Energy-saving control optimization method for high-speed motor of air compressor
By obtaining the air pressure and flow demand information of the air compressor, performing control parameter matching and abnormal analysis, optimizing the control strategy of the air compressor, solving the problem that traditional control systems cannot respond to load changes, and improving equipment stability and energy utilization efficiency.
Patent Information
- Application Number
- CN202411129033.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-16
- Publication Date
- 2024-12-06
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Traditional air compressor control systems cannot respond to load changes or fluctuations in equipment status in a timely manner, resulting in fluctuations in air pressure and flow, affecting equipment stability and product quality.
By interactively obtaining the air pressure and flow demand information of the target pneumatic equipment, performing control parameters matching and continuous simulation, performing abnormal analysis to generate compensation control parameters combinations, and optimizing the control strategy of the air compressor.
It improves the response accuracy and stability of the control system, reduces energy waste and equipment overload, and improves equipment performance and system efficiency.
Smart Images

Figure CN119087801A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of motor energy-saving control, and in particular to an energy-saving control optimization method for a high-speed motor of an air compressor. Background Art
[0002] The energy efficiency and economy of air compressors are often limited by the accuracy and adaptability of the control system. The control systems of traditional air compressors are often based on fixed parameter settings, and fail to make dynamic adjustments according to actual needs to adapt to actual operating conditions. This may cause the equipment to over-operate unnecessarily, thereby wasting energy. In addition, traditional control systems cannot respond to load changes or fluctuations in equipment status in a timely manner, resulting in fluctuations in air pressure and flow. Such fluctuations in the production process can lead to inconsistent product quality and may even cause damage to the equipment. Summary of the invention
[0003] The present application provides an energy-saving control optimization method for a high-speed motor of an air compressor, aiming to solve the technical problem that the setting of control parameters in the prior art fails to adapt to the real-time demand changes of the equipment, resulting in fluctuations in air pressure and flow, and the possibility of equipment overload or unstable operation.
[0004] The present application discloses an energy-saving control optimization method for a high-speed motor of an air compressor, the method comprising: interacting with a target pneumatic device to obtain compressed air demand information, wherein the compressed air demand information includes multiple air pressure demands and multiple flow demands of the target pneumatic device at multiple preset time nodes; obtaining a first target air pressure demand and a first target flow demand at a first target time node according to the compressed air demand information; matching control parameters according to the first target air pressure demand and the first target flow demand to generate a first control parameter combination; performing continuous control simulation of the high-speed motor of the air compressor based on the first control parameter combination, and performing simulation data collection to obtain a first simulation data set; performing an abnormality analysis on the first simulation data set to generate an abnormality analysis result, wherein the abnormality analysis includes an air pressure value abnormality analysis, an air pressure fluctuation abnormality analysis, a flow value abnormality analysis, a flow fluctuation abnormality analysis, a temperature value abnormality analysis, and a temperature fluctuation abnormality analysis; based on the abnormality analysis result, performing compensation optimization of the first control parameter combination to generate a first compensation control parameter combination; adding the first compensation control parameter combination to the target control scheme to perform optimized control of the high-speed motor of the air compressor.
[0005] One or more technical solutions provided in this application have at least the following technical effects or advantages: By interacting with the target pneumatic equipment, the air pressure and flow requirements at multiple time nodes are accurately obtained to ensure that the control system can be adjusted based on actual needs, improve the response accuracy to actual needs, and optimize energy utilization efficiency; control parameters are matched according to the target air pressure and flow requirements to ensure that the control parameters of the air compressor match the actual needs, improve the accuracy and stability of control, and reduce fluctuations and energy consumption during operation; through continuous control simulation and data acquisition, the first simulation data set is obtained to provide data support for further analysis and optimization; through detailed anomaly analysis of the simulation data, anomalies in air pressure, flow, temperature, etc. are identified, thereby improving the system's fault detection capability and response speed; control parameters are compensated and optimized according to the results of the anomaly analysis to generate a compensation control parameter combination, which improves the stability and response speed of the control and reduces the impact of anomalies on equipment performance; the compensation control parameter combination is applied to the actual control scheme to achieve optimized control of the high-speed motor of the air compressor, improve the overall performance of the equipment, reduce energy waste, and improve the stability and efficiency of the system.
