Energy-saving control method and device for gas compressor and medium

Abstract

The invention discloses an energy-saving control method and device for a gas compressor and a medium. The method comprises the steps that historical operation data of a gas compressor are collected, and the historical operation data comprise compressor operation parameters, environment parameters, gas parameters and pipe network operation parameters; training a compressor performance model, a load prediction model and an energy efficiency optimization model according to the preprocessed historical operation data; performing operation data prediction according to the collected real-time operation data by using a compressor performance model, a load prediction model and an energy efficiency optimization model to obtain predicted operation data in a future predetermined time period; calculating the predicted operation data by adopting a non-dominated sorting genetic algorithm, and determining an optimal operation scheme; and the control parameters of the optimal operation scheme are issued to control systems of all the compressors for energy-saving control over the compressors.

Description

Technical Field

[0001] The present invention relates to the technical field of compressor energy-saving control, and more specifically, to a gas compressor energy-saving control method, device and medium. Background Art

[0002] Gas compressors are important core power equipment in industrial production and are widely used in many fields such as petroleum, natural gas, and chemicals for gas pressurization, transportation, and process. In the process of energy transportation and conversion, the pressure increase of gas is crucial to ensure stable and effective gas transmission. As a key node in the gas transportation network, the gas compression station uses a gas compressor to increase the low-pressure gas to the required pressure to meet long-distance transportation or process requirements. With the rapid growth of my country's industrial demand and the continuous expansion of the transportation network, the energy efficiency optimization of compression stations has also received more and more attention. The operating efficiency of the compression station directly affects the cost and energy consumption of gas transportation. Therefore, how to improve the energy efficiency level of gas compressors has become a focus of industry attention.

[0003] In a gas compression station, the energy efficiency of the gas compressor is affected by many factors, including intake pressure, exhaust pressure, compression ratio, flow rate, ambient temperature, gas composition, etc. Traditional compressor control methods often find it difficult to achieve optimal energy efficiency under complex and changeable working conditions, especially when gas demand fluctuates greatly and upstream gas source pressure changes frequently.

[0004] Invention patent CN 115750426 A adopts a compressor control system based on PID algorithm + manual experience. The system mainly controls the exhaust pressure of the compressor by adjusting the opening of the compressor's intake valve or the frequency of the inverter, thereby meeting the pressure requirements of the downstream pipeline network. The system first selects the maximum opening value as the final opening size of the anti-surge valve through manual setting, anti-surge PID control, and pressure PID control; on the basis of the final opening adjustment of the anti-surge valve, the pressure PID control is adjusted to determine the outlet pressure value, and the centrifugal compressor motor current is adjusted according to the outlet pressure value. The optimal operating condition is selected according to the centrifugal compressor motor current, and finally plays an energy-saving adjustment role. However, there are the following technical problems: (1) Limited energy efficiency optimization capability: PID control mainly focuses on pressure stability and lacks direct optimization of compressor energy efficiency. When the natural gas flow and pressure fluctuate greatly, it is difficult to always keep the compressor running at the optimal efficiency point. (2) Insufficient adaptability: The operating conditions faced by natural gas booster stations are complex, including seasonal demand changes, daily load fluctuations, and upstream gas source pressure fluctuations. The parameters of traditional PID control are difficult to adapt to these complex changes and often require manual intervention and adjustment. (3) Inability to achieve multi-objective optimization: It is difficult to take into account multiple objectives such as flow rate, compression ratio, and energy consumption at the same time when only exhaust pressure is used as the control target. In actual operation, it is necessary to meet the pressure requirements of downstream users while maximizing energy efficiency, which poses a challenge to traditional PID control. (4) Lack of predictive ability: It is impossible to make adjustments in advance based on historical data and natural gas demand forecasts, and it is often a passive response, which makes it difficult to cope with sudden large load forecast results. (5) Insufficient coordination control capabilities: Natural gas booster stations usually contain multiple compressors running in parallel. Traditional methods make it difficult to achieve coordinated optimization control of multiple compressors, which often leads to low overall system operating efficiency. Summary of the invention

[0005] In view of the deficiencies in the prior art, the present invention provides a gas compressor energy-saving control method, device and medium.

[0006] According to one aspect of the present invention, a gas compressor energy-saving control method is provided, comprising: Collect historical operating data of the gas compressor, where the historical operating data includes: compressor operating parameters, environmental parameters, gas parameters and pipeline network operating parameters; Train the compressor performance model, load prediction model and energy efficiency optimization model based on the preprocessed historical operation data; Use the compressor performance model, load prediction model and energy efficiency optimization model to predict operation data based on the collected real-time operation data, and obtain the predicted operation data within the future predetermined time period; The non-dominated sorting genetic algorithm is used to calculate the predicted operation data and determine the optimal operation plan; The control parameters of the optimal operation plan are sent to the control system of each compressor to perform energy-saving control of the compressor.

