Compressor control method and system

Abstract

The invention provides a compressor control method and system. The method belongs to the technical field of compressor control, and comprises the following steps: collecting multi-dimensional data in the operation process of a compressor in real time through a multi-parameter sensor network; preprocessing the collected multi-dimensional data, and constructing a data set; learning and optimizing a compressor control strategy based on historical data and a current environment state through a reinforcement learning model based on a deep neural network; continuous iterative updating is carried out through analog simulation and online learning; and on the basis of the adaptive neural network model, the running state and performance parameters of the compressor in a future period of time are predicted in real time, and the network structure and parameters are dynamically adjusted according to the current working condition and historical data of the compressor. Multi-dimensional data in the operation process of the compressor are collected in real time through a multi-parameter sensor network. The data are preprocessed, including denoising, missing value filling, abnormal value detection and the like, so that the data quality is ensured.

Description

Technical Field

[0001] The invention provides a compressor control method and system, belonging to the technical field of compressor control. Background Art

[0002] Traditional compressor control technologies mostly rely on preset algorithms and fixed control logic, which are difficult to cope with dynamically changing operating conditions. Although there have been attempts to use simple machine learning models for optimization in recent years, these methods are often limited by model complexity, data dependency, and generalization capabilities, making it difficult to achieve deep optimization of compressor performance. In particular, when faced with complex operating conditions (such as extreme temperatures, pressure fluctuations, load changes, etc.), traditional methods are often unable to quickly and accurately adjust compressor operating parameters, resulting in low energy efficiency and frequent failures. Summary of the invention

[0003] The present invention provides a compressor control method and system to solve the problems mentioned in the above background technology: The present invention provides a compressor control method, the method comprising: S1. Collect multi-dimensional data in real time during the operation of the compressor through a multi-parameter sensor network; pre-process the collected multi-dimensional data and construct a data set; S2. Learn and optimize the compressor control strategy based on historical data and current environmental conditions through a reinforcement learning model based on deep neural networks; continuously iterate and update through simulation and online learning; S3, based on the adaptive neural network model, the operating status and performance parameters of the compressor in the future are predicted in real time, and the network structure and parameters are dynamically adjusted according to the current working conditions and historical data of the compressor; S4, integrating the outputs of the deep reinforcement learning decision module and the adaptive neural network prediction module to generate a comprehensive control strategy; S5. Intelligently adjust the compressor operating parameters according to the comprehensive control strategy. At the same time, through the closed-loop feedback mechanism, continuously monitor the compressor operating status and adjust the control strategy in time.

[0004] The present invention provides a compressor control system, the system comprising: Data acquisition module: Through a multi-parameter sensor network, it collects multi-dimensional data during the operation of the compressor in real time, pre-processes the collected multi-dimensional data, and constructs a data set; Optimization learning module: Through the reinforcement learning model based on deep neural network, the compressor control strategy is learned and optimized based on historical data and current environmental status; it is continuously updated through simulation and online learning; Real-time prediction module: Based on the adaptive neural network model, it can make real-time predictions on the operating status and performance parameters of the compressor in the future, and dynamically adjust the network structure and parameters according to the current working conditions and historical data of the compressor; Strategy generation module: fuses the outputs of the deep reinforcement learning decision module and the adaptive neural network prediction module to generate a comprehensive control strategy; Closed-loop control module: intelligently adjusts the compressor operating parameters according to the comprehensive control strategy; at the same time, through the closed-loop feedback mechanism, continuously monitors the compressor operating status and adjusts the control strategy in time.

[0005] Beneficial effects of the present invention: multi-dimensional data during the operation of the compressor is collected in real time through a multi-parameter sensor network. These data are preprocessed, including denoising, filling missing values, outlier detection, etc., to ensure data quality. Then, these data are organized into a time series data set to provide a basis for subsequent model training and prediction; using historical data and current environmental status, the control strategy of the compressor is learned and optimized through a deep neural network reinforcement learning model. The model is continuously iterated and updated through simulation and online learning to adapt to different operating conditions and environmental changes; an adaptive neural network model is used to predict the operating status and performance parameters of the compressor in the future in real time. The network structure and parameters are dynamically adjusted according to the current operating conditions and historical data to improve the accuracy of the prediction; the outputs of the deep reinforcement learning decision module and the adaptive neural network prediction module are fused to generate a comprehensive control strategy. This strategy takes into account immediate rewards and long-term returns, as well as stability and robustness under different operating conditions; the operating parameters of the compressor are intelligently adjusted according to the comprehensive control strategy, and the operating status and performance parameters of the compressor are continuously monitored through a closed-loop feedback mechanism. When anomalies or deviations from expectations are detected, the control strategy is adjusted in a timely manner, and the safe operation of the compressor is ensured through the exception handling process and fault warning system; as new data continues to arrive, the model will be updated according to the importance of the data to maintain its accuracy and adaptability. At the same time, through the rolling time window technology and online learning framework, the model can continuously receive new operating data and optimize itself; build a simulation system that highly simulates the actual operating environment of the compressor, receive the compressor operating data in the simulation environment in real time through the online learning framework, and interact with the deep reinforcement learning model. This allows the model to learn and adapt in a changing environment, thereby improving the performance of the control strategy; verify and optimize the comprehensive control strategy in the simulation environment, evaluate the performance of the strategy through comparative experiments, and adjust the parameters of the fusion algorithm and control strategy based on the verification results; through the fault warning system, when a potential fault is predicted, the operator is notified in advance to take corresponding measures. At the same time, the exception handling process can immediately initiate emergency protection measures when an anomaly is detected, ensuring that the key events and abnormal states of the compressor are recorded and processed. BRIEF DESCRIPTION OF THE DRAWINGS

[0006] Figure 1 It is a step diagram of the method of the present invention; Figure 2 This is a system module diagram of the present invention. DETAILED DESCRIPTION

[0007] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0008] One embodiment of the present invention, as Figure 1 As shown, a compressor control method, the method comprising: S1. Collect multi-dimensional data in real time during the operation of the compressor through a multi-parameter sensor network, wherein the multi-dimensional data includes pressure, temperature, current, vibration and flow; pre-process the collected multi-dimensional data and construct a data set; S2. Learn and optimize the compressor control strategy based on historical data and current environmental conditions (such as operating conditions, compressor status, etc.) through a reinforcement learning model based on a deep neural network; continuously iterate and update through simulation and online learning to generate optimal control instructions; S3, based on the adaptive neural network model, the operating status and performance parameters of the compressor in the future are predicted in real time, and the network structure and parameters are dynamically adjusted according to the current working conditions and historical data of the compressor; S4. The outputs of the deep reinforcement learning decision module and the adaptive neural network prediction module are integrated to generate a comprehensive control strategy; this strategy not only considers the optimal control under the current working conditions, but also incorporates predictive adjustments for future state changes; S5. Intelligently adjust the compressor operating parameters (such as speed, air intake, loading / unloading strategy, etc.) according to the comprehensive control strategy; at the same time, continuously monitor the compressor operating status through the closed-loop feedback mechanism and adjust the control strategy in time.

[0009] The working principle of the above technical solution is as follows: using a multi-parameter sensor network to collect key data in the operation process of the compressor in real time, including pressure, temperature, current, vibration, flow, etc.; pre-processing the collected multi-dimensional data, including data cleaning (noise removal, filling missing values, etc.), anomaly detection (identifying and processing abnormal data points) and feature engineering (extracting useful features, dimensionality reduction, etc.) to build a high-quality data set; using a reinforcement learning model based on a deep neural network, combined with historical data and current environmental conditions (such as operating conditions, compressor status, etc.), the control strategy of the compressor is learned and optimized; through simulation and online learning, the model is continuously iterated and updated to generate optimal control instructions with the goal of maximizing long-term benefits (such as energy efficiency, stability, etc.); based on an adaptive neural network model, the operating status and performance parameters of the compressor in the future are predicted in real time; according to the current operating conditions and historical data of the compressor, the network structure and parameters are dynamically adjusted to improve the accuracy of the prediction. The prediction result is used as one of the inputs of the deep reinforcement learning model to assist it in making more accurate decisions. The outputs of the deep reinforcement learning decision module and the adaptive neural network prediction module are integrated to generate a comprehensive control strategy. This strategy not only takes into account the optimal control under the current operating conditions, but also incorporates predictive adjustments to future state changes, thereby achieving comprehensive optimization of the compressor operating parameters. According to the comprehensive control strategy, the operating parameters of the compressor (such as speed, air intake, loading / unloading strategy, etc.) are intelligently adjusted. Through a closed-loop feedback mechanism, the operating status of the compressor is continuously monitored and the control strategy is adjusted in a timely manner.

[0010] The effects of the above technical solutions are as follows: by collecting multi-dimensional data in real time and preprocessing it, a high-quality data set is constructed, which provides a solid foundation for subsequent model learning and optimization. It helps to more accurately reflect the actual operating status of the compressor, so as to formulate a more efficient control strategy; the reinforcement learning model can continuously iterate and update the control strategy according to historical data and current environmental status, with the goal of maximizing long-term benefits. It can not only improve the operating efficiency of the compressor, but also optimize energy use and reduce energy consumption costs while maintaining efficient operation; the adaptive neural network model can predict the operating status and performance parameters of the compressor in the future in real time, and dynamically adjust according to the current working conditions and historical data. This predictive adjustment helps to discover and respond to potential operating problems in advance, thereby enhancing the operating stability and reliability of the compressor; the comprehensive control strategy integrates the outputs of the deep reinforcement learning decision module and the adaptive neural network prediction module, taking into account the optimal control under the current working conditions and incorporating predictive adjustments to future state changes. This comprehensive control strategy helps to ensure that the compressor can maintain a stable operating state under various working conditions; by introducing advanced artificial intelligence technologies such as deep neural networks, reinforcement learning and adaptive neural networks, intelligent optimization and real-time adjustment of the compressor control strategy are achieved. This greatly improves the intelligence and automation level of the compressor, reducing manual intervention and dependence; the closed-loop feedback mechanism can continuously monitor the operating status of the compressor and adjust the control strategy in time according to the actual situation. This automated adjustment mechanism helps to ensure that the compressor always maintains the best operating state, improving the reliability and flexibility of the overall system; by real-time monitoring and prediction of the operating status and performance parameters of the compressor, potential operating problems and failures can be discovered in time. This helps to take maintenance measures in advance to avoid the occurrence or expansion of failures, thereby reducing maintenance costs and downtime; intelligent and automated control strategies help optimize the operating parameters and working modes of the compressor and reduce unnecessary wear and loss. This helps to extend the service life of the compressor and improve the economy and sustainability of the overall system.

