Air compression system energy-saving optimization method based on data analysis modeling

Abstract

The invention relates to the technical field of air compression system energy saving, in particular to an air compression system energy-saving optimization method based on data analysis modeling, which comprises the following steps of: firstly, acquiring operation data of each key component in an air compression system and related information of gas utilization equipment; key operation data in the air compression system and related information of the gas consumption equipment are preprocessed, then a data model and an intelligent prediction model are constructed through a machine learning algorithm, and the intelligent prediction model is constructed on the basis of the trained data model, the trained intelligent prediction model, the preprocessed key operation data and the preprocessed related information of the gas consumption equipment. Constructing a relation model between the operation state and the energy consumption of the air compression system; inputting the collected operation data into a relation model between the operation state and the energy consumption of the air compression system for prediction, formulating an energy-saving optimization strategy based on the predicted energy consumption conditions under different operation conditions, and finally determining the energy-saving optimization strategy based on the correlation analysis of the standard square flow of the air compressor and the gas-electricity ratio and the analysis result of the regression curve of the variable-frequency air compressor. And a relation model between the main pipe flow and the main pipe pressure of the air compression system is constructed through a deep learning algorithm, so that an energy-saving optimization strategy of the air compression system is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of energy saving of air compression systems, and particularly to an energy saving optimization method and device for air compression systems based on data analysis and modeling. Background Art

[0002] Air compression systems are widely used in industrial production, but their energy consumption is huge. The traditional operation control method of air compression systems generally relies on manual experience for adjustment, but this adjustment method is relatively rough and often cannot adjust the operation state of air compressors in real time and accurately according to the actual gas consumption demand, resulting in a large amount of energy waste.

[0003] How to optimize the energy saving of air compression systems through advanced technical means, improve energy utilization efficiency, and reduce production costs has become an urgent problem to be solved at present. Summary of the Invention

[0004] The purpose of the present invention is to propose an energy saving optimization method and device for air compression systems based on data analysis and modeling to solve the problem that the traditional operation control method of air compression systems is relatively rough and often cannot adjust the operation state of air compressors in real time and accurately according to the actual gas consumption demand, resulting in a large amount of energy waste.

[0005] To solve the above technical problems, the present invention adopts the following technical solutions:

[0006] In the first aspect, the present invention proposes an energy saving optimization method for air compression systems based on data analysis and modeling, including the following steps:

[0007] S1. Collect the operation data of each key component in the air compression system and the relevant information of gas-using equipment to obtain the key operation data and the relevant information of gas-using equipment in the air compression system; among them, the operation data includes pressure, flow rate, temperature, motor speed, etc.; the relevant information of gas-using equipment includes information such as the opening time of gas-using equipment, the closing time of gas-using equipment, and the change of gas consumption demand;

[0008] S2. Preprocess the key operation data and the relevant information of gas-using equipment in the air compression system to obtain the preprocessed key operation data and the relevant information of gas-using equipment;

[0009] S3. Use machine learning algorithms to construct a data model and a smart prediction model, and based on the trained data model, the trained smart prediction model, the preprocessed key operation data, and the preprocessed relevant information of gas-using equipment, construct a relationship model between the operation state and energy consumption of the air compression system; among them, the data model is constructed by using the DeepAR deep learning model; the smart prediction model is constructed by using the polynomial regression algorithm;

[0010] S4. Collect the operation data in the air compressor system in real time, input the collected operation data into the relationship model between the operation state and energy consumption of the air compressor system for prediction, and formulate an energy-saving optimization strategy based on the predicted energy consumption under different operation conditions;

[0011] S5. Based on the correlation analysis of the standard cubic flow rate and the gas-electricity ratio of the air compressor and the results of the regression curve analysis of the variable-frequency air compressor, and by using a deep learning algorithm to construct the relationship model between the total pipe flow rate and the total pipe pressure of the air compressor system, and then based on the formulated energy-saving optimization strategy and the relationship model between the total pipe flow rate and the total pipe pressure of the air compressor system, realize the energy-saving optimization strategy of the air compressor system.