[0007] Optionally, the compressor operating parameters include intake pressure, outlet pressure, intake temperature, gas flow, compressor speed and shaft power; environmental parameters include ambient temperature and humidity; gas parameters include composition, density and calorific value; and pipeline network operating parameters include downstream historical gas demand and upstream gas supply pressure.

[0008] Optionally, a compressor performance model, a load prediction model, and an energy efficiency optimization model are trained based on the preprocessed historical operation data, including: Perform outlier detection on historical operation data to determine short-term missing data and long-term missing data of historical operation data; The linear difference algorithm is used to complete the short-term missing data, and the historical data of the same period is used to complete the long-term missing data to determine the pre-processed historical operation data; Perform feature extraction on the preprocessed historical operation data to obtain a feature data set, wherein the feature data set includes compressor efficiency, weather model, and load factor; The Min-Max standardization method is used to standardize the feature data set and the pre-processed historical operation data; The random forest algorithm is used to generate a load forecasting model with standardized network operation parameters, environmental parameters, compressor efficiency, load rate and seasonal time characteristics as input and the load forecast results for the next 24 hours as output; A neural network model is used to generate a compressor performance model with standardized compressor operating parameters, environmental parameters and gas parameters as input and the compressor compression ratio prediction result as output; An XGBoost-based regression model is used to generate an energy efficiency optimization model with load prediction results, compression ratio prediction results, standardized compressor operating parameters, environmental parameters and gas parameters as input and system comprehensive energy consumption as output.

[0009] Optionally, the optimization objective of the non-dominated sorting genetic algorithm is: Min F = (f1, f2, f3) Where, f1 = E; f2 = |P - P_target|; f3 = σ(L); E is the total energy consumption of the system; P is the actual outlet pressure; P_target is the target outlet pressure; σ(L) is the standard deviation of the load rate of each compressor; The constraints of the non-dominated sorting genetic algorithm are: minimizing energy consumption, stabilizing exhaust pressure, and balancing equipment load.

[0010] Optionally, the control parameters of the optimal operation scheme are sent to the control system of each compressor to perform energy-saving control of the compressor, including: The control parameters of the optimal operation scheme are sent to each compressor through the OPC protocol, where the control parameters include the start / stop status and the speed setting value; Each compressor uses a slow and gradual method to adjust parameters until the control parameters are reached to achieve energy-saving control.

[0011] Optionally, it also includes: The real-time operating parameters of the compressor within a preset time are collected in real time to update and optimize the compressor performance model, load prediction model and energy efficiency optimization model.

[0012] According to another aspect of the present invention, there is provided a gas compressor energy-saving control device, comprising: A collection module is used to collect historical operation data of the gas compressor, wherein the historical operation data includes: compressor operation parameters, environmental parameters, gas parameters and pipeline network operation parameters; A training module, used for training a compressor performance model, a load prediction model and an energy efficiency optimization model based on preprocessed historical operation data; A prediction module is used to predict operation data based on the collected real-time operation data using a compressor performance model, a load prediction model, and an energy efficiency optimization model, and obtain predicted operation data within a future predetermined time period; A calculation module is used to calculate the predicted operation data using a non-dominated sorting genetic algorithm to determine the optimal operation plan; The control module is used to send the control parameters of the optimal operation plan to the control system of each compressor to perform energy-saving control of the compressor.

[0013] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the storage medium stores a computer program, and the computer program is used to execute the method described in any one of the above aspects of the present invention.

[0014] According to another aspect of the present invention, an electronic device is provided, comprising: a processor; a memory for storing instructions executable by the processor; the processor is configured to read the executable instructions from the memory and execute the instructions to implement the method described in any one of the above aspects of the present invention.

[0015] Therefore, the present invention realizes adaptive optimization control of the gas compressor group by combining data-driven and intelligent algorithms, can effectively cope with complex and changeable operating conditions, and significantly improve the energy efficiency level and operational reliability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] A more complete understanding of exemplary embodiments of the present invention may be obtained by referring to the following drawings: Figure 1 is a flow chart of a gas compressor energy-saving control method provided by an exemplary embodiment of the present invention; Figure 2 is another flow chart of a gas compressor energy-saving control method provided by an exemplary embodiment of the present invention; Figure 3 It is a schematic diagram of a specific implementation of a gas compressor energy-saving control method provided by an exemplary embodiment of the present invention; Figure 4 is a structural schematic diagram of a gas compressor energy-saving control device provided by an exemplary embodiment of the present invention; Figure 5 This is a structure of an electronic device provided by an exemplary embodiment of the present invention. DETAILED DESCRIPTION

[0017] Below, the exemplary embodiments according to the present invention will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments of the present invention, and it should be understood that the present invention is not limited to the exemplary embodiments described here.

