Compressor control management system based on Internet of Things

Abstract

The invention discloses a compressor control management system based on the Internet of Things, and relates to the field of industrial automation and intelligent control technology. The compressor control management system based on the Internet of Things includes a multidimensional data acquisition module that acquires multidimensional data and historical data of the compressor in real time through a multidimensional sensor of the Internet of Things technology. The intake valve model construction unit establishes the relationship between the intake valve opening and the compressor load, energy efficiency and intake flow rate based on a long short-term memory network, and the exhaust valve model construction unit establishes the relationship between the exhaust valve opening and the exhaust pressure, flow rate and compressor energy efficiency based on support vector regression. The control module dynamically adjusts the intake valve opening through a particle swarm optimization algorithm, and adjusts the exhaust valve opening through a fuzzy control algorithm to optimize the energy efficiency and stability of the compressor. Automatic adjustment of the compressor opening is achieved, energy efficiency is improved, energy consumption is reduced, and the automation level and adaptive ability of the system are enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial automation and intelligent control, and in particular to a compressor control management system based on the Internet of Things. Background Art

[0002] With the continuous acceleration of the industrialization process, energy consumption and environmental protection have become the focus of global attention. As an important equipment commonly used in industrial production, compressors play a key role in many fields, including air conditioning, refrigeration, air compression, petrochemicals, etc. The efficient operation of compressors is of great significance to energy conservation and emission reduction and improving production efficiency. At the same time, with the rapid development of Internet of Things technology, the Industrial Internet of Things provides new opportunities for the intelligent management and optimization of compressors. By combining compressors with multi-dimensional sensors, data processing platforms and intelligent control systems, real-time monitoring, precise control and efficient management can be achieved, thereby reducing energy consumption, extending equipment life and improving production stability, and promoting the development of industrial equipment towards intelligence and greenness.

[0003] At present, most traditional compressor control management methods rely on manual adjustment or fixed algorithms for operation. These methods have shortcomings such as poor real-time response capability and low optimization degree. It is difficult for traditional control systems to make fast and accurate adjustments based on the load fluctuations, exhaust pressure and energy efficiency requirements of the compressor, resulting in low compressor operating efficiency and high energy consumption. In addition, the lack of a predictive model based on data analysis makes it difficult for the control system to achieve intelligent and personalized prediction of equipment failures and formulation of maintenance plans. Even if automated control is adopted, there is a lack of comprehensive optimization and dynamic adaptation to complex working conditions, and the optimal efficiency of compressor operation cannot be achieved. Therefore, the existing methods cannot give full play to the energy-saving potential of the compressor and improve its operating stability. There is an urgent need for an intelligent, data-driven control and management system. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention provides a compressor control management system based on the Internet of Things, which solves the problems of the above-mentioned background technology.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: a compressor control management system based on the Internet of Things, including the following modules: a multidimensional data acquisition module, a model building module, and a control module; the module is used to connect a multidimensional sensor through the Internet of Things to obtain multidimensional data and historical multidimensional data of the compressor; the model building module includes an intake valve model building unit and an exhaust valve model building unit; the intake valve model building unit is used to establish a mathematical relationship between the intake valve opening and the compressor load, energy efficiency and intake flow rate through a long short-term memory network according to the multidimensional data and historical multidimensional data of the compressor, and to construct an intake valve model for predicting the influence of the intake valve opening adjustment on the compressor efficiency under different loads; the exhaust valve model building unit is used to The multi-dimensional data and historical multi-dimensional data of the compressor are used to establish a mathematical relationship between the exhaust valve opening and the compressor exhaust pressure, exhaust flow and compressor energy efficiency through support vector regression, and an exhaust valve model is constructed to predict the impact of the exhaust valve opening adjustment on the compressor energy efficiency and stability under different load and exhaust pressure conditions; the control module is used to include an intake valve control unit and an exhaust valve control unit; the intake valve control unit is used to dynamically adjust the intake valve opening through a particle swarm optimization algorithm based on the intake valve model, combined with real-time load data and compressor energy efficiency requirements; the exhaust valve control unit is used to dynamically adjust the exhaust valve opening through a fuzzy control algorithm based on the prediction model generated by the exhaust valve model construction unit, combined with real-time exhaust pressure, exhaust flow and compressor load data.

[0006] Furthermore, the multi-dimensional data includes but is not limited to compressor load, exhaust temperature, exhaust pressure, intake volume, intake valve and exhaust valve opening, and motor speed.

[0007] Furthermore, the specific process of establishing the mathematical relationship between the intake valve opening and the compressor load, energy efficiency and intake flow rate through the long short-term memory network is as follows: preprocessing is performed based on the multi-dimensional data of the compressor and the historical multi-dimensional data, including: data cleaning, data normalization and feature extraction, and the data is converted into a time series format; the historical data is divided into multiple samples according to the set time window, and each window is used as the input data of the long short-term memory network; the input data of each time step is divided by the window, and the input data contains the characteristic data of the compressor load, energy efficiency and intake flow rate; the network structure of the long short-term memory network model is set, including setting the input layer to accept the characteristic data such as the compressor load, energy efficiency and intake flow rate, setting the number of network model layers and the number of neurons in each layer to capture the temporal dependency between the data, and setting the output layer to predict the intake valve opening; the long short-term memory network model is trained through the historical multi-dimensional data, including setting the loss function to measure the difference between the predicted value and the actual value and updating the weight of the model through the back propagation and gradient descent algorithm.

[0008] Furthermore, the specific process of constructing the intake valve model is as follows: through the trained long short-term memory network model, the mathematical relationship between the intake valve opening and the compressor load, energy efficiency and intake flow rate is obtained; according to the obtained mathematical relationship, combined with the real-time collected compressor load, energy efficiency, and intake flow rate, the intake valve opening under different conditions is calculated to generate an intake valve model between the intake valve opening adjustment and the compressor efficiency.

