A gas compressor energy-saving control method, device and medium

Abstract

The present invention discloses a gas compressor energy-saving control method, device, and medium. The method comprises: 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; training a compressor performance model, a load prediction model, and an energy efficiency optimization model based on the preprocessed historical operating data; using the compressor performance model, the load prediction model, and the energy efficiency optimization model to predict operating data based on the collected real-time operating data, and obtaining predicted operating data for a predetermined future time period; calculating the predicted operating data using a non-dominated sorting genetic algorithm to determine an optimal operating plan; and distributing control parameters of the optimal operating plan to the control system of each compressor to perform energy-saving control of the compressor.

Description

Technical Field

[0001] The present invention relates to the technical field of compressor energy-saving control, and more particularly, 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, gas pressure increase is crucial to ensure stable and efficient gas transmission. As a key node in the gas transportation network, gas compression stations use gas compressors to increase 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 increasing 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 multiple factors, including inlet pressure, exhaust pressure, compression ratio, flow rate, ambient temperature, and gas composition. Traditional compressor control methods often struggle to achieve optimal energy efficiency under complex and changing operating conditions, especially when gas demand fluctuates significantly and upstream gas source pressure fluctuates 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 intake valve or the frequency converter to meet 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; based on the final opening adjustment of the anti-surge valve, the pressure PID control adjustment is performed 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, intraday load fluctuations, upstream gas source pressure fluctuations, etc. 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: With only exhaust pressure as the control target, it is difficult to take into account multiple targets such as flow rate, compression ratio, and energy consumption at the same time. 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. It is often a passive response and difficult to cope with sudden large load forecast results. (5) Insufficient coordinated 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:

[0007] Collect historical operating data of gas compressors, including compressor operating parameters, environmental parameters, gas parameters, and pipeline network operating parameters;

[0008] Train the compressor performance model, load prediction model, and energy efficiency optimization model based on preprocessed historical operating data;

[0009] Use the compressor performance model, load prediction model, and energy efficiency optimization model to predict operating data based on the collected real-time operating data and obtain predicted operating data within a predetermined time period in the future;

[0010] A non-dominated sorting genetic algorithm is used to calculate the predicted operation data and determine the optimal operation plan;

[0011] 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.

[0012] Optionally, the compressor operating parameters include inlet pressure, outlet pressure, inlet temperature, gas flow, compressor speed and shaft power; environmental parameters include ambient temperature and humidity; gas parameters include composition, density and calorific value; pipeline network operating parameters include downstream historical gas demand and upstream gas supply pressure.

[0013] Optionally, a compressor performance model, a load prediction model, and an energy efficiency optimization model are trained based on the preprocessed historical operating data, including:

[0014] Perform outlier detection on historical operation data to determine short-term missing data and long-term missing data of historical operation data;

[0015] The linear interpolation algorithm is used to fill in the short-term missing data, and the historical data of the same period is used to fill in the long-term missing data to determine the pre-processed historical operation data;

[0016] Perform feature extraction on the preprocessed historical operating data to obtain a feature data set, where the feature data set includes compressor efficiency, weather model, and load rate;

[0017] The Min-Max normalization method is used to standardize the feature data set and the pre-processed historical operation data;

[0018] A random forest algorithm is used to generate a load forecasting model with standardized network operating parameters, environmental parameters, compressor efficiency, load rate, and seasonal time characteristics as input and load forecast results for the next 24 hours as output.

[0019] 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;

[0020] 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.

[0021] Optionally, the optimization objective of the non-dominated sorting genetic algorithm is:

[0022] Min F = (f1, f2, f3)

[0023] 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 factor of each compressor;

[0024] The constraints of the non-dominated sorting genetic algorithm are: minimizing energy consumption, stabilizing exhaust pressure, and balancing equipment load.

[0025] 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:

[0026] The control parameters of the optimal operation plan are sent to each compressor through the OPC protocol, where the control parameters include the start and stop status and the speed setting value;

[0027] Each compressor uses a slow and gradual method to adjust parameters until the control parameters are reached to achieve energy-saving control.