[0018] It should be noted that the relative arrangement of components and steps, the numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present invention unless specifically stated otherwise.

[0019] Those skilled in the art can understand that the terms "first" and "second" in the embodiments of the present invention are only used to distinguish different steps, devices or modules, etc., and neither represent any specific technical meaning nor indicate the necessary logical order between them.

[0020] It should also be understood that, in the embodiments of the present invention, “plurality” may refer to two or more than two, and “at least one” may refer to one, two or more than two.

[0021] It should also be understood that any component, data or structure mentioned in the embodiments of the present invention can generally be understood as one or more, unless explicitly limited or otherwise indicated in the context.

[0022] In addition, the term "and / or" in the present invention is only a description of the association relationship of the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in the present invention generally indicates that the associated objects before and after are in an "or" relationship.

[0023] It should also be understood that the description of the various embodiments of the present invention focuses on the differences between the various embodiments, and the same or similar aspects thereof can be referenced to each other, and for the sake of brevity, they will not be described one by one.

[0024] At the same time, it should be understood that for the convenience of description, the sizes of the various parts shown in the drawings are not drawn according to the actual proportional relationship.

[0025] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the invention, its application, or uses.

[0026] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods, and equipment should be considered part of the specification.

[0027] It should be noted that like reference numerals and letters refer to similar items in the following figures, and therefore, once an item is defined in one figure, it need not be further discussed in subsequent figures.

[0028] Embodiments of the present invention can be applied to electronic devices such as terminal devices, computer systems, servers, etc., which can operate with many other general or special computing system environments or configurations. Examples of well-known terminal devices, computing systems, environments and / or configurations suitable for use with electronic devices such as terminal devices, computer systems, servers, etc. include, but are not limited to: personal computer systems, server computer systems, thin clients, thick clients, handheld or laptop devices, microprocessor-based systems, set-top boxes, programmable consumer electronics, network personal computers, small computer systems, large computer systems, and distributed cloud computing technology environments including any of the above systems, etc.

[0029] Electronic devices such as terminal devices, computer systems, servers, etc. can be described in the general context of computer system executable instructions (such as program modules) executed by computer systems. Generally, program modules can include routines, programs, object programs, components, logic, data structures, etc., which perform specific tasks or implement specific abstract data types. Computer systems / servers can be implemented in a distributed cloud computing environment, where tasks are performed by remote processing devices linked through a communication network. In a distributed cloud computing environment, program modules can be located on local or remote computing system storage media including storage devices.

[0030] Exemplary Methods Figure 1 1 is a flow chart of a gas compressor energy-saving control method provided by an exemplary embodiment of the present invention. The present invention can be applied to electronic devices, such as Figure 1As shown, the gas compressor energy-saving control method 100 includes the following steps: Step 101, collecting historical operating data of the gas compressor, wherein the historical operating data includes: compressor operating parameters, environmental parameters, gas parameters and pipeline network operating parameters; Step 102, training a compressor performance model, a load prediction model, and an energy efficiency optimization model based on the preprocessed historical operation data; Step 103, using the compressor performance model, the load prediction model and the energy efficiency optimization model to perform operation data prediction based on the collected real-time operation data, and obtain the predicted operation data within a future predetermined time period; Step 104, using a non-dominated sorting genetic algorithm to calculate the predicted operation data and determine the optimal operation plan; Step 105: Send the control parameters of the optimal operation solution to the control system of each compressor to perform energy-saving control on the compressor.

[0031] Specifically, refer to Figure 2 As shown, the overall technical solution of the gas compressor group control optimization method proposed by the present invention is as follows: (1) Data acquisition module: real-time collection of various operating data of the gas booster station, including but not limited to: compressor operating parameters: inlet and outlet pressure, temperature, flow, speed, power, etc.; environmental parameters: ambient temperature, humidity, etc.; gas parameters: composition, density, calorific value, etc.; pipeline network operating data: upstream gas pressure, downstream user demand, etc.

[0032] (2) Data preprocessing module: Cleans, screens and standardizes the collected raw data, including: outlier detection and processing; data completion; feature extraction and selection; and data standardization.

[0033] (3) Model training module: Based on the preprocessed historical data, multiple machine learning models are trained: Compressor performance model: describes the performance characteristics of the compressor under different working conditions; Load forecasting model: predicting changes in gas demand in the short term; Energy efficiency optimization model: Establish a relationship model between compressor operating parameters and energy efficiency.

[0034] (4) Prediction and Optimization Module: Use load forecasting models to predict gas demand in the future; Combining the compressor performance model and energy efficiency optimization model, an intelligent optimization algorithm (such as the non-dominated sorting genetic algorithm NSGA-II) is used to calculate the optimal operation plan; Optimization goals include: minimizing energy consumption, stabilizing exhaust pressure, balancing equipment load, etc. Output optimized control parameters: start / stop status, speed, air intake volume, etc. of each compressor.