[0009] Furthermore, the specific process of establishing the mathematical relationship between the exhaust valve opening and the compressor exhaust pressure, exhaust flow rate and compressor energy efficiency through support vector regression is as follows: through the support vector regression model, based on the historical multi-dimensional data, the historical data is preprocessed, including data cleaning, normalization and feature extraction; the training data is fitted through the support vector regression model to establish the mathematical relationship between the exhaust valve opening and the compressor exhaust pressure, exhaust flow rate and energy efficiency; by optimizing the hyperparameters in the SVR model, including the penalty factor and the kernel function type, the accuracy and generalization ability of the model are ensured.

[0010] Furthermore, the specific process of constructing the exhaust valve model is as follows: through the trained support vector regression model, the mathematical relationship between the exhaust valve opening and the compressor exhaust pressure, exhaust flow and energy efficiency is obtained; according to the obtained mathematical relationship, combined with the real-time collected compressor exhaust pressure, exhaust flow and energy efficiency data, the exhaust valve opening under different working conditions is calculated; an exhaust valve model between the exhaust valve opening adjustment and the compressor energy efficiency and stability is generated, which is used to dynamically adjust the exhaust valve opening of the compressor and optimize the operating efficiency and stability of the compressor.

[0011] Furthermore, the specific process of dynamically adjusting the opening of the intake valve through the particle swarm optimization algorithm is as follows: obtaining the real-time collected compressor load, energy efficiency and intake flow data, and inputting them into the intake valve model to calculate the current intake valve opening; setting the target opening of the intake valve according to the real-time collected data and the compressor energy efficiency requirements, and calculating the difference between the target opening and the current opening; initializing the particle swarm in the particle swarm optimization algorithm, and setting the fitness function of each particle, which measures the closeness of the intake valve opening adjusted by the particle to the target opening; iteratively updating the position of the particle through the particle swarm optimization algorithm, and calculating the fitness function in each iteration, and selecting the particle with the best fitness as the optimal solution; when the iterative process of the particle swarm converges, the optimal solution obtained is the optimized intake valve opening, which is used to dynamically adjust the intake valve and optimize the operating efficiency of the compressor.

[0012] Furthermore, the specific process of dynamically adjusting the exhaust valve opening through the fuzzy control algorithm is as follows: obtain the real-time collected exhaust pressure, exhaust flow and compressor load data as the input variables of the fuzzy control algorithm; according to the actual data of the exhaust pressure, exhaust flow and compressor load, convert the input variables into fuzzy sets through fuzzification processing; set the fuzzy control rule base, and according to the exhaust valve model, determine the relationship between the exhaust pressure, exhaust flow and compressor load, and determine the direction and degree of adjustment of the exhaust valve opening; reason the fuzzy control rules through fuzzy reasoning, and calculate the adaptive output value of the exhaust valve, that is, the exhaust valve opening adjustment amount; defuzzify the fuzzy reasoning result to obtain the actual exhaust valve opening adjustment value, and dynamically adjust the exhaust valve opening through the control system to optimize the energy efficiency and stability of the compressor.

[0013] The present invention has the following beneficial effects:

[0014] (1) The compressor control and management system based on the Internet of Things, the model building module can establish an accurate mathematical relationship model based on the multi-dimensional data and historical data of the compressor through the intake valve model building unit and the exhaust valve model building unit, and perform dynamic predictions on the intake valve and exhaust valve respectively. The intake valve model can predict the impact of the intake valve opening adjustment on the compressor efficiency under different loads, while the exhaust valve model can predict the impact of the exhaust valve opening adjustment on the compressor energy efficiency and stability. Through the establishment of these models, accurate data support and optimization basis are provided for the compressor control system, ensuring that the system can be accurately adjusted according to the real-time status, thereby improving the overall energy efficiency and stability.

[0015] (2) Based on the Internet of Things, the control module of the compressor control and management system uses the suction valve control unit and the exhaust valve control unit to fine-tune the established suction valve and exhaust valve models in combination with real-time data using the particle swarm optimization algorithm and the fuzzy control algorithm. The suction valve control unit dynamically adjusts the suction valve opening through the optimization algorithm to ensure the best match between the compressor load and energy efficiency, significantly improving the system's operating efficiency and reducing energy consumption; while the exhaust valve control unit uses the fuzzy control algorithm to adjust the exhaust valve opening, which can accurately respond to compressor load fluctuations and exhaust pressure changes, enhancing the stability of the system, reducing the risk of failures, and optimizing the operation and management of the equipment.

[0016] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is a flow chart of the compressor control management system based on the Internet of Things of the present invention. DETAILED DESCRIPTION

[0018] The embodiment of the present application solves the deficiencies of traditional compressor control systems in energy efficiency management, load regulation and equipment stability through a compressor control management system based on the Internet of Things. By real-time acquisition and analysis of multi-dimensional data, combined with long short-term memory networks and particle swarm optimization algorithms, the system can dynamically adjust the opening of the compressor's suction valve and exhaust valve, achieve precise control, optimize the compressor's operating efficiency, extend equipment life, and effectively reduce energy consumption.

[0019] The overall idea of ​​the solution in the embodiments of this application is as follows:

[0020] Through the Internet of Things, multi-dimensional sensors are connected to obtain multi-dimensional data and historical multi-dimensional data of the compressor.

[0021] Based on the multi-dimensional data and historical multi-dimensional data of the compressor, the mathematical relationship between the suction valve opening and the compressor load, energy efficiency and suction flow rate is established through the long short-term memory network, and the suction valve model is constructed to predict the impact of the suction valve opening adjustment on the compressor efficiency under different loads.