[0011] In one embodiment of the present invention, the S1 includes: S11, collecting multi-dimensional data in the operation process of the compressor in real time through a multi-parameter sensor network, and using a sliding window algorithm to smooth the collected multi-dimensional data to remove noise; S12. Detect and fill missing values ​​through statistical methods, apply machine learning algorithms (such as isolation forests) to detect outliers, and mark or remove them; S13. Implement feature engineering to extract characteristic variables that have a significant impact on the operating status of the compressor, such as pressure fluctuation rate and temperature change trend; organize the preprocessed data into time series to construct a data set containing historical data and current data; S14. The data set is stored through a distributed storage solution, and the data set is backed up based on a set data backup mechanism.

[0012] The working principle of the above technical solution is as follows: a multi-parameter sensor network is deployed on the compressor to collect multi-dimensional data in real time during the operation of the compressor, including but not limited to pressure, temperature, current, vibration and flow. In order to remove noise in the data, a sliding window algorithm is used to smooth the collected data. The sliding window algorithm defines a fixed-size or variable-size window on the data sequence and slides the window on the sequence at a certain step size, so as to average or weighted average the data in the window at each position to achieve the effect of smoothing the data; missing values ​​are detected and filled by statistical methods (such as interpolation, regression, etc.) to ensure the integrity of the data. Then, a machine learning algorithm (such as isolation forest) is applied to detect outliers. The isolation forest algorithm is an outlier detection method based on a decision tree, which distinguishes outliers from normal points by placing them in shallower branches of the tree. The detected outliers can be marked or removed to improve the quality and reliability of the data; in the feature engineering stage, feature variables that have an important impact on the operating status of the compressor are extracted, which can reflect the operating status, performance change trends and potential faults of the compressor. For example, characteristic variables such as pressure fluctuation rate and temperature change trend can be extracted. Then, the preprocessed data is organized in time series to construct a data set containing historical data and current data. Such a data set is helpful for subsequent model learning and optimization; in order to efficiently store and manage large-scale data sets, a distributed storage solution is adopted. The distributed storage solution improves the reliability and scalability of data by distributing and storing data on multiple nodes. At the same time, the data set is backed up based on the set data backup mechanism to prevent data loss or damage. Data backups can be saved locally or on a backup server, or online backup services such as cloud storage can be used to ensure data security and recoverability.

[0013] The effects of the above technical solutions are as follows: multi-dimensional data of the compressor operation process is collected in real time through a multi-parameter sensor network, ensuring the timeliness and comprehensiveness of the data; the sliding window algorithm is used to smooth the collected multi-dimensional data, effectively removing noise and improving the accuracy and reliability of the data; missing values ​​are detected and filled by statistical methods, avoiding analysis bias caused by missing data; machine learning algorithms (such as isolation forests) are used to detect outliers and mark or remove them, further improving the purity and accuracy of the data set; feature engineering is implemented to extract characteristic variables that have an important impact on the operating status of the compressor, such as pressure fluctuation rate, temperature change trend, etc. These features can more intuitively reflect the compressor The operating status and performance of the compressor; feature extraction is helpful for subsequent data analysis and model building, and improves the accuracy and generalization ability of the model; the preprocessed data is organized in time series, and a data set containing historical data and current data is constructed, which provides a basis for time series analysis and prediction; the data set is stored through a distributed storage solution, which makes full use of network resources and improves storage efficiency and scalability; distributed storage also helps to achieve high availability and fault tolerance of data, and enhances data reliability and security; the data set is backed up based on the data backup mechanism to ensure the recoverability of data in unexpected situations; the data backup mechanism helps to reduce the losses and risks caused by data loss or damage.

[0014] In one embodiment of the present invention, the S13 includes: Use correlation analysis to evaluate the correlation between various dimensional data (such as pressure, temperature, current, vibration, etc.) and the compressor operating status (such as efficiency, fault tendency, etc.). Based on the analysis results, select characteristic variables that are highly correlated with the compressor operating status; The importance of each feature variable is further quantified through feature importance evaluation methods (such as feature importance of random forest, coefficient of Lasso regression, etc.); based on the evaluation results, feature variables that have a significant impact on the compressor operating status, such as pressure fluctuation rate, temperature change trend, etc., are retained; Standardize or normalize the selected feature variables, and derive new feature variables based on domain knowledge and data characteristics; for example, the ratio of pressure to temperature, the spectral characteristics of vibration signals, etc. can be calculated to enrich the information content of the data set; Align all feature variables in the time series, that is, there is a corresponding data record under each timestamp; for missing timestamps, interpolate or fill in according to the trend of the previous and next data; According to the compressor's operating cycle and data analysis requirements, the data is divided into multiple time windows; each time window contains time series data of a certain length; The preprocessed historical data and current data are organized in time series to construct a comprehensive data set containing rich information; the historical data is used for model training, and the current data is used for model verification and prediction; The comprehensive dataset is divided into training set, validation set and test set; the training set is used for model training, the validation set is used for model selection and parameter adjustment, and the test set is used to evaluate the generalization ability of the model.

[0015] The working principle of the above technical solution is: using statistical methods (such as Pearson correlation coefficient, etc.) to evaluate the correlation between various dimensional data (such as pressure, temperature, current, vibration, etc.) and the operating status of the compressor (such as efficiency, fault tendency, etc.); by analyzing the results, identifying the characteristic variables that are highly correlated with the operating status of the compressor. These variables can usually better reflect the operating status and performance changes of the compressor; using feature importance evaluation methods (such as feature importance of random forest, coefficient of Lasso regression, etc.) to further quantify the importance of each feature variable; according to the evaluation results, screen out the characteristic variables that have an important impact on the operating status of the compressor, such as pressure fluctuation rate, temperature change trend, etc. These variables will play a key role in subsequent model training; standardize or normalize the screened feature variables to eliminate the dimensional differences between different features and improve the convergence speed and prediction performance of the model; derive new feature variables based on domain knowledge and data characteristics. For example, calculate the ratio of pressure to temperature, the spectral characteristics of the vibration signal, etc., to enrich the information content of the data set. These derived features help the model to understand the operating status of the compressor more comprehensively; align all feature variables in the time series to ensure that there is a corresponding data record at each timestamp. It helps to maintain the consistency and integrity of the data; for missing timestamps, interpolate or fill in according to the trend of the previous and next data. It can ensure the continuity and reliability of the data set and avoid negative impact on model training; divide the data into multiple time windows according to the operating cycle of the compressor and data analysis requirements. Each time window contains a certain length of time series data, which helps the model capture the temporal dependency and periodic changes of the data; organize the preprocessed historical data and current data in time series to build a comprehensive data set containing rich information. Among them, historical data is used for model training, and current data is used for model verification and prediction; the comprehensive data set is divided into training set, validation set and test set. The training set is used for model training to provide enough data for the model to learn the inherent laws and patterns of the data; the validation set is used for model selection and parameter adjustment to help select the optimal model parameters and configuration; the test set is used to evaluate the generalization ability of the model to ensure that the model can also perform well on unseen data.

[0016] The effects of the above technical solution are as follows: through correlation analysis, the characteristic variables that are highly correlated with the operating status of the compressor can be accurately identified, avoiding the interference of irrelevant or redundant data; the selected characteristic variables are more focused on the key indicators of the compressor operation, improving the efficiency and accuracy of data analysis and model training; using the feature importance evaluation method, the importance of each characteristic variable is further quantified, ensuring that the most valuable features can be fully utilized during the model training process; the characteristic variables that have an important impact on the operating status of the compressor, such as pressure fluctuation rate, temperature change trend, etc., are retained. These features can more accurately reflect the operating status and performance changes of the compressor; the selected characteristic variables are standardized or normalized, eliminating the dimensional differences between different features, and improving the convergence speed and prediction performance of the model; standardization or normalization helps to reduce the risk of overfitting of the model and improve the stability and generalization ability of the model; based on domain knowledge and data characteristics, new characteristic variables are derived, such as the ratio of pressure to temperature, the spectral characteristics of the vibration signal, etc. These features can provide richer information and help the model to understand the operating status of the compressor more comprehensively; feature derivation also helps to capture the potential relationship between data, improving the prediction performance of the model The method improves the accuracy and robustness of the model. All feature variables are aligned in time series to ensure that there is a corresponding data record under each timestamp, which helps to maintain the consistency and integrity of the data. Time series alignment provides a reliable data basis for subsequent model training and prediction. For missing timestamps, interpolation or filling is performed according to the trend of the previous and next data to ensure the continuity and reliability of the data set. Missing value processing avoids analysis bias and model performance degradation caused by missing data. According to the operating cycle of the compressor and data analysis requirements, the data is divided into multiple time windows, each of which contains time series data of a certain length. The time window setting helps the model capture the temporal dependency and periodic changes of the data, and improves the prediction accuracy and adaptability of the model. The preprocessed historical data and current data are organized in time series to construct a comprehensive data set containing rich information. The comprehensive data set provides sufficient data support for model training and prediction, which helps to improve the accuracy and generalization ability of the model. The comprehensive data set is divided into training set, validation set and test set to ensure the independence of model training, selection and evaluation. The training set is used for model training, the validation set is used for model selection and parameter adjustment, and the test set is used to evaluate the generalization ability of the model. This division method helps to avoid overfitting and underfitting problems and improves the reliability and practicality of the model.