[0035] (5) Control execution module: Receiving control parameters output by the optimization module; Send control instructions to the control systems of each compressor; Monitor the execution effect in real time and feed back the actual operation data to the data acquisition module.

[0036] (6) Model update and optimization: Regularly update each model with newly collected operational data to ensure model accuracy and adaptability; According to the actual operation results, the parameters and constraints of the optimization algorithm are continuously adjusted.

[0037] Implementation process: The system continuously collects real-time operation data through the data acquisition module.

[0038] After the collected data is processed by the preprocessing module, part of it is used for real-time optimization control, and the other part is stored in the historical database for model training.

[0039] The model training module retrains each model using updated historical data periodically or when significant operating condition changes are detected.

[0040] The predictive optimization module calculates the optimal operation plan based on the latest model, combining the current operating status and predicted future load.

[0041] The control execution module sends the optimized control parameters to each compressor and monitors the execution effect.

[0042] The system continuously cycles the above process, constantly optimizing the control strategy to achieve efficient operation of the compressor group.

[0043] This solution realizes adaptive optimization control of gas compressor groups through the combination of data-driven and intelligent algorithms. It can effectively cope with complex and changeable operating conditions and significantly improve the energy efficiency and operational reliability of the system.

[0044] refer to Figure 3 As shown, taking a mid-section booster station of a long-distance gas pipeline (for example, natural gas) as an example, the technical solution of this application is implemented, and the specific contents are as follows: Background information: The booster station is equipped with three centrifugal compressors, each with a designed flow rate of 500,000 cubic meters per day; upstream gas pressure range: 1.5-5.0 MPa; downstream pipeline network required pressure: <=9.15 MPa; the station is equipped with a SCADA system to collect various operating data in real time.

[0045] The specific implementation steps are as follows: 1. Data collection: The solution of the present invention first expands the data collection scope of the existing SCADA system and adds the following data points: (1) Compressor operating parameters: inlet and outlet pressures and temperatures (1 second / time); shaft power and speed (1 second / time); air intake volume (1 minute / time); bearing temperature and vibration (5 minutes / time).

[0046] (2) Environmental parameters: ambient temperature and humidity (10 minutes / time).

[0047] (3) Gas parameters: composition (daily); density, calorific value (hourly).

[0048] (4) Pipeline network operation data: upstream gas pressure (1 minute / time); downstream user flow demand (5 minutes / time).

[0049] 2. Data preprocessing: (1) Outlier detection: Detect outliers using statistical and machine learning based methods (isolation forest algorithm).

[0050] (2) Data completion: For short-term missing data, linear interpolation is used to complete the data; for long-term missing data, historical data from the same period are used to complete the data.

[0051] (3) Feature extraction: Calculate compressor efficiency; extract weather patterns (weekdays / holidays); calculate derived features such as load factor.

[0052] (4) Data standardization: The Min-Max standardization method is used to map each eigenvalue to the [0,1] interval.

[0053] 3. Model training: (1) Compressor performance model: The random forest algorithm is used, with compressor operating parameters: intake pressure, intake temperature, gas flow, compressor speed, shaft power; environmental parameters: ambient temperature, humidity; and gas parameters: composition, density, calorific value as input; output characteristics: compression ratio (2) Load forecasting model: Using the LSTM neural network, the input features are: historical downstream gas demand; upstream gas supply pressure; ambient temperature and humidity; compressor start and stop status and frequency; seasonal time characteristics.

[0054] Output characteristics: Gas demand in the next 24 hours.

[0055] (3) Energy efficiency optimization model: A regression model based on XGBoost was established, with the following input features: load prediction results; compressor performance model output value; compressor operating parameters: intake pressure, intake temperature, gas flow, compressor speed, shaft power; environmental parameters: ambient temperature, humidity; and gas parameters: composition, density, calorific value. Output feature: comprehensive energy consumption.

[0056] 4. Prediction Optimization (1) Load forecast: The load forecast for the next 24 hours is updated every hour.

[0057] (2) Optimization algorithm: The improved non-dominated sorting genetic algorithm NSGA-II algorithm is used, and the optimization objective function is: Min F = (f1, f2, f3) Where: f1 = E; f2 = |P - P_target|; f3 = σ(L); E: total system energy consumption; P: actual outlet pressure; P_target: target outlet pressure; σ(L): standard deviation of each compressor load factor.

[0058] Constraints: Compressor operating range limitations; system flow balance; pressure limitations.

[0059] (3) Optimization cycle: Under normal circumstances, optimization is performed every 15 minutes. When a large load change is detected, optimization is triggered immediately.

