Automatic frequency modulation method and system based on intelligent control

Abstract

The invention discloses an automatic frequency modulation method and system based on intelligent control, and belongs to the field of intelligent frequency modulation, and the method comprises the following steps: carrying out the preprocessing of collected equipment key operation parameters, and obtaining a standardized equipment operation parameter data set; an intelligent frequency modulation model based on fuzzy control is adopted to process the standardized equipment operation parameter data set, and a fuzzy control rule base of the equipment operation frequency and the equipment key operation parameters is established; judging the optimal operation frequency of the current equipment based on the fuzzy control rule base and outputting a frequency modulation instruction; and performing optimization control on the frequency modulation process of the frequency modulation instruction based on an adaptive dynamic compensation algorithm to realize automatic frequency modulation of the equipment. According to the invention, accurate, rapid and intelligent adjustment of the equipment operation frequency is realized, and the equipment operation efficiency and adaptability are improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of intelligent frequency modulation, and particularly relates to an automatic frequency modulation method and system based on intelligent control. Background Art

[0002] In industrial production, the operating frequency of equipment directly affects production efficiency and product quality. Traditional manual frequency modulation methods have problems such as slow response and low accuracy, and it is difficult to meet the requirements of modern industry for high-efficiency and precise frequency modulation. Although automatic frequency modulation systems have solved these problems to a certain extent, they still face the challenge of how to achieve intelligent control.

[0003] Specifically, the existing automatic frequency modulation systems have insufficient adaptability under complex working conditions, and the frequency modulation accuracy and speed need to be improved. The system has limited perception ability of equipment operating parameters, and it is difficult to obtain and analyze key data in real time, which affects the timeliness and accuracy of frequency modulation decisions. In addition, the intelligence level of frequency modulation algorithms is not high, lacking self-learning and self-adaptive capabilities, and unable to autonomously optimize frequency modulation strategies according to changes in equipment status and production requirements.

[0004] Therefore, it is urgent to develop an automatic frequency modulation system based on intelligent control to improve the system's perception, analysis, decision-making, and execution capabilities, and achieve dynamic optimization control of the equipment operating frequency. Summary of the Invention

[0005] To solve the above technical problems, the present invention proposes an automatic frequency modulation method and system based on intelligent control to solve the problems existing in the above prior art.

[0006] To achieve the above object, the present invention provides an automatic frequency modulation method based on intelligent control, including:

[0007] Preprocessing the collected key equipment operating parameters to obtain a normalized dataset of equipment operating parameters;

[0008] Using an intelligent frequency modulation model based on fuzzy control to process the normalized dataset of equipment operating parameters to establish a fuzzy control rule base for the equipment operating frequency and key equipment operating parameters;

[0009] Based on the fuzzy control rule base, determining the optimal operating frequency of the current equipment and outputting a frequency modulation instruction;

[0010] Based on the adaptive dynamic compensation algorithm, optimizing the control of the frequency modulation process of the frequency modulation instruction to achieve automatic frequency modulation of the equipment.

[0011] Optionally, the process of preprocessing the collected key equipment operating parameters includes:

[0012] Outlier detection is performed on the collected key operating parameters of the device to obtain the operating parameters with outliers removed;

[0013] The operating parameters with outliers removed are sorted according to the timestamp information to obtain time series data;

[0014] The time series data is normalized to obtain a normalized dataset of device operating parameters.

[0015] Optionally, the process of constructing a fuzzy control rule base by processing the normalized dataset of device operating parameters using an intelligent frequency modulation model based on fuzzy control includes:

[0016] The fuzzy C - means clustering algorithm is used to perform clustering analysis on the normalized dataset of device operating parameters. By setting different numbers of clusters and membership threshold values, clustering results with different granularities are obtained;

[0017] Based on the clustering results at the current granularity, the central point coordinates of each category are calculated to obtain category representative points;

[0018] Based on the category representative points, the distribution range of key parameters of the internal data of the current category is analyzed to obtain the key parameter range under the current working condition;

[0019] The operating frequencies of the internal data of each category are statistically analyzed to obtain the optimal operating frequency under the current working condition;

[0020] The final clustering result is selected by comparing the clustering results with different granularities;

[0021] The key parameter range and the optimal operating frequency corresponding to the final clustering result are used as the optimization control parameters under the current working condition;

[0022] A fuzzy control rule base is constructed based on the optimization control parameters under different working conditions.

[0023] Optionally, the process of determining the optimal operating frequency of the current device based on the fuzzy control rule base:

[0024] The operating parameter data of the device and the frequency modulation rule are input, and the optimal operating frequency under the current working condition is calculated based on the intelligent frequency modulation model;

[0025] When the calculated optimal operating frequency under the current working condition exceeds the safe frequency range of the device in the fuzzy control rule base, the calculated optimal operating frequency under the current working condition is subjected to safety restriction based on the safe frequency range of the device in the fuzzy control rule base to obtain the target operating frequency;

[0026] Judge the deviation between the actual operating frequency and the target operating frequency of the device. If the deviation exceeds the preset threshold, trigger the intelligent frequency modulation model to recalculate the optimal operating frequency and update the operating frequency of the device.

