to predict the service life of the motor according to the optimized operating efficiency, the humidity, the temperature and the dust amount to obtain the motor health index;

[0071] The adjustment module 40 is connected to the analysis module 20, calculates the actual input power according to the current and the voltage, calculates the optimized output power according to the actual power and the optimized operating efficiency, compares the optimized output power with a preset target output power to obtain a comparison result, and adjusts the real-time data of the motor according to the comparison result and the motor health index.

[0072] Specifically, the acquisition module installs a current transformer (CT) and a voltage transformer (VT) to monitor the current and voltage of the motor. Use a temperature sensor and a speed sensor to obtain the temperature and speed data of the motor. Ensure that all sensors have high precision and fast response characteristics. Establish a database to store historical data of motor operation. Use instruments to monitor the load data of the ball mill (raw material humidity, hardness and feed amount). Deploy environmental sensors to monitor the humidity, temperature and dust volume of the surrounding environment. The analysis module uses a machine learning algorithm (such as regression analysis) to predict the motor operation efficiency. Train the model to predict the real-time operating efficiency of the motor and verify it with historical data. Use multivariate analysis methods, such as multivariate regression analysis, to link raw material humidity, hardness, feed amount and motor operating efficiency. Apply optimization algorithms (such as genetic algorithms, particle swarm optimization) to optimize the relationship model. Combine the optimized operating efficiency and other environmental and load factors to predict the service life of the motor. The service life prediction model (such as accelerated life test data) calculates the motor health index. Based on the collected current and voltage data, the actual input power is calculated using the power formula P = UI × cos (phi), where cos (phi) is the power factor. Use the optimized operating efficiency provided by the analysis module in combination with the actual input power to calculate the optimized output power. Compare the optimized output power with the preset target output power. Based on the comparison results and the motor health index, formulate an adjustment strategy, such as adjusting the motor's operating voltage, current limit, speed or load distribution. Execute the adjustment strategy through the motor drive or control system. After the adjustment is implemented, monitor the operation of the motor and collect feedback data.

[0073] Specifically, through the real-time data collection and analysis of the acquisition module, the system can accurately understand the current working state of the motor. Based on historical data and real-time data, the analysis module can predict the operating efficiency of the motor and optimize the working parameters of the motor. The adjustment module adjusts the operating state of the motor according to the comparison result of the actual input power and the optimized output power to reduce unnecessary energy consumption. The relationship model is constructed according to the environmental data and load conditions, which can more accurately predict the service life of the motor. By optimizing the working parameters of the motor, the system can reduce the loss of invalid power, thereby reducing the overall energy consumption.

[0074] Specifically, if Figure 2 As shown, the analysis module 20 includes:

[0075] A first data preprocessing unit 21, used for cleaning, transforming and normalizing the real-time data and the historical data to obtain a first processing result;

[0076] A first feature extraction unit 22, connected to the first data preprocessing unit 21, for extracting harmonic components of current, voltage stability, temperature distribution and speed fluctuation from the first processing result to obtain a first feature result;

[0077] The model building unit 23 is connected to the first feature extraction unit 22, and is used to build a prediction model according to the first feature result to predict the predicted operating efficiency.

[0078] Specifically, the data preprocessing unit removes noise and outliers from the data to ensure the accuracy and reliability of the data. Convert the data into a format suitable for further analysis, such as from an analog signal to a digital signal. Scale the data to a uniform range to obtain a first processing result. The feature extraction unit analyzes the spectrum of the current signal and extracts harmonic components to identify electromagnetic interference or grid problems of the motor. Monitor the fluctuation and stability of the voltage and evaluate the voltage environment in which the motor operates. Measure the temperature distribution of various parts of the motor to identify hot spots or temperature non-uniformity problems. Detect fluctuations in the motor speed to evaluate the impact of mechanical vibration or load changes. The model building unit uses the preprocessed and feature-extracted data to prepare a training data set. Select a suitable machine learning algorithm to build a prediction model, such as a support vector machine, a random forest, a neural network, etc. Use the training data set to train the model, optimize the model parameters and predict the prediction operation efficiency through techniques such as cross-validation.