[0012] Preferably, the step S1 of collecting the operation data of each key component in the air compressor system and the relevant information of the gas-using equipment to obtain the key operation data and the relevant information of the gas-using equipment in the air compressor system includes the following steps:

[0013] S1.1. Collect the operation data such as the pressure, flow rate, temperature and motor speed of the air compressor in the air compressor system to obtain the operation data such as the pressure, flow rate, temperature and motor speed of the air compressor in the air compressor system;

[0014] S1.2. Collect the operation data such as the pressure, flow rate and temperature of the air storage tank in the air compressor system to obtain the operation data such as the pressure, flow rate and temperature of the air storage tank in the air compressor system;

[0015] S1.3. Collect the operation data such as the pressure, flow rate and temperature of the pipeline in the air compressor system to obtain the operation data such as the pressure, flow rate and temperature of the pipeline in the air compressor system;

[0016] S1.4. Integrate the operation data such as the pressure, flow rate and temperature of the pipeline in the air compressor system, the operation data such as the pressure, flow rate and temperature of the air storage tank in the air compressor system, the operation data such as the pressure, flow rate, temperature and motor speed of the air compressor in the air compressor system, the opening time of the gas-using equipment, the closing time of the gas-using equipment and the change information of the gas demand of the gas-using equipment to obtain the key operation data and the relevant information of the gas-using equipment in the air compressor system.

[0017] Preferably, the step S2 of preprocessing the key operation data and the relevant information of the gas-using equipment in the air compressor system to obtain the preprocessed key operation data and the relevant information of the gas-using equipment includes the following steps:

[0018] S2.1. Perform noise reduction processing on the key operation data and the relevant information of the gas-using equipment in the air compressor system, and then perform abnormal value removal processing on the key operation data and the relevant information of the gas-using equipment in the air compressor system after the noise reduction processing to obtain the key operation data and the relevant information of the gas-using equipment after the abnormal value removal;

[0019] S2.2. Smooth the key operation data and gas-using equipment related information after removing abnormal values using a data smoothing algorithm, and then perform standardization and normalization processing on the smoothed key operation data and gas-using equipment related information to obtain the preprocessed key operation data and gas-using equipment related information.

[0020] Preferably, the step S3. Build a data model and an intelligent prediction model using a machine learning algorithm, and based on the trained data model, the trained intelligent prediction model, the preprocessed key operation data, and the preprocessed gas-using equipment related information, build a relationship model between the operation state and energy consumption of the air compressor system, including the following steps:

[0021] S3.1. Build a data model using a DeepAR deep learning model, and input the preprocessed key operation data and gas-using equipment related information into the data model for training to obtain the trained data model;

[0022] S3.2. Build an intelligent prediction model using a polynomial regression algorithm, and input the preprocessed key operation data and gas-using equipment related information into the intelligent prediction model for training to obtain the trained intelligent prediction model;

[0023] S3.3. Based on the trained intelligent prediction model, the trained data model, the preprocessed key operation data, and the preprocessed gas-using equipment related information, build a relationship model between the operation state and energy consumption of the air compressor system.

[0024] Preferably, the data model includes:

[0025] Single-machine model. The single-machine model is used to perform data analysis on two variable-frequency machines, explore the relationship between the standard flow rate and the gas-electricity ratio in the variable-frequency machines, and then fit the relationship through model establishment to obtain the optimal operation range of the frequency conversion;

[0026] Main station model. The main station model is used to perform data analysis on the main pipe pressure and main pipe flow rate of the air compressor station, and fit the relationship between the two through model establishment to obtain a model for predicting the future main pipe flow rate.

[0027] Preferably, the step S5. Based on the correlation analysis of the standard flow rate and gas-electricity ratio of the air compressor and the analysis results of the regression curve of the variable-frequency air compressor, and through a deep learning algorithm, build a relationship model between the main pipe flow rate and main pipe pressure of the air compressor system, and then based on the formulated energy-saving optimization strategy and the relationship model between the main pipe flow rate and main pipe pressure of the air compressor system, implement the energy-saving optimization strategy of the air compressor system, including the following steps:

[0028] S5.1. Analyze the correlation between the standard flow rate and gas-electricity ratio of the air compressor in the air compressor system to obtain the analysis results of the correlation between the standard flow rate and gas-electricity ratio of the air compressor;

[0029] S5.2. Analyze the regression curve of the variable-frequency air compressor in the air compression system to obtain the analysis results of the regression curve of the variable-frequency air compressor;

[0030] S5.3. Based on the analysis results of the regression curve of the variable-frequency air compressor, the analysis results of the correlation between the standard cubic flow rate of the air compressor and the air-electricity ratio, and through the deep learning algorithm, construct a relationship model between the total flow rate and the total pressure of the air compression system;

[0031] S5.4. Based on the relationship model between the total flow rate and the total pressure of the air compression system and the formulated energy-saving optimization strategy, implement the energy-saving optimization strategy of the air compression system.