[0022] Based on the multi-dimensional data and historical multi-dimensional data of the compressor, the mathematical relationship between the exhaust valve opening and the compressor exhaust pressure, exhaust flow rate and compressor energy efficiency is established through support vector regression, and an exhaust valve model is constructed to predict the impact of the exhaust valve opening adjustment on the compressor energy efficiency and stability under different load and exhaust pressure conditions.

[0023] According to the suction valve model, combined with real-time load data and compressor energy efficiency requirements, the opening of the suction valve is dynamically adjusted through the particle swarm optimization algorithm.

[0024] According to the prediction model generated by the exhaust valve model building unit, combined with the real-time exhaust pressure, exhaust flow and compressor load data, the exhaust valve opening is dynamically adjusted through the fuzzy control algorithm.

[0025] See also Figure 1The embodiment of the present invention provides a technical solution: a compressor control management system based on the Internet of Things, comprising the following modules: a multi-dimensional data acquisition module, a model building module, and a control module; the module is used to connect a multi-dimensional sensor through the Internet of Things to obtain multi-dimensional data and historical multi-dimensional data of the compressor; the model building module includes an intake valve model building unit and an exhaust valve model building unit; the intake valve model building unit is used to establish a mathematical relationship between the intake valve opening and the compressor load, energy efficiency and intake flow rate through a long short-term memory network according to the multi-dimensional data and historical multi-dimensional data of the compressor, and to build an intake valve model for predicting the influence of the intake valve opening adjustment on the compressor efficiency under different loads; the exhaust valve model building unit is used to establish a mathematical relationship between the intake valve opening and the compressor load, energy efficiency and intake flow rate according to the multi-dimensional data and historical multi-dimensional data of the compressor according to the long short-term memory network, and to build an intake valve model for predicting the influence of the intake valve opening adjustment on the compressor efficiency under different loads; the exhaust valve model building unit is used to establish a mathematical relationship between the intake valve opening and the compressor load, energy efficiency and intake flow rate according to the multi-dimensional data and historical multi-dimensional data of the compressor according to the long short-term memory network, and to build a ... dimensional data and historical multi-dimensional data, and establishes the mathematical relationship between the exhaust valve opening and the compressor exhaust pressure, exhaust flow and compressor energy efficiency through support vector regression, and constructs an exhaust valve model to predict the impact of the exhaust valve opening adjustment on the compressor energy efficiency and stability under different load and exhaust pressure conditions; the control module is used to include an intake valve control unit and an exhaust valve control unit; the intake valve control unit is used to dynamically adjust the intake valve opening through a particle swarm optimization algorithm based on the intake valve model in combination with real-time load data and compressor energy efficiency requirements; the exhaust valve control unit is used to dynamically adjust the exhaust valve opening through a fuzzy control algorithm based on the prediction model generated by the exhaust valve model construction unit in combination with real-time exhaust pressure, exhaust flow and compressor load data.

[0026] In this implementation scheme, a multi-dimensional data acquisition module is used to connect multiple multi-dimensional sensors through the Internet of Things technology to obtain relevant data on the operation of the compressor in real time, including: compressor load: indicating the current working intensity or load level of the compressor; energy efficiency: the working efficiency of the compressor; suction flow: the intake flow of the compressor, which directly affects its performance; exhaust pressure: the pressure data on the exhaust side of the compressor; exhaust flow: the exhaust flow of the compressor; these data are not only collected in real time, but also include historical data for model construction and training. The model construction module includes two key parts: the suction valve model construction unit and the exhaust valve model construction unit. The suction valve model construction unit: This unit uses the long short-term memory network (LSTM) to establish the mathematical relationship between the suction valve opening and the compressor load, energy efficiency, and suction flow through the collected multi-dimensional data and historical data of the compressor. LSTM is a neural network that can capture long-term dependencies in time series data, and can effectively handle the impact of the adjustment of the suction valve opening of the compressor under different load and flow conditions on the compressor efficiency. Through this model, the optimization effect of the suction valve opening on the compressor performance can be accurately predicted. Exhaust valve model building unit: This unit uses the support vector regression (SVR) algorithm to establish the mathematical relationship between the exhaust valve opening and the compressor exhaust pressure, exhaust flow and energy efficiency. The SVR algorithm is good at handling complex nonlinear regression problems and can analyze the impact of changes in the compressor exhaust valve opening on the compressor's energy efficiency and stability based on historical data. Through the construction of the exhaust valve model, the exhaust valve opening can be predicted and optimized under different load and exhaust pressure conditions. The control module is the executive part of the entire system and is responsible for adjusting the working state of the compressor in real time according to the results generated by the model to improve its efficiency and stability. The control module includes two submodules: Intake valve control unit: This unit uses the particle swarm optimization algorithm (PSO) to dynamically adjust the opening of the intake valve based on the intake valve model, combined with the real-time collected load data and compressor energy efficiency requirements. The particle swarm optimization algorithm is an optimization algorithm based on swarm intelligence that can quickly find the global optimal solution in a multi-dimensional space and adjust the intake valve opening to keep the compressor at the best energy efficiency and performance under different loads. Exhaust valve control unit: This unit uses the fuzzy control algorithm to dynamically adjust the opening of the exhaust valve according to the prediction results generated by the exhaust valve model, combined with the exhaust pressure, exhaust flow and compressor load data collected in real time. The fuzzy control algorithm has strong adaptability and robustness, and can be effectively regulated in an uncertain environment to ensure the stable operation of the compressor under complex load and exhaust pressure conditions. The overall workflow of the system: Data acquisition: Collect real-time and historical data of the compressor through IoT devices. Model training and construction: Use the long short-term memory network (LSTM) and support vector regression (SVR) algorithm to build the control model of the suction valve and exhaust valve.Control decision: The opening of the suction valve and exhaust valve is dynamically adjusted through the particle swarm optimization algorithm and fuzzy control algorithm to optimize the performance and energy efficiency of the compressor.