[0060] 5. Control Execution: (1) Control command issuance: The optimized parameters (start / stop status, speed setting value, etc.) are sent to each compressor PLC through the OPC protocol. The parameters are adjusted in a slow and gradual manner to avoid drastic fluctuations.

[0061] (2) Execution monitoring: Real-time monitoring of the response of each compressor. If an abnormality is detected (such as excessive execution deviation), an alarm is triggered and the control scheme is switched to the backup scheme.

[0062] 6. Model update and optimization: (1) Regular updates: Retrain each model using the latest data every week. Evaluate model performance every month and adjust model structure if necessary.

[0063] (2) Adaptive optimization: Dynamically adjust the weight coefficient of the optimization algorithm according to the actual operation results. Introduce reinforcement learning methods to continuously optimize the control strategy.

[0064] Implementation effect: By deploying the solution of the present invention, the gas booster station achieved remarkable results during the three-month trial operation period: 1. Reduced energy consumption: The overall energy consumption of the system is reduced by about 8.5% compared with the original solution.

[0065] 2. Improved pressure stability: The outlet pressure fluctuation range is reduced from ±0.3MPa to ±0.1MPa.

[0066] 3. Improved equipment utilization: The average load factor of the compressor increased from 65% to 78%.

[0067] 4. Improved operation and maintenance efficiency: The system automation level has been significantly improved, and the number of manual interventions has been reduced by 60%.

[0068] The present invention demonstrates the feasibility and effectiveness of the solution in practical applications. Through the combination of data-driven and intelligent algorithms, efficient coordinated control of gas compressor groups is achieved, providing a new solution for energy conservation, emission reduction and intelligent transformation in the industry.

[0069] This application solves the following technical problems: 1. Insufficient energy efficiency optimization: Existing technologies mainly focus on pressure control, which makes it difficult to achieve global optimization of energy efficiency.

[0070] The present invention achieves a significant reduction (8.5%) in system energy consumption by establishing a compressor performance model and an energy efficiency optimization model in combination with an intelligent optimization algorithm.

[0071] Improve energy efficiency optimization capabilities: The present invention aims to develop a control method that can optimize the compressor operating parameters in real time, so that the compressor can maintain an efficient operating state under various operating conditions, thereby significantly improving the overall energy efficiency level of the gas boosting station.

[0072] 2. Poor adaptability: Traditional PID control is difficult to adapt to complex and changing working conditions.

[0073] The present invention adopts a machine learning model, which can adaptively adjust the control strategy and effectively cope with load fluctuations and changes in operating conditions.

[0074] Enhance system adaptability: By introducing machine learning and intelligent algorithms, the control system can adaptively adjust the control strategy to adapt to various complex operating conditions faced by the gas booster station, such as seasonal demand fluctuations, daily load forecast results, upstream gas source pressure fluctuations, etc.

[0075] 3. Insufficient multi-objective optimization capabilities: Existing technologies often focus on a single objective (e.g., pressure stabilization).

[0076] The present invention achieves an improvement in comprehensive performance by adopting a multi-objective optimization algorithm while taking into account energy consumption, pressure stability and equipment load balance.

[0077] Achieving multi-objective optimization: One of the objectives of the present invention is to develop a control method that can simultaneously consider multiple optimization objectives, including but not limited to exhaust pressure stability, system energy consumption, equipment life, etc., so as to maximize system operating efficiency while meeting downstream user needs.

[0078] 4. Lack of predictive ability: Traditional methods are mostly passive responses, making it difficult to respond to changes in operating conditions in advance.

[0079] The present invention introduces a load prediction model, which can predict load changes 24 hours in advance and realize active optimization control.

[0080] Providing predictive control capabilities: By integrating historical data analysis and load forecasting technology, the present invention aims to predict gas demand and operating condition changes, so that the control system can make adjustments in advance, achieve active optimization control, and improve the system's ability to respond to sudden load forecast results.

[0081] 5. Insufficient coordination and control capabilities: It is difficult to achieve coordinated optimization of multiple compressors using existing technologies.

[0082] The present invention realizes the coordinated control of the compressor group through a global optimization algorithm, thereby improving the equipment utilization rate (from 65% to 78%).

[0083] Optimizing coordinated control of compressor groups: In view of the situation where multiple compressors operate in parallel, the present invention aims to propose a control strategy that can achieve coordinated optimization of compressor groups, thereby improving the system efficiency of the entire booster station by reasonably distributing loads and optimizing operating parameters.

[0084] 6. High dependence on human intervention: Traditional methods require frequent manual adjustments and interventions.

[0085] The present invention significantly improves the automation level and reduces the number of manual interventions by 60%.

[0086] Reduce the need for human intervention: By introducing intelligent decision-making algorithms, the present invention aims to reduce the reliance on human intervention during system operation, improve the level of automation, and reduce operation and maintenance costs.