[0017] In one embodiment of the present invention, the S2 includes: S21. Construct a reinforcement learning model architecture based on a deep neural network, wherein the model framework includes a policy network and a value network; the policy network is used to generate control instructions, and the value network is used to evaluate the quality of the control instructions; S22, dividing the constructed data set into a training set and a validation set for model training and validation, using a stochastic gradient descent algorithm to perform offline training on the model to learn the optimal control strategy of the compressor under different working conditions; S23. Optimize the model performance by adjusting hyperparameters (such as learning rate and batch size), build a compressor operation simulation environment, and simulate the compressor behavior under different working conditions, including normal working conditions and abnormal working conditions; S24, implement online learning in the simulation environment, and collect new data for model updating; continuously update the data in the simulation environment through rolling time window technology; S25. Generate optimal control instructions based on the output of the deep reinforcement learning model, including adjustment suggestions for parameters such as compressor speed, air intake volume, and loading / unloading strategy.

[0018] The working principle of the above technical solution is as follows: a reinforcement learning model architecture based on a deep neural network is constructed, which includes a policy network and a value network; the policy network is responsible for generating control instructions, which will directly act on the compressor to adjust its operating state; the value network is used to evaluate the quality of the control instructions generated by the policy network, thereby providing feedback for the optimization of the policy network; the constructed data set is divided into a training set and a validation set, which are used for model training and validation respectively; the model is trained offline using a stochastic gradient descent algorithm. In the offline training stage, the model gradually optimizes the parameters of the policy network and the value network by repeatedly learning the data in the training set, so as to learn to optimally control the compressor under different working conditions; the performance of the model is optimized by adjusting hyperparameters (such as learning rate and batch size). The adjustment of these hyperparameters will directly affect the training speed and convergence performance of the model; a compressor operation simulation environment is constructed to simulate the behavior of the compressor under different working conditions. These working conditions include normal working conditions and abnormal working conditions, etc., to comprehensively test the adaptability and robustness of the model; online learning is implemented in the simulation environment. During the online learning phase, the model will continuously receive new data inputs and adjust its parameters and strategies in real time based on these data to adapt to more complex and changeable operating conditions; the data in the simulation environment will be continuously updated through rolling time window technology. This helps to maintain the timeliness and accuracy of the model data, thereby improving the prediction and control performance of the model; based on the output of the deep reinforcement learning model, the optimal control instructions are generated. These instructions include adjustment suggestions for parameters such as compressor speed, air intake, loading / unloading strategies, etc. These control instructions will directly guide the operation of the compressor to achieve a more efficient and stable operating state. At the same time, these instructions can also be dynamically adjusted according to actual conditions to adapt to changing operating conditions.

[0019] The effect of the above technical solution is: the deep neural network has a strong learning ability, can automatically learn complex and high-order feature representations, and is suitable for processing large-scale, high-dimensional data. In the reinforcement learning model, the deep neural network is used to construct a policy network and a value network, which are responsible for generating control instructions and evaluating the pros and cons of control instructions respectively. This structure enables the model to more accurately learn the optimal control strategy of the compressor under different working conditions; reinforcement learning learns through the interaction between the agent and the environment to maximize the long-term cumulative reward. In the compressor control scenario, the agent can select actions (such as adjusting the speed, intake volume, etc.) according to the state of the environment (such as the compressor working condition), and adjust its behavior strategy through feedback from the environment (such as compressor performance, energy consumption, etc.). This trial and error method enables the model to adapt to different working conditions and improve robustness; dividing the constructed data set into a training set and a validation set is helpful for model training and validation. The training set is used for the learning process of the model, while the validation set is used to evaluate the performance of the model to ensure that the model can also show good generalization ability on unseen data; the model is trained offline using the stochastic gradient descent algorithm, which can efficiently update the model parameters and accelerate the training process. At the same time, by continuously adjusting hyperparameters such as learning rate, the model performance can be further optimized; by building a compressor operation simulation environment, the compressor behavior under different working conditions, including normal working conditions and abnormal working conditions, can be simulated. This makes it possible for the online learning and adaptation of the model, so that the model can show good performance under more complex and changeable working conditions; implementing online learning in the simulation environment enables the model to adapt to new working conditions and collect new data for model updates. The data in the simulation environment is continuously updated through the rolling time window technology to ensure that the model can always reflect the latest working conditions; based on the output of the deep reinforcement learning model, the optimal control instructions can be generated, including the adjustment suggestions of parameters such as compressor speed, air intake, loading / unloading strategy, etc. These suggestions can guide the optimal control of the compressor in actual operation and improve the system performance and stability; this technical solution has broad application prospects in the field of compressor control and can bring significant economic and social benefits to enterprises. For example, by optimizing the compressor control strategy, energy consumption can be reduced, production efficiency can be improved, and equipment life can be extended.

[0020] In one embodiment of the present invention, the S24 includes: S241, constructing a simulation system that highly simulates the actual operating environment of the compressor, receiving the compressor operating data in the simulation environment in real time through an online learning framework, and interacting the operating data with the deep reinforcement learning model; S242, simulating various complex and changeable working conditions in a simulation environment, wherein the complex and changeable working conditions include different load requirements, ambient temperature changes, and power supply voltage fluctuations; during the simulation process, collecting compressor operation data in real time, including key parameters such as pressure, temperature, current, and vibration; S243, continuously updating the data in the simulation environment through the rolling time window technology, and adjusting the size of the time window according to the change speed of the compressor operation characteristics and the update requirements of the model; S244, perform quality assessment and preprocessing on the newly collected data, perform online verification and evaluation on the model through the new data, and evaluate the accuracy and performance of the model by comparing the model prediction results with the actual simulation results; S245. According to the results of online verification, the parameters of the deep reinforcement learning model are adjusted in real time, including the learning rate, batch size, and network weight. Based on the adaptive learning rate adjustment mechanism, the learning rate is dynamically adjusted according to the learning progress and error changes of the model. S246. Update the model parameters and strategies obtained through online learning to the compressor control system in actual operation, and iteratively optimize the control strategy by combining historical data and real-time data through the strategy optimization algorithm.

[0021] The working principle of the above technical solution is as follows: the simulation system can accurately replicate the physical characteristics and behavior patterns of the compressor, including stable operation under normal conditions and response mechanisms under abnormal conditions. Through the online learning framework, the compressor operation data in the simulation environment is received in real time, and these data are interacted with the deep reinforcement learning model to provide a basis for the online learning and updating of the model; the simulation system can simulate various complex and changeable operating conditions, such as different load requirements, ambient temperature changes, power supply voltage fluctuations, etc.; during the simulation process, the compressor operation data is collected in real time, including key parameters such as pressure, temperature, current, vibration, etc., which will be used for online learning and verification of the model; the rolling time window technology is used to continuously update the data in the simulation environment to ensure that the model can learn the latest compressor operating characteristics and trends; according to the speed of change of the compressor operating characteristics and the update requirements of the model, the size of the time window is dynamically adjusted to improve the adaptability and accuracy of the model; the quality of the newly collected data is evaluated to ensure that the data The accuracy and reliability of the data are evaluated; the data are preprocessed to meet the requirements of the model input; the accuracy and performance of the model are evaluated by comparing the model prediction results with the actual simulation results, providing a basis for the parameter adjustment and optimization of the model; the parameters of the model, including learning rate, batch size, network weight, etc., are adjusted in real time according to the results of online verification; an adaptive learning rate adjustment mechanism is adopted to dynamically adjust the learning rate according to the learning progress and error changes of the model to improve the convergence speed and accuracy of the model; the model parameters and strategies obtained from online learning are updated to the compressor control system in actual operation to realize the real-time application and optimization of the model; the control strategy is iteratively optimized through the strategy optimization algorithm in combination with historical data and real-time data to find better control instructions and parameter adjustment schemes to improve the operating efficiency and stability of the compressor.