[0027] Specifically, the multi-dimensional data includes but is not limited to compressor load, exhaust temperature, exhaust pressure, intake volume, intake valve and exhaust valve opening, and motor speed.

[0028] In this embodiment, compressor load: compressor load refers to the degree of load borne by the compressor during operation, that is, the ratio between the actual compression capacity provided by the compressor and its designed maximum capacity. The compressor load directly affects its energy efficiency and working stability, so real-time monitoring of load changes helps to optimize the control strategy and prevent the equipment from overloading or being in an inefficient state. Exhaust temperature: Exhaust temperature refers to the temperature of the gas at the exhaust end of the compressor. This data can help determine the thermodynamic state of the compressor when it is working. Too high an exhaust temperature may mean that the compressor is inefficient, which may be due to factors such as too large an intake valve opening or too small an exhaust valve opening. Therefore, the monitoring of exhaust temperature can reflect the stability and energy efficiency of the compressor performance. Exhaust pressure: Exhaust pressure refers to the pressure generated by the compressor at the exhaust end. Exhaust pressure has an important impact on the energy efficiency of the compressor. Excessive or low exhaust pressure may cause the compressor to lose efficiency or excessive wear. Therefore, by monitoring the exhaust pressure and combining it with other parameters, the operating state of the compressor can be effectively controlled to maintain its optimal performance. Inhalation volume: Inhalation volume refers to the gas flow rate of the compressor at the intake end. It directly affects the working efficiency of the compressor. Excessive or small intake volume will affect the load and energy efficiency of the compressor. Under different load conditions, reasonable suction volume can help maintain the efficient operation of the compressor, so the monitoring of suction volume is one of the important parameters for controlling the performance of the compressor. Intake valve and exhaust valve opening: The opening of the intake valve and the exhaust valve affect the suction and exhaust flow of the compressor respectively. The intake valve opening determines the gas flow entering the compressor, while the exhaust valve opening affects the exhaust gas flow. The dynamic adjustment of the two can directly affect the compression efficiency and energy efficiency of the compressor. Reasonable valve opening adjustment helps to optimize the working state of the compressor. Motor speed: Motor speed refers to the speed at which the motor driving the compressor rotates, which is usually related to the workload and operating efficiency of the compressor. Too fast or too slow motor speed may cause the compressor to work inefficiently, and may even affect the stability of the equipment. By real-time monitoring of the motor speed, it can be ensured that the motor operates within the appropriate speed range, thereby maintaining the energy efficiency of the system.

[0029] Specifically, the specific process of establishing the mathematical relationship between the intake valve opening and the compressor load, energy efficiency and intake flow rate through the long short-term memory network is as follows: preprocessing is performed based on the multi-dimensional data of the compressor and the historical multi-dimensional data, including: data cleaning, data normalization and feature extraction, and the data is converted into a time series format; the historical data is divided into multiple samples according to the set time window, and each window is used as the input data of the long short-term memory network; the input data of each time step is divided by the window, and the input data contains the characteristic data of the compressor load, energy efficiency and intake flow rate; the network structure of the long short-term memory network model is set, including setting the input layer to accept the characteristic data such as the compressor load, energy efficiency and intake flow rate, setting the number of network model layers and the number of neurons in each layer to capture the temporal dependency between the data, and setting the output layer to predict the intake valve opening; the long short-term memory network model is trained through the historical multi-dimensional data, including setting the loss function to measure the difference between the predicted value and the actual value and updating the weight of the model through the back propagation and gradient descent algorithm.

[0030] In this implementation scheme, data preprocessing: Data cleaning: The cleaning process is to organize the acquired multi-dimensional data, remove noise, missing values ​​and outliers, and ensure the quality of the data. The cleaned data is more accurate and suitable for subsequent modeling. Data normalization: Since the dimensions and ranges of different data vary greatly, normalization is to compress the data to the same scale, usually through standardization or minimum-maximum normalization. This can avoid a certain feature value range being too large, affecting the training efficiency and accuracy of the model. Feature extraction: Feature extraction is to extract meaningful features that can describe the behavior of the system from the original data. For example, compressor load, energy efficiency, and suction flow related features are extracted from the original data for subsequent modeling analysis. Time series format: Converting historical multi-dimensional data into a time series format is to capture the temporal relationship of the data, so that the model can predict the future state through historical input data. In time series data, each data point represents the state at a specific timestamp. Divide the historical data into multiple samples according to the set time window. Each time window will be used as input data for the LSTM network. For example, if the time window is set to 10 seconds, the data of every 10 seconds will be regarded as a sample input into the LSTM model. The data in each time window contains multiple features, such as compressor load, energy efficiency and suction flow. These feature data will be used as input in each time step of the model to help the model learn the temporal change law of each feature. Input layer: The input layer receives data from each time window, including the feature data of compressor load, energy efficiency and suction flow. Each input feature will be mapped to the neurons of the input layer to provide input signals for subsequent network calculations. The number of network model layers and the number of neurons: The number of layers of the LSTM model and the number of neurons in each layer determine the complexity and expression ability of the model. Multi-layer networks can better capture the complex relationship of data, and the number of neurons in each layer affects the learning ability of the model. At each layer, LSTM captures the temporal dependency of data through a gating mechanism. Output layer: The output layer is used to predict the opening of the suction valve. After the network is trained, the output layer will give a value representing the predicted opening value of the suction valve under the current input conditions. Loss function: The loss function is used to measure the difference between the model's prediction results and the actual results. Common loss functions include mean square error (MSE) and others. The optimization of the loss function is the core of the entire training process, and the purpose is to improve the accuracy of the model by minimizing the prediction error. Back propagation and gradient descent: The back propagation algorithm is used to calculate the gradient of the loss function to the model parameters (such as weights and biases), and then the gradient descent algorithm is used to update these parameters and gradually optimize the model. Back propagation can help the model adjust the weights so that the predicted values ​​are closer to the true values, thereby improving the performance of the model.