[0028] Optionally, it also includes:

[0029] 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.

[0030] According to another aspect of the present invention, there is provided a gas compressor energy-saving control device, comprising:

[0031] The acquisition module is used to collect 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;

[0032] A training module, used to train the compressor performance model, load prediction model, and energy efficiency optimization model based on preprocessed historical operating data;

[0033] A prediction module is used to predict operating data based on the collected real-time operating data using the compressor performance model, load prediction model, and energy efficiency optimization model, and obtain predicted operating data within a predetermined time period in the future;

[0034] A calculation module is used to calculate the predicted operation data using a non-dominated sorting genetic algorithm to determine the optimal operation plan;

[0035] 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.

[0036] 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 according to any one of the above aspects of the present invention.

[0037] 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; and the processor for reading the executable instructions from the memory and executing the instructions to implement the method described in any one of the above aspects of the present invention.

[0038] Therefore, the present invention realizes adaptive optimization control of the gas compressor group through the combination of data-driven and intelligent algorithms, can effectively cope with complex and changeable operating conditions, and significantly improve the energy efficiency and operational reliability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] A more complete understanding of exemplary embodiments of the present invention may be obtained by referring to the following drawings:

[0040] Figure 1 1 is a flow chart of a gas compressor energy-saving control method provided by an exemplary embodiment of the present invention;

[0041] Figure 2 is another flow chart of a gas compressor energy-saving control method provided by an exemplary embodiment of the present invention;

[0042] 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;

[0043] Figure 4 1 is a schematic structural diagram of a gas compressor energy-saving control device provided by an exemplary embodiment of the present invention;

[0044] Figure 5 This is a structure of an electronic device provided by an exemplary embodiment of the present invention. DETAILED DESCRIPTION

[0045] 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 herein.

[0046] 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.

[0047] Those skilled in the art will understand that the terms "first" and "second" in the embodiments of the present invention are only used to distinguish different steps, devices or modules, and neither represent any specific technical meaning nor indicate the necessary logical order between them.

[0048] It should also be understood that, in the embodiments of the present invention, “a plurality of” may refer to two or more than two, and “at least one” may refer to one, two or more than two.

[0049] 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.

[0050] In addition, the term "and / or" in this invention merely describes an association relationship between related objects, indicating that three possible relationships exist. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. Furthermore, the character " / " in this invention generally indicates that the related objects are in an "or" relationship.

[0051] 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 with each other. For the sake of brevity, they will not be described one by one.

[0052] 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.

[0053] 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.

[0054] 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.

[0055] It should be noted that like reference numerals and letters refer to like items in the following figures, and therefore, once an item is defined in one figure, it need not be further discussed in subsequent figures.

[0056] Embodiments of the present invention can be applied to electronic devices such as terminal devices, computer systems, and servers, and can operate in conjunction with numerous other general-purpose or specialized computing system environments or configurations. Examples of well-known terminal devices, computing systems, environments, and / or configurations suitable for use with terminal devices, computer systems, servers, and other electronic devices 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, minicomputer systems, mainframe computer systems, and distributed cloud computing technology environments including any of the above.

[0057] Electronic devices such as terminal devices, computer systems, and servers can be described in the general context of computer system-executable instructions (such as program modules) executed by a computer system. 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 via 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.

[0058] Exemplary Methods

[0059] Figure 1 FIG. 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 1 As shown, the gas compressor energy-saving control method 100 includes the following steps:

[0060] Step 101: Collect 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;

[0061] Step 102: training a compressor performance model, a load prediction model, and an energy efficiency optimization model based on the preprocessed historical operation data;

[0062] Step 103: Using the compressor performance model, load prediction model, and energy efficiency optimization model, the operation data is predicted based on the collected real-time operation data to obtain predicted operation data within a predetermined time period in the future.