[0032] In the second aspect, the present invention proposes an energy-saving optimization device for an air compression system based on data analysis and modeling, including

[0033] A data acquisition module, which is used to collect the operation data at each key part in the air compression system and the relevant information of the gas-using equipment, and obtain the key operation data and the relevant information of the gas-using equipment in the air compression system;

[0034] A data preprocessing module, which is connected to the data acquisition module through a database. The data preprocessing module is used to preprocess the key operation data and the relevant information of the gas-using equipment in the air compression system to obtain the preprocessed key operation data and the relevant information of the gas-using equipment;

[0035] A data analysis module, which is connected to the data preprocessing module. The data analysis module is used to construct a data model and an intelligent prediction model with machine learning algorithms, and based on the trained data model, the trained intelligent prediction model, the preprocessed key operation data and the preprocessed relevant information of the gas-using equipment, construct a relationship model between the operation state and the energy consumption of the air compression system;

[0036] An energy-saving optimization strategy module, which is connected to the data analysis module. The energy-saving optimization strategy module is used to collect the operation data in the air compression system in real time, input the collected operation data into the relationship model between the operation state and the energy consumption of the air compression system for prediction, and based on the predicted energy consumption in different operation conditions, formulate an energy-saving optimization strategy;

[0037] An energy-saving optimization strategy implementation module, which is connected to the energy-saving optimization strategy module. The energy-saving optimization strategy implementation module is used to based on the correlation analysis of the standard cubic flow rate of the air compressor and the air-electricity ratio and the analysis results of the regression curve of the variable-frequency air compressor, and through the deep learning algorithm, construct a relationship model between the total flow rate and the total pressure of the air compression system, and then based on the formulated energy-saving optimization

[0038] Preferably, an energy-saving optimization device for an air compressor system based on data analysis and modeling further includes an execution module, which is connected to the energy-saving optimization strategy implementation module. The execution module is used to convert the strategy of the energy-saving optimization of the air compressor system implemented in the energy-saving optimization strategy implementation module into control instructions and send them to the controller of the air compressor system for automatic control of equipment such as air compressors and valves.

[0039] Compared with the prior art, the present invention has at least one of the following beneficial effects:

[0040] 1. The present invention first collects the operation data of each key component in the air compressor system and the relevant information of the gas-using equipment to obtain the key operation data and the relevant information of the gas-using equipment in the air compressor system. Then, it preprocesses the key operation data and the relevant information of the gas-using equipment in the air compressor system to obtain the preprocessed key operation data and the relevant information of the gas-using equipment. Then, it uses machine learning algorithms to construct a data model and a smart prediction model, and based on the trained data model, the trained smart prediction model, the preprocessed key operation data, and the preprocessed relevant information of the gas-using equipment, constructs a relationship model between the operation state and energy consumption of the air compressor system. After that, it collects the operation data in the air compressor system in real time, inputs the collected operation data into the relationship model between the operation state and energy consumption of the air compressor system for prediction, and based on the predicted energy consumption under different operation conditions, formulates an energy-saving optimization strategy. Finally, based on the correlation analysis of the standard cubic flow rate of the air compressor and the air-electricity ratio and the analysis results of the regression curve of the variable-frequency air compressor, and through deep learning algorithms, constructs a relationship model between the total pipe flow rate and the total pipe pressure of the air compressor system, and then based on the formulated energy-saving and the relationship model between the total pipe flow rate and the total pipe pressure of the air compressor system, realizes the energy-saving optimization strategy of the air compressor system to solve the problem that the traditional operation control method of the air compressor system is relatively rough and often unable to adjust the operation state of the air compressor in real time and accurately according to the actual gas demand, resulting in a large amount of energy waste.

[0041] 2. The present invention realizes the intelligent and accurate energy-saving control of the air compressor system, improves the energy utilization efficiency, has good universality and scalability, effectively reduces the energy consumption of the air compressor system, and has important application value in the energy-saving transformation of the air compressor system in industrial production. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 It is a schematic flow chart of an energy-saving optimization method for an air compressor system based on data analysis and modeling in the present invention.

[0043] Figure 2 It is a schematic diagram of the air compressor control system in the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0044] As Figure 1-2As shown below, to make the objectives, technical solutions, and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0045] Embodiment

[0046] Air compression systems are widely used in industrial production, but they consume a huge amount of energy. The traditional operation control method of air compression systems generally relies on manual experience for adjustment. However, this adjustment method is relatively rough and cannot adjust the operating state of the air compressor in real time and accurately according to the actual gas consumption demand, resulting in a large amount of energy waste.

[0047] Therefore, this application proposes an energy-saving optimization method and device for air compression systems based on data analysis and modeling to solve the problem that the traditional operation control method of air compression systems is relatively rough and often cannot adjust the operating state of the air compressor in real time and accurately according to the actual gas consumption demand, resulting in a large amount of energy waste.