[0006] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS
[0007] Figure 1 A schematic flow chart of an energy-saving control optimization method for a high-speed motor of an air compressor is provided for an embodiment of the present application.
[0008] Figure 2 A schematic flow chart of obtaining a first target air pressure requirement and a first target flow requirement in an energy-saving control optimization method for a high-speed motor of an air compressor is provided in an embodiment of the present application. DETAILED DESCRIPTION
[0009] The embodiment of the present application provides an energy-saving control optimization method for a high-speed motor of an air compressor, thereby solving the technical problem that the setting of control parameters in the prior art fails to adapt to the real-time demand changes of the equipment, resulting in fluctuations in air pressure and flow, and causing equipment overload or unstable operation.
[0010] After introducing the basic principles of the present application, various non-limiting implementation methods of the present application will be specifically described below in conjunction with the drawings in the specification.
[0011] like Figure 1 As shown, the embodiment of the present application provides an energy-saving control optimization method for a high-speed motor of an air compressor, the method comprising: The target pneumatic device is interacted with to obtain compressed air demand information, wherein the compressed air demand information includes multiple air pressure demands and multiple flow demands of the target pneumatic device at multiple preset time nodes.
[0012] First, determine the target pneumatic equipment that requires compressed air supply, including various industrial machines such as pneumatic tools, pneumatic conveyors, pneumatic actuators, etc. Determine the preset time nodes, which can be fixed time intervals, such as every hour, every minute, or a specific working period. The preset time nodes are determined based on the production process and equipment operation characteristics to accurately reflect the changes in the equipment's compressed air demand. Continuously collect the air pressure demand and flow demand of the target pneumatic equipment at the preset time nodes. The air pressure demand refers to the pressure value of the compressed air required by the equipment during operation, and the flow demand refers to the flow rate of compressed air required by the equipment during operation. Integrate the demand data to obtain compressed air demand information.
[0013] According to the compressed air demand information, a first target air pressure demand and a first target flow demand at a first target time node are acquired.
[0014] Determine the specific time point that needs to be analyzed, that is, the first target time node. By analyzing the compressed air demand information, determine the demand pattern at different time nodes, establish a mapping relationship between the time node and the air pressure demand and flow demand, and generate an air pressure demand scatter plot and a flow demand scatter plot based on the mapping relationship. These scatter plots show the demand changes at each preset time node. Perform curve fitting on the air pressure demand scatter plot and the flow demand scatter plot to generate an air pressure demand polynomial and a flow demand polynomial. Substitute the first target time node into the air pressure demand polynomial to calculate the first target air pressure demand at the time node, which represents the pressure value of the compressed air required by the target pneumatic equipment at the first target time node; similarly, substitute the first target time node into the flow demand polynomial to calculate the first target flow demand at the time node.
[0015] Control parameters are matched according to the first target air pressure requirement and the first target flow requirement to generate a first control parameter combination.
[0016] Obtain the historical control record set of the air compressor from big data, extract the historical control data related to the first target air pressure demand and the first target flow demand, including sample air pressure, sample flow and corresponding control parameter combination, perform similarity analysis on the sample air pressure and sample flow in the historical record and the current first target air pressure demand and first target flow demand, calculate the similarity coefficient between each historical record and the current demand, judge the degree of matching with the current demand, and if the similarity coefficient meets the preset similarity coefficient threshold, add the corresponding historical control parameter combination to the control parameter combination library. Introduce the fitness evaluation function, evaluate each control parameter combination in the control parameter combination library, calculate the fitness value of each combination, and obtain the combination with the highest fitness value as the first control parameter combination.
[0017] Based on the first control parameter combination, continuous control simulation of the high-speed motor of the air compressor is performed, and simulation data collection is performed to obtain a first simulation data set.