[0087] 7. The pressure control accuracy is limited: It is difficult to accurately control the outlet pressure with existing technology.

[0088] The present invention reduces the pressure fluctuation range from ±0.3MPa to ±0.1MPa, thereby greatly improving the pressure stability.

[0089] 8. Data value is not fully explored: Traditional methods do not fully utilize historical operating data.

[0090] The present invention fully taps the value of data through machine learning algorithms and achieves continuous optimization of the model.

[0091] Realizing data value mining: Another purpose of the present invention is to make full use of the massive operating data accumulated by the booster station, and continuously optimize the control model and improve system performance through data mining and analysis.

[0092] 9. System reliability needs to be improved: Existing technologies may cause equipment to start and stop frequently, affecting system reliability.

[0093] The present invention reduces unnecessary equipment starts and stops and improves system stability by optimizing the control strategy.

[0094] Improve system reliability: By optimizing the control strategy, the present invention aims to reduce the frequent start and stop of the compressor and the drastic changes in operating conditions, extend the life of the equipment, and improve the overall reliability of the system.

[0095] 10. Lack of intelligence and self-learning capabilities: Traditional methods lack the ability to continuously learn and self-optimize.

[0096] The present invention introduces adaptive optimization and reinforcement learning methods, so that the system has the ability of continuous improvement.

[0097] Adapting to the needs of intelligent transformation: In line with the trend of digital and intelligent transformation in the energy industry, the present invention aims to provide a smart control solution with learning and continuous optimization capabilities for gas boosting stations.

[0098] Therefore, the present invention realizes adaptive optimization control of the gas compressor group by combining data-driven and intelligent algorithms, can effectively cope with complex and changeable operating conditions, and significantly improve the energy efficiency level and operational reliability of the system.

[0099] Exemplary Devices Figure 4 FIG. 1 is a schematic diagram of a gas compressor energy-saving control device provided by an exemplary embodiment of the present invention. Figure 4 As shown, the device 400 includes: The acquisition module 410 is used to acquire historical operation data of the gas compressor, wherein the historical operation data includes: compressor operation parameters, environmental parameters, gas parameters and pipeline network operation parameters; A training module 420, for training a compressor performance model, a load prediction model and an energy efficiency optimization model according to the preprocessed historical operation data; The prediction module 430 is used to use the compressor performance model, the load prediction model and the energy efficiency optimization model to predict the operation data according to the collected real-time operation data, and obtain the predicted operation data within a predetermined time period in the future; A calculation module 440 is used to calculate the predicted operation data using a non-dominated sorting genetic algorithm to determine the optimal operation plan; The control module 450 is used to send the control parameters of the optimal operation scheme to the control system of each compressor to perform energy-saving control on the compressor.

[0100] Optionally, the compressor operating parameters include intake pressure, outlet pressure, intake temperature, gas flow, compressor speed and shaft power; environmental parameters include ambient temperature and humidity; gas parameters include composition, density and calorific value; and pipeline network operating parameters include downstream historical gas demand and upstream gas supply pressure.

[0101] Optionally, the training module 420 includes: The detection submodule is used to detect outliers in historical operation data and determine short-term missing data and long-term missing data of historical operation data; The completion submodule is used to complete the short-term missing data using a linear interpolation algorithm, and to complete the long-term missing data using historical data from the same period, and to determine the pre-processed historical operation data; A feature extraction submodule is used to extract features from the preprocessed historical operation data to obtain a feature data set, wherein the feature data set includes compressor efficiency, weather model, and load factor; The standardization submodule is used to standardize the feature data set and the preprocessed historical operation data using the Min-Max standardization method; The first generation submodule is used to generate a load forecasting model by using a random forest algorithm, taking standardized pipe network operation parameters, environmental parameters, compressor efficiency, load rate and seasonal time characteristics as inputs and taking the load forecast results for the next 24 hours as outputs; The second generation submodule is used to generate a compressor performance model by using a neural network model, taking the standardized compressor operating parameters, environmental parameters and gas parameters as inputs and taking the compression ratio prediction result of the compressor as output; The third generation submodule is used to use an XGBoost-based regression model, with load prediction results, compression ratio prediction results, standardized compressor operating parameters, environmental parameters and gas parameters as input, and system comprehensive energy consumption as output to generate an energy efficiency optimization model.

[0102] Optionally, the optimization objective of the non-dominated sorting genetic algorithm is: Min F = (f1, f2, f3) Where, f1 = E; f2 = |P - P_target|; f3 = σ(L); E is the total energy consumption of the system; P is the actual outlet pressure; P_target is the target outlet pressure; σ(L) is the standard deviation of the load rate of each compressor; The constraints of the non-dominated sorting genetic algorithm are: minimizing energy consumption, stabilizing exhaust pressure, and balancing equipment load.