[0048] Specifically, in the first aspect, the present invention proposes an energy-saving optimization method for air compression systems based on data analysis and modeling. Please refer to Figure 1 and Figure 2 , an energy-saving optimization method for air compression systems based on data analysis and modeling, including the following steps:

[0049] The first step is to collect the operation data of each key component in the air compression system and the relevant information of the gas-consuming equipment to obtain the key operation data and the relevant information of the gas-consuming equipment in the air compression system, specifically as follows:

[0050] (1) Collect the operation data such as pressure, flow rate, temperature, and motor speed of the air compressor in the air compression system to obtain the operation data such as pressure, flow rate, temperature, and motor speed of the air compressor in the air compression system;

[0051] (2) Collect the operation data such as pressure, flow rate, and temperature of the air storage tank in the air compression system to obtain the operation data such as pressure, flow rate, and temperature of the air storage tank in the air compression system;

[0052] (3) Collect the operation data such as pressure, flow rate, and temperature of the pipeline in the air compression system to obtain the operation data such as pressure, flow rate, and temperature of the pipeline in the air compression system;

[0053] (4) Integrate the operation data such as pressure, flow rate, and temperature of the pipeline in the air compression system, the operation data such as pressure, flow rate, and temperature of the air storage tank in the air compression system, the operation data such as pressure, flow rate, temperature, and motor speed of the air compressor in the air compression system, the start time of the gas-consuming equipment, the shutdown time of the gas-consuming equipment, and the change information of the gas consumption demand of the gas-consuming equipment to obtain the key operation data and the relevant information of the gas-consuming equipment in the air compression system.

[0054] In this embodiment, the operating data (operating data: pressure, flow, temperature and motor speed) of each key component in the air compression system (key components: air compressor, gas storage tank and pipeline) and gas-using equipment related information (gas-using equipment related information: gas-using equipment opening time, gas-using equipment closing time and gas demand changes of gas-using equipment) are collected to obtain key operating data and gas-using equipment related information in the air compression system, providing data analysis support for subsequent data analysis modeling.

[0055] The second step is to pre-process the key operating data and related information of the gas-using equipment in the air compression system to obtain the pre-processed key operating data and related information of the gas-using equipment, as follows:

[0056] (1) performing noise reduction processing on key operating data and related information of gas-using equipment in the air compression system, and then performing abnormal value removal processing on the key operating data and related information of gas-using equipment in the air compression system after the noise reduction processing, to obtain the key operating data and related information of gas-using equipment after the abnormal value removal;

[0057] (2) Use a data smoothing algorithm to smooth the key operating data and gas equipment related information after removing abnormal values, and then standardize and normalize the smoothed key operating data and gas equipment related information to obtain the pre-processed key operating data and gas equipment related information.

[0058] In this embodiment, key operating data and gas-using equipment related information in the air compressor system are preprocessed to obtain preprocessed and high-quality key operating data and gas-using equipment related information, providing high-quality and effective data for subsequent data analysis and modeling.

[0059] The third step is to use machine learning algorithms to build a data model and an intelligent prediction model. Based on the trained data model, the trained intelligent prediction model, the pre-processed key operating data, and the pre-processed information about gas-using equipment, a relationship model between the operating status of the air compressor system and energy consumption is constructed. The details are as follows:

[0060] (1) Use the DeepAR deep learning model to build a data model, and input the pre-processed key operating data and relevant information of gas-using equipment into the data model for training to obtain the trained data model; wherein, the data model includes a single-machine model and a main station model. Specifically, the single-machine model is used to perform data analysis on two frequency converters, and explore the relationship between the flow rate of the frequency converter winning bidder and the gas-to-electricity ratio, and then fit the relationship by establishing a model to obtain the optimal operating range of the frequency converter; the main station model is used to perform data analysis on the main pipe pressure and main pipe flow of the air compressor station, and fit the relationship between the two by establishing a model to obtain a model for predicting the future main pipe flow.

[0061] (2) Use the polynomial regression algorithm to construct a smart prediction model, and input the preprocessed key operation data and gas equipment-related information into the smart prediction model for training to obtain the trained smart prediction model.

[0062] (3) Based on the trained smart prediction model, the trained data model, the preprocessed key operation data, and the preprocessed gas equipment-related information, construct a relationship model between the operation state and energy consumption of the air compressor system.

[0063] In this embodiment, by using machine learning algorithms to construct a data model and a smart prediction model, and based on the trained data model, the trained smart prediction model, the preprocessed key operation data, and the preprocessed gas equipment-related information, a relationship model between the operation state and energy consumption of the air compressor system is constructed to prepare for subsequent prediction of the energy consumption of the air compressor system under different operating conditions.