[0031] Specifically, the specific process of constructing the intake valve model is as follows: through the trained long short-term memory network model, the mathematical relationship between the intake valve opening and the compressor load, energy efficiency and intake flow rate is obtained; according to the obtained mathematical relationship, combined with the real-time collected compressor load, energy efficiency, and intake flow rate, the intake valve opening under different conditions is calculated to generate an intake valve model between the intake valve opening adjustment and the compressor efficiency.

[0032] In this implementation, the process of constructing the suction valve model is as follows: Obtaining the mathematical relationship between the suction valve opening and the compressor load, energy efficiency and suction flow rate Through the trained long short-term memory network (LSTM) model, the complex time series relationship between the suction valve opening and the compressor load, energy efficiency and suction flow rate can be learned from historical data. The mathematical relationship is set as: in: Indicates time The opening of the suction valve under Load Indicates time Compressor load under Indicates time Compressor efficiency under SuctionFlow Indicates time Inspiratory flow rate. It represents the nonlinear mapping relationship obtained by the trained LSTM model, capturing the dependency between compressor load, energy efficiency, and suction flow. Calculate the suction valve opening under different conditions. According to the relationship obtained by the LSTM model, combined with the real-time collected compressor load, energy efficiency, and suction flow data, the suction valve opening can be dynamically calculated. The suction valve opening calculation formula is set as follows: Where: W and b represent the weight and bias of the LSTM model, respectively, which are parameters obtained through model training. g() represents the prediction function of the LSTM model obtained through training, which is used to calculate the opening of the intake valve based on real-time data. After obtaining the opening of the intake valve, the relationship between the adjustment of the intake valve opening and the efficiency of the compressor can be further analyzed. It can be expressed as: ; Among them: Efficiency Indicates time Compressor energy efficiency under . is the opening of the intake valve obtained by the above calculation formula, c is the parameter of the model, these parameters are obtained by fitting historical data, is a function that represents the relationship between the suction valve opening and the compressor efficiency. Combining the above relationships, a complete suction valve model is obtained, which is used to calculate the suction valve opening according to the real-time load, energy efficiency and suction flow, and then predict and optimize the compressor efficiency. The final suction valve model can be expressed as: ; The model enables the suction valve opening to be adjusted dynamically based on the real-time collected compressor data (load, energy efficiency, suction flow), thereby optimizing the operating efficiency and stability of the compressor.

[0033] Specifically, the specific process of establishing the mathematical relationship between the exhaust valve opening and the compressor exhaust pressure, exhaust flow rate and compressor energy efficiency through support vector regression is as follows: through the support vector regression model, based on the historical multi-dimensional data, the historical data is preprocessed, including data cleaning, normalization and feature extraction; the training data is fitted through the support vector regression model to establish the mathematical relationship between the exhaust valve opening and the compressor exhaust pressure, exhaust flow rate and energy efficiency; by optimizing the hyperparameters in the SVR model, including the penalty factor and the kernel function type, the accuracy and generalization ability of the model are ensured.

[0034] In this implementation scheme, data preprocessing: First, preprocess the historical multi-dimensional data to ensure the quality and adaptability of the data. This process includes: Data cleaning: remove noise data and missing values ​​to ensure that the data used for modeling is accurate and complete. Normalization: In order to improve the training effect of the model, scale the data so that all feature data are at the same level to avoid excessive influence of certain features on model training. Feature extraction: Extract features useful for prediction from the original data. These features may include exhaust pressure, exhaust flow, and compressor energy efficiency, etc., in order to provide valuable input for the model. Model fitting and training: Use the support vector regression (SVR) model to fit the training model through historical data. SVR is a regression analysis method based on statistical learning theory, which can effectively capture the nonlinear relationship between input features and target variables (exhaust valve opening). During the training process, SVR optimizes the objective function and finds the regression function that best suits the data, thereby obtaining the mathematical relationship between the exhaust valve opening and the compressor exhaust pressure, exhaust flow and energy efficiency. Optimize hyperparameters: In order to improve the accuracy and generalization ability of the SVR model, its hyperparameters need to be optimized, mainly including: Penalty factor (C): This parameter is used to control the error tolerance of the model during the fitting process. A larger C value will reduce the training error, but may lead to overfitting; a smaller C value increases the error tolerance and helps avoid overfitting. Kernel function type: The SVR model uses different kernel functions (such as linear kernel, radial basis kernel, etc.) to process the nonlinear relationship of the input data. Choosing a suitable kernel function can improve the predictive ability of the model and ensure that the model better captures the complex relationship between the exhaust valve opening and other variables. Model evaluation and validation: The trained SVR model is evaluated through cross-validation or independent validation sets to ensure its stable performance on different data sets and avoid overfitting or underfitting problems in the model.

[0035] Specifically, the specific process of constructing the exhaust valve model is as follows: through the trained support vector regression model, the mathematical relationship between the exhaust valve opening and the compressor exhaust pressure, exhaust flow and energy efficiency is obtained; according to the obtained mathematical relationship, combined with the real-time collected compressor exhaust pressure, exhaust flow and energy efficiency data, the exhaust valve opening under different working conditions is calculated; an exhaust valve model between the exhaust valve opening adjustment and the compressor energy efficiency and stability is generated, which is used to dynamically adjust the exhaust valve opening of the compressor and optimize the operating efficiency and stability of the compressor.