[0103] Optionally, the control module 450 includes: The sending submodule is used to send the control parameters of the optimal operation scheme to each compressor through the OPC protocol, where the control parameters include the start / stop status and the speed setting value; The control submodule is used to adjust the parameters of each compressor in a slow and gradual manner until the control parameters are reached to achieve energy-saving control.

[0104] Optionally, the apparatus 400 further includes: The optimization module is used to collect the real-time operating parameters of the compressor within a preset time to update and optimize the compressor performance model, load prediction model and energy efficiency optimization model.

[0105] Exemplary Electronic Devices Figure 5 This is a structure of an electronic device provided by an exemplary embodiment of the present invention. Figure 5 As shown, the electronic device 50 includes one or more processors 51 and a memory 52 .

[0106] The processor 51 may be a central processing unit (CPU) or other forms of processing units having data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device to perform desired functions.

[0107] The memory 52 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, a random access memory (RAM) and / or a cache memory (cache), etc. The non-volatile memory may include, for example, a read-only memory (ROM), a hard disk, a flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 51 may run the program instructions to implement the methods of the software programs of the various embodiments of the present invention described above and / or other desired functions. In one example, the electronic device may also include: an input device 53 and an output device 54, which are interconnected via a bus system and / or other forms of connection mechanisms (not shown).

[0108] In addition, the input device 53 may also include, for example, a keyboard, a mouse, etc.

[0109] The output device 54 can output various information to the outside. The output device 54 can include, for example, a display, a speaker, a printer, a communication network and a remote output device connected thereto.

[0110] Of course, to simplify, Figure 5 Only some of the components related to the present invention in the electronic device are shown, and components such as a bus, an input / output interface, etc. are omitted. In addition, the electronic device may further include any other appropriate components according to specific application conditions.

[0111] Exemplary computer program products and computer-readable storage media In addition to the above-mentioned methods and devices, an embodiment of the present invention may also be a computer program product, which includes computer program instructions, which, when executed by a processor, enable the processor to execute the steps of the method according to various embodiments of the present invention described in the above-mentioned "Exemplary Method" section of this specification.

[0112] The computer program product may be written in any combination of one or more programming languages ​​to write program code for performing the operations of the embodiments of the present invention, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0113] In addition, an embodiment of the present invention may also be a computer-readable storage medium having computer program instructions stored thereon, which, when executed by a processor, enable the processor to execute the steps of the method according to various embodiments of the present invention described in the above “Exemplary Method” section of this specification.

[0114] The computer readable storage medium can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can include, for example, but is not limited to, a system, system or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0115] The basic principle of the present invention is described above in conjunction with specific embodiments. However, it should be pointed out that the advantages, strengths, effects, etc. mentioned in the present invention are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. must be possessed by each embodiment of the present invention. In addition, the specific details disclosed above are only for the purpose of illustration and facilitation of understanding, rather than limitation, and the above details do not limit the present invention to being implemented by adopting the above specific details.

[0116] Each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the system embodiment, since it basically corresponds to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0117] The block diagrams of the devices, systems, equipment, and systems involved in the present invention are only illustrative examples and are not intended to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagram. As will be appreciated by those skilled in the art, these devices, systems, equipment, and systems can be connected, arranged, and configured in any manner. Words such as "including", "comprising", "having", etc. are open words, referring to "including but not limited to", and can be used interchangeably with them. The words "or" and "and" used here refer to the words "and / or" and can be used interchangeably with them, unless the context clearly indicates otherwise. The word "such as" used here refers to the phrase "such as but not limited to", and can be used interchangeably with it.

[0118] The method and system of the present invention may be implemented in many ways. For example, the method and system of the present invention may be implemented by software, hardware, firmware or any combination of software, hardware, firmware. The above order of steps for the method is only for illustration, and the steps of the method of the present invention are not limited to the order specifically described above, unless otherwise specifically stated. In addition, in some embodiments, the present invention may also be implemented as a program recorded in a recording medium, which includes machine-readable instructions for implementing the method according to the present invention. Thus, the present invention also covers a recording medium storing a program for executing the method according to the present invention.

[0119] It should also be noted that in the system, device and method of the present invention, each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent schemes of the present invention. The above description of the disclosed aspects is provided to enable any technician in the field to make or use the present invention. Various modifications to these aspects are very obvious to those skilled in the art, and the general principles defined here can be applied to other aspects without departing from the scope of the present invention. Therefore, the present invention is not intended to be limited to the aspects shown here, but in accordance with the widest range consistent with the principles and novel features disclosed here.

[0120] The above description has been given for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present invention to the forms disclosed herein. Although a number of example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions and sub-combinations thereof.