[0064] Fourth step: Real-time collect the operation data in the air compressor system, input the collected operation data into the relationship model between the operation state and energy consumption of the air compressor system for prediction, and based on the predicted energy consumption under different operating conditions, formulate an energy-saving optimization strategy, specifically as follows:

[0065] Use sensors or industrial cameras to real-time collect the operation data in the air compressor system, input the collected operation data into the relationship model between the operation state and energy consumption of the air compressor system for prediction, and based on the predicted energy consumption under different operating conditions, formulate an energy-saving optimization strategy.

[0066] In this embodiment, by real-time collecting the operation data in the air compressor system, inputting the collected operation data into the relationship model between the operation state and energy consumption of the air compressor system for prediction, and based on the predicted energy consumption under different operating conditions, an energy-saving optimization strategy is formulated to prepare for subsequent implementation of the energy-saving optimization strategy.

[0067] Fifth step: Based on the correlation analysis of the standard cubic flow rate and gas-electricity ratio of the air compressor and the analysis results of the regression curve of the variable-frequency air compressor, and through deep learning algorithms, construct a relationship model between the total pipe flow rate and the total pipe pressure of the air compressor system. Then, based on the formulated energy-saving optimization strategy and the relationship model between the total pipe flow rate and the total pipe pressure of the air compressor system, implement the energy-saving optimization strategy of the air compressor system, specifically as follows:

[0068] (1) Analyze the correlation between the standard cubic flow rate and gas-electricity ratio of the air compressor in the air compressor system to obtain the analysis results of the correlation between the standard cubic flow rate and gas-electricity ratio of the air compressor.

[0069] (2) Analyze the regression curve of the variable-frequency air compressor in the air compressor system to obtain the analysis results of the regression curve of the variable-frequency air compressor.

[0070] (3) Based on the analysis results of the regression curve of the variable-frequency air compressor, the analysis results of the correlation between the standard cubic flow rate of the air compressor and the air-electricity ratio, and through a deep learning algorithm, a relationship model between the total flow rate and the total pressure of the air compression system is constructed.

[0071] (4) Based on the relationship model between the total flow rate and the total pressure of the air compression system and the formulated energy-saving optimization strategy, the energy-saving optimization strategy of the air compression system is realized, that is, the energy-saving optimization strategy of the air compression system is applied to Figure 2 the air compression control system in.

[0072] In this embodiment, based on the analysis results of the correlation between the standard cubic flow rate of the air compressor and the air-electricity ratio and the analysis of the regression curve of the variable-frequency air compressor, a relationship model between the total flow rate and the total pressure of the air compression system is constructed through a deep learning algorithm. Then, based on the formulated energy-saving and the relationship model between the total flow rate and the total pressure of the air compression system, the energy-saving optimization strategy of the air compression system is realized.

[0073] An energy-saving optimization method for an air compression system based on data analysis and modeling in this application. First, the operation data of each key component in the air compression system and the relevant information of the gas-using equipment are collected to obtain the key operation data and the relevant information of the gas-using equipment in the air compression system. Then, the key operation data and the relevant information of the gas-using equipment in the air compression system are preprocessed to obtain the preprocessed key operation data and the relevant information of the gas-using equipment. Then, a data model and a smart prediction model are constructed using a machine learning algorithm. And based on the trained data model, the trained smart prediction model, the preprocessed key operation data, and the preprocessed relevant information of the gas-using equipment, a relationship model between the operation state and the energy consumption of the air compression system is constructed. After that, the operation data in the air compression system is collected in real time, and the collected operation data is input into the relationship model between the operation state and the energy consumption of the air compression system for prediction. And based on the predicted energy consumption under different operation conditions, an energy-saving optimization strategy is formulated. Finally, based on the analysis results of the correlation between the standard cubic flow rate of the air compressor and the air-electricity ratio and the analysis of the regression curve of the variable-frequency air compressor, a relationship model between the total flow rate and the total pressure of the air compression system is constructed through a deep learning algorithm. Then, based on the formulated energy-saving optimization strategy and the relationship model between the total flow rate and the total pressure of the air compression system, the energy-saving optimization strategy of the air compression system is realized to solve the problem that the traditional operation control method of the air compression system is relatively rough and often cannot adjust the operation state of the air compressor in real time and accurately according to the actual gas consumption demand, resulting in a large amount of energy waste.