[0022] The effect of the above technical solution is: by building a simulation system that highly simulates the actual operating environment of the compressor, the physical characteristics and behavior patterns of the compressor can be accurately replicated, including responses under normal and abnormal conditions. It helps the model to learn and optimize under conditions close to the real environment, improving the practicality and accuracy of the model; the simulation system receives the compressor operation data in real time through the online learning framework and interacts with the deep reinforcement learning model. This real-time data-driven learning method enables the model to quickly adapt to changes in the compressor's operating state, improving the model's response speed and adaptability; the simulation environment can simulate a variety of complex and changeable operating conditions, such as different load requirements, ambient temperature changes, power supply voltage fluctuations, etc. This helps the model learn the optimal control strategy under different working conditions and improve the generalization ability of the model; during the simulation process, the key operating parameters of the compressor, such as pressure, temperature, current, vibration, etc., are collected in real time. These data provide rich information for model training and verification, which helps the model to more accurately predict and control the operating state of the compressor; the data in the simulation environment is continuously updated through the rolling time window technology to ensure that the model can learn the latest compressor operating characteristics and trends. It helps the model to keep real-time tracking and adaptability to the compressor's operating status; adjust the size of the time window according to the speed of change of the compressor's operating characteristics and the update requirements of the model to improve the update efficiency and accuracy of the model. This flexibility enables the model to better adapt to changes in the compressor's operating status; perform quality assessment and preprocessing on newly collected data to ensure the accuracy and reliability of the data. This helps to avoid misleading learning results of the model due to data quality issues; verify and evaluate the model online with new data, compare the model's prediction results with the actual simulation results, and evaluate the model's accuracy and performance. This verification method helps to timely discover problems in the model and make adjustments to improve the stability and reliability of the model; adjust the parameters of the deep reinforcement learning model in real time according to the results of online verification, including learning rate, batch size, network weight, etc. This real-time adjustment method helps the model converge to the optimal solution faster and improve the learning efficiency of the model; based on the adaptive learning rate adjustment mechanism, dynamically adjust the learning rate according to the model's learning progress and error changes. This adaptive adjustment method helps the model maintain a stable convergence speed during training and avoid overfitting or underfitting problems; update the model parameters and strategies obtained from online learning to the actual operating compressor control system to achieve real-time application and optimization of the model. This helps to transform the learning results of the model into actual production benefits and improve the operating efficiency and stability of the compressor; the control strategy is iteratively optimized by combining historical data and real-time data through the strategy optimization algorithm to find better control instructions and parameter adjustment solutions. This iterative optimization method helps to continuously improve the performance and intelligence level of the control system.

[0023] In one embodiment of the present invention, the S243 includes: Evaluate the timeliness of the data by comparing its timestamp, rate of change, and correlation with other parameters to determine whether the data still represents the current operating status of the compressor; Based on the speed of change of compressor operating characteristics and the need to update the model, the dynamically adjusted time window size is designed; initially, a larger time window is set to capture the operating trend over a longer period of time; as the model becomes more adaptable to the data, the time window is gradually reduced to focus on recent data changes; The sliding strategy of the time window is set based on a fixed time interval or the change of data volume, and based on the automatic data update mechanism, when new data enters the time window, the oldest data is automatically replaced; Through the model feedback loop, the updated data is re-input into the deep reinforcement learning model for a new round of training and verification; by comparing the model prediction results of new and old data, the adaptability and accuracy of the model are evaluated.

[0024] Identify and filter out abnormal data in the simulation environment through anomaly detection algorithms. Abnormal data may be caused by sensor failure, data transmission errors, or abnormal behavior of the compressor itself. According to the results of anomaly detection, formulate data filtering strategies. For example, for data determined to be abnormal, you can choose to directly delete it, replace it with the average value, or perform other reasonable processing. According to the adaptability evaluation index, the model's adaptability to new data is quantified, and the model's optimization strategy is dynamically adjusted according to the results of the adaptability evaluation. For example, when the model's adaptability to new data is weak, the learning rate can be increased or the network structure can be adjusted; when the model has shown strong adaptability, the learning rate can be reduced to avoid overfitting.

[0025] The working principle of the above technical solution is: by comparing the timestamp, change rate and correlation with other parameters of the data, the timeliness of the data is evaluated. The timestamp is used to determine the data collection time, the change rate reflects the trend of data change over time, and the correlation with other parameters helps to identify the potential connection between the data. These data features together constitute the basis for evaluating whether the data still represents the current operating status of the compressor; according to the speed of change of the compressor operating characteristics and the update requirements of the model, the dynamically adjusted time window size is designed. In the early stage, in order to capture the operating trend for a long time, a larger time window is set. As the model's adaptability to the data gradually increases, the time window gradually shrinks to focus on recent data changes, so as to more accurately reflect the current state of the compressor; the sliding strategy of the time window is set based on a fixed time interval or a change in the amount of data. When new data enters the time window, the oldest data is automatically replaced according to the sliding strategy to maintain the timeliness and representativeness of the data in the time window; the data is automatically updated and replaced to ensure that the time window always contains the latest and most accurate data. This mechanism provides stable data support for the continuous learning and optimization of the model; the updated data is re-input into the deep reinforcement learning model for a new round of training and verification. The adaptability and accuracy of the model are evaluated by comparing the model prediction results of new and old data. This feedback loop helps the model to continuously learn and optimize to adapt to changes in the operating status of the compressor; the abnormal data in the simulation environment is identified and filtered out through the anomaly detection algorithm. Abnormal data may be caused by sensor failure, data transmission errors, or abnormal behavior of the compressor itself. According to the results of anomaly detection, a data filtering strategy is formulated, such as directly deleting abnormal data, replacing it with the average value, or performing other reasonable processing to ensure the accuracy and reliability of the data input to the model; according to the adaptability evaluation index, the model's adaptability to new data is quantified. When the model's adaptability to new data is weak, the adaptability of the model is enhanced by increasing the learning rate, adjusting the network structure, and other strategies. When the model has shown strong adaptability, the learning rate is reduced to avoid overfitting and ensure the stability and accuracy of the model.

[0026] The effect of the above technical solution is: by comparing the timestamp, change rate and correlation with other parameters of the data, the timeliness of the data is accurately evaluated to ensure that the data input into the model can truly reflect the current operating status of the compressor. This helps the model to make more accurate predictions and decisions, and improve the response speed and accuracy of the control system; dynamically adjust the size of the time window according to the speed of change of the compressor operating characteristics and the update requirements of the model. Initially, a larger time window is set to capture the operating trend for a longer time. As the model's adaptability to the data increases, the time window is gradually narrowed to focus on recent data changes. This dynamic adjustment strategy helps the model better adapt to changes in the compressor's operating status and improve the generalization and robustness of the model; the sliding strategy of the time window is set based on a fixed time interval or a change in the amount of data, and the data is automatically updated. When new data enters the time window, the oldest data is automatically replaced to ensure that the time window always contains the latest and most accurate data. This helps the model to continuously learn the latest compressor operating characteristics and improve the real-time and accuracy of the model; through the model feedback loop, the updated data is re-input into the deep reinforcement learning model for a new round of training and verification. By comparing the model prediction results of new and old data, the adaptability and accuracy of the model are evaluated. This feedback loop mechanism helps the model to continuously learn and optimize, and improves the performance and stability of the model; anomaly detection algorithms are used to identify and filter out abnormal data in the simulation environment. Abnormal data may be caused by sensor failure, data transmission errors, or abnormal behavior of the compressor itself. By timely detecting and filtering abnormal data, the model can be prevented from being misled and the prediction accuracy and reliability of the model can be improved; a reasonable data filtering strategy can be formulated based on the results of anomaly detection. For data determined to be abnormal, you can choose to directly delete, replace it with the average value, or perform other reasonable processing. This helps to ensure the accuracy and consistency of the data input into the model and improve the stability and robustness of the model; according to the adaptability evaluation index, the model's adaptability to new data is quantified. This helps to timely discover problems and deficiencies in the model and provide strong support for the optimization of the model; according to the results of the adaptability evaluation, the optimization strategy of the model is dynamically adjusted. When the model's adaptability to new data is weak, the learning rate can be increased or the network structure can be adjusted to enhance the adaptability of the model; when the model has shown strong adaptability, the learning rate can be reduced to avoid overfitting. This dynamic adjustment strategy helps the model maintain the best learning state and performance at different stages.

[0027] In one embodiment of the present invention, the S245 includes: Analyze the error between the model prediction results and the actual simulation results; Based on the error analysis, identify the performance bottlenecks of the model under different working conditions; For example, the model may perform poorly under certain load demands or ambient temperatures, which may be related to the physical characteristics of the compressor or the complexity of the behavior pattern; Through the adaptive learning rate adjustment mechanism, the learning rate is dynamically adjusted according to the model's learning progress and error changes, and the impact of batch size on model training efficiency and stability is analyzed; by comparing the model performance under different batch sizes, the optimal batch size that can ensure both training efficiency and model stability is selected; Implement parameter adjustment experiments in the simulation environment, select the optimal parameter settings by comparing the model performance under different parameter combinations, continuously monitor the performance changes of the model during the parameter adjustment process, and provide real-time feedback based on the monitoring results; The performance of the adjusted model is evaluated on the validation set, and the adjusted model parameters and strategies are applied to the actual compressor control system. The control strategy is iteratively optimized by combining real-time data and historical data.

[0028] The working principle of the above technical solution is: analyze the error between the model prediction results and the actual simulation results, and calculate statistical indicators such as absolute error, relative error, and mean square error (MSE); these error indicators can quantify the accuracy of model prediction and provide a basis for subsequent model optimization; based on the results of error analysis, identify the performance bottleneck of the model under different working conditions. For example, the model may perform poorly under certain load demands or ambient temperatures, which may be related to the physical characteristics of the compressor or the complexity of its behavior patterns; by identifying performance bottlenecks, the model can be optimized in a targeted manner to improve its prediction accuracy under various operating conditions; through the adaptive learning rate adjustment mechanism, the learning rate is dynamically adjusted according to the model's learning progress and error changes; the loss function changes on the validation set are monitored, and the learning rate is reduced when the loss function tends to be stable to promote model convergence; the learning rate is increased when the loss function suddenly increases to avoid falling into a local optimal solution; this method of dynamically adjusting the learning rate helps to improve the training efficiency and accuracy of the model; analyze the impact of batch size on model training efficiency and stability; by comparing the model performance under different batch sizes, select the optimal batch size that can ensure both training efficiency and model stability; batch size optimization helps to balance the training speed and stability of the model; in the simulation environment Parameter adjustment experiments are implemented in the process to select the optimal parameter settings by comparing the model performance under different parameter combinations; parameter adjustment experiments can systematically explore the impact of model parameters on performance and provide the possibility of finding the best parameter combination; during the parameter adjustment process, the performance changes of the model are continuously monitored, and real-time feedback is provided based on the monitoring results; real-time feedback helps to promptly discover changes in model performance and adjust parameters to optimize model performance; the adjusted model performance is evaluated on the validation set to ensure the accuracy and reliability of the model in practical applications; the performance evaluation on the validation set provides strong support for the practical application of the model; the adjusted model parameters and strategies are applied to the actual operating compressor control system; the control strategy is iteratively optimized in combination with real-time data and historical data to improve the performance and stability of the compressor control system; iterative optimization is a continuous process that helps to continuously improve the intelligence level of the compressor control system.