[0079] Specifically, the data preprocessing unit improves the data quality by cleaning, converting and normalizing the real-time data and historical data. The feature results extract the current harmonic components, voltage stability, temperature distribution and speed fluctuation to make the data analysis closer to the actual working conditions of the motor. The model building unit uses the extracted feature results to build a prediction model, which can accurately predict the operating efficiency of the motor.

[0080] Specifically, the model building unit includes:

[0081] A model training subunit, used for training the prediction model according to the feature result and a part of the historical data to obtain a training model;

[0082] A model verification subunit, connected to the model training subunit, for verifying the training model according to another part of the historical data to obtain a verification model;

[0083] The model optimization subunit is connected to the model verification subunit and is used to optimize the verification model to predict the prediction operation efficiency.

[0084] In this embodiment, there is a motor operation data set containing the following information: current (I): 12.5A; voltage: 240V; temperature (T): 85°C speed (N): 1450RPM; current harmonic component: 10%; voltage stability: 97%; temperature distribution: mean 80°C, standard deviation 5°C; speed fluctuation: mean 10RPM, standard deviation 2RPM.

[0085] First, delete the records with missing values ​​or use interpolation to fill the missing values. Convert non-numeric data (such as temperature distribution) to numeric data. For example, convert it to a value between 0 and 100. For example, if 80°C is the mean, convert it to 50 (assuming that 50°C corresponds to 0 and 100°C corresponds to 100). If the main harmonics detected are the 3rd and 5th, two new features can be created. If the voltage stability is less than 95%, mark it as 1, otherwise it is 0. Use the mean and standard deviation as features. Use the mean and standard deviation as features. Use scikit-learn's RandomForestRegressor to train the model. RandomForestRegressor is a regression model in the scikit-learn library, which is based on the random forest algorithm. Random forest is an ensemble learning method that improves the accuracy and stability of predictions by combining multiple decision trees.

[0086] Specifically, first, you need to import the scikit-learn library and the RandomForestRegressor class. Organize the historical data of the motor into a format suitable for model training, including converting non-numeric features to numeric types and handling missing values ​​and outliers. Create an instance of RandomForestRegressor and set appropriate parameters, such as the number of trees (n_estimators), maximum depth (max_depth), minimum number of samples required for splitting (min_samples_split), etc. Use historical data to train the model, the model will automatically build multiple decision trees, and adjust parameters during training to optimize performance. Use the validation data set to evaluate the performance of the model and calculate indicators such as prediction error, correlation coefficient, and mean square error. Adjust the model parameters based on the evaluation results to improve the accuracy of the prediction.

[0087] Specifically, the process of the model training subunit and the model verification subunit helps to improve the generalization ability of the model when facing new data, ensuring that the model can stably predict the motor operating efficiency. The optimization subunit further enhances the generalization ability of the model by reducing the number of features and dealing with data imbalance.

[0088] Specifically, if Figure 3 As shown, the prediction module 30 includes:

[0089] A data integration unit 31, for integrating the raw material moisture, the raw material hardness, the feed amount and the predicted operation efficiency into a data set;

[0090] A second feature extraction unit 32, connected to the data integration unit 31, for extracting the raw material hardness grade, feed amount distribution and feed rate of the data set to obtain a second feature result;

[0091] The model training unit 33 is connected to the second feature extraction unit 32, and is used to construct a second prediction model using the second feature result as an input parameter of the model and train the second prediction model to predict the optimized operation efficiency.