[0027] Optionally, the process of optimizing and controlling the frequency modulation process of the frequency modulation instruction based on the adaptive dynamic compensation algorithm includes:

[0028] Based on the acquired real-time device operating parameters, use the Kalman filtering algorithm to filter the real-time device operating parameters to obtain a smooth parameter curve;

[0029] Compare the smooth parameter curve with the preset standard curve to obtain a deviation value;

[0030] Based on the deviation value, use the fuzzy control algorithm to adaptively generate a frequency modulation compensation instruction;

[0031] Superimpose the generated frequency modulation compensation instruction on the original frequency modulation instruction to obtain a corrected frequency modulation instruction and send it to the device for execution.

[0032] Optionally, the automatic frequency modulation method further includes analyzing historical frequency modulation data by using a machine learning algorithm to obtain an optimized fuzzy rule base;

[0033] The process of obtaining the optimized fuzzy rule base includes:

[0034] Preprocess the historical frequency modulation data to obtain an input data set;

[0035] Classify and cluster the input data set to identify data subsets under different working conditions;

[0036] Based on the data subsets under different working conditions, use a machine learning algorithm to train an optimal frequency modulation strategy model;

[0037] Convert the extracted optimal frequency modulation strategy into fuzzy rules to optimize the fuzzy rule base of the intelligent frequency modulation model.

[0038] The present invention also provides an automatic frequency modulation system based on intelligent control for implementing an automatic frequency modulation method based on intelligent control. The system includes:

[0039] A data acquisition module, which is used to install a variety of high-precision sensors on the device to collect key operating parameters of the device in real time;

[0040] A data preprocessing module, which is used to preprocess the key operating parameters of the device obtained to obtain a normalized data set of device operating parameters;

[0041] Intelligent frequency modulation modeling module, which is used to input the normalized device operation parameter dataset into the intelligent frequency modulation model based on fuzzy control to establish a fuzzy control rule base for the device operation frequency and key parameters;

[0042] Frequency modulation analysis module, which is used to judge the optimal operation frequency of the device under the current working condition according to the fuzzy rule base and output a frequency modulation instruction;

[0043] Variable frequency control module, which is used to send the frequency modulation instruction to the frequency converter, and the frequency converter dynamically adjusts the motor frequency according to the instruction;

[0044] Frequency modulation optimization module, which is used to optimize the control of the frequency modulation process by using an adaptive dynamic compensation algorithm;

[0045] Self-learning optimization module, which is used to analyze the historical frequency modulation data through machine learning algorithms and perform self-learning optimization on the fuzzy rule base of the intelligent frequency modulation model.

[0046] Compared with the prior art, the present invention has the following advantages and technical effects:

[0047] The automatic frequency modulation method based on intelligent control provided by the present invention realizes precise control of the device operation frequency by integrating high-precision sensors to collect key operation parameters in real time and using fuzzy control theory to establish a rule base. This method can quickly respond to changes in the device working condition, automatically adjust to the optimal frequency, improve the device operation efficiency and adaptability. The application of the adaptive dynamic compensation algorithm further optimizes the frequency modulation process, ensures the accuracy and stability of the frequency modulation, reduces energy waste, and extends the device life. In addition, this method has a high level of intelligence, reduces manual intervention, lowers the operation complexity, and improves production safety. Generally speaking, the present invention has significant technical advantages and broad application prospects in improving device performance, energy conservation and consumption reduction, and the field of intelligent manufacturing. Brief Description of the Drawings

[0048] The drawings constituting a part of this application are used to provide a further understanding of this application. The schematic embodiments of this application and their descriptions are used to explain this application and do not constitute an improper limitation to this application. In the drawings:

[0049] Figure 1 is the flowchart of the automatic frequency modulation method based on intelligent control according to the embodiment of the present invention;

[0050] Figure 2 is the structure diagram of the automatic frequency modulation system based on intelligent control according to the embodiment of the present invention. Detailed Embodiments

[0051] It should be noted that, without conflict, the embodiments in the present application and the features in the embodiments can be combined with each other. The present application will be described in detail below with reference to the drawings and in combination with the embodiments.

[0052] It should be noted that the steps shown in the flowchart of the drawings can be executed in a computer system such as a set of computer-executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than here.