[0029] The effects of the above technical solution are as follows: by calculating statistical indicators such as absolute error, relative error, mean square error (MSE), etc., the difference between the model prediction results and the actual simulation results can be quantified; based on error analysis, the performance bottleneck of the model under different working conditions can be identified, such as poor performance under specific load requirements or ambient temperature; this helps to optimize the model in a targeted manner and improve its prediction accuracy; implement parameter adjustment experiments in a simulation environment, and select the optimal parameter settings by comparing the model performance under different parameter combinations; during the parameter adjustment process, continuously monitor the performance changes of the model and provide real-time feedback based on the monitoring results; this helps to dynamically adjust the model parameters to adapt to the compressor characteristics under different working conditions, thereby improving the prediction accuracy; through the adaptive learning rate adjustment mechanism, the learning rate is dynamically adjusted according to the learning progress and error changes of the model; when the loss function tends to be stable, the learning rate is reduced to promote the convergence of the model; when the loss function suddenly increases, the learning rate is increased to avoid falling into the local optimal solution; this helps to improve the training efficiency of the model while maintaining the stability of the model; through Compare the model performance under different batch sizes, and select the optimal batch size that can ensure both training efficiency and model stability; this helps to balance the training speed and stability of the model and improve the overall performance; evaluate the adjusted model performance on the validation set to ensure the accuracy and reliability of the model in practical applications; this helps to verify the generalization ability of the model and ensure its applicability under different working conditions; apply the adjusted model parameters and strategies to the actual operating compressor control system; through the combination of real-time data and historical data, iteratively optimize the control strategy; this helps the model to continuously learn and adapt in practical applications and improve the overall performance of the compressor control system; this technical solution is based on a data-driven approach, and continuously optimizes the model through error analysis, parameter adjustment and other means; it helps to promote the intelligent development of compressor control systems and improve their automation level and operating efficiency; this technical solution provides a framework for continuous optimization, which can continuously optimize models and control strategies as data accumulates and technology advances; it helps to maintain the advancement and competitiveness of compressor control systems.

[0030] In one embodiment of the present invention, S3 includes: S31, selecting an adaptive neural network model, and designing an input layer and an output layer of the model, wherein the input layer is used to receive the preprocessed compressor operation data, and the output layer is used to predict the operation status and performance parameters of the compressor in the future; S32. Perform offline training on the model through the back propagation algorithm and the Adam optimizer, so that the model can predict the operating status and performance parameters of the compressor in the future (for example, one week); S33, dynamically adjusting the structure and parameters of the adaptive neural network according to the current working conditions and historical data of the compressor, such as increasing or decreasing the hidden layer, adjusting the number of neurons, etc., and preventing the model from overfitting through regularization; S34. Based on the preset model update strategy, when new data arrives, the model parameters are updated according to the importance of the data; the prediction results of the adaptive neural network are used as one of the inputs of the deep reinforcement learning model to assist it in making decisions.

[0031] The working principle of the above technical solution is as follows: the solution uses adaptive neural network models such as long short-term memory network (LSTM) or gated recurrent unit (GRU), which are particularly suitable for processing data with time series characteristics, such as compressor operation data; including key parameters such as intake pressure, intake temperature, exhaust pressure, exhaust temperature, speed, flow rate, etc.; the output layer is used to predict the operating status and performance parameters of the compressor in the future, such as exhaust pressure, efficiency, etc.; the adaptive neural network model is trained offline using the back propagation algorithm and Adam optimizer. The back propagation algorithm is used to calculate the error between the model prediction result and the actual value, and reduce the error by adjusting the model parameters; the Adam optimizer is an efficient optimization algorithm that can dynamically adjust the learning rate of each parameter according to the first-order moment estimation and second-order moment estimation of the gradient; the training goal is to enable the model to accurately predict the operating status and performance parameters of the compressor in the future (such as a week); according to the current working conditions and compressor historical data, the structure and parameters of the adaptive neural network are dynamically adjusted. This includes measures such as adding or reducing hidden layers and adjusting the number of neurons to adapt to data characteristics and prediction requirements under different working conditions; the purpose of dynamic adjustment is to improve the adaptability and prediction accuracy of the model; in the process of model training, regularization technology is used to prevent model overfitting. Regularization limits the complexity of model parameters by adding penalty terms to the loss function, thereby avoiding the problem that the model performs too well on training data but has poor generalization ability on test data; based on the preset model update strategy, when new data arrives, the model parameters are updated according to the importance of the data. This ensures that the model can continue to learn and adapt to new data characteristics; model update strategies may include incremental learning, online learning and other methods to adapt to different application scenarios and data update frequencies; the prediction results of the adaptive neural network are used as one of the inputs of the deep reinforcement learning model. The deep reinforcement learning model can make more accurate decisions based on the prediction results and other relevant information to optimize the operation strategy and energy efficiency of the compressor; this combination can give full play to the advantages of adaptive neural networks in prediction and the ability of deep reinforcement learning in decision-making, and jointly improve the operating efficiency and reliability of the compressor.

[0032] The effects of the above technical solution are as follows: by selecting adaptive neural network models such as long short-term memory network (LSTM) or gated recurrent unit (GRU), the solution can fully capture the time series characteristics of compressor operation data; these models have excellent performance in processing time series data and can accurately predict the operation status and performance parameters of the compressor in the future; through offline training with back propagation algorithm and Adam optimizer, the model can learn the inherent laws and patterns of compressor operation data; during online prediction, the model can predict the operation status and performance parameters of the compressor in real time according to the current operating conditions and historical data, thereby improving the accuracy and real-time performance of the prediction; according to the current operating conditions and historical data of the compressor, the solution can dynamically adjust the structure and parameters of the adaptive neural network; for example, increase or decrease hidden layers, adjust the number of neurons, etc., to adapt to different prediction needs and changes in operating conditions; through regularization technology, the solution can effectively prevent model overfitting and improve the generalization ability of the model; this enables the model to be able to face new data. The solution adopts a preset model update strategy to update the model parameters according to the importance of the new data, which ensures that the model can learn new data features in a timely manner and improve the accuracy and reliability of the prediction. The prediction results of the adaptive neural network are used as one of the inputs of the deep reinforcement learning model to assist it in making more accurate decisions. The deep reinforcement learning model can optimize the operating parameters and strategies of the compressor according to the prediction results and other relevant information, and reduce energy consumption and maintenance costs. By accurately predicting the operating status and performance parameters of the compressor, the solution can detect potential problems in a timely manner and make optimization adjustments. This helps to maintain the stable operation of the compressor and improve its operating efficiency. By predicting the failure risk and performance degradation trend of the compressor, the solution can formulate maintenance plans in advance and take corresponding measures. This helps to reduce the maintenance cost and downtime of the compressor. The application of this solution can improve the production efficiency and product quality of the enterprise and reduce operating costs. It helps to enhance the competitiveness of the enterprise in the market and achieve sustainable development.

[0033] In one embodiment of the present invention, the S33 includes: The operating data of the compressor is collected in real time through the sensor network, including key parameters such as pressure, temperature, current, and vibration. The principal component analysis (PCA) is used to perform feature selection and dimension reduction on the collected operating data to extract the feature vector that best represents the operating conditions of the compressor. Clean, denoise and standardize the compressor's historical operating data, use clustering algorithms to perform pattern recognition on historical data, and identify different operating modes and fault types; According to the results of operating condition analysis and historical data mining, the number of hidden layers and the number of neurons in each layer of the adaptive neural network are dynamically adjusted; for example, when it is identified that the compressor is under high load or abnormal operating conditions, the number of hidden layers and neurons can be increased to improve the prediction accuracy of the model; Based on network pruning and layer merging technology, the network topology is optimized according to model performance and computing resource constraints. The network weights and biases are initialized using Xavier or He initialization methods combined with Adam or RMSprop optimizers, and dynamically adjusted during training. L1 and L2 regularization terms are introduced, and the performance of the model is monitored on the validation set; when the performance of the validation set begins to decline, the early stopping method is used to stop training.

[0034] The performance of the adjusted model is evaluated using the cross-validation method. Based on the evaluation results, the structure and parameters of the model are iteratively optimized, and the optimized model is applied to the actual compressor control system for verification.

[0035] The working principle of the above technical solution is as follows: with the help of sensor networks, multiple operating data of the compressor are captured in real time, covering key indicators such as pressure, temperature, current and vibration; principal component analysis (PCA) technology is used to screen out the most representative feature vectors from massive data, effectively reducing data dimensions and improving processing efficiency; historical operating data is deeply cleaned, noise is removed and standardized; clustering algorithms are applied to identify different operating modes and potential fault types, providing a strong basis for subsequent model adjustments; the number of hidden layers and the number of neurons in each layer of the adaptive neural network are flexibly adjusted according to the operating condition analysis and historical data mining results; for example, when the compressor is under high load or abnormal operating conditions, the number of hidden layers and neurons is appropriately increased to enhance the prediction accuracy and generalization ability of the model; combined with network pruning and layer merging techniques, the topology of the network is adjusted according to model performance and computing resource limitations. Fine-tune; use Xavier or He initialization methods to set reasonable initial values ​​for the network's weights and biases to ensure the stability and efficiency of the training process; use efficient optimizers such as Adam or RMSprop to dynamically adjust the network's weights and biases to accelerate the training process and improve model performance; introduce L1 and L2 regularization terms to effectively prevent model overfitting and improve the generalization ability of the model; use cross-validation methods to conduct a comprehensive performance evaluation of the adjusted model, including key indicators such as accuracy, recall rate, and F1 score; by comparing the evaluation results of different models, select the model structure and parameter combination with the best performance; based on the evaluation results, iteratively optimize the model's structure and parameters to continuously improve the model's prediction accuracy and stability; apply the optimized model to the actual compressor control system for verification to ensure its reliability and effectiveness in the actual operating environment.

