Intelligent energy-saving management system and method for electric power engineering equipment

Abstract

The invention discloses an intelligent energy-saving management system and method for electric power engineering equipment, and relates to the technical field of energy-saving management of the electric power engineering equipment, the intelligent energy-saving management system is composed of a data acquisition subsystem, an analysis processing subsystem, a decision generation subsystem, a control execution subsystem and a feedback optimization subsystem, the analysis processing subsystem learns and mines a data rule by using a machine and builds an energy consumption model, the decision generation subsystem generates an energy-saving decision by using an optimization algorithm according to a result and a strategy, the control execution subsystem converts an instruction to regulate and control equipment, and the feedback optimization subsystem evaluates an energy-saving effect and dynamically adjusts the strategy. The system further comprises a data storage management and communication network subsystem for guaranteeing data security and communication stability. The system has the advantages of remarkable energy conservation, capability of reducing the energy consumption of equipment, realization of intelligent and automatic management, improvement of the management efficiency, adoption of advanced technologies, adaptation to different working conditions, high stability, support of multiple protocols and equipment interfaces, good expansibility and compatibility, and capability of meeting various requirements.

Description

Technical Field

[0001] The present invention relates to the technical field of energy-saving management of power engineering equipment, and particularly to an intelligent energy-saving management system and method for power engineering equipment. Background Art

[0002] At present, with the development of the global economy and the acceleration of industrialization, electricity, as a key energy source, has seen a continuous and rapid increase in demand. Power engineering equipment is widely used in various fields and plays a decisive role in the utilization efficiency of power resources and cost control. However, there are many serious problems in the current operation energy consumption management of power engineering equipment.

[0003] Lack of intelligent management means: Traditional management of power engineering equipment mainly relies on manual inspections and empirical judgments, making it difficult to accurately and timely grasp the energy consumption and operation efficiency of equipment. In industrial production, for equipment such as motors and transformers in large factories, due to the inability to adjust the operation state in a timely manner according to load changes, situations such as excessive energy consumption and idling often occur. For example, when the load of some motors decreases, the speed is not adjusted accordingly, resulting in a significant increase in energy consumption. There is a lack of coordination mechanisms between different equipment, and it is impossible to optimize the configuration according to production needs, further reducing the utilization efficiency of power resources.

[0004] Energy consumption problems are prominent in the commercial and residential sectors: Air conditioning and lighting equipment in commercial buildings still operate at high energy consumption levels when not in use or with low demand. The number of household electrical appliances has increased, but their energy-saving functions are limited, and users lack effective energy-saving management methods, resulting in high household electricity consumption.

[0005] Existing management systems have limitations: Existing power engineering equipment management systems focus on fault diagnosis and maintenance and pay insufficient attention to energy consumption management. Their data analysis capabilities are weak, unable to deeply mine a large amount of equipment operation data, difficult to accurately locate the energy-saving direction, and unable to provide strong support for energy-saving decisions. Moreover, these systems lack an adaptive adjustment function and cannot optimize energy-saving strategies in a timely manner according to the real-time