Claims

1. A gas compressor energy-saving control method, characterized in that: include: Collecting historical operating data of the gas compressor, wherein the historical operating data includes: compressor operating parameters, environmental parameters, gas parameters and pipeline network operating parameters; Train the compressor performance model, load prediction model and energy efficiency optimization model based on the preprocessed historical operation data; Using the compressor performance model, the load prediction model and the energy efficiency optimization model to predict operation data according to the collected real-time operation data, and obtain predicted operation data within a future predetermined time period; Using a non-dominated sorting genetic algorithm to calculate the predicted operation data to determine the optimal operation plan; The control parameters of the optimal operation scheme are sent to the control system of each compressor to perform energy-saving control of the compressor.

2. The method according to claim 1, characterized in that The compressor operating parameters include intake pressure, outlet pressure, intake temperature, gas flow, compressor speed and shaft power; the environmental parameters include ambient temperature and humidity; the gas parameters include composition, density and calorific value; the pipeline network operating parameters include downstream historical gas demand and upstream gas supply pressure.

3. The method according to claim 2, characterized in that The compressor performance model, load prediction model and energy efficiency optimization model are trained based on the pre-processed historical operation data, including: Performing outlier detection on the historical operation data to determine short-term missing data and long-term missing data of the historical operation data; A linear interpolation algorithm is used to complete the short-term missing data, and historical data from the same period is used to complete the long-term missing data, to determine the pre-processed historical operation data; Performing feature extraction on the preprocessed historical operation data to obtain a feature data set, wherein the feature data set includes compressor efficiency, weather model, and load factor; The Min-Max standardization method is used to standardize the characteristic data set and the pre-processed historical operation data; The load forecasting model is generated by using a random forest algorithm, with the standardized pipe network operation parameters, environmental parameters, the compressor efficiency, load rate and seasonal time characteristics as inputs and the load forecasting result for the next 24 hours as output; A neural network model is used, with the standardized compressor operating parameters, environmental parameters and gas parameters as input and the compression ratio prediction result of the compressor as output to generate the compressor performance model; The energy efficiency optimization model is generated by adopting a regression model based on XGBoost, taking load prediction results, compression ratio prediction results, standardized compressor operating parameters, environmental parameters and gas parameters as inputs, and taking system comprehensive energy consumption as output.

4. The method according to claim 1, characterized in that: The optimization goal of the non-dominated sorting genetic algorithm is: Min F = (f1, f2, f3) Where, f1 = E; f2 = |P - P_target|; f3 = σ(L); E is the total energy consumption of the system; P is the actual outlet pressure; P_target is the target outlet pressure; σ(L) is the standard deviation of the load rate of each compressor; The constraints of the non-dominated sorting genetic algorithm are: minimizing energy consumption, stabilizing exhaust pressure, and balancing equipment load.

5. The method according to claim 1, characterized in that The control parameters of the optimal operation scheme are sent to the control system of each compressor to perform energy-saving control of the compressor, including: Sending the control parameters of the optimal operation scheme to each compressor through the OPC protocol, wherein the control parameters include the start / stop state and the speed setting value; Each compressor adjusts parameters in a slow and gradual manner until the control parameters are reached to achieve energy-saving control.

6. The method according to claim 1, characterized in that Also includes: The real-time operating parameters of the compressor within a preset time are collected in real time to update and optimize the compressor performance model, load prediction model and energy efficiency optimization model.

7. A gas compressor energy-saving control device, characterized in that: include: A collection module, used to collect historical operation data of the gas compressor, wherein the historical operation data includes: compressor operation parameters, environmental parameters, gas parameters and pipeline network operation parameters; A training module, used for training a compressor performance model, a load prediction model and an energy efficiency optimization model based on preprocessed historical operation data; A prediction module, used to use the compressor performance model, the load prediction model and the energy efficiency optimization model to perform operation data prediction according to the collected real-time operation data, and obtain the predicted operation data within a future predetermined time period; A calculation module, used to calculate the predicted operation data using a non-dominated sorting genetic algorithm to determine an optimal operation plan; The control module is used to send the control parameters of the optimal operation scheme to the control systems of each compressor to perform energy-saving control of the compressor.

8. The device according to claim 7, characterized in that The compressor operating parameters include intake pressure, outlet pressure, intake temperature, gas flow, compressor speed and shaft power; the environmental parameters include ambient temperature and humidity; the gas parameters include composition, density and calorific value; the pipeline network operating parameters include downstream historical gas demand and upstream gas supply pressure.

9. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and the computer program is used to execute the method according to any one of claims 1 to 6.

10. An electronic device, characterized in that: The electronic device comprises: processor; a memory for storing instructions executable by the processor; The processor is used to read the executable instructions from the memory and execute the instructions to implement the method described in any one of claims 1 to 6.

Images