[0036] The effects of the above technical solutions are: collecting key parameters in real time through the sensor network, and using principal component analysis (PCA) for feature selection and dimensionality reduction, effectively reducing data redundancy and improving the efficiency and accuracy of data processing. This helps to quickly identify the feature vector that best represents the compressor operating conditions, providing a high-quality data basis for subsequent model training; deep cleaning, denoising and standardization of historical operating data, and using clustering algorithms to identify different operating modes and fault types. This not only helps to understand the operating characteristics of the compressor, but also provides an important basis for the dynamic adjustment of the model, improving the adaptability and prediction accuracy of the model under different operating conditions; according to the results of operating condition analysis and historical data mining, dynamically adjust the number of hidden layers and the number of neurons in each layer of the adaptive neural network. This flexibility enables the model to better adapt to the operating characteristics of the compressor under different operating conditions and improve the accuracy and robustness of the prediction; based on network pruning and layer merging technology, the network structure is optimized according to model performance and computing resource constraints. This helps to reduce the complexity and computational cost of the model while ensuring the prediction performance, and improve the practicality and scalability of the model; the weights and biases of the network are initialized by using the Xavier or He initialization method combined with the Adam or RMSprop optimizer, and are dynamically adjusted during the training process. This helps to speed up the convergence of the model and improve the training efficiency; L1 and L2 regularization terms are introduced to prevent the model from overfitting, and the model performance is monitored on the validation set. When the performance of the validation set begins to decline, the early stopping method is used to stop the training. This helps to ensure the generalization ability of the model and avoid performance degradation caused by overfitting; the performance of the adjusted model is evaluated using the cross-validation method, including indicators such as accuracy, recall rate, and F1 score. This helps to comprehensively and objectively evaluate the performance of the model and provide a reliable basis for iterative optimization; the structure and parameters of the model are iteratively optimized according to the evaluation results, and the optimized model is applied to the actual compressor control system for verification. This systematic optimization process helps to continuously improve the prediction accuracy and practicality of the model, and provides strong support for the intelligent control and maintenance of the compressor.

[0037] In one embodiment of the present invention, the S4 includes: S41. Based on the fusion algorithm, the outputs of the deep reinforcement learning decision module and the adaptive neural network prediction module are fused to generate a comprehensive control strategy; S42. Verify and optimize the comprehensive control strategy in a simulation environment, and evaluate the performance of the strategy through comparative experiments; adjust the parameters of the fusion algorithm and control strategy according to the verification results; S43. Based on the preset strategy update mechanism, when new data or working conditions change, the comprehensive control strategy is updated in a timely manner.

[0038] The working principle of the above technical solution is: based on the fusion algorithm, the outputs of the deep reinforcement learning decision module and the adaptive neural network prediction module are effectively integrated; a comprehensive control strategy is generated that not only takes into account the optimal control under the current working conditions, but also foresees future state changes and makes corresponding adjustments; the fusion algorithm needs to fully consider the output characteristics of the two modules to ensure the accuracy and effectiveness of the control strategy. The deep reinforcement learning decision-making module is responsible for making immediate decisions based on the current operating conditions, while the adaptive neural network prediction module is responsible for predicting future states and adjusting the control strategy in advance; the generated comprehensive control strategy is verified and optimized in a simulation environment; the performance of the strategy is evaluated through comparative experiments, including comparisons of control effects and stability under different parameters; based on the verification results, the parameters of the fusion algorithm and control strategy are fine-tuned to further improve the performance of the strategy; this process may require multiple iterations until the optimal parameter combination and control strategy are found; based on the preset strategy update mechanism, the comprehensive control strategy is updated in a timely manner when new data or operating conditions change; new data may come from real-time collection of the sensor network, or from further mining and analysis of historical data; changes in operating conditions may include changes in compressor load, changes in ambient temperature, etc., all of which require the strategy to respond and make adjustments in a timely manner; the update process should be as automated as possible to reduce manual intervention and improve update efficiency.

[0039] The effects of the above technical solution are as follows: by integrating the outputs of the deep reinforcement learning decision-making module and the adaptive neural network prediction module, it is possible to comprehensively consider the optimal control under the current working conditions and the predictive adjustment of future state changes; this integration not only takes into account the needs of immediate decision-making, but also takes into account the predictability of long-term planning, thereby ensuring the accuracy and effectiveness of the control strategy; the generated comprehensive control strategy combines the advantages of the two advanced algorithms and can more comprehensively cope with complex and changeable working conditions; through verification and optimization in a simulation environment, the performance of the strategy can be further improved to ensure its stability and reliability in practical applications; verifying the comprehensive control strategy in a simulation environment can avoid the risks and losses that may be caused in practical applications; by evaluating the performance of the strategy through comparative experiments, we can intuitively understand the performance of the strategy under different working conditions, providing a basis for subsequent parameter adjustments; according to the results of simulation verification, the parameters of the fusion algorithm and the control strategy can be adjusted. Fine-tune to optimize its performance; the preset strategy update mechanism can ensure that when new data or working conditions change, the system can update the comprehensive control strategy in time to maintain its adaptability and flexibility; deep reinforcement learning is good at handling complex decision-making problems, while adaptive neural networks are good at predicting future states; the combination of the two enables the system to have both decision-making ability and foresight, thereby improving the intelligence level of the system; the preset strategy update mechanism can realize automatic updates, reducing the need for human intervention; through continuous learning and optimization, the system can gradually improve its control performance and adaptability, and achieve an improved level of intelligence; accurate and effective control strategies can reduce the failure rate of equipment and extend the service life of equipment; this helps to reduce downtime and maintenance costs caused by equipment failures; optimized control strategies can improve the operating efficiency of equipment, thereby improving production efficiency; this helps companies reduce costs, increase profits, and enhance market competitiveness.

[0040] In one embodiment of the present invention, the S41 includes: Extract control strategies based on immediate rewards and long-term reward optimization under current working conditions from the deep reinforcement learning module; including key information such as action selection probability and state value estimation; The extracted strategies are evaluated for adaptability and the stability and robustness of the extracted measurements under different operating conditions are analyzed; for example, by simulating different loads, ambient temperatures, and supply voltage fluctuations.

[0041] Use adaptive neural networks to predict the future operating status of the compressor, including the changing trends of key parameters such as pressure, temperature, and current. Verify the accuracy of the prediction model by comparing the prediction results with the actual operating data. Through the fusion algorithm architecture, the output of the deep reinforcement learning decision module and the adaptive neural network prediction module are used as input to generate a comprehensive control strategy through nonlinear transformation, etc. Use machine learning algorithms (such as genetic algorithms, particle swarm optimization, etc.) to optimize the weights in the fusion algorithm and conduct preliminary verification of the fusion strategy in a simulation environment; According to the operating characteristics of the compressor under different working conditions, the fusion strategy is adaptively analyzed; including analyzing the performance of the strategy under different loads, ambient temperatures, and power supply voltage fluctuations. According to the results of the operating adaptability analysis, the parameters of the fusion algorithm and control strategy are adjusted and optimized; including adjusting weights, optimizing the neural network structure, etc.

[0042] The working principle of the above technical solution is as follows: from the deep reinforcement learning module, the system can extract control strategies based on immediate rewards and long-term return optimization under current working conditions; these strategies contain key information such as action selection probability and state value estimation, which together constitute the optimal behavior guide for the intelligent agent (i.e., the compressor control system) under specific circumstances; the extracted strategies need to be adaptively evaluated to verify their stability and robustness under different working conditions; by simulating conditions such as different loads, ambient temperatures, and power supply voltage fluctuations, the system can evaluate the performance of the strategies under these conditions to ensure their reliability in practical applications; using adaptive neural networks, the system can predict the future operating status of the compressor; the prediction content includes the changing trends of key parameters such as pressure, temperature, and current, which are crucial for evaluating compressor performance and formulating control strategies; by comparing the prediction results with the actual operating data, the system The system can verify the accuracy of the prediction model; this helps to ensure the reliability of the prediction model in practical applications and provide strong support for the subsequent control strategy formulation; the fusion algorithm architecture takes the output of the deep reinforcement learning decision module and the adaptive neural network prediction module as input; through methods such as nonlinear transformation, the fusion algorithm can generate a comprehensive control strategy that not only considers the optimal control under the current working conditions, but also foresees changes in future states; using machine learning algorithms (such as genetic algorithms, particle swarm optimization, etc.), the system can optimize the weights in the fusion algorithm; by optimizing the weights, the system can ensure that the comprehensive control strategy can fully consider various factors and conduct preliminary verification in the simulation environment; the purpose of the preliminary verification is to evaluate the performance and stability of the fusion strategy in practical applications and provide a basis for subsequent optimization and adjustment; according to the operating characteristics of the compressor under different working conditions, the system conducts an adaptability analysis of the fusion strategy. The analysis includes the performance of the strategy under different loads, ambient temperature, and power supply voltage fluctuations; based on the results of the adaptability analysis, the system can adjust and optimize the parameters of the fusion algorithm and control strategy; the adjustment content may include weight adjustment, neural network structure optimization, etc., to ensure that the fusion strategy can perform optimally under different working conditions.