[0092] Specifically, the data integration unit collects historical data on raw material moisture, raw material hardness, feed amount and predicted operating efficiency. A database or data warehouse is used to store these data and establish data connections. Incomplete, inaccurate or inconsistent data is eliminated through data cleaning and preprocessing. The cleaned data is integrated into a unified data set. The second feature extraction unit extracts information about the raw material hardness grade, feed amount distribution and feed rate from the integrated data set. Cluster analysis is applied to determine the grade of raw material hardness. Statistical methods such as standard deviation, mean or median are used to determine the distribution of feed amount. The feed rate is determined by time series analysis or rate calculation formula. These extracted features are combined into a second feature result. A random forest algorithm is selected as the prediction model. The second feature result is used as the input parameter of the model. The model is trained using the historical data set, and the model parameters are adjusted to minimize the prediction error. The cross-validation method is applied to evaluate the performance and generalization ability of the model. Once the second prediction model is trained and its performance meets the preset standards, it can be used to predict the efficiency of the production line.

[0093] Specifically, the data integration unit can reduce the time and complexity of data processing and improve data quality by integrating the data into one data set. The feature extraction of the second feature extraction unit and the model training of the model training unit realize efficient conversion from raw data to prediction results, which not only improves production efficiency, but also helps enterprises reduce costs, improve product quality and enhance market competitiveness.

[0094] Specifically, the prediction module also includes:

[0095] a second data preprocessing unit, configured to filter, denoise and normalize the humidity, the temperature, the dust amount and the optimized operation efficiency to obtain a second processing result;

[0096] a degree impact analysis unit, used for analyzing the relationship between the humidity, the temperature and the amount of dust on the optimized operation efficiency to obtain an analysis result;

[0097] a third feature extraction unit connected to the second data preprocessing unit, for extracting the humidity level, the temperature range, and the dust volume threshold of the second processing result to obtain a third feature result;

[0098] A health index calculation unit is connected to the degree impact analysis unit and the third feature weighting unit respectively, and is used to calculate the motor health index according to the analysis result and the third feature result.

[0099] In this embodiment, it is assumed that the collected data includes humidity, temperature, dust volume and the optimized operation efficiency of the motor. For example, the humidity is 60%, the temperature is 30°C, the dust volume is 50 g / m3, and the optimized operation efficiency of the motor is 85%. These data are filtered and denoised to eliminate inaccurate data caused by sensor errors or environmental interference. The data are normalized so that the data is scaled to the same range for easy analysis. For example, the humidity, temperature and dust volume are converted to values ​​between 0 and 1, and the optimized operation efficiency of the motor is converted to a value between 0 and 100. The degree of impact analysis unit analyzes these pre-processed data to determine the degree of their influence on the optimized operation efficiency of the motor. For example, by calculating the correlation coefficient between humidity, temperature and dust volume and the optimized operation efficiency of the motor, it can be found that humidity has a strong negative correlation with motor efficiency (correlation coefficient is -0.8), while temperature and dust volume have a weak correlation with motor efficiency. The third feature extraction unit extracts the features that have the greatest impact on the optimized operation efficiency of the motor according to the results of the degree of impact analysis unit. In this case, the humidity level is extracted as a key feature because it has a significant impact on the motor efficiency. The health index calculation unit uses the extracted features and degree of impact analysis results to calculate the health index of the motor. For example, a simple linear model can be used to predict the motor efficiency: motor efficiency = 85-0.5×humidity. Substituting the humidity level into the model, a predicted value of the motor efficiency can be obtained. Then, the health index of the motor can be calculated based on this predicted value and other indicators (such as temperature and dust volume). The health index can be a simple numerical value that indicates how good the motor is running.

[0100] Specifically, the second preprocessing unit improves the quality and accuracy of the data through filtering, denoising and normalization. The degree impact analysis unit can identify which environmental factors have the greatest impact on the motor's operating efficiency by analyzing the relationship between humidity, temperature and dust volume and optimizing operating efficiency. This helps to formulate targeted maintenance strategies to maximize the efficiency of the motor. The third feature extraction unit helps to reduce the complexity of the data by extracting key features. The health index calculation unit can provide a standardized evaluation of the health status of the motor by calculating the health index, which helps to improve the management level of the entire motor population.