[0074] The above is an energy-saving optimization method for an air compression system based on data analysis and modeling proposed in the first aspect of this application. The following is an energy-saving optimization device for an air compression system based on data analysis and modeling proposed in the second aspect of this application. An energy-saving optimization device for an air compression system based on data analysis and modeling includes:

[0075] Data acquisition module, which is used to collect operating data of key parts of the air compression system and related information of gas-using equipment, and obtain key operating data and related information of gas-using equipment in the air compression system;

[0076] The data preprocessing module is connected to the data acquisition module through the database. The data preprocessing module is used to preprocess the key operating data and gas-using equipment related information in the air compression system to obtain the key operating data and gas-using equipment related information after preprocessing;

[0077] The data analysis module is connected to the data preprocessing module. The data analysis module is used to build a data model and an intelligent prediction model using a machine learning algorithm, and to build a relationship model between the operating status of the air compressor system and energy consumption based on the trained data model, the trained intelligent prediction model, the preprocessed key operating data, and the preprocessed information related to the gas-using equipment;

[0078] The energy-saving optimization strategy module is connected to the data analysis module. The energy-saving optimization strategy module is used to collect the operating data of the air compressor system in real time, input the collected operating data into the relationship model between the operating status of the air compressor system and energy consumption for prediction, and formulate energy-saving optimization strategies based on the predicted energy consumption under different operating conditions;

[0079] Energy-saving optimization strategy implementation module, the energy-saving optimization strategy implementation module is connected with the energy-saving optimization strategy module. The energy-saving optimization strategy implementation module is used to build a relationship model between the main pipe flow and the main pipe pressure of the air compressor system based on the correlation analysis of the standard cubic flow of the air compressor and the gas-to-electricity ratio and the regression curve analysis of the variable frequency air compressor through a deep learning algorithm, and then based on the formulated energy-saving optimization strategy and the relationship model between the main pipe flow and the main pipe pressure of the air compressor system, the energy-saving optimization strategy of the air compressor system is realized.

[0080] Among them, the air compressor system energy-saving optimization device based on data analysis modeling also includes an execution module, which is connected to the energy-saving optimization strategy implementation module. The execution module is used to convert the air compressor system energy-saving optimization strategy implemented in the energy-saving optimization strategy implementation module into a control instruction and send it to the controller of the air compressor system for automatic control of equipment such as air compressors and valves.

[0081] Among them, the database is used to store the key operating data of the air compression system and related information of gas-using equipment collected by the data acquisition module.

[0082] An energy-saving optimization device for an air compressor system based on data analysis and modeling in the present application. The data acquisition module first collects the operation data at key parts of the air compressor system and the relevant information of the gas-using equipment to obtain the key operation data and the relevant information of the gas-using equipment in the air compressor system. Then, the data preprocessing module preprocesses the key operation data and the relevant information of the gas-using equipment in the air compressor system to obtain the preprocessed key operation data and the relevant information of the gas-using equipment. Then, the data analysis module uses machine learning algorithms to construct a data model and a smart prediction model, and based on the trained data model, the trained smart prediction model, the preprocessed key operation data, and the preprocessed relevant information of the gas-using equipment, constructs a relationship model between the operation state and energy consumption of the air compressor system. Next, the energy-saving optimization strategy module continuously collects the operation data in the air compressor system and inputs the collected operation data into the relationship model between the operation state and energy consumption of the air compressor system for prediction. Then, based on the predicted energy consumption under different operation conditions, an energy-saving optimization strategy is formulated. After that, the energy-saving optimization strategy implementation module, based on the correlation analysis of the standard cubic flow rate of the air compressor and the gas-electricity ratio and the analysis result of the regression curve of the variable-frequency air compressor, constructs a relationship model between the total pipe flow rate and the total pipe pressure of the air compressor system through a deep learning algorithm. Then, based on the formulated energy-saving optimization strategy and the relationship model between the total pipe flow rate and the total pipe pressure of the air compressor system, the energy-saving optimization strategy of the air compressor system is realized. Finally, the execution module converts the energy-saving optimization strategy of the air compressor system implemented in the energy-saving optimization strategy implementation module into a control instruction and sends it to the controller of the air compressor system to automatically control equipment such as air compressors and valves, so as to solve the problem that the traditional operation control mode of the air compressor system is relatively rough and often unable to adjust the operation state of the air compressor in real time and accurately according to the actual gas consumption demand, resulting in a large amount of energy waste.

[0083] Although the present invention has been described herein with reference to a number of illustrative embodiments of the invention, it should be understood that the skilled person in the art can design many other modifications and embodiments that will fall within the scope of the principles of the present application and the spirit thereof. More specifically, within the scope of the present application, the drawings, and the claims, various modifications and improvements can be made to the components and / or the layout of the subject combination layout. In addition to the modifications and improvements to the components and / or the layout, other uses will also be apparent to the skilled person in the art.