[0063] Step 104, using a non-dominated sorting genetic algorithm to calculate the predicted operation data and determine the optimal operation plan;

[0064] Step 105: Send the control parameters of the optimal operation solution to the control system of each compressor to perform energy-saving control of the compressor.

[0065] 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:

[0066] (1) Data acquisition module: real-time collection of various operating data of the gas boosting 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.

[0067] (2) Data preprocessing module: cleans, filters and standardizes the collected raw data, including: outlier detection and processing; data completion; feature extraction and selection; and data standardization.

[0068] (3) Model training module: Based on pre-processed historical data, multiple machine learning models are trained:

[0069] Compressor performance model: describes the performance characteristics of the compressor under different working conditions;

[0070] Load forecasting model: predicts short-term gas demand changes;

[0071] Energy efficiency optimization model: Establish a relationship model between compressor operating parameters and energy efficiency.

[0072] (4) Prediction and optimization module:

[0073] Use load forecasting models to predict gas demand in the future;

[0074] 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;

[0075] Optimization goals include: minimizing energy consumption, stabilizing exhaust pressure, balancing equipment load, etc.

[0076] Output optimized control parameters: start / stop status, speed, air intake volume, etc. of each compressor.

[0077] (5) Control execution module:

[0078] Receive control parameters output by the optimization module;

[0079] Send control instructions to the control system of each compressor;

[0080] Monitor the execution effect in real time and feed back the actual operation data to the data acquisition module.

[0081] (6) Model update and optimization:

[0082] Regularly update each model with newly collected operational data to ensure model accuracy and adaptability;

[0083] Based on the actual operation results, the parameters and constraints of the optimization algorithm are continuously adjusted.

[0084] Implementation process:

[0085] The system continuously collects real-time operation data through the data acquisition module.

[0086] 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.

[0087] The model training module retrains each model using updated historical data periodically or when significant changes in operating conditions are detected.

[0088] The prediction and optimization module calculates the optimal operation plan based on the latest model, combining the current operation status and predicted future load.

[0089] The control execution module sends the optimized control parameters to each compressor and monitors the execution effect.

[0090] The system continuously cycles the above process, continuously optimizing the control strategy to achieve efficient operation of the compressor group.

[0091] This solution achieves adaptive optimization control of gas compressor groups through a combination of data-driven and intelligent algorithms. It can effectively cope with complex and changeable operating conditions and significantly improve the system's energy efficiency and operational reliability.

[0092] 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:

[0093] Background Information: The booster station is equipped with three centrifugal compressors, each with a designed flow rate of 500,000 cubic meters per day. The upstream air pressure range is 1.5-5.0 MPa; the required downstream pipeline pressure is <= 9.15 MPa. The station is equipped with a SCADA system to collect various operating data in real time.

[0094] The specific implementation steps are as follows:

[0095] 1. Data Collection:

[0096] The solution of the present invention first expands the data collection scope of the existing SCADA system and adds the following data points:

[0097] (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).

[0098] (2) Environmental parameters: ambient temperature and humidity (10 minutes / time).

[0099] (3) Gas parameters: composition (daily); density, calorific value (hourly).

[0100] (4) Pipeline network operation data: upstream gas pressure (1 minute / time); downstream user flow demand (5 minutes / time).

[0101] 2. Data preprocessing:

[0102] (1) Outlier detection: Detect outliers using statistical and machine learning based methods (isolation forest algorithm).

[0103] (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.

[0104] (3) Feature extraction: Calculate compressor efficiency; extract weather patterns (weekdays / holidays); calculate derived features such as load rate.

[0105] (4) Data standardization: The Min-Max standardization method is used to map each eigenvalue to the interval [0,1].

[0106] 3. Model training:

[0107] (1) Compressor performance model: Using random forest algorithm, the 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 are input; output characteristics: compression ratio

[0108] (2) Load forecasting model:

[0109] An LSTM neural network is used, with the following input features: historical downstream gas demand; upstream gas supply pressure; ambient temperature and humidity; compressor on / off status and frequency; and seasonal time characteristics.