[0053] Embodiment 1

[0054] As Figure 1 shown, in this embodiment, an automatic frequency modulation method based on intelligent control is provided, including the following steps: preprocessing the collected key operation parameters of the device to obtain a normalized device operation parameter data set; using an intelligent frequency modulation model based on fuzzy control to process the normalized device operation parameter data set to establish a fuzzy control rule base for the device operation frequency and the key operation parameters of the device; judging the optimal operation frequency of the current device based on the fuzzy control rule base and outputting a frequency modulation instruction; optimizing and controlling the frequency modulation process of the frequency modulation instruction based on an adaptive dynamic compensation algorithm to achieve automatic frequency modulation of the device. The specific implementation process includes:

[0055] Step 1: By installing a variety of high-precision sensors on the device, key operation parameters such as vibration, temperature, and current of the device are collected in real time to obtain data reflecting the real-time working conditions of the device.

[0056] According to the device type and monitoring requirements, high-precision sensors are selected, such as vibration sensors, temperature sensors, and current sensors, etc., and they are installed at the key parts of the device. The operation parameter data such as vibration, temperature, and current of the device are collected in real time through the sensors.

[0057] As a specific implementation manner of this embodiment, taking a certain large industrial pump as an example, acceleration sensors can be selected to monitor vibration, thermocouples to monitor temperature, and Hall sensors to monitor current. These sensors are installed at key parts such as the pump body, motor, and bearing to collect operation parameters in real time. The original data can be significantly improved in the accuracy of subsequent analysis after preprocessing. For vibration data, wavelet transform is used to remove high-frequency noise; the temperature data can be smoothed by moving average filtering; and the current data needs to be normalized to eliminate the amplitude differences under different working conditions. The preprocessed data can better reflect the real state of the device.

[0058] Step 2: Transmit the obtained device operation parameter data to the PLC, and the PLC preprocesses the data, eliminates outliers, and organizes the data according to the time series to obtain a normalized device operation parameter data set.

[0059] The process of preprocessing the collected key operating parameters of the equipment includes: performing outlier detection on the collected key operating parameters of the equipment to obtain operating parameters with outliers removed; sorting the operating parameters with outliers removed according to timestamp information to obtain time series data; and normalizing the time series data to obtain a normalized equipment operating parameter data set.

[0060] Furthermore, the equipment operation parameter data is obtained through the data acquisition module and the data is transmitted to the PLC. After receiving the equipment operation parameter data, the PLC pre-processes the data. If the data exceeds the preset normal range threshold, it is determined as an abnormal value and removed. According to the timestamp information of the data, the data is sorted in chronological order to form time series data. The time series data is normalized, the data format and unit are unified, and a standardized equipment operation parameter data set is obtained.

[0061] As a specific implementation of this embodiment, the data acquisition module obtains the operating parameter data of the equipment in real time through various sensors. For example, for an industrial motor, its speed, current, temperature and other parameters can be collected. These data are then transmitted to the programmable logic controller (PLC), which is responsible for the preliminary processing of the original data as the data processing center. In the data preprocessing stage, the PLC will first detect abnormal values ​​on the received data. Assuming that the normal operating temperature range of the motor is 20-80°C, if the temperature value collected at a certain time is 150°C, which obviously exceeds the preset normal range threshold, the system will determine it as an abnormal value and remove it to ensure the accuracy of subsequent analysis. Next, the PLC will sort the data according to the timestamp information to form time series data. This step is crucial for analyzing the trend of equipment performance over time. For example, by observing the curve of the change of motor temperature over time, it can be found whether there is an abnormal temperature rise, so as to timely discover potential failure risks. Data normalization is a key step to ensure the comparability of different types of parameters. For example, the speed of the motor may be in revolutions per minute (RPM), while the temperature is in degrees Celsius. Through normalization, these data in different units can be unified into a standard scale, which is convenient for subsequent comprehensive analysis. Data cleaning is an important part of improving data quality. In actual operation, data may be missing or duplicated. For example, due to sensor failure, all temperature data for a certain period of time may be missing. Data cleaning algorithms can supplement missing data through interpolation and other methods, or delete duplicate records to ensure data integrity and consistency.

[0062] Step 3: Input the standardized equipment operation parameter data set into the intelligent frequency modulation model based on fuzzy control. The model comprehensively considers factors such as equipment load and production process requirements to establish a fuzzy control rule base for equipment operation frequency and key parameters.

[0063] Furthermore, obtain a normalized dataset of device operation parameters as the input data for the fuzzy control intelligent frequency modulation model. According to the device load and production process requirements, determine the key parameters affecting the device operation frequency as the input variables for fuzzy control. Use the fuzzy clustering algorithm to analyze the device operation parameter dataset to obtain the optimal operation frequency and the range of key parameters under different working conditions. Based on expert knowledge and data analysis results, establish a fuzzy control rule base between the device operation frequency and key parameters.

[0064] Even further, use the fuzzy clustering algorithm to analyze the device operation parameter dataset to obtain the optimal operation frequency and the range of key parameters under different working conditions.