[0101] Specifically, the impact degree analysis unit includes:

[0102] A humidity impact subunit, used for analyzing the impact of the humidity on the optimized operation efficiency to obtain a first analysis result;

[0103] a temperature impact subunit, used for analyzing the impact of the temperature on the optimized operation efficiency to obtain a second analysis result;

[0104] a dust amount impact subunit, used for analyzing the impact of the dust amount on the optimized operation efficiency to obtain a third analysis result;

[0105] a factor interaction subunit, used for analyzing the interaction among the temperature, the humidity and the dust amount to obtain a fourth analysis result;

[0106] The degree ranking subunit is respectively connected to the humidity impact subunit, the temperature impact subunit, the dust amount impact subunit and the factor interaction impact subunit, and calculates the impact degrees of the temperature, the humidity and the dust amount according to the first analysis result, the second analysis result, the third analysis result and the fourth analysis result to obtain an impact score, and sets a priority according to the impact score.

[0107] Specifically, use statistical methods (such as regression analysis) to analyze the relationship between humidity and motor operating efficiency. Based on historical data, determine the quantitative impact of humidity on motor operating efficiency. For example, when the humidity of the raw material increases from 10% to 20%, the motor efficiency decreases by 5%. Also use statistical methods to analyze the relationship between temperature and motor operating efficiency. For example, for every 10°C increase in ambient temperature, the motor efficiency decreases by 3%. Analyze the relationship between dust volume and motor operating efficiency. For example, for every 10mg / m increase in dust volume, the motor efficiency decreases by 3%. 3, the motor efficiency drops by 1%. Use multivariate statistical analysis methods (such as multiple regression analysis) to evaluate the interaction of these factors. Based on the analysis results of the above sub-units, calculate the impact score of each factor. The impact score is calculated by quantifying the contribution of each factor to the motor operating efficiency. The impact score is used to set priorities and determine which factors need to be prioritized in order to optimize the motor operating efficiency. For example, if humidity has the highest impact score, then reducing the humidity of the raw materials is a priority.

[0108] Specifically, the humidity impact subunit helps to identify and quantify the impact of humidity changes on motor operating efficiency, so as to control and adjust humidity in a targeted manner to improve motor efficiency. The temperature impact subunit can evaluate the impact of ambient temperature on motor performance, so as to take measures to optimize temperature conditions during design or operation to improve motor efficiency and reliability. The dust volume impact subunit can analyze the impact of dust volume on motor operating efficiency and take corresponding cleaning and protection measures to reduce the negative impact of dust on motor performance. The factor interaction subunit helps to reveal the interaction between environmental factors such as humidity, temperature and dust volume, and provide a basis for comprehensive optimization of the motor operating environment. The degree ranking subunit calculates the impact score of each influencing factor on the motor operating efficiency based on the analysis results of each influencing factor, and provides a quantitative basis for formulating optimization strategies. It helps to determine which factors have the most significant impact on motor efficiency, so as to formulate targeted priority strategies and improve the efficiency and effectiveness of optimization measures.

[0109] Specifically, if Figure 4 As shown, the adjustment module 40 includes:

[0110] A power factor calculation unit 41, used for measuring a phase difference according to the voltage and the current to obtain a power factor;

[0111] An input power calculation unit 42, connected to the power factor calculation unit, calculates the actual input power according to the power factor, the current and the voltage;

[0112] The output power calculation unit 43 is connected to the input power calculation unit 41, and calculates the optimized output power according to the actual input power and the optimized operating efficiency.