[0036] In this implementation, in the specific process of constructing the exhaust valve model, the mathematical relationship between the exhaust valve opening and the compressor exhaust pressure, exhaust flow rate and energy efficiency is obtained through the trained support vector regression (SVR) model. The following is the detailed process: Model training and mathematical relationship acquisition: Through the support vector regression model, the historical data is input into the training model to obtain the exhaust valve opening and compressor discharge pressure , Exhaust flow and energy efficiency After training, the SVR model can derive a mapping function; ,This function describes the change of the exhaust valve opening under different exhaust pressure, exhaust flow and energy efficiency conditions. Calculate the exhaust valve opening in combination with real-time data: Based on the trained SVR model, in the actual operation process, combined with the real-time collected compressor exhaust pressure, exhaust flow and energy efficiency data, the above mathematical relationship is used to calculate the exhaust valve opening under different working conditions ( ). The specific calculation process is as follows: ;in, Indicates the current time point, and the exhaust valve opening is continuously updated and calculated through real-time data. Generate an exhaust valve model and optimize the operating efficiency and stability of the compressor: By obtaining the relationship between the exhaust valve opening and the compressor energy efficiency and stability, the exhaust valve model is further constructed to dynamically adjust the exhaust valve opening of the compressor to optimize the operating efficiency and stability of the compressor. This model not only takes into account energy efficiency ( ) and also considers stability factors such as the stability of exhaust pressure. By adjusting the exhaust valve opening in real time, the operating state of the compressor can be effectively controlled to avoid over-compression or inefficient operation, ultimately achieving energy saving and improving system stability. The key objectives of the exhaust valve model are: ;in, The function obtained by fitting the support vector regression (SVR) model describes the relationship between the exhaust valve opening and the compressor status (exhaust pressure, exhaust flow and energy efficiency). The goal is to ensure that the compressor operates in an efficient and stable state by dynamically adjusting the exhaust valve opening.

[0037] Specifically, the specific process of dynamically adjusting the opening of the intake valve through the particle swarm optimization algorithm is as follows: obtain the real-time collected compressor load, energy efficiency and intake flow data, and input them into the intake valve model to calculate the current intake valve opening; set the target opening of the intake valve according to the real-time collected data and the compressor energy efficiency requirements, and calculate the difference between the target opening and the current opening; initialize the particle swarm in the particle swarm optimization algorithm, and set the fitness function of each particle, which measures the closeness of the intake valve opening adjusted by the particle to the target opening; iteratively update the position of the particle through the particle swarm optimization algorithm, calculate the fitness function in each iteration, and select the particle with the best fitness as the optimal solution; when the iterative process of the particle swarm converges, the best solution obtained is the optimized intake valve opening, which is used to dynamically adjust the intake valve and optimize the operating efficiency of the compressor.

[0038] In this implementation scheme, real-time data is obtained and the current opening is calculated with the suction valve model: First, the system collects data such as the load, energy efficiency and suction flow of the compressor in real time. These real-time data are passed as input to the suction valve model, and the model calculates the current suction valve opening based on these data. The purpose of this step is to determine the current suction valve opening based on the real-time monitored working status and serve as the starting point of the optimization process. Set the target opening and calculate the difference: According to the actual load and energy efficiency requirements of the compressor, a target suction valve opening is set. The target opening is set according to the optimal operating efficiency and energy efficiency requirements of the system. Calculate the difference between the current opening and the target opening. This difference will be used in the fitness function of the particle swarm optimization algorithm to guide the direction of algorithm optimization. The target opening can be dynamically adjusted according to the real-time data such as the load, energy efficiency, and suction flow of the compressor to ensure that the compressor always operates in the optimal state. Initialize the particle swarm optimization algorithm: In the particle swarm optimization algorithm, a group of particle swarms are first initialized. Each particle represents a possible suction valve opening solution. Each particle has a position and a velocity. The position represents the solution of the current particle (i.e., the current intake valve opening), and the velocity determines the speed at which the particle updates its position in the search space. The size of the particle swarm depends on the complexity of the problem. Generally, the more particles there are, the wider the algorithm search range is, but the amount of calculation also increases. Set the fitness function and calculate the fitness of the particles: Set a fitness function for each particle, which is used to measure the closeness of the particle's current solution to the target solution. The fitness function is usually the error between the target opening and the particle position (the current intake valve opening). The smaller the error, the higher the fitness. The fitness function can be designed as: ;in, is the target opening, is the current opening of the particle. The purpose of the fitness function is to minimize this difference to obtain the optimal solution. Particle Swarm Optimization Iterative Update: The particle swarm optimization algorithm gradually approaches the global optimal solution by iteratively updating the speed and position of the particles. At each iteration, the speed and position of the particle are adjusted according to its own experience (individual optimal position) and the experience of the group (group optimal position) ; ;in, For particles At time step speed, For particles The position of the air intake valve (i.e. the current opening of the air intake valve), For particles The best location in history, Best location for the whole group. is the learning factor, is a random number, is the inertia weight. Through continuous iterations, the particles gradually converge to the optimal solution, which is the value closest to the target intake valve opening. In each iteration, the particle swarm will gradually reduce the opening difference through optimization until the algorithm converges. Convergence usually means that the value of the fitness function no longer changes significantly, or the set maximum number of iterations is reached. When the particle swarm converges, the solution corresponding to the best particle is the optimized intake valve opening, which makes the intake valve adjustment most in line with the energy efficiency requirements of the compressor. Finally, the optimized intake valve opening will be dynamically adjusted to the compressor, thereby optimizing the operating efficiency of the compressor.