[0065] Even further, obtain the device operation parameter dataset, perform preprocessing on the data, including data cleaning, normalization, etc., to obtain the preprocessed dataset. According to the preprocessed dataset, use the fuzzy C-means clustering algorithm to perform clustering analysis on the data. By setting different numbers of clusters and membership thresholds, obtain clustering results with different granularities. For each clustering result, statistically analyze the data distribution within each category, calculate the center point coordinates of each category to obtain the category representative points. According to the representative points of each category, analyze the distribution range of key parameters of the data within the category to determine the range of key parameters under this working condition. Statistically analyze the operation frequency of the data within each category, calculate the mean and variance of the frequency, and determine the optimal operation frequency under this working condition according to the mean and variance. Integrate the analysis results under different clustering granularities, compare the range of key parameters and the optimal operation frequency under different working conditions, and select the optimal clustering granularity as the final clustering result. Use the range of key parameters and the optimal operation frequency corresponding to each category in the final clustering result as the optimized control parameters under this working condition to guide the actual operation adjustment of the device, improve the device operation efficiency and reliability. Based on the optimized control parameters under different working conditions, construct a fuzzy control rule base.

[0066] As a specific implementation manner of this embodiment, it is first necessary to collect the operation parameter data of the device under different working conditions. For example, the operation data of a certain chemical reactor, including temperature, pressure, stirring speed, feeding speed, etc. These data can be obtained from the historical database or the real-time monitoring system. Preprocess the collected data, such as removing outliers and filling in missing values. If the temperature data at a certain time point significantly deviates from the normal range, it can be considered an outlier and needs to be removed; if the pressure data at a certain time point is missing, it can be interpolated and filled according to the data at the previous and subsequent time points. Then normalize the data to convert data with different dimensions to the same scale. For example, map the temperature data and pressure data to the range of 0 to 1 to eliminate the influence of dimensions and facilitate subsequent clustering analysis. Next, use the fuzzy C-means clustering algorithm (FCM) to perform clustering analysis on the preprocessed data. FCM is a fuzzy clustering algorithm based on the objective function. It iteratively optimizes the objective function to divide the data set into multiple fuzzy clusters. For example, for the operation data of the above chemical reactor, different numbers of clusters can be set, such as 3, 4, 5, and different membership threshold values, such as 0.6, 0.7, 0.8, and multiple clustering experiments can be carried out to obtain clustering results with different granularities. Suppose when the number of clusters is 3, the data can be divided into three categories: low-temperature and low-pressure working conditions, medium-temperature and medium-pressure working conditions, and high-temperature and high-pressure working conditions. The membership threshold is used to control the fuzziness of the clustering. The higher the threshold, the clearer the clustering result, and vice versa. For each clustering result, it is necessary to count the distribution of data within each category. For example, for the low-temperature and low-pressure working condition category, the distribution ranges of parameters such as temperature, pressure, stirring speed, and feeding speed of all data points within this category can be counted, and the center point coordinates of each category can be calculated, that is, the average value of each parameter of all data points within this category, as the representative point of this category. For example, the representative point of the low-temperature and low-pressure working condition may be (temperature = 50°C, pressure = 0.5 MPa, stirring speed = 100 rpm, feeding speed = 5 L / min). According to the representative point of each category, analyze the distribution range of the key parameters of the data within this category to determine the key parameter range under this working condition. For example, under the low-temperature and low-pressure working condition, the distribution range of temperature may be 45°C to 55°C, and the distribution range of pressure is 0.4 MPa to 0.6 MPa. These ranges are the key parameter ranges under this working condition. At the same time, statistically analyze the operation frequency of the data within each category. For example, under the low-temperature and low-pressure working condition, the mean value of the equipment operation frequency is 40 Hz, and the variance may be 2 Hz. The optimal operation frequency under this working condition can be determined based on the mean value and variance. 40 Hz can be used as the optimal operation frequency under this working condition. This is because the mean value represents the average level of the frequency under this working condition, and the variance represents the degree of fluctuation of the frequency. Selecting the mean value as the optimal operation frequency can ensure the stable operation of the equipment under this working condition.Integrate the analysis results under different clustering granularities, compare the key parameter ranges and optimal operating frequencies under different working conditions, and select the optimal clustering granularity as the final clustering result. For example, if the clustering result when the number of clusters is 3 can clearly reflect the characteristics of different working conditions, and the key parameter ranges and optimal operating frequencies under each working condition have good distinguishability, then the number of clusters 3 can be selected as the final clustering result. The purpose of selecting the optimal clustering granularity is to find the clustering method that can best reflect the internal structure and laws of the data, so as to provide more accurate guidance for subsequent optimal control. Finally, take the key parameter ranges and optimal operating frequencies corresponding to each category in the final clustering result as the optimal control parameters under this working condition, and use them to guide the actual operation adjustment of the equipment. For example, when the equipment operates under low temperature and low pressure conditions, the temperature can be controlled between 45°C and 55°C, the pressure can be controlled between 0.4 MPa and 0.6 MPa, and the operating frequency can be set to 40 Hz, so as to improve the operation efficiency and reliability of the equipment. In this way, the operation parameters of the equipment can be finely adjusted according to different working conditions, realizing the intelligent optimal control of the equipment and improving the production efficiency and product quality.