[0113] Specifically, the voltage and current values ​​of the motor when it is running are measured using a voltage and current measurement unit. The phase difference between the voltage and current is calculated, which can be achieved by measuring the phase angle between the two. The power factor is calculated based on the phase difference, and the power factor is the ratio of the power of the same phase part of the voltage and current to the total power. Using the calculated power factor, the measured current and voltage values, the power formula P = UIcos (φ) is applied to calculate the actual input power of the motor. Among them, P is power, U is voltage, I is current, and φ is the phase angle corresponding to the power factor. According to the target value of the optimized operating efficiency, combined with the actual input power obtained by the input power calculation unit, the efficiency formula η = P_out / P_in is applied to calculate the optimized output power.

[0114] Where η is the efficiency, P_out is the optimized output power, and P_in is the input power.

[0115] Specifically, the power factor calculation unit can timely discover efficiency problems in the operation of the motor by real-time monitoring of the power factor. The input power calculation unit can adjust the load of the motor by calculating the actual output power to ensure that the motor operates at the optimal operating point, thereby improving the overall operating efficiency. The output power calculation unit helps to determine the ideal operating point of the motor in an optimized state, thereby improving the working efficiency and stability of the motor.

[0116] Specifically, the adjustment module also includes:

[0117] A target output power setting unit, used to set the target output power;

[0118] a power comparison unit connected to the target output power setting unit, for comparing the optimized output power with the target output power to obtain a comparison result;

[0119] An adjustment strategy formulation unit is connected to the power comparison unit and formulates the adjustment strategy according to the comparison result and the motor health index.

[0120] Specifically, the target output power of the motor is set according to the working mode of the motor and the external load demand. The target output power setting unit may include a database or algorithm for calculating the target power according to different working conditions. The power comparison unit uses the real-time optimized output power data to compare with the preset target output power. The adjustment strategy formulation unit determines whether it is necessary to adjust the motor's voltage, current, speed and other parameters, as well as the direction and amplitude of the adjustment based on the comparison result and the health index of the motor.

[0121] Specifically, the target output power setting unit helps to clarify the target of motor operation, ensure that the motor operates in the high-efficiency area, and improve the overall operating efficiency. By setting a reasonable power target, the motor can be avoided from overload or underload operation and the life of the motor can be extended. The power unit can monitor the motor operating status in real time, and by comparing the actual output power with the target output power, promptly discover and solve problems in the motor operation. It helps to ensure that the motor always operates at the optimal efficiency point and reduce energy waste. The adjustment strategy unit formulates targeted adjustment strategies based on the comparison results and the motor health index to optimize the motor operating parameters.

[0122] Specifically, the power comparison unit includes:

[0123] A target power receiving subunit, used for receiving the target output power;

[0124] A comparison calculation subunit is connected to the target power receiving subunit, and is used to compare the actual output power with the target output power to determine whether there is a power deviation in the actual output efficiency, wherein:

[0125] If the actual output power is greater than or equal to the target output power, then there is no deviation in the actual output power;

[0126] If the actual output power is less than the target output power, then there is a deviation in the actual output power.

[0127] Specifically, the actual output power of the motor is monitored in real time. The actual output power is compared with the target output power. The comparison result is calculated to determine whether there is a deviation in the actual output power. If there is a deviation in the actual output power, the cause of the deviation is further analyzed. According to the cause of the deviation, corresponding adjustment measures are taken, such as adjusting the working parameters of the motor, changing the load distribution, starting the backup system, etc. After the adjustment, the actual output power is monitored again, and the comparison calculation steps are repeated to ensure that the motor operates in an optimized state.

[0128] Specifically, by comparing the actual output power with the target output power in real time, the power comparison unit can timely detect and correct the power deviation, thereby improving the operating efficiency of the motor. By keeping the motor running in an optimized power output state, the power comparison unit helps reduce the wear of the motor caused by long-term operation in a non-optimized state, thereby extending the service life of the motor.