[0039] Specifically, the specific process of dynamically adjusting the exhaust valve opening through the fuzzy control algorithm is as follows: obtain the real-time collected exhaust pressure, exhaust flow and compressor load data as the input variables of the fuzzy control algorithm; according to the actual data of exhaust pressure, exhaust flow and compressor load, convert the input variables into fuzzy sets through fuzzification processing; set the fuzzy control rule base, and determine the relationship between exhaust pressure, exhaust flow and compressor load according to the exhaust valve model, and determine the direction and degree of adjustment of the exhaust valve opening; reason the fuzzy control rules through fuzzy reasoning, and calculate the adaptive output value of the exhaust valve, that is, the exhaust valve opening adjustment amount; defuzzify the fuzzy reasoning result to obtain the actual exhaust valve opening adjustment value, and dynamically adjust the exhaust valve opening through the control system to optimize the energy efficiency and stability of the compressor.

[0040] In this implementation scheme, real-time data is obtained: First, the system collects data related to the operating status of the compressor in real time, mainly including exhaust pressure, exhaust flow and compressor load. These data will be used as input variables of the fuzzy control algorithm to determine the adjustment of the exhaust valve opening. Fuzzification of input variables: Fuzzification is the process of converting precise input data into fuzzy sets. In this step, the three input variables of exhaust pressure, exhaust flow and compressor load are converted into fuzzy values ​​according to the preset fuzzy membership function. Each input variable is usually divided into several different linguistic variables ("high", "medium" and "low") and mapped with fuzzy sets. For example, exhaust pressure can be divided into three fuzzy states of "high pressure", "medium pressure" and "low pressure", and compressor load can be divided into "heavy load", "medium load" and "light load". This fuzzification process helps to deal with the noise and uncertainty of input data, so that the fuzzy control system can flexibly handle complex and nonlinear control problems. Set the fuzzy control rule base: The fuzzy rule base is one of the cores of the fuzzy control system. It contains a set of rules that describe the relationship between input variables and output variables. In this process, a set of control rules based on actual operating requirements needs to be set according to the exhaust valve model. Control rules are usually composed of "if...then..." statements, for example: "If the exhaust pressure is high and the compressor load is heavy, then the exhaust valve opening should be greatly reduced." These rules reflect the relationship between exhaust pressure, exhaust flow and compressor load under different operating conditions, and indicate the direction and degree of adjustment of the exhaust valve opening. Fuzzy reasoning: Fuzzy reasoning is the process of deriving fuzzy control rules. In this step, the control system calculates the adjustment amount of the exhaust valve opening through reasoning. To determine the output adjustment amount corresponding to each input state. The reasoning process considers the influence of all fuzzy rules and combines them to obtain an exhaust valve adjustment amount that conforms to the actual situation. Defuzzification: After fuzzy reasoning, the output value obtained by the system is still fuzzy and needs to be converted into an accurate exhaust valve opening adjustment value through the defuzzification process. Defuzzification methods include central average method and weighted average method, which can map fuzzy output to actual value range. The result obtained after defuzzification is the actual opening adjustment amount of the exhaust valve, which will be used to actually adjust the opening of the exhaust valve in the control system. Dynamically adjust the exhaust valve opening: Finally, the exhaust valve opening adjustment value obtained will be used to dynamically adjust the exhaust valve opening through the control system. The exhaust valve opening will be adjusted based on real-time data (such as exhaust pressure, exhaust flow, compressor load) and the adjustment amount calculated by the fuzzy control algorithm. Through continuous dynamic adjustment, the compressor exhaust valve opening is always in the optimal state under different working conditions to maximize the compressor's energy efficiency and maintain its stability.Optimize the energy efficiency and stability of the compressor: Through the continuous adjustment of the fuzzy control algorithm, the exhaust valve opening can respond to the load changes of the compressor, exhaust pressure fluctuations and other factors in real time, thereby optimizing the operating state of the compressor. Specifically, through the reasonable adjustment of the exhaust valve, the energy efficiency of the compressor can be improved, energy consumption can be reduced, and working stability can be improved, and unstable operation or low energy efficiency caused by too high or too low opening can be avoided.

[0041] In summary, this application has at least the following effects:

[0042] The compressor control and management system based on the Internet of Things can accurately control the operating status of the compressor by dynamically adjusting the opening of the suction valve and the exhaust valve, improve the energy efficiency of the compressor, reduce energy consumption, and thus maximize energy utilization. Through precise valve opening adjustment, the changes in compressor load and exhaust pressure can be balanced, equipment shock or failure caused by improper valve control can be avoided, and the long-term stability and safety of the compressor can be improved. By adopting long-term and short-term memory networks, support vector regression, particle swarm optimization and fuzzy control algorithms, intelligent dynamic adjustment of the compressor opening can be achieved, reducing human intervention and reducing operational complexity. It can flexibly respond to various changes and disturbances in a complex and uncertain environment, improve the system's anti-interference ability, and ensure the efficient operation of the compressor. Through automated and intelligent control methods, the dependence on manual operation is reduced, the operation process is simplified, the technical threshold of the operator is lowered, and the convenience and accuracy of operation are improved.

[0043] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0044] The present invention is described with reference to flowcharts and / or block diagrams of systems, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0045] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0046] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0047] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0048] 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. The compressor control management system based on the Internet of Things is characterized by: It includes the following modules: multi-dimensional data acquisition module, model building module, and control module; The module is used to connect the multi-dimensional sensor through the Internet of Things to obtain the multi-dimensional data and historical multi-dimensional data of the compressor; The model building module includes an intake valve model building unit and an exhaust valve model building unit; The suction valve model building unit is used to establish a mathematical relationship between the suction valve opening and the compressor load, energy efficiency and suction flow rate through a long short-term memory network according to the multi-dimensional data and historical multi-dimensional data of the compressor, so as to build a suction valve model; The exhaust valve model building unit is used to establish a mathematical relationship between the exhaust valve opening and the exhaust pressure, exhaust flow rate and energy efficiency of the compressor through support vector regression according to the multi-dimensional data and historical multi-dimensional data of the compressor, so as to build an exhaust valve model; The control module is used to include an intake valve control unit and an exhaust valve control unit; The suction valve control unit is used to dynamically adjust the opening of the suction valve through a particle swarm optimization algorithm according to the suction valve model, combined with real-time load data and compressor energy efficiency requirements; The exhaust valve control unit is used to dynamically adjust the exhaust valve opening through a fuzzy control algorithm based on the prediction model generated by the exhaust valve model building unit in combination with real-time exhaust pressure, exhaust flow and compressor load data.