[0067] Step 4: The intelligent frequency modulation model conducts real-time analysis on the equipment operation parameter data, judges the optimal operating frequency under the current working condition of the equipment according to the fuzzy rule base, and outputs a frequency modulation command.

[0068] Furthermore, in the fuzzy rule base, find the corresponding optimal operating frequency range and frequency modulation rule according to the current working condition type. Input the standardized equipment operation parameter data into the intelligent frequency modulation model, combine the frequency modulation rules in the fuzzy rule base, and calculate the optimal operating frequency under the current working condition through fuzzy inference. Compare the calculated optimal operating frequency with the current operating frequency of the equipment. If the difference between the two exceeds the preset threshold, then generate the corresponding frequency modulation command. Output the generated frequency modulation command to the equipment control system, and the control system adjusts the operating frequency of the equipment according to the frequency modulation command to achieve the intelligent frequency modulation control of the equipment.

[0069] As a specific implementation of this embodiment, in the fuzzy rule base, the corresponding optimal operating frequency range and frequency modulation rules are found according to the current operating condition type. The fuzzy rule base is the core of intelligent frequency modulation, which stores the expert experience and knowledge obtained from data analysis. For example, when operating at high load, if the steam pressure is lower than the set value and the gas flow rate is already relatively large, it indicates that the operating frequency of the equipment needs to be increased at this time. For example, increase the rotational speeds of the induced draft fan and the blower to increase the air intake volume, promote combustion, and thus increase the steam pressure. Here, "relatively low" and "relatively large" are both fuzzy concepts, and the specific numerical ranges need to be defined in the rule base. For example, defining the steam pressure being lower than the set value by 0.5 MPa as "relatively low" and the gas flow rate being greater than 80% of the rated flow rate as "relatively large". Input the standardized equipment operating parameter data into the intelligent frequency modulation model, combine the frequency modulation rules in the fuzzy rule base, and obtain the optimal operating frequency under the current operating condition through fuzzy inference calculation. For example, the current steam pressure is 1.0 MPa, the set value is 1.2 MPa, and the gas flow rate is 90% of the rated flow rate. According to the above rules, it can be judged that the current steam pressure is relatively low and the gas flow rate is relatively large, and the operating frequency of the equipment needs to be increased. Specifically, how much to increase needs to be determined according to the result of fuzzy inference. That is, according to the degree of relatively low steam pressure and the degree of relatively large gas flow rate, a membership function is calculated to represent the degree to which the current operating condition belongs to "needing to increase the frequency", and then according to the membership function and the preset frequency modulation step size, the optimal operating frequency is calculated. Compare the calculated optimal operating frequency with the current operating frequency of the equipment. If the difference between the two exceeds the preset threshold, a corresponding frequency modulation instruction is generated. For example, the current operating frequency of the equipment is 50 Hz, the calculated optimal operating frequency is 52 Hz, and the difference between the two is 2 Hz, exceeding the preset threshold of 1 Hz, then a frequency modulation instruction needs to be generated. The specific content of the frequency modulation instruction depends on the control system of the equipment. For example, for a motor controlled by a frequency converter, the frequency modulation instruction can be to change the value of the output frequency. Finally, output the generated frequency modulation instruction to the equipment control system, and the control system adjusts the operating frequency of the equipment according to the frequency modulation instruction to achieve intelligent frequency modulation control of the equipment. For example, after the control system receives the instruction to increase the motor operating frequency by 2 Hz, it will control the frequency converter to adjust the output frequency from 50 Hz to 52 Hz, thereby achieving intelligent frequency modulation control of the equipment and making it operate in a better state.

[0070] That is, in the intelligent frequency modulation model, a fuzzy inference algorithm is adopted to calculate the optimal operating frequency under the current working conditions based on the input device operating parameter data and frequency modulation rules. It is judged whether the calculated optimal operating frequency exceeds the safe frequency range of the device. If it exceeds the safe range, the optimal operating frequency is limited within the safe range. The calculated optimal operating frequency is used as the target operating frequency of the device to control the device to operate at this frequency and monitor the operating state of the device in real time. According to the real-time operating state data of the device, the deviation between the actual operating frequency and the target operating frequency of the device is judged. If the deviation exceeds the preset threshold, the intelligent frequency modulation model is triggered to recalculate the optimal operating frequency and update the operating frequency of the device.

[0071] Step Five: If the deviation between the current device operating frequency and the optimal frequency exceeds the preset threshold, the frequency modulation instruction is sent to the frequency converter, and the frequency converter dynamically adjusts the motor frequency according to the instruction to make the device operating frequency quickly reach the optimal value.