[0043] The effects of the above technical solution are as follows: the extracted control strategy not only takes into account immediate rewards, but also long-term returns, thus ensuring the optimization and foresight of the strategy; the key information contained, such as the probability of action selection and state value estimation, provides a clear direction and basis for the execution of the strategy; the extracted strategy is subjected to stability and robustness analysis under different working conditions to ensure the reliability and applicability of the strategy in practical applications; by simulating a variety of conditions (such as different loads, ambient temperatures, and power supply voltage fluctuations), the adaptability of the strategy can be comprehensively evaluated, providing a basis for subsequent optimization; the use of adaptive neural networks to predict the future operating status of the compressor can accurately capture the changing trends of key parameters (such as pressure, temperature, and current); by comparing the prediction results with the actual operating data, the accuracy of the prediction model can be verified, providing strong support for the subsequent formulation of control strategies; the outputs of the deep reinforcement learning decision module and the adaptive neural network prediction module are combined into a The two modules are fused and a comprehensive control strategy is generated through nonlinear transformation. This fusion method can make full use of the advantages of the two modules to achieve comprehensive optimization of the control strategy. The weights in the fusion algorithm are optimized using machine learning algorithms such as genetic algorithms and particle swarm optimization, which further improves the performance of the comprehensive control strategy. By optimizing the weights, it can be ensured that the strategy can foresee future state changes and make adjustments while considering the optimal control under the current working conditions. The fusion strategy is preliminarily verified in a simulation environment to evaluate its performance and stability in practical applications. This verification method can reduce risks in practical applications and improve the reliability and safety of the strategy. The fusion strategy is adaptively analyzed according to the operating characteristics of the compressor under different working conditions. According to the analysis results, the parameters of the fusion algorithm and the control strategy are adjusted and optimized, such as adjusting the weights and optimizing the neural network structure, to ensure that the strategy can perform optimally under different working conditions.

[0044] In one embodiment of the present invention, S5 includes: S51. According to the comprehensive control strategy, intelligently adjust the operating parameters of the compressor, such as speed, air intake, loading / unloading strategy, etc., and record key data during the adjustment process, such as the operating status and energy efficiency before and after the adjustment, for subsequent analysis and optimization; S52. Based on the closed-loop feedback mechanism, the operating status and performance parameters of the compressor, such as pressure, temperature, current, etc., are continuously monitored. When an abnormality or deviation from expectations is detected, the control strategy is adjusted in a timely manner; S53. When a serious abnormality is detected through the abnormality handling process, emergency protection measures are immediately initiated to prevent damage to the compressor, and key events and abnormal conditions during the operation of the compressor are recorded, including adjustment records, fault records, etc.; S54. When a potential fault is predicted through the fault warning system, the operator is notified in advance to take appropriate measures to avoid the occurrence or expansion of the fault.

[0045] The working principle of the above technical solution is as follows: according to the comprehensive control strategy generated in the previous step (such as S4), the system intelligently adjusts the operating parameters of the compressor, such as speed, air intake, loading / unloading strategy, etc.; these adjustments are aimed at optimizing the operating efficiency and energy efficiency of the compressor while meeting production needs; during the adjustment process, the system records key data, including the operating status before and after the adjustment (such as pressure, temperature, current, etc.) and energy efficiency; these data are used for subsequent analysis and optimization to help the system better understand the operating characteristics and needs of the compressor; the system continuously monitors the operating status and performance parameters of the compressor based on a closed-loop feedback mechanism; the monitored parameters include but are not limited to pressure, temperature, current, etc., which can reflect the health status and operating efficiency of the compressor; when the parameters are detected to be abnormal or deviate from expectations, the system adjusts the control strategy in time according to preset rules or algorithms; this adjustment It aims to quickly respond to changes in the operation of the compressor and maintain its stability and efficiency. When the system detects serious anomalies such as excessive temperature and abnormal pressure through the abnormal handling process, it immediately initiates emergency protection measures. These measures are aimed at preventing damage to the compressor and protecting equipment and production safety. The system records key events and abnormal conditions during the operation of the compressor, including adjustment records, fault records, etc. These records provide valuable data support for subsequent fault analysis and processing. Through the fault warning system, the system uses historical data and prediction models to predict potential faults. These predictions are based on the operating characteristics and historical failure modes of the compressor, and aim to detect potential hidden faults in advance. When a potential fault is predicted, the system notifies the operator in advance. The operator can take corresponding preventive measures based on the notification, such as shutdown inspection and maintenance, to avoid the occurrence or expansion of the fault.

[0046] The effects of the above technical solution are: intelligently adjust the key operating parameters of the compressor, such as the speed, air intake, loading / unloading strategy, etc., according to the comprehensive control strategy; this adjustment can ensure that the compressor can maintain the best operating state under different working conditions, thereby improving the operating efficiency and energy efficiency; during the adjustment process, record key data such as the operating state and energy efficiency before and after the adjustment; these data provide a basis for subsequent analysis and optimization, and help the system to continuously learn and improve the control strategy, and further improve the operating efficiency of the compressor; based on the closed-loop feedback mechanism, continuously monitor the operating state and performance parameters of the compressor (such as pressure, temperature, current, etc.); when an abnormality or deviation from expectations is detected, the system can adjust the control strategy in time to maintain the stable operation of the compressor; when a serious abnormality is detected, immediately start emergency protection measures to prevent damage to the compressor; This instant response mechanism can greatly reduce the risk of compressor shutdown due to failure, and ensure the continuity and stability of the production line; record key events and abnormal conditions during the operation of the compressor, including adjustment records, fault records, etc.; these records provide valuable data support for subsequent fault analysis and processing, which helps the system to continuously accumulate experience and improve fault response capabilities; through the fault warning system, historical data and predictive models are used to predict potential faults; this predictive capability enables the system to notify operators in advance before a fault occurs, thereby avoiding the occurrence or expansion of the fault; operators can take corresponding preventive measures in advance (such as shutdown inspection, maintenance, etc.) based on the notification of the fault warning system; this preventive maintenance strategy can significantly reduce the failure rate and maintenance costs of the compressor, and improve the reliability and service life of the equipment.

[0047] One embodiment of the present invention, as Figure 2 As shown, a compressor control system, the system comprising: Data acquisition module: collects multi-dimensional data in real time during the operation of the compressor through a multi-parameter sensor network, including pressure, temperature, current, vibration and flow; pre-processes the collected multi-dimensional data, including data cleaning, anomaly detection and feature engineering, and builds a high-quality data set; Optimization learning module: Through the reinforcement learning model based on deep neural network, the compressor control strategy is learned and optimized based on historical data and current environmental status (such as operating conditions, compressor status, etc.); continuous iteration and updating is carried out through simulation and online learning; Real-time prediction module: Based on the adaptive neural network model, it can make real-time predictions on the operating status and performance parameters of the compressor in the future, and dynamically adjust the network structure and parameters according to the current working conditions and historical data of the compressor; Strategy generation module: fuses the outputs of the deep reinforcement learning decision module and the adaptive neural network prediction module to generate a comprehensive control strategy; Closed-loop control module: Intelligently adjusts compressor operating parameters (such as speed, air intake, loading / unloading strategies, etc.) based on comprehensive control strategies; at the same time, through a closed-loop feedback mechanism, continuously monitors the compressor operating status and adjusts the control strategy in a timely manner.

[0048] The working principle of the above technical solution is as follows: using a multi-parameter sensor network to collect key data in the operation process of the compressor in real time, including pressure, temperature, current, vibration, flow, etc.; pre-processing the collected multi-dimensional data, including data cleaning (noise removal, filling missing values, etc.), anomaly detection (identifying and processing abnormal data points) and feature engineering (extracting useful features, dimensionality reduction, etc.) to build a high-quality data set; using a reinforcement learning model based on a deep neural network, combined with historical data and current environmental conditions (such as operating conditions, compressor status, etc.), the control strategy of the compressor is learned and optimized; through simulation and online learning, the model is continuously iterated and updated to generate optimal control instructions with the goal of maximizing long-term benefits (such as energy efficiency, stability, etc.); based on an adaptive neural network model, the operating status and performance parameters of the compressor in the future are predicted in real time; according to the current operating conditions and historical data of the compressor, the network structure and parameters are dynamically adjusted to improve the accuracy of the prediction. The prediction result is used as one of the inputs of the deep reinforcement learning model to assist it in making more accurate decisions. The outputs of the deep reinforcement learning decision module and the adaptive neural network prediction module are integrated to generate a comprehensive control strategy. This strategy not only takes into account the optimal control under the current operating conditions, but also incorporates predictive adjustments to future state changes, thereby achieving comprehensive optimization of the compressor operating parameters. According to the comprehensive control strategy, the operating parameters of the compressor (such as speed, air intake, loading / unloading strategy, etc.) are intelligently adjusted. Through a closed-loop feedback mechanism, the operating status of the compressor is continuously monitored and the control strategy is adjusted in a timely manner.