2. The compressor control management system based on the Internet of Things according to claim 1, characterized in that: The multi-dimensional data includes but is not limited to compressor load, exhaust temperature, exhaust pressure, intake volume, intake valve and exhaust valve opening, and motor speed.

3. The compressor control management system based on the Internet of Things according to claim 2, characterized in that: The specific process of establishing the mathematical relationship between the suction valve opening and the compressor load, energy efficiency and suction flow rate through the long short-term memory network is as follows: Based on the multi-dimensional data of the compressor and the historical multi-dimensional data, pre-processing is performed, including: data cleaning, data normalization and feature extraction, and the data is converted into a time series format; The historical data is divided into multiple samples according to the set time window, and each window is used as the input data of the long short-term memory network; The input data of each time step is divided by windows, and the input data includes characteristic data of compressor load, energy efficiency and suction flow rate; Setting the network structure of the long short-term memory network model, including setting the input layer to receive characteristic data such as compressor load, energy efficiency and suction flow, setting the number of network model layers and the number of neurons in each layer to capture the temporal dependency between data, and setting the output layer to predict the opening of the suction valve; The long short-term memory network model is trained through historical multi-dimensional data, including setting the loss function to measure the difference between the predicted value and the actual value and updating the model weights through back propagation and gradient descent algorithms.

4. The compressor control management system based on the Internet of Things according to claim 3 is characterized in that: The specific process of building the suction valve model is as follows: The mathematical relationship between the suction valve opening and the compressor load, energy efficiency and suction flow rate is obtained through the trained long short-term memory network model; Based on the acquired mathematical relationship, combined with the real-time collected compressor load, energy efficiency, and intake flow rate, the intake valve opening under different conditions is calculated, and an intake valve model between the intake valve opening adjustment and the compressor efficiency is generated. This is used to predict the impact of the intake valve opening adjustment on the compressor efficiency under different loads.

5. The compressor control management system based on the Internet of Things according to claim 4 is characterized in that: The specific process of establishing the mathematical relationship between the exhaust valve opening and the compressor exhaust pressure, exhaust flow rate and compressor energy efficiency through support vector regression is as follows: Through the support vector regression model, historical data is preprocessed based on historical multi-dimensional data, including data cleaning, normalization and feature extraction; The mathematical relationship between the exhaust valve opening and the compressor exhaust pressure, exhaust flow rate and energy efficiency is established by fitting the training data with the support vector regression model; The accuracy and generalization ability of the model are ensured by optimizing the hyperparameters in the SVR model, including the penalty factor and kernel function type.

6. The compressor control management system based on the Internet of Things according to claim 5, characterized in that: The specific process of building the exhaust valve model is as follows: The mathematical relationship between the exhaust valve opening and the compressor exhaust pressure, exhaust flow rate and energy efficiency is obtained through the trained support vector regression model; Based on the obtained mathematical relationship, combined with the real-time collected data such as compressor exhaust pressure, exhaust flow rate and energy efficiency, the exhaust valve opening under different working conditions is calculated; An exhaust valve model between exhaust valve opening adjustment and compressor energy efficiency and stability is generated to predict the impact of exhaust valve opening adjustment on compressor energy efficiency and stability under different load and exhaust pressure conditions.

7. The compressor control management system based on the Internet of Things according to claim 6, characterized in that: The specific process of dynamically adjusting the opening of the intake valve through the particle swarm optimization algorithm is as follows: Obtain the real-time collected compressor load, energy efficiency and suction flow data, and input them into the suction valve model to calculate the current suction valve opening; According to the real-time collected data and the compressor energy efficiency requirements, the target opening of the suction valve is set, and the difference between the target opening and the current opening is calculated; Initialize the particle swarm in the particle swarm optimization algorithm and set the fitness function of each particle, which measures the closeness between the opening of the intake valve adjusted by the particle and the target opening; The particle positions are iteratively updated through the particle swarm optimization algorithm, and the fitness function is calculated in each iteration, and the particle with the best fitness is selected as the best solution; When the iterative process of the particle swarm converges, the best solution obtained is the optimized suction valve opening, which is used to dynamically adjust the suction valve and optimize the operating efficiency of the compressor.

8. The compressor control management system based on the Internet of Things according to claim 7, characterized in that: The specific process of dynamically adjusting the exhaust valve opening through the fuzzy control algorithm is as follows: Obtain real-time collected exhaust pressure, exhaust flow and compressor load data as input variables of the fuzzy control algorithm; According to the actual data of exhaust pressure, exhaust flow and compressor load, the input variables are transformed into fuzzy sets through fuzzy processing; Set up the fuzzy control rule base, determine the relationship between exhaust pressure, exhaust flow and compressor load according to the exhaust valve model, and determine the direction and degree of adjustment of the exhaust valve opening; The fuzzy control rules are inferred through fuzzy reasoning to calculate the adaptive output value of the exhaust valve, that is, the opening adjustment amount of the exhaust valve; The fuzzy reasoning result is defuzzified to obtain the actual exhaust valve opening adjustment value, and the exhaust valve opening is dynamically adjusted through the control system to optimize the energy efficiency and stability of the compressor.

Images