Claims

1. An energy-saving optimization method for an air compressor system based on data analysis and modeling, characterized in that: Including the following steps: S1. Collect the operation data of each key component in the air compressor system and the relevant information of the gas-using equipment to obtain the key operation data in the air compressor system and the relevant information of the gas-using equipment. Among them, the operation data includes pressure, flow rate, temperature, motor speed, etc.; the relevant information of the gas-using equipment includes the opening time of the gas-using equipment, the closing time of the gas-using equipment, and the change of gas demand, etc. S2. Preprocess the key operation data in the air compressor system and the relevant information of the gas-using equipment to obtain the preprocessed key operation data and the relevant information of the gas-using equipment. S3. Use machine learning algorithms to construct a data model and a smart prediction model, and based on the trained data model, the trained smart prediction model, the preprocessed key operation data, and the preprocessed relevant information of the gas-using equipment, construct a relationship model between the operation state and energy consumption of the air compressor system. Among them, the data model is constructed using the DeepAR deep learning model; the smart prediction model is constructed using the polynomial regression algorithm. S4. Real-time collect the operation data in the air compressor system, input the collected operation data into the relationship model between the operation state and energy consumption of the air compressor system for prediction, and formulate an energy-saving optimization strategy based on the predicted energy consumption under different operation conditions. S5. Based on the correlation analysis of the standard cubic flow rate of the air compressor and the gas-electricity ratio and the analysis result of the regression curve of the variable-frequency air compressor, and through the deep learning algorithm, construct a relationship model between the total pipe flow rate and the total pipe pressure of the air compressor system, and then based on the formulated energy-saving optimization strategy and the relationship model between the total pipe flow rate and the total pipe pressure of the air compressor system, realize the energy-saving optimization strategy of the air compressor system.

2. The energy-saving optimization method for an air compressor system based on data analysis and modeling according to claim 1, characterized in that: The above S1. Collect the operation data of each key component in the air compressor system and the relevant information of the gas-using equipment to obtain the key operation data in the air compressor system and the relevant information of the gas-using equipment, including the following steps: S1.

1. Collect the operation data such as pressure, flow rate, temperature, and motor speed of the air compressor in the air compressor system to obtain the operation data such as pressure, flow rate, temperature, and motor speed of the air compressor in the air compressor system. S1.

2. Collect the operation data such as pressure, flow rate, and temperature of the gas storage tank in the air compressor system to obtain the operation data such as pressure, flow rate, and temperature of the gas storage tank in the air compressor system. S1.

3. Collect the operation data such as pressure, flow rate, and temperature of the pipeline in the air compressor system to obtain the operation data such as pressure, flow rate, and temperature of the pipeline in the air compressor system. S1.

4. Integrate the operation data such as pressure, flow rate, and temperature of the pipeline in the air compressor system, the operation data such as pressure, flow rate, and temperature of the gas storage tank in the air compressor system, the operation data such as pressure, flow rate, temperature, and motor speed of the air compressor in the air compressor system, the opening time of the gas-using equipment, the closing time of the gas-using equipment, and the change information of the gas demand of the gas-using equipment to obtain the key operation data in the air compressor system and the relevant information of the gas-using equipment.

3. The energy-saving optimization method for an air compressor system based on data analysis and modeling according to claim 1, characterized in that: The above S2. Preprocess the key operation data in the air compressor system and the relevant information of the gas-using equipment to obtain the preprocessed key operation data and the relevant information of the gas-using equipment, including the following steps: S2.

1. Denoise the key operation data in the air compressor system and the information related to the gas-using equipment, and then remove the abnormal values from the key operation data and the information related to the gas-using equipment in the air compressor system after denoising, to obtain the key operation data and the information related to the gas-using equipment after removing the abnormal values; S2.

2. Smooth the key operation data and the information related to the gas-using equipment after removing the abnormal values by using the data smoothing algorithm, and then perform standardization and normalization processing on the key operation data and the information related to the gas-using equipment after smoothing, to obtain the key operation data and the information related to the gas-using equipment after preprocessing.

4. The energy-saving optimization method for the air compressor system based on data analysis and modeling according to claim 1, characterized in that: S3. Use machine learning algorithms to construct a data model and a smart prediction model, and based on the trained data model, the trained smart prediction model, the preprocessed key operation data, and the preprocessed information related to the gas-using equipment, construct a relationship model between the operation state and energy consumption of the air compressor system, including the following steps: S3.

1. Use the DeepAR deep learning model to construct a data model, and input the preprocessed key operation data and the information related to the gas-using equipment into the data model for training, to obtain the trained data model; S3.