[0018] Construct a simulation model of the high-speed motor of the air compressor. The simulation model includes the physical characteristics, control logic, compressed air system characteristics, etc. of the motor, and can accurately simulate the operating state and response characteristics of the actual air compressor. Input the first control parameter combination into the simulation model as the initial parameter setting of the simulation control, start the simulation model, and perform continuous control simulation. During the simulation process, the high-speed motor of the air compressor operates according to the first control parameter combination to simulate the response under actual operating conditions. During the simulation process, the operation data is collected in real time according to the preset frequency, including air pressure, flow, motor speed, motor power, temperature, etc. The data collected during the simulation process are integrated to generate the first simulation data set.
[0019] Anomaly analysis is performed on the first simulation data set to generate anomaly analysis results, wherein the anomaly analysis includes air pressure value anomaly analysis, air pressure fluctuation anomaly analysis, flow value anomaly analysis, flow fluctuation anomaly analysis, temperature value anomaly analysis, and temperature fluctuation anomaly analysis.
[0020] Extract key parameters from the first simulation data set, including air pressure, flow rate, temperature, etc., organize these data in time series, and conduct numerical anomaly analysis. Specifically, according to the design specifications and operating experience of the air compressor, set the normal range of each parameter, check whether the value of each parameter at each time point exceeds the normal range, and take the value that exceeds the normal range as a numerical anomaly point, and record the time point of the numerical anomaly point and the corresponding parameter value. Perform fluctuation anomaly analysis, specifically, calculate the change of the parameter between adjacent time points, check whether the change exceeds the fluctuation threshold, and record the time point of the fluctuation anomaly point and the corresponding change value. Summarize all data of numerical anomalies and fluctuation anomalies to generate anomaly analysis results, which include specific information of each anomaly, such as abnormal time point, abnormal type, abnormal parameter and abnormal value.
[0021] Based on the abnormality analysis result, compensation optimization of the first control parameter combination is performed to generate a first compensation control parameter combination.
[0022] Extract the characteristics of various types of anomalies from the anomaly analysis results, including anomaly types, anomaly parameters and their specific anomaly values or changes, count the frequency and time points of anomalies, analyze the laws of anomalies, and determine corresponding compensation strategies based on different types of anomalies. For example, for numerical anomalies, you can adjust the set value range or add protection measures. For fluctuation anomalies, you can adjust the control algorithm parameters to improve the stability and response speed of the system. Using the adaptive control algorithm, according to the characteristic values of the abnormal characteristics, the control parameters are adaptively adjusted. The adaptive adjustment should consider the response speed weight and the control stability weight to ensure that the adjusted parameters can both respond quickly to the anomaly and maintain the stability of the system. According to the results of the adaptive adjustment, generate the first compensation control parameter combination, which contains all the adjusted control parameters.
[0023] The first compensation control parameter combination is added to the target control scheme to perform optimal control of the high-speed motor of the air compressor.
[0024] The first compensation control parameter combination is integrated into the target control scheme. The target control scheme includes parameter settings for the air compressor high-speed motor at all target time nodes, which is used to guide the operation of the air compressor high-speed motor to achieve optimal performance and energy efficiency. The target control scheme is applied to the control of the air compressor high-speed motor to achieve optimized control of the air compressor high-speed motor, thereby improving the overall performance and operation stability of the system.
[0025] Furthermore, if Figure 2 As shown, the method of obtaining a first target air pressure requirement and a first target flow requirement at a first target time node according to the compressed air requirement information includes: According to the compressed air demand information, a first mapping relationship between multiple preset time nodes and multiple air pressure demands is obtained, and a second mapping relationship between multiple preset time nodes and multiple flow demands is obtained; an air pressure demand scatter plot is generated according to the first mapping relationship, and a flow demand scatter plot is generated according to the second mapping relationship; an air pressure demand polynomial is generated by fitting the air pressure demand scatter plot, and a flow demand polynomial is generated by fitting the flow demand scatter plot; the first target time node is substituted into the air pressure demand polynomial to generate a first target air pressure demand, and the first target time node is substituted into the flow demand polynomial to generate a first target flow demand.