[0072] Further, obtain the real-time operating frequency of the device, compare it with the preset optimal frequency, and calculate the current frequency deviation value. Determine whether the frequency deviation value exceeds the preset threshold. If it exceeds the threshold, trigger the frequency modulation process; if it does not exceed the threshold, continue to monitor the device operating frequency. According to the magnitude and direction of the frequency deviation value, use the fuzzy control algorithm to calculate the corresponding frequency modulation command and determine the motor frequency value that needs to be adjusted. Send the calculated frequency modulation command to the frequency converter. After receiving the command, the frequency converter controls the motor to operate at the specified frequency, realizing the dynamic adjustment of the device operating frequency. During the frequency modulation process, continuously obtain the real-time operating frequency of the device, compare it with the optimal frequency, and calculate the frequency deviation value and the frequency modulation command in real time through the PID control algorithm to form a closed-loop control. When the device operating frequency reaches near the optimal value and the frequency deviation value is continuously less than the preset threshold for multiple times, it is determined that the device has returned to the optimal operating state, and the frequency modulation control is stopped. During the entire frequency modulation process, use the Kalman filter algorithm to filter the obtained device operating frequency data to eliminate frequency fluctuations and noise interference, improving the frequency measurement accuracy and control effect. This dynamic adjustment enables the device to always maintain the best working state, improving energy efficiency and extending the device life. The PID control algorithm plays an important role in the frequency modulation process. It calculates a more accurate frequency modulation command by considering the current deviation, the accumulation of historical deviations, and the trend of deviation changes through the three links of proportional, integral, and differential. For example, if the frequency deviation persists, the integral term will gradually increase, prompting the system to make a stronger adjustment; if the deviation changes rapidly, the differential term will play a role in suppressing excessive adjustment. The Kalman filter algorithm is used to process the device operating frequency data, effectively eliminating random fluctuations and measurement noise. Suppose the original measurement data shows that the pump frequency fluctuates between 49.8 Hz and 50.2 Hz. The Kalman filter may give a more stable estimated value, such as 50.0 Hz. This filtering process improves the accuracy of frequency measurement and provides a more reliable data basis for subsequent control decisions. The entire frequency modulation process forms a closed-loop control system. Taking the pump as an example, when the system detects that the pump frequency deviates from the optimal value, it will calculate and send a frequency modulation command. Subsequently, the system will continuously monitor the new operating frequency of the pump and make further adjustments according to the new deviation value. This continuous feedback and adjustment ensure that the pump always operates near the best state. When the pump operating frequency stabilizes near the optimal value and the frequency deviation is continuously less than the preset threshold (such as 0.5 Hz) for multiple times, the system determines that the pump has reached the optimal operating state and suspends the frequency modulation control. This mechanism avoids unnecessary frequent adjustments and ensures the stable operation of the device. Through this intelligent frequency modulation system, industrial devices can automatically adjust operating parameters according to actual working conditions, improving energy utilization efficiency and extending the device service life. At the same time, the system has a high degree of automation, reducing manual intervention and improving production efficiency and safety. This technology has broad application prospects in the fields of Industry 4.0 and intelligent manufacturing.

[0073] Step 6: Use an adaptive dynamic compensation algorithm to optimize the frequency modulation process and modify the frequency modulation instructions in real time according to the dynamic changes of the equipment operating parameters to ensure the accuracy and stability of the frequency modulation.

[0074] Furthermore, the real-time operating parameters of the device, including key indicators such as frequency, power, and temperature, are obtained as inputs to the algorithm. According to the obtained real-time operating parameters, the Kalman filter algorithm is used to filter the parameters, remove noise interference, and obtain a smooth parameter curve. The filtered parameter curve is compared with the preset standard curve, and the deviation value of the two curves is calculated. If the deviation value exceeds the preset threshold, it is determined that frequency modulation compensation is required. If frequency modulation compensation is required, the fuzzy control algorithm is used according to the size of the deviation value to adaptively generate a frequency modulation compensation instruction, and the amplitude of the instruction is proportional to the deviation value. The generated frequency modulation compensation instruction is superimposed on the original frequency modulation instruction to obtain a corrected frequency modulation instruction, which is issued to the device for execution. During the frequency modulation process, the real-time operating parameters of the device are continuously obtained, and steps 2 to 5 are repeated to dynamically correct the frequency modulation instruction until the deviation value between the parameter curve and the standard curve is lower than the preset threshold. After the frequency modulation process is completed, the principal component analysis algorithm is used to analyze the parameter data of the entire frequency modulation process, extract key feature parameters, optimize the algorithm model, and provide a reference for the next frequency modulation.

[0075] Step 7: Use machine learning algorithms to mine and analyze historical frequency modulation data, extract the optimal frequency modulation strategy for equipment under different working conditions, perform self-learning optimization on the fuzzy rule base of the intelligent frequency modulation model, and continuously improve the intelligence level and adaptability of the system.