[0129] Specifically, the adjustment strategy formulation unit includes:

[0130] An operating point optimization subunit, for adjusting the operating point of the motor to a target efficiency point when the actual operating point of the motor deviates from the highest efficiency point;

[0131] The health management subunit is used to change the operating parameters of the motor when the motor health index is lower than a preset safety health index.

[0132] Specifically, the actual working point of the motor is monitored, which can be determined by measuring the current, voltage, speed and other parameters of the motor in real time. The highest efficiency point of the motor is determined, which is usually achieved through the characteristic curve of the motor. The highest efficiency point corresponds to the optimal efficiency of the motor. The actual working point is compared with the highest efficiency point. If the actual working point deviates from the highest efficiency point, the motor operating parameters that need to be adjusted, such as current, voltage, speed, etc., are calculated based on the degree of deviation and the target efficiency point. The working point of the motor is adjusted, and the operating parameters of the motor are changed by controlling the motor driver so that the actual working point gradually approaches the desired target efficiency point.

[0133] Specifically, a preset safety and health index is set, which can be determined based on factors such as the motor's design parameters, service life, and operating conditions. The motor's health index is monitored regularly by monitoring and analyzing key parameters of the motor, such as temperature, vibration, noise, etc. Compare the monitored motor health index with the preset safety and health index. If the motor health index is lower than the preset safety and health index, determine the measures that need to be taken to improve the motor's operating conditions based on the motor's current health status and the preset safety and health index, such as adjusting the load, changing the operating frequency, etc. Change the motor's operating parameters and adjust the motor's operating status according to the determined measures to protect the motor and extend its service life.

[0134] Specifically, through the Susonghu working point optimization subunit, the motor can always operate near the optimal efficiency point during its operating cycle, which can reduce energy consumption, reduce operating costs, and improve overall energy efficiency. The health management subunit can monitor the health status of the motor in real time and adjust the operating parameters in time when the motor health index is lower than the preset safety health index, thereby extending the service life of the motor.

[0135] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0136] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A motor drive optimization management system based on data analysis, characterized in that: A collection module is used to collect the current, voltage, temperature and speed of the motor in real time to obtain real-time data, obtain corresponding historical data according to the real-time data, and collect the load data of the ball mill and the surrounding environmental data, the load data includes raw material humidity, raw material hardness and feed amount, and the environmental data includes humidity, temperature and dust amount; An analysis module, connected to the acquisition module, for predicting the operating efficiency of the motor according to the real-time data and the historical data to obtain a predicted operating efficiency; A prediction module connected to the analysis module, constructing a relationship model according to the raw material humidity, the raw material hardness, the feed amount and the predicted operation efficiency to optimize the predicted operation efficiency to obtain the optimized operation efficiency, and analyzing the influence of the humidity, the temperature and the dust amount on the optimized operation efficiency to obtain the motor health index; an adjustment module, connected to the prediction module, calculating the actual input power according to the current and the voltage, calculating the optimized output power according to the actual input power and the optimized operating efficiency, comparing the optimized output power with a preset target output power to obtain a comparison result, and formulating an adjustment strategy according to the comparison result and the motor health index; The prediction module comprises: A data integration unit, for integrating the raw material moisture, the raw material hardness, the feed amount and the predicted operation efficiency into a data set; a second feature extraction unit connected to the data integration unit, for extracting the raw material hardness grade, feed amount distribution and feed rate of the data set to obtain a second feature result; a model training unit, connected to the second feature extraction unit, for constructing a second prediction model using the second feature result as an input parameter of the model and training the second prediction model to predict the optimization operation efficiency; The prediction module also includes: a second data preprocessing unit, configured to filter, denoise and normalize the humidity, the temperature, the dust amount and the optimized operation efficiency to obtain a second processing result; a degree impact analysis unit, used for analyzing the relationship between the humidity, the temperature and the amount of dust on the optimized operation efficiency to obtain an analysis result; a third feature extraction unit connected to the second data preprocessing unit, for extracting the humidity level, the temperature range, and the dust volume threshold of the second processing result to obtain a third feature result; a health index calculation unit, connected to the degree impact analysis unit and the third feature weighting unit respectively, for calculating the motor health index according to the analysis result and the third feature result; The motor health index indicates how good the motor operating status is.