[0026] Determine multiple preset time nodes, such as every hour, every half hour, every minute, etc., and set them according to actual needs. The preset time nodes are used to identify the demand conditions at different time points, extract the air pressure demand and flow demand at each time node, and establish a mapping relationship between the multiple preset time nodes and the multiple air pressure demands. Each time node corresponds to an air pressure demand value, forming a mapping between the time node and the air pressure demand, that is, the first mapping relationship; similarly, establish a mapping relationship between the multiple preset time nodes and the multiple flow demands. Each time node corresponds to a flow demand value, forming a mapping between the time node and the flow demand, that is, the second mapping relationship.
[0027] Draw a plane rectangular coordinate system, and according to the first mapping relationship, mark the preset time nodes on the X-axis, mark the air pressure demand values on the Y-axis, mark each time node and the corresponding air pressure demand with a point, and generate an air pressure demand scatter plot; similarly, according to the second mapping relationship, mark the preset time nodes on the X-axis, mark the flow demand values on the Y-axis, mark each time node and the corresponding flow demand with a point, and generate a flow demand scatter plot.
[0028] Select a fitting method, including polynomial fitting, such as linear, quadratic, multi-order polynomials, or other curve fitting methods, such as spline functions. For the pressure demand scatter plot, select the appropriate polynomial order according to the complexity of the data, perform polynomial fitting, calculate the polynomial coefficients, minimize the error between the fitting curve and the scattered data points, and generate the pressure demand polynomial based on the fitted polynomial coefficients. Use the same polynomial fitting method to fit the flow data and generate the flow demand polynomial.
[0029] Substitute the value of the first target time node into the air pressure demand polynomial for calculation, and the calculation result is the first target air pressure demand; substitute the value of the first target time node into the flow demand polynomial for calculation, and the calculation result is the first target flow demand.
[0030] Furthermore, the method of generating an air pressure demand polynomial by fitting the air pressure demand scatter plot includes: Based on the air pressure demand scatter plot, a first scatter point set is randomly selected; based on a piecewise cubic spline function, the first scatter point set is fitted to generate a first spline curve; based on the first scatter point set, a first reference scatter point set is extracted from the air pressure demand scatter plot; based on the first reference scatter point set, a deviation distance is verified for the first spline curve to generate a first deviation distance; and so on, multiple deviation distances of multiple spline curves are generated; the multiple deviation distances are arranged in descending order, and the spline curve corresponding to the minimum deviation distance is obtained as the target spline curve; and a target polynomial of the target spline curve is obtained as the air pressure demand polynomial.
[0031] Each data point in the air pressure demand scatter plot represents a time node and a corresponding air pressure demand value, and a portion of scatter points are randomly selected from the air pressure demand scatter plot as a first scatter point set.
[0032] The piecewise cubic spline function is an interpolation method used to generate smooth curves between data points. Each segment is a cubic polynomial to ensure that the curve has a smooth transition at each data point. The first set of scattered points is used as the input data points, and the data points are divided into several intervals. Each interval is determined by two adjacent data points. For each interval, a cubic polynomial is calculated. The first and second order derivatives of each polynomial at the endpoints are continuous to ensure the smoothness of the overall curve. The coefficients of the cubic polynomial are calculated so that each segment of the curve passes through the given scattered points and smoothly connects the segments. The calculated cubic spline polynomials are combined to form a first spline curve that is smooth over the entire data range. The first spline curve approximately passes through all the scattered points.
[0033] The reference scatter point set is used to verify the accuracy of the fitted spline curve. Points not used in the fitting process can be selected as independent data for verification. The first scatter point set is excluded from the original air pressure demand scatter plot, and a part of the data points are selected from the remaining data as the first reference scatter point set. The reference points should cover the entire data range so that the spline curve can be fully verified.
[0034] For each point in the reference scattered point set, the time node of the reference point is substituted into the first spline curve to obtain the predicted air pressure demand value. For each reference scattered point, the deviation between the spline curve predicted value and the actual air pressure demand value is calculated, and the deviation distance of all reference points is calculated. For each reference point, a first deviation distance is generated. For example, the maximum deviation and root mean square error are calculated as indicators for verifying the spline curve fitting quality, which is used to evaluate the spline curve fitting quality.