[0076] Further, obtain the historical frequency modulation data of the device, and preprocess the data, including operations such as data cleaning, feature extraction, and data standardization, to obtain an input data set suitable for machine learning algorithms. According to the working conditions of the device, classify and cluster the historical frequency modulation data to identify data subsets under different working conditions, preparing for subsequent strategy extraction. For each data subset under the working conditions, use machine learning algorithms such as decision trees, support vector machines, or neural networks to train an optimal frequency modulation strategy model to obtain a frequency modulation strategy applicable to this working condition. Convert the extracted optimal frequency modulation strategy into fuzzy rules to supplement and optimize the fuzzy rule base of the intelligent frequency modulation model, improving the adaptability of the model to different working conditions. During the inference process of the intelligent frequency modulation model, dynamically select the corresponding fuzzy rule subset according to the current working conditions of the device to make frequency modulation decisions, realizing intelligent frequency modulation with working condition adaptability. During the operation of the system, continuously collect the real-time frequency modulation data and performance feedback of the device, conduct online learning and optimization of the intelligent frequency modulation model, dynamically adjust the fuzzy rule base, and improve the intelligence level of the system. Regularly evaluate the performance of the intelligent frequency modulation model, analyze the adaptability and optimization effect of the model under different working conditions, identify the rules and strategies to be improved, and conduct algorithm optimization and rule base update accordingly to ensure the continuous evolution and intelligent improvement of the system.

[0077] The present invention discloses an automatic frequency modulation method based on intelligent control. Aiming at the problems in business scenarios such as slow response, low accuracy, and inability to adapt to complex working conditions in traditional device frequency modulation methods, a comprehensive solution integrating multi-sensor data acquisition, fuzzy control, adaptive dynamic compensation, and machine learning is proposed. In the present invention, high-precision sensors are installed on the device to collect key operating parameters such as vibration, temperature, and current in real time, and a programmable logic controller is used for data preprocessing and standardization to construct a data set of device operating parameters. This data set is input into an intelligent frequency modulation model based on fuzzy control. This model analyzes the data in real time and determines the optimal operating frequency of the device under the current working conditions according to the fuzzy control rule base established based on factors such as device load and production process requirements. When the deviation between the actual frequency and the optimal frequency exceeds the threshold, a frequency modulation instruction is sent to the frequency converter to dynamically adjust the motor frequency. In addition, an adaptive dynamic compensation algorithm is used to optimize the frequency modulation process, and machine learning algorithms are combined to mine and analyze historical data to realize self-learning optimization of the fuzzy rule base. Finally, the present invention realizes precise, fast, and intelligent adjustment of the device operating frequency, improving the operating efficiency and adaptability of the device.

[0078] Embodiment 2

[0079] As Figure 2 shown, in this embodiment, an automatic frequency modulation system based on intelligent control is provided, including:

[0080] The data acquisition module is used to install a variety of high-precision sensors on the device to collect key operating parameters such as vibration, temperature, and current of the device in real time, and obtain data reflecting the real-time working conditions of the device;

[0081] The data preprocessing module is used to transmit the obtained device operating parameter data to the PLC. The PLC preprocesses the data, eliminates outliers, and organizes the data according to the time series to obtain a normalized device operating parameter data set;

[0082] The intelligent frequency modulation modeling module is used to input the normalized device operating parameter data set into an intelligent frequency modulation model based on fuzzy control. This model comprehensively considers factors such as device load and production process requirements, and establishes a fuzzy control rule base for the device operating frequency and key parameters;

[0083] The frequency modulation analysis module is used to perform real-time analysis on the device operating parameter data by the intelligent frequency modulation model, judge the optimal operating frequency of the device under the current working condition according to the fuzzy rule base, and output a frequency modulation instruction;

[0084] The variable frequency control module is used to, if the deviation between the current device operating frequency and the optimal frequency exceeds a preset threshold, send the frequency modulation instruction to the frequency converter. The frequency converter dynamically adjusts the motor frequency according to the instruction to make the device operating frequency quickly reach the optimal value;

[0085] The frequency modulation optimization module is used to optimize the control of the frequency modulation process by using an adaptive dynamic compensation algorithm, and correct the frequency modulation instruction in real time according to the dynamic changes of the device operating parameters to ensure the accuracy and stability of the frequency modulation;

[0086] The self-learning optimization module is used to mine and analyze the historical frequency modulation data by using machine learning algorithms, extract the optimal frequency modulation strategies of the device under different working conditions, perform self-learning optimization on the fuzzy rule base of the intelligent frequency modulation model, and continuously improve the intelligence level and adaptability of the system.

[0087] The above is only a preferred specific embodiment of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by those skilled in the art within the technical scope disclosed in the present application should be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. An automatic frequency modulation method based on intelligent control, characterized in that: The following steps are involved: Preprocessing the collected key equipment operating parameters to obtain a standardized equipment operating parameter data set; The standardized equipment operation parameter data set is processed by using an intelligent frequency modulation model based on fuzzy control to establish a fuzzy control rule base of equipment operation frequency and key equipment operation parameters; Determine the optimal operating frequency of the current device based on the fuzzy control rule base and output a frequency modulation instruction; Based on the adaptive dynamic compensation algorithm, the frequency modulation process of the frequency modulation instruction is optimized and controlled to realize automatic frequency modulation of the equipment.