[0110] Output characteristics: gas demand in the next 24 hours.

[0111] (3) Energy efficiency optimization model:

[0112] A regression model based on XGBoost was built. The input features included the load forecast results; the output of the compressor performance model; the compressor operating parameters (inlet pressure, inlet temperature, gas flow, compressor speed, and shaft power); the environmental parameters (ambient temperature and humidity); and the gas parameters (composition, density, and calorific value). The output feature was the overall energy consumption.

[0113] 4. Prediction Optimization

[0114] (1) Load forecast: The load forecast for the next 24 hours is updated every hour.

[0115] (2) Optimization algorithm: The improved non-dominated sorting genetic algorithm NSGA-II is used, and the optimization objective function is:

[0116] Min F = (f1, f2, f3)

[0117] 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.

[0118] Constraints: Compressor operating range limitations; system flow balance; pressure limitations.

[0119] (3) Optimization cycle: Under normal circumstances, optimization is performed every 15 minutes. When a large load change is detected, optimization is triggered immediately.

[0120] 5. Control Execution:

[0121] (1) Control command issuance: Optimized parameters (start / stop status, speed setting, etc.) are sent to each compressor PLC via the OPC protocol. Parameters are adjusted slowly and gradually to avoid drastic fluctuations.

[0122] (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 backup control scheme is switched.

[0123] 6. Model update and optimization:

[0124] (1) Regular Updates: Retrain each model weekly using the latest data. Evaluate model performance monthly and adjust the model structure if necessary.

[0125] (2) Adaptive optimization: Dynamically adjust the weight coefficients of the optimization algorithm based on the actual operating results. Introduce reinforcement learning methods to continuously optimize the control strategy.

[0126] Implementation effect: By deploying the solution of the present invention, the gas boosting station achieved remarkable results during the three-month trial operation period:

[0127] 1. Reduced energy consumption: The overall energy consumption of the system is reduced by approximately 8.5% compared to the original solution.

[0128] 2. Improved pressure stability: The outlet pressure fluctuation range is reduced from ±0.3MPa to ±0.1MPa.

[0129] 3. Improved equipment utilization: The average compressor load rate increased from 65% to 78%.

[0130] 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%.

[0131] This paper demonstrates the feasibility and effectiveness of the proposed solution in practical applications. By combining data-driven and intelligent algorithms, it achieves efficient coordinated control of gas compressor clusters, providing a new solution for energy conservation, emission reduction, and intelligent transformation in the industry.

[0132] This application solves the following technical problems:

[0133] 1. Insufficient energy efficiency optimization:

[0134] Existing technologies mainly focus on pressure control, which makes it difficult to achieve global optimization of energy efficiency.

[0135] 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, combined with an intelligent optimization algorithm.

[0136] 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 working conditions, thereby significantly improving the overall energy efficiency level of the gas boosting station.

[0137] 2. Poor adaptability:

[0138] Traditional PID control is difficult to adapt to complex and changing working conditions.

[0139] The present invention adopts a machine learning model, which can adaptively adjust the control strategy to effectively cope with load fluctuations and changes in operating conditions.

[0140] Enhanced 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 gas boosting stations, such as seasonal demand fluctuations, intraday load forecast results, and upstream gas source pressure fluctuations.

[0141] 3. Insufficient multi-objective optimization capabilities:

[0142] Existing technologies often focus on a single objective (such as pressure stabilization).

[0143] The present invention achieves an improvement in comprehensive performance by taking into account energy consumption, pressure stability and equipment load balance through a multi-objective optimization algorithm.

[0144] Achieving multi-objective optimization: One of the purposes 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 operation efficiency while meeting the needs of downstream users.

[0145] 4. Lack of predictive ability:

[0146] Traditional methods are mostly passive responses, making it difficult to respond to changes in working conditions in advance.

[0147] The present invention introduces a load forecasting model, which can predict load changes 24 hours in advance and realize active optimization control.