2. The motor drive optimization management system based on data analysis according to claim 1 is characterized in that: The analysis module comprises: A first data preprocessing unit, used for cleaning, converting and normalizing the real-time data and the historical data to obtain a first processing result; a first feature extraction unit connected to the first data preprocessing unit, for extracting harmonic components of current, stability of voltage, distribution of temperature and rotation speed fluctuation from the first processing result to obtain a first feature result; A model building unit is connected to the first feature extraction unit and is used to build a prediction model according to the first feature result to predict the prediction operation efficiency.

3. The motor drive optimization management system based on data analysis according to claim 2 is characterized in that: The model building unit comprises: A model training subunit, used for training the prediction model according to the feature result and a part of the historical data to obtain a training model; A model verification subunit, connected to the model training subunit, for verifying the training model according to another part of the historical data to obtain a verification model; The model optimization subunit is connected to the model verification subunit and is used to optimize the verification model to predict the prediction operation efficiency.

4. The motor drive optimization management system based on data analysis according to claim 1, characterized in that: The impact degree analysis unit comprises: A humidity impact subunit, used for analyzing the impact of the humidity on the optimized operation efficiency to obtain a first analysis result; a temperature impact subunit, used for analyzing the impact of the temperature on the optimized operation efficiency to obtain a second analysis result; a dust amount impact subunit, used for analyzing the impact of the dust amount on the optimized operation efficiency to obtain a third analysis result; a factor interaction subunit, used for analyzing the interaction among the temperature, the humidity and the dust amount to obtain a fourth analysis result; The degree ranking subunit is respectively connected to the humidity impact subunit, the temperature impact subunit, the dust amount impact subunit and the factor interaction impact subunit, and calculates the impact degrees of the temperature, the humidity and the dust amount according to the first analysis result, the second analysis result, the third analysis result and the fourth analysis result to obtain an impact score, and sets a priority according to the impact score.

5. The motor drive optimization management system based on data analysis according to claim 4 is characterized in that: The adjustment module comprises: A power factor calculation unit, used for measuring a phase difference according to the voltage and the current to obtain a power factor; an input power calculation unit, connected to the power factor calculation unit, and calculating the actual input power according to the power factor, the current and the voltage; An output power calculation unit is connected to the input power calculation unit and calculates the optimized output power according to the actual input power and the optimized operating efficiency.

6. The motor drive optimization management system based on data analysis according to claim 5, characterized in that: The adjustment module also includes: A target output power setting unit, used to set the target output power; a power comparison unit connected to the target output power setting unit, for comparing the optimized output power with the target output power to obtain a comparison result; An adjustment strategy formulation unit is connected to the power comparison unit and formulates the adjustment strategy according to the comparison result and the motor health index.

7. The motor drive optimization management system based on data analysis according to claim 6, characterized in that: The power comparison unit comprises: A target power receiving subunit, used for receiving the target output power; A comparison calculation subunit is connected to the target power receiving subunit, and is used to compare the actual output power with the target output power to determine whether there is a power deviation in the actual output efficiency, wherein: If the actual output power is greater than or equal to the target output power, then there is no deviation in the actual output power; If the actual output power is less than the target output power, then there is a deviation in the actual output power.

8. The motor drive optimization management system based on data analysis according to claim 7, characterized in that: The adjustment strategy formulation unit includes: An operating point optimization subunit, for adjusting the operating point of the motor to a target efficiency point when the actual operating point of the motor deviates from the highest efficiency point; The health management subunit is used to change the operating parameters of the motor when the motor health index is lower than a preset safety health index.

Images