[0035] Repeat the above steps, randomly select different scatter point sets from the air pressure demand scatter plot, generate multiple spline curves, and perform deviation distance calculation to generate multiple deviation distances. Arrange the deviation distances of all generated spline curves in descending order, that is, sort from the largest deviation distance to the smallest deviation distance, and select the spline curve corresponding to the smallest deviation distance from the sorted list as the target spline curve to ensure the best fit. Extract the polynomial expression from the target spline curve. If the target spline curve has multiple segments, each segment corresponds to a polynomial. Combine the polynomials of all segments to form a complete air pressure demand polynomial.
[0036] Furthermore, the method of matching control parameters according to the first target air pressure requirement and the first target flow requirement to generate a first control parameter combination includes: Based on big data, a set of historical control records of air compressors is obtained, and a first historical control record of air compressor is extracted, wherein the first historical control record of air compressor includes a first sample air pressure, a first sample flow rate, and a first sample control parameter combination; a similarity analysis is performed on the first target air pressure requirement and the first sample air pressure, as well as the first target flow rate requirement and the first sample flow rate, to generate a first similarity coefficient; if the first similarity coefficient meets a similarity coefficient threshold, the first sample control parameter combination is added to a control parameter combination library; a fitness evaluation function is introduced to screen and obtain an optimal control parameter combination from the control parameter combination library as the first control parameter combination.
[0037] Historical record data related to air compressor control is extracted from big data, and a sample is randomly extracted from the historical record as the first air compressor historical control record, wherein the first sample air pressure is the air pressure value at the recording time point, the first sample flow is the air flow value at the recording time point, and the first sample control parameter combination is the control parameter combination used at the recording time point.
[0038] Similarity analysis aims to compare the target air pressure and flow requirements with the air pressure and flow in historical records to determine their similarity. The value of the similarity coefficient is between 0 and 1. The closer the coefficient is to 1, the more similar the target air pressure and flow requirements are to the historical samples. The first similarity coefficient obtained provides a basis for control parameter matching.
[0039] The similarity coefficient threshold is a preset standard used to determine whether the target air pressure demand and flow demand match the historical samples sufficiently. It can be determined based on empirical data, historical analysis or business needs. For example, setting the threshold to 0.7 means that the similarity coefficient between the target demand and the sample record must be greater than or equal to 0.7 to be considered a valid match.
[0040] The calculated first similarity coefficient is compared with the set threshold. If the similarity coefficient meets the threshold condition, it means that the match between the target demand and the sample record is high enough. The first sample control parameter combination that meets the condition is added to the control parameter combination library. The control parameter combination library is used to store all control parameter combinations that meet the condition.
[0041] The fitness evaluation function is used to evaluate the performance of each control parameter combination to select the best control parameter combination. Extract multiple alternative control parameter combinations from the control parameter combination library, use the simulation model to test, simulate the operating status of the air compressor under different control parameters, record performance data, use the fitness evaluation function to evaluate the simulation results, and calculate the fitness value of each control parameter combination. Sort all the alternative control parameter combinations according to the fitness value, and select the optimal control parameter combination with the highest fitness value as the first control parameter combination.
[0042] Furthermore, the control parameter combination library also includes: Acquire multiple control parameter adjustment intervals of the high-speed motor of the air compressor; and use the multiple control parameter adjustment intervals as the pre-constraint space of the control parameter combination library.
[0043] The control parameters of the air compressor high-speed motor include motor speed, pressure setting, temperature setting, flow setting, etc. Each control parameter has its physical and technical limitations. The adjustable range of these control parameters is obtained through the equipment manual, manufacturer's technical specifications, or through equipment testing to generate multiple control parameter adjustment intervals.
[0044] The pre-constraint space is used to limit the acceptable range of control parameters in the control parameter combination library. These constraints ensure that the control parameter combination is effective and safe in actual equipment operation. Add these adjustment range constraints in the control parameter combination library to avoid selecting control parameter combinations that do not meet equipment specifications or safety standards. When adding a new combination, check it through the pre-constraint space to ensure that each parameter value in the combination is within its corresponding adjustment range.