[0049] The effects of the above technical solutions are as follows: by collecting multi-dimensional data in real time and preprocessing it, a high-quality data set is constructed, which provides a solid foundation for subsequent model learning and optimization. It helps to more accurately reflect the actual operating status of the compressor, so as to formulate a more efficient control strategy; the reinforcement learning model can continuously iterate and update the control strategy according to historical data and current environmental status, with the goal of maximizing long-term benefits. It can not only improve the operating efficiency of the compressor, but also optimize energy use and reduce energy consumption costs while maintaining efficient operation; the adaptive neural network model can predict the operating status and performance parameters of the compressor in the future in real time, and dynamically adjust according to the current working conditions and historical data. This predictive adjustment helps to discover and respond to potential operating problems in advance, thereby enhancing the operating stability and reliability of the compressor; the comprehensive control strategy integrates the outputs of the deep reinforcement learning decision module and the adaptive neural network prediction module, taking into account the optimal control under the current working conditions and incorporating predictive adjustments to future state changes. This comprehensive control strategy helps to ensure that the compressor can maintain a stable operating state under various working conditions; by introducing advanced artificial intelligence technologies such as deep neural networks, reinforcement learning and adaptive neural networks, intelligent optimization and real-time adjustment of the compressor control strategy are achieved. This greatly improves the intelligence and automation level of the compressor, reducing manual intervention and dependence; the closed-loop feedback mechanism can continuously monitor the operating status of the compressor and adjust the control strategy in time according to the actual situation. This automated adjustment mechanism helps to ensure that the compressor always maintains the best operating state, improving the reliability and flexibility of the overall system; by real-time monitoring and prediction of the operating status and performance parameters of the compressor, potential operating problems and failures can be discovered in time. This helps to take maintenance measures in advance to avoid the occurrence or expansion of failures, thereby reducing maintenance costs and downtime; intelligent and automated control strategies help optimize the operating parameters and working modes of the compressor and reduce unnecessary wear and loss. This helps to extend the service life of the compressor and improve the economy and sustainability of the overall system.

[0050] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A compressor control method, characterized in that: The method comprises: S1. Collect multi-dimensional data in real time during the operation of the compressor through a multi-parameter sensor network; pre-process the collected multi-dimensional data and construct a data set; S2. Learn and optimize the compressor control strategy based on historical data and current environmental conditions through a reinforcement learning model based on deep neural networks; continuously iterate and update through simulation and online learning; S3, based on the adaptive neural network model, the operating status and performance parameters of the compressor in the future are predicted in real time, and the network structure and parameters are dynamically adjusted according to the current working conditions and historical data of the compressor; S4, integrating the outputs of the deep reinforcement learning decision module and the adaptive neural network prediction module to generate a comprehensive control strategy; S5. Intelligently adjust the compressor operating parameters according to the comprehensive control strategy. At the same time, through the closed-loop feedback mechanism, continuously monitor the compressor operating status and adjust the control strategy in time.

2. A compressor control method according to claim 1, characterized in that: Said S1 comprises: S11, collecting multi-dimensional data in the operation process of the compressor in real time through a multi-parameter sensor network, and using a sliding window algorithm to smooth the collected multi-dimensional data to remove noise; S12. Detect and fill missing values ​​through statistical methods, apply machine learning algorithms to detect outliers, and mark or remove them; S13, implement feature engineering, extract feature variables that affect the operating status of the compressor, organize the preprocessed data in time series, and construct a data set containing historical data and current data; S14. The data set is stored through a distributed storage solution, and the data set is backed up based on a set data backup mechanism.

3. A compressor control method according to claim 1, characterized in that: The S2 comprises: S21. Construct a reinforcement learning model architecture based on a deep neural network, wherein the model framework includes a policy network and a value network; the policy network is used to generate control instructions, and the value network is used to evaluate the quality of the control instructions; S22, dividing the constructed data set into a training set and a validation set for model training and validation, using a stochastic gradient descent algorithm to perform offline training on the model to learn the optimal control strategy of the compressor under different working conditions; S23. Optimize the model performance by adjusting the hyperparameters, build a compressor operation simulation environment, and simulate the compressor behavior under different working conditions; S24, implement online learning in the simulation environment, and collect new data for model updating; continuously update the data in the simulation environment through rolling time window technology; S25. Generate control instructions based on the output of the deep reinforcement learning model.

4. A compressor control method according to claim 3, characterized in that: The S24 comprises: S241, constructing a simulation system that highly simulates the actual operating environment of the compressor, receiving the compressor operating data in the simulation environment in real time through an online learning framework, and interacting the operating data with the deep reinforcement learning model; S242. Simulate various complex and changeable working conditions in a simulation environment; during the simulation process, collect compressor operation data in real time; S243, continuously updating the data in the simulation environment through the rolling time window technology, and adjusting the size of the time window according to the change speed of the compressor operation characteristics and the update requirements of the model; S244, perform quality assessment and preprocessing on the newly collected data, perform online verification and evaluation on the model through the new data, and evaluate the accuracy and performance of the model by comparing the model prediction results with the actual simulation results; S245. According to the results of the online verification, the parameters of the deep reinforcement learning model are adjusted in real time, and the learning rate is dynamically adjusted according to the learning progress and error changes of the model based on the adaptive learning rate adjustment mechanism; S246. Update the model parameters and strategies obtained through online learning to the compressor control system in actual operation, and iteratively optimize the control strategy by combining historical data and real-time data through the strategy optimization algorithm.

5. A compressor control method according to claim 4, characterized in that: The S243 includes: Evaluate the timeliness of the data by comparing its timestamp, rate of change, and correlation with other parameters to determine whether the data still represents the current operating status of the compressor; Design the dynamically adjusted time window size based on the speed of change of compressor operating characteristics and the need to update the model; The sliding strategy of the time window is set based on a fixed time interval or the change of data volume, and based on the automatic data update mechanism, when new data enters the time window, the oldest data is automatically replaced; Through the model feedback loop, the updated data is re-input into the deep reinforcement learning model for a new round of training and verification; Identify and filter out abnormal data in the simulation environment through anomaly detection algorithms; formulate data filtering strategies based on the results of anomaly detection; According to the adaptability evaluation indicators, the model's adaptability to new data is quantified, and according to the results of the adaptability evaluation, the model's optimization strategy is dynamically adjusted.

6. A compressor control method according to claim 1, characterized in that: The S3 includes: S31, selecting an adaptive neural network model, and designing an input layer and an output layer of the model, wherein the input layer is used to receive the pre-processed compressor operation data, and the output layer is used to predict the operation status and performance parameters of the compressor in the future; S32. The model is trained offline through the back propagation algorithm and the Adam optimizer, so that the model can predict the operating status and performance parameters of the compressor in the future; S33, dynamically adjusting the structure and parameters of the adaptive neural network according to the current working conditions and historical data of the compressor, and preventing the model from overfitting through regularization; S34. Based on the preset model update strategy, when new data arrives, the model parameters are updated according to the importance of the data; the prediction results of the adaptive neural network are used as one of the inputs of the deep reinforcement learning model to assist it in making decisions.

7. A compressor control method according to claim 1, characterized in that: The S4 comprises: S41. Based on the fusion algorithm, the outputs of the deep reinforcement learning decision module and the adaptive neural network prediction module are fused to generate a comprehensive control strategy; S42. Verify and optimize the comprehensive control strategy in a simulation environment, and evaluate the performance of the strategy through comparative experiments; adjust the parameters of the fusion algorithm and control strategy according to the verification results; S43. Based on the preset strategy update mechanism, when new data or working conditions change, the comprehensive control strategy is updated in a timely manner.

8. A compressor control method according to claim 7, characterized in that: The S41 includes: Extract the control strategy based on the optimization of immediate reward and long-term return under the current working conditions from the deep reinforcement learning module; The adaptability of the extracted strategies is evaluated, and the stability and robustness of the extracted measurements under different working conditions are analyzed; Use adaptive neural networks to predict the future operating status of the compressor, and verify the accuracy of the prediction model by comparing the prediction results with the actual operating data; Through the fusion algorithm architecture, the output of the deep reinforcement learning decision module and the adaptive neural network prediction module are used as input to generate a comprehensive control strategy through nonlinear transformation, etc. Use machine learning algorithms to optimize the weights in the fusion algorithm and conduct preliminary verification of the fusion strategy in a simulation environment; According to the operating characteristics of the compressor under different working conditions, the adaptability of the fusion strategy is analyzed; according to the results of the working condition adaptability analysis, the parameters of the fusion algorithm and control strategy are adjusted and optimized.

9. A compressor control method according to claim 1, characterized in that: The S5 comprises: S51. Intelligently adjust the operating parameters of the compressor according to the comprehensive control strategy, and record key data during the adjustment process; S52. Based on the closed-loop feedback mechanism, the operating status and performance parameters of the compressor are continuously monitored, and the control strategy is adjusted in time when an abnormality or deviation from expectations is detected; S53, through the abnormality handling process, when an abnormality is detected, the emergency protection measures are immediately initiated, and the key events and abnormal conditions during the operation of the compressor are recorded; S54. Through the fault warning system, when a potential fault is predicted, the operator is notified in advance to take corresponding measures.

10. A compressor control system, characterized in that: The system comprises: Data acquisition module: Through a multi-parameter sensor network, it collects multi-dimensional data during the operation of the compressor in real time, pre-processes the collected multi-dimensional data, and constructs a data set; Optimization learning module: Through the reinforcement learning model based on deep neural network, the compressor control strategy is learned and optimized based on historical data and current environmental status; it is continuously updated through simulation and online learning; Real-time prediction module: Based on the adaptive neural network model, it can make real-time predictions on the operating status and performance parameters of the compressor in the future, and dynamically adjust the network structure and parameters according to the current working conditions and historical data of the compressor; Strategy generation module: fuses the outputs of the deep reinforcement learning decision module and the adaptive neural network prediction module to generate a comprehensive control strategy; Closed-loop control module: intelligently adjusts the compressor operating parameters based on the comprehensive control strategy; at the same time, through the closed-loop feedback mechanism, continuously monitors the compressor operating status and adjusts the control strategy in a timely manner.

Images