[0148] Provide 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, realize active optimization control, and improve the system's ability to respond to sudden load forecast results.

[0149] 5. Insufficient coordination and control capabilities:

[0150] It is difficult to achieve coordinated optimization of multiple compressors using existing technologies.

[0151] 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%).

[0152] 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.

[0153] 6. High dependence on manual intervention:

[0154] Traditional methods require frequent manual adjustments and interventions.

[0155] The present invention significantly improves the automation level and reduces the number of manual interventions by 60%.

[0156] Reduce the need for manual intervention: By introducing intelligent decision-making algorithms, the present invention aims to reduce the dependence on manual intervention during system operation, improve the level of automation, and reduce operation and maintenance costs.

[0157] 7. Limited pressure control accuracy:

[0158] It is difficult to accurately control the outlet pressure with existing technology.

[0159] The present invention reduces the pressure fluctuation range from ±0.3MPa to ±0.1MPa, greatly improving the pressure stability.

[0160] 8. Data value is not fully tapped:

[0161] Traditional methods do not fully utilize historical operating data.

[0162] This invention fully taps the value of data through machine learning algorithms and achieves continuous optimization of the model.

[0163] Realize 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.

[0164] 9. System reliability needs to be improved:

[0165] Existing technologies may cause equipment to start and stop frequently, affecting system reliability.

[0166] The present invention reduces unnecessary equipment starts and stops and improves system stability by optimizing the control strategy.

[0167] 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.

[0168] 10. Lack of intelligence and self-learning capabilities:

[0169] Traditional methods lack the ability to continuously learn and self-optimize.

[0170] The present invention introduces adaptive optimization and reinforcement learning methods to enable the system to have the ability of continuous improvement.

[0171] Adapting to the needs of intelligent transformation: In line with the trend of digital and intelligent transformation in the energy industry, this invention aims to provide a smart control solution with learning and continuous optimization capabilities for gas boosting stations.

[0172] Therefore, the present invention realizes adaptive optimization control of the gas compressor group through the combination of data-driven and intelligent algorithms, can effectively cope with complex and changeable operating conditions, and significantly improve the energy efficiency and operational reliability of the system.

[0173] Exemplary devices

[0174] Figure 4FIG. 1 is a schematic diagram of a gas compressor energy-saving control device according to an exemplary embodiment of the present invention. Figure 4 As shown, the apparatus 400 includes:

[0175] The acquisition module 410 is used to collect 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;

[0176] A training module 420 is used to train a compressor performance model, a load prediction model, and an energy efficiency optimization model based on preprocessed historical operation data;

[0177] Prediction module 430, for using the compressor performance model, load prediction model and energy efficiency optimization model to perform operation data prediction based on the collected real-time operation data, and obtain predicted operation data within a predetermined time period in the future;

[0178] 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;

[0179] The control module 450 is used to send the control parameters of the optimal operation plan to the control system of each compressor to perform energy-saving control on the compressor.

[0180] Optionally, the compressor operating parameters include inlet pressure, outlet pressure, inlet temperature, gas flow, compressor speed and shaft power; environmental parameters include ambient temperature and humidity; gas parameters include composition, density and calorific value; pipeline network operating parameters include downstream historical gas demand and upstream gas supply pressure.

[0181] Optionally, the training module 420 includes:

[0182] The detection submodule is used to detect outliers in historical operation data and determine short-term missing data and long-term missing data in historical operation data;

[0183] The completion submodule is used to complete the short-term missing data using the linear interpolation algorithm, and to complete the long-term missing data using the historical data of the same period, and to determine the pre-processed historical operation data;

[0184] A feature extraction submodule is used to extract features from the pre-processed historical operating data to obtain a feature data set, where the feature data set includes compressor efficiency, weather model, and load rate;

[0185] The standardization submodule is used to standardize the feature data set and the pre-processed historical operation data using the Min-Max standardization method;

[0186] The first generation submodule is used to generate a load forecasting model using a random forest algorithm, with standardized pipe network operating parameters, environmental parameters, compressor efficiency, load rate and seasonal time characteristics as input and the load forecast result for the next 24 hours as output;

[0187] The second generation submodule is used to generate a compressor performance model using a neural network model, with the standardized compressor operating parameters, environmental parameters and gas parameters as input and the compression ratio prediction result of the compressor as output;

[0188] 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.