[0045] Furthermore, the method of introducing a fitness evaluation function and selecting an optimal control parameter combination from the control parameter combination library as the first control parameter combination includes: Based on the control parameter combination library, extract a first candidate control parameter combination; based on the first candidate control parameter combination, perform simulation control on the high-speed motor of the air compressor to obtain first simulation information, wherein the first simulation information includes a first simulation power set within a preset time period; analyze the first simulation power set to obtain a first simulation power center value and a first simulation power discrete value; based on the fitness evaluation function, perform fitness evaluation on the first simulation power center value and the first simulation power discrete value to generate a first fitness; traverse the control parameter combination library to obtain multiple fitnesses; obtain the candidate control parameter combination corresponding to the optimal value among the multiple fitnesses as the first control parameter combination.
[0046] A control parameter combination is randomly selected from the control parameter combination library as the first candidate control parameter combination. A computer simulation model is used to simulate the working state of the high-speed motor of the air compressor, the first candidate control parameter combination is input into the simulation system, the simulation model is run, the behavior of the air compressor under the specified control parameters is simulated, its operation data is recorded, a preset time period is defined, such as 24 hours, to collect simulation data, and within the preset time period, the power consumption data of the air compressor at each time point is recorded to form a first simulation power set.
[0047] The power center value is the average value of the power set, representing the concentration trend of the power. The first simulation power center value is obtained by adding up all the values in the first simulation power set and dividing by the amount of data. The power discrete value describes the degree of dispersion of the data in the power set, usually expressed by the standard deviation. After calculating the standard deviation, the first simulation power discrete value is obtained.
[0048] The fitness evaluation function is used to comprehensively calculate the power center value and discrete value, and evaluate the pros and cons of the control parameter combination, specifically, whether the power center value is close to the target value and whether the power discreteness is low. The closer the power center value is to the target value, the better. The smaller the discrete value, the smaller the power fluctuation and the more stable the control. The calculated power center value and discrete value are evaluated based on the fitness evaluation function to generate the first fitness, and the fitness value is used to select the optimal control parameter combination.
[0049] Each candidate control parameter combination in the control parameter combination library is taken out one by one, and a simulation test is performed. According to the power data obtained by the simulation, the fitness value of each control parameter combination is calculated using a fitness evaluation function to obtain multiple fitness values.
[0050] From all fitness values, the maximum fitness value is selected, and the control parameter combination of the maximum fitness value is selected as the optimal combination, that is, the first control parameter combination, to optimize the control effect of the air compressor.
[0051] Furthermore, the fitness evaluation function is as follows: ; in, Characterize fitness, , represents the first weight coefficient and the second weight coefficient, and , is the simulation power center value, is the target simulation power center value, To simulate the discrete value of power, Discrete values of target simulation power.
[0052] Specifically, the fitness evaluation function is as follows: ; Substitute the simulated power center value, calculate the absolute difference between the center value and the target power center value, and take the reciprocal, which means that the closer the simulated power center value is to the target value, the higher the fitness score; substitute the simulated power discrete value, calculate the absolute difference between the discrete value and the target power discrete value, and take the reciprocal, which means that the closer the simulated power discrete value is to the target value, the higher the fitness score. The first weight coefficient and the second weight coefficient are used to adjust the relative influence of the center value matching and the discrete value matching in the overall fitness score. Through this fitness evaluation function, the control parameter combination closest to the target power effect can be effectively screened out, thereby optimizing the energy-saving control performance of the high-speed motor of the air compressor.
[0053] Furthermore, the method of performing compensation optimization of the first control parameter combination based on the abnormality analysis result to generate a first compensation control parameter combination includes: Based on the abnormal analysis result, the abnormal feature is extracted; based on the characteristic value of the abnormal feature, the control parameter is adaptively adjusted, and according to the adaptive adjustment result, a first compensation control parameter combination is generated, wherein the weight of the adaptive adjustment includes a response speed weight and a control stability weight.
[0054] Abnormal features are information extracted from the abnormal analysis results, which are used to describe and quantify abnormal situations, including abnormal air pressure values, abnormal air pressure fluctuations, abnormal flow values, abnormal flow fluctuations, abnormal temperature values, abnormal temperature fluctuations, etc.