2. Use the polynomial regression algorithm to construct a smart prediction model, and input the preprocessed key operation data and the information related to the gas-using equipment into the smart prediction model for training, to obtain the trained smart prediction model; S3.

3. Based on the trained smart prediction model, the trained data model, the preprocessed key operation data, and the preprocessed information related to the gas-using equipment, construct a relationship model between the operation state and energy consumption of the air compressor system.

5. The energy-saving optimization method for an air compressor system based on data analysis and modeling according to claim 4, characterized in that: The data model includes: Single-machine model. The single-machine model is used to perform data analysis on two variable-frequency machines, explore the relationship between the standard flow rate and the gas-electricity ratio in the variable-frequency machines, and then fit the relationship by establishing a model to obtain the optimal operation range of the frequency conversion; Total-station model. The total-station model is used to perform data analysis on the main pipe pressure and the main pipe flow rate of the air compressor station, and fit the relationship between the two by establishing a model to obtain a model for predicting the future main pipe flow rate.

6. The energy-saving optimization method for an air compressor system based on data analysis and modeling according to claim 1, characterized in that: S5. Based on the analysis results of the correlation between the standard flow rate of the air compressor and the gas-electricity ratio and the analysis of the regression curve of the variable-frequency air compressor, and by using the deep learning algorithm to construct a relationship model between the main pipe flow rate and the main pipe pressure of the air compressor system, and then based on the formulated energy-saving optimization strategy and the relationship model between the main pipe flow rate and the main pipe pressure of the air compressor system, implement the energy-saving optimization strategy of the air compressor system, including the following steps: S5.

1. Analyze the correlation between the standard flow rate of the air compressor and the gas-electricity ratio in the air compressor system to obtain the analysis results of the correlation between the standard flow rate of the air compressor and the gas-electricity ratio; S5.

2. Analyze the regression curve of the variable-frequency air compressor in the air compressor system to obtain the analysis results of the regression curve of the variable-frequency air compressor; S5.

3. Based on the analysis results of the regression curve of the variable-frequency air compressor, the analysis results of the correlation between the standard flow rate of the air compressor and the gas-electricity ratio, and by using the deep learning algorithm, construct a relationship model between the main pipe flow rate and the main pipe pressure of the air compressor system; S5.

4. Based on the relationship model between the main pipe flow rate and the main pipe pressure of the air compressor system and the formulated energy-saving optimization strategy, implement the energy-saving optimization strategy of the air compressor system.

7. The air compressor system energy-saving optimization device based on data analysis and modeling according to any one of claims 1-6, comprising: A data acquisition module, which is used to collect the operation data at each key part in the air compressor system and the relevant information of the gas-using equipment, and obtain the key operation data and the relevant information of the gas-using equipment in the air compressor system; A data preprocessing module, which is connected to the data acquisition module through a database. The data preprocessing module is used to preprocess the key operation data and the relevant information of the gas-using equipment in the air compressor system, and obtain the preprocessed key operation data and the relevant information of the gas-using equipment; A data analysis module, which is connected to the data preprocessing module. The data analysis module is used to construct a data model and an intelligent prediction model with machine learning algorithms, and based on the trained data model, the trained intelligent prediction model, the preprocessed key operation data and the preprocessed relevant information of the gas-using equipment, construct a relationship model between the operation state and the energy consumption of the air compressor system; An energy-saving optimization strategy module, which is connected to the data analysis module. The energy-saving optimization strategy module is used to collect the operation data in the air compressor system in real time, input the collected operation data into the relationship model between the operation state and the energy consumption of the air compressor system for prediction, and based on the predicted energy consumption under different operating conditions, formulate an energy-saving optimization strategy; An energy-saving optimization strategy implementation module, which is connected to the energy-saving optimization strategy module. The energy-saving optimization strategy implementation module is used to analyze the correlation between the standard cubic flow rate of the air compressor and the gas-electricity ratio and the regression curve of the variable-frequency air compressor, and construct a relationship model between the main pipe flow rate and the main pipe pressure of the air compressor system through a deep learning algorithm. Then, based on the formulated energy-saving optimization strategy and the relationship model between the main pipe flow rate and the main pipe pressure of the air compressor system, implement the energy-saving optimization strategy of the air compressor system.

8. The air compressor system energy-saving optimization device based on data analysis and modeling according to any one of claim 7 further includes an execution module, which is connected to the energy-saving optimization strategy implementation module. The execution module is used to convert the energy-saving optimization strategy of the air compressor system implemented in the energy-saving optimization strategy implementation module into control instructions and send them to the controller of the air compressor system for automatic control of equipment such as air compressors and valves.

Images