[0189] Optionally, the optimization objective of the non-dominated sorting genetic algorithm is:

[0190] Min F = (f1, f2, f3)

[0191] 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 factor of each compressor;

[0192] The constraints of the non-dominated sorting genetic algorithm are: minimizing energy consumption, stabilizing exhaust pressure, and balancing equipment load.

[0193] Optionally, the control module 450 includes:

[0194] The sending submodule is used to send the control parameters of the optimal operation plan to each compressor through the OPC protocol, where the control parameters include the start and stop status and the speed setting value;

[0195] 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.

[0196] Optionally, the apparatus 400 further includes:

[0197] 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.

[0198] Exemplary electronic devices

[0199] Figure 5 This is the structure of an electronic device provided by an exemplary embodiment of the present invention. Figure 5As shown, the electronic device 50 includes one or more processors 51 and a memory 52 .

[0200] 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.

[0201] 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, random access memory (RAM) and / or cache memory. The non-volatile memory may include, for example, read-only memory (ROM), a hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 51 may execute the program instructions to implement the software program methods and / or other desired functions of the various embodiments of the present invention described above. In one example, the electronic device may further include an input device 53 and an output device 54, which are interconnected via a bus system and / or other form of connection mechanism (not shown).

[0202] In addition, the input device 53 may also include, for example, a keyboard, a mouse, and the like.

[0203] 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.

[0204] 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.

[0205] Exemplary computer program products and computer-readable storage media

[0206] 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 perform the steps of the method according to various embodiments of the present invention described in the above "Exemplary Method" section of this specification.

[0207] The computer program product may be written in any combination of one or more programming languages ​​to implement the operations of embodiments of the present invention, including object-oriented programming languages ​​such as Java, C++, and conventional procedural programming languages ​​such as C or similar programming languages. The program code may be executed entirely on the user's computing device, partially on the user's computing device, as a stand-alone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0208] 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.

[0209] The computer-readable storage medium may be any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may include, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, system, or device, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: an electrical connection having 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 thereof.

[0210] The basic principles of the present invention have been described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, and effects mentioned in the present invention are merely illustrative and non-limiting, and should not be construed as necessarily possessed by each embodiment of the present invention. Furthermore, the specific details disclosed above are provided for illustrative purposes and to facilitate understanding, and are not intended to be limiting. These details do not necessarily limit the present invention to being implemented using these specific details.

[0211] Each embodiment in this specification is described in a progressive manner, with each embodiment focusing on its differences from the other embodiments. References to the same or similar parts between the various embodiments are sufficient. For system embodiments, since they largely correspond to method embodiments, their description is relatively simple. For relevant parts, references to the description of the method embodiments are sufficient.

[0212] The block diagrams of the devices, systems, equipment, and systems involved in the present invention are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As will be appreciated by those skilled in the art, these devices, systems, equipment, and systems can be connected, arranged, or configured in any manner. Words such as "including," "comprising," "having," and the like are open-ended words, meaning "including but not limited to," and can be used interchangeably therewith. The words "or" and "and" used herein refer to the words "and / or" and can be used interchangeably therewith, unless the context clearly indicates otherwise. The word "such as" used herein refers to the phrase "such as but not limited to," and can be used interchangeably therewith.

[0213] 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, and firmware. The above sequence of steps for the method is for illustration only, and the steps of the method of the present invention are not limited to the sequence specifically described above, unless otherwise specified. 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 recording media that store programs for executing the method according to the present invention.