[0055] Adjust the control parameters according to the extracted abnormal features to improve the performance of the equipment. The response speed weight reflects the response speed of the control system to changes, focusing on improving the sensitivity of the equipment response. The control stability weight reflects the stability of the control system, focusing on reducing the volatility of the equipment and maintaining a stable operating state. The required adjustment amount is calculated using the abnormal characteristic value. For example, the air pressure deviation and fluctuation amplitude will affect the adjustment amount of the air pressure control parameter. Use the weighted formula to adjust the control parameter. Multiply the response speed weight by the response adjustment amount, multiply the control stability weight by the stability adjustment amount, add the two together, and get the final adjustment amount. Apply it to the control parameter to generate the first compensation control parameter combination. By setting the weights of response speed and control stability, optimize the control parameter combination to improve the overall performance of the equipment.
[0056] In summary, the energy-saving control optimization method for a high-speed motor of an air compressor provided in the embodiment of the present application has the following technical effects: By interacting with the target pneumatic equipment, the air pressure and flow requirements at multiple time nodes are accurately obtained to ensure that the control system can be adjusted based on actual needs, improve the response accuracy to actual needs, and optimize energy utilization efficiency; control parameters are matched according to the target air pressure and flow requirements to ensure that the control parameters of the air compressor match the actual needs, improve the accuracy and stability of control, and reduce fluctuations and energy consumption during operation; through continuous control simulation and data acquisition, the first simulation data set is obtained to provide data support for further analysis and optimization; through detailed anomaly analysis of the simulation data, anomalies in air pressure, flow, temperature, etc. are identified, thereby improving the system's fault detection capability and response speed; control parameters are compensated and optimized according to the results of the anomaly analysis to generate a compensation control parameter combination, which improves the stability and response speed of the control and reduces the impact of anomalies on equipment performance; the compensation control parameter combination is applied to the actual control scheme to achieve optimized control of the high-speed motor of the air compressor, improve the overall performance of the equipment, reduce energy waste, and improve the stability and efficiency of the system.
[0057] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.
Claims
1. A method for optimizing energy-saving control of a high-speed motor of an air compressor, characterized in that: The method comprises: Interact with the target pneumatic equipment to obtain compressed air demand information, wherein the compressed air demand information includes multiple air pressure demands and multiple flow demands of the target pneumatic equipment at multiple preset time nodes; According to the compressed air demand information, obtaining a first target air pressure demand and a first target flow demand at a first target time node; Matching control parameters according to the first target air pressure requirement and the first target flow requirement to generate a first control parameter combination; Based on the first control parameter combination, continuous control simulation of the high-speed motor of the air compressor is performed, and simulation data is collected to obtain a first simulation data set; Performing an anomaly analysis on the first simulation data set to generate an anomaly analysis result, wherein the anomaly analysis includes an air pressure value anomaly analysis, an air pressure fluctuation anomaly analysis, a flow value anomaly analysis, a flow fluctuation anomaly analysis, a temperature value anomaly analysis, and a temperature fluctuation anomaly analysis; Based on the abnormal analysis result, performing compensation optimization of the first control parameter combination to generate a first compensation control parameter combination; The first compensation control parameter combination is added to the target control scheme to perform optimal control of the high-speed motor of the air compressor.
2. The energy-saving control optimization method for a high-speed motor of an air compressor according to claim 1, characterized in that: The method of obtaining a first target air pressure requirement and a first target flow requirement at a first target time node according to the compressed air requirement information includes: According to the compressed air demand information, a first mapping relationship between a plurality of preset time nodes and a plurality of air pressure demands is obtained, and a second mapping relationship between a plurality of preset time nodes and a plurality of flow demands is obtained; Generate an air pressure demand scatter plot according to the first mapping relationship, and generate a flow demand scatter plot according to the second mapping relationship; Generate an air pressure demand polynomial by fitting the air pressure demand scatter plot, and generate a flow demand polynomial by fitting the flow demand scatter plot; Substitute the first target time node into the air pressure requirement polynomial to generate a first target air pressure requirement, and substitute the first target time node into the flow requirement polynomial to generate a first target flow requirement.