2. The method according to claim 1, characterized in that The process of preprocessing the collected key operating parameters of the equipment includes: Perform outlier detection on the key operating parameters of the collected equipment to obtain operating parameters without outliers; Sorting the operating parameters for removing abnormal values ​​according to timestamp information to obtain time series data; The time series data is normalized to obtain a normalized equipment operation parameter data set.

3. The method according to claim 1, characterized in that The process of using the intelligent frequency modulation model based on fuzzy control to process the standardized equipment operation parameter data set and construct a fuzzy control rule base includes: The fuzzy C-means clustering algorithm is used to perform cluster analysis on the standardized equipment operation parameter data set. By setting different cluster numbers and membership thresholds, clustering results of different granularities are obtained. Based on the clustering results at the current granularity, the coordinates of the center point of each category are calculated to obtain the category representative point; Analyze the key parameter distribution range of the internal data of the current category based on the representative points of the category to obtain the key parameter range under the current working condition; Perform statistical analysis on the operating frequency of the internal data of each category to obtain the optimal operating frequency under the current working conditions; Compare the clustering results of different granularities and select the final clustering result; The key parameter range and the optimal operating frequency corresponding to the final clustering result are used as the optimization control parameters under the current working condition; A fuzzy control rule base is constructed based on the optimized control parameters under different working conditions.

4. The method according to claim 3, characterized in that The process of judging the optimal operating frequency of the current device based on the fuzzy control rule base: Input the equipment's operating parameter data and frequency regulation rules to calculate the optimal operating frequency under current working conditions based on the intelligent frequency regulation model; When the calculated optimal operating frequency under the current working condition exceeds the safe frequency range of the equipment in the fuzzy control rule base, the calculated optimal operating frequency under the current working condition is safely restricted based on the safe frequency range of the equipment in the fuzzy control rule base to obtain a target operating frequency; Determine the deviation between the actual operating frequency of the device and the target operating frequency. If the deviation exceeds the preset threshold, the intelligent frequency modulation model is triggered to recalculate the optimal operating frequency and update the operating frequency of the device.

5. The method according to claim 3, characterized in that: The process of optimizing and controlling the frequency modulation process of the frequency modulation instruction based on the adaptive dynamic compensation algorithm includes: Based on the acquired real-time equipment operating parameters, the Kalman filter algorithm is used to filter the real-time equipment operating parameters to obtain a smooth parameter curve; Compare the smoothing parameter curve with the preset standard curve to obtain the deviation value; Based on the deviation value, a fuzzy control algorithm is used to adaptively generate a frequency modulation compensation instruction; The generated frequency modulation compensation instruction is added to the original frequency modulation instruction to obtain the corrected frequency modulation instruction and sent to the device for execution.

6. The method according to claim 1, characterized in that The automatic frequency modulation method further comprises analyzing the historical frequency modulation data by using a machine learning algorithm to obtain an optimized fuzzy rule base; The process of obtaining the optimized fuzzy rule base includes: Preprocess the historical frequency modulation data to obtain the input data set; Classify and cluster the input data set to identify data subsets under different working conditions; Based on the data subsets under the different working conditions, a machine learning algorithm is used to train an optimal frequency modulation strategy model; The extracted optimal frequency modulation strategy is converted into fuzzy rules to optimize the fuzzy rule base of the intelligent frequency modulation model.

7. An automatic frequency modulation system based on intelligent control, characterized in that: The system for implementing the automatic frequency modulation method based on intelligent control according to any one of claims 1 to 6 comprises: A data acquisition module, which is used to collect key operating parameters of the device in real time by installing a variety of high-precision sensors on the device; A data preprocessing module, which is used to preprocess the key operating parameters of the acquired equipment to obtain a standardized equipment operating parameter data set; An intelligent frequency modulation modeling module, which is used to input a standardized data set of equipment operating parameter data into an intelligent frequency modulation model based on fuzzy control, and establish a fuzzy control rule base of equipment operating frequency and key parameters; A frequency modulation analysis module, which is used to determine the optimal operating frequency of the equipment under the current working condition according to the fuzzy rule base and output a frequency modulation instruction; A frequency conversion control module, which is used to send frequency modulation instructions to the frequency converter, and the frequency converter dynamically adjusts the motor frequency according to the instructions; A frequency modulation optimization module, wherein the frequency modulation optimization module is used to optimize and control the frequency modulation process by using an adaptive dynamic compensation algorithm; A self-learning optimization module is used to analyze historical frequency modulation data through a machine learning algorithm and perform self-learning optimization on the fuzzy rule base of the intelligent frequency modulation model.

Images