[0214] 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 this field to make or use the present invention. Various modifications to these aspects will be 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 according to the widest scope consistent with the principles disclosed here and novel features.

[0215] The above description has been presented for purposes of illustration and description. Furthermore, 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, alterations, 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 preprocessed historical operating data; Utilizing the compressor performance model, the load prediction model, and the energy efficiency optimization model, and performing operation data prediction based on the collected real-time operation data, to obtain predicted operation data within a predetermined future time period; Using a non-dominated sorting genetic algorithm to calculate the predicted operation data to determine the optimal operation plan; Sending the control parameters of the optimal operation plan to the control system of each compressor to perform energy-saving control of the compressor; The compressor operating parameters include inlet pressure, outlet pressure, inlet 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; The compressor performance model, load prediction model, and energy efficiency optimization model are trained based on pre-processed historical operating 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 fill in the short-term missing data, and historical data from the same period is used to fill in the long-term missing data to determine the pre-processed historical operating data; Performing feature extraction on the preprocessed historical operating data to obtain a feature data set, wherein the feature data set includes compressor efficiency, weather model, and load rate; The Min-Max normalization method is used to normalize the feature data set and the pre-processed historical operation data; A random forest algorithm is used to generate the load forecasting model by taking the standardized pipe network operating parameters, environmental parameters, the compressor efficiency, the load rate, and seasonal time characteristics as inputs and the load forecast result for the next 24 hours as output; A neural network model is used to generate the compressor performance model by taking the standardized compressor operating parameters, environmental parameters and gas parameters as input and the compression ratio prediction result of the compressor as output; The energy efficiency optimization model is generated by adopting an XGBoost-based regression model, 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.

2. The method according to claim 1, characterized in that The optimization goal of the non-dominated sorting genetic algorithm is: MinF=(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 loads.

3. 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 plan to each compressor through the OPC protocol, wherein the control parameters include the start / stop status and the speed setting value; Each compressor adjusts parameters in a slow and gradual manner until the control parameters are reached, thereby achieving energy-saving control.

4. The method according to claim 1, wherein Also includes: The real-time operation data of the compressor within a preset time is collected in real time to update and optimize the compressor performance model, load prediction model and energy efficiency optimization model.

5. A gas compressor energy-saving control device, characterized in that: include: A collection module is used to collect 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; A training module, used to train the compressor performance model, load prediction model, and energy efficiency optimization model based on preprocessed historical operating data; A prediction module, configured to use the compressor performance model, the load prediction model, and the energy efficiency optimization model, and to perform operation data prediction based on the collected real-time operation data to obtain predicted operation data within a predetermined time period in the future; A calculation module, configured to calculate the predicted operation data using a non-dominated sorting genetic algorithm to determine an optimal operation plan; A control module, configured to send the control parameters of the optimal operation scheme to the control systems of the compressors to perform energy-saving control of the compressors; The compressor operating parameters include inlet pressure, outlet pressure, inlet 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; The compressor performance model, load prediction model, and energy efficiency optimization model are trained based on pre-processed historical operating 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 fill in the short-term missing data, and historical data from the same period is used to fill in the long-term missing data to determine the pre-processed historical operating data; Performing feature extraction on the preprocessed historical operating data to obtain a feature data set, wherein the feature data set includes compressor efficiency, weather model, and load rate; The Min-Max normalization method is used to normalize the feature data set and the pre-processed historical operation data; A random forest algorithm is used to generate the load forecasting model by taking the standardized pipe network operating parameters, environmental parameters, the compressor efficiency, the load rate, and seasonal time characteristics as inputs and the load forecast result for the next 24 hours as output; A neural network model is used to generate the compressor performance model by taking the standardized compressor operating parameters, environmental parameters and gas parameters as input and the compression ratio prediction result of the compressor as output; The energy efficiency optimization model is generated by adopting an XGBoost-based regression model, 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.

6. 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 4.

7. An electronic device, characterized in that: The electronic device comprises: 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 according to any one of claims 1 to 4.

Images