3. The energy-saving control optimization method for a high-speed motor of an air compressor according to claim 2, characterized in that: The method of generating an air pressure demand polynomial by fitting the air pressure demand scatter plot comprises: Based on the air pressure demand scatter plot, randomly select and obtain a first scatter point set; Fitting the first scattered point set based on a piecewise cubic spline function to generate a first spline curve; Extracting a first reference scattered point set from the air pressure demand scatter plot according to the first scattered point set; Performing deviation distance verification on the first spline curve according to the first reference scattered point set to generate a first deviation distance; And so on, multiple deviation distances of multiple spline curves are generated; Arrange the multiple deviation distances in descending order, and obtain a spline curve corresponding to the minimum deviation distance as a target spline curve; A target polynomial of the target spline curve is obtained as the air pressure requirement polynomial.
4. The energy-saving control optimization method for a high-speed motor of an air compressor according to claim 1, characterized in that: The method of matching control parameters according to the first target air pressure requirement and the first target flow requirement to generate a first control parameter combination includes: Acquire a set of air compressor historical control records based on big data, and extract a first air compressor historical control record, wherein the first air compressor historical control record includes a first sample air pressure, a first sample flow, and a first sample control parameter combination; Performing a similarity analysis on the first target air pressure requirement and the first sample air pressure, and the first target flow requirement and the first sample flow, to generate a first similarity coefficient; If the first similarity coefficient meets the similarity coefficient threshold, adding the first sample control parameter combination to the control parameter combination library; A fitness evaluation function is introduced to screen and obtain an optimal control parameter combination from the control parameter combination library as the first control parameter combination.
5. The energy-saving control optimization method for a high-speed motor of an air compressor as claimed in claim 4, characterized in that: The control parameter combination library also includes: Obtain multiple control parameter adjustment intervals of the air compressor high-speed motor; The multiple control parameter adjustment intervals are used as the pre-constraint space of the control parameter combination library.
6. The energy-saving control optimization method for a high-speed motor of an air compressor as claimed in claim 4, characterized in that: The method of introducing a fitness evaluation function and selecting an optimal control parameter combination from the control parameter combination library as the first control parameter combination includes: Based on the control parameter combination library, extracting a first candidate control parameter combination; Based on the first candidate control parameter combination, a simulation control is performed on the high-speed motor of the air compressor to obtain first simulation information, wherein the first simulation information includes a first simulation power set within a preset time period; Analyze the first simulation power set to obtain a first simulation power center value and a first simulation power discrete value; Based on the fitness evaluation function, performing fitness evaluation on the first simulation power center value and the first simulation power discrete value to generate a first fitness; Traversing the control parameter combination library to obtain multiple fitness levels; A candidate control parameter combination corresponding to an optimal value among the multiple fitness values is obtained as the first control parameter combination.
7. The energy-saving control optimization method for a high-speed motor of an air compressor according to claim 6, characterized in that: The fitness evaluation function is as follows: ; in, Characterize fitness, , represents the first weight coefficient and the second weight coefficient, and , is the simulation power center value, is the target simulation power center value, To simulate the discrete value of power, Discrete values of target simulation power.
8. The energy-saving control optimization method for a high-speed motor of an air compressor according to claim 1, characterized in that: The method of performing compensation optimization of the first control parameter combination based on the abnormal analysis result to generate a first compensation control parameter combination includes: Extracting abnormal features based on the abnormal analysis results; Based on the characteristic value of the abnormal characteristic, the control parameter is adaptively adjusted, and according to the adaptive adjustment result, a first compensation control parameter combination is generated, wherein the weight of the adaptive adjustment includes a response speed weight and a control stability weight.
Citation Information
Patent Citations
Air compression station optimization method based on deep learning
CN108268359A
Visual energy-saving management and control method and system
CN115327930A
Control method of fuel cell cogeneration system
CN115911456A
Intelligent control method and system for air compressor
CN116498537A
Online monitoring method and system for mixing machine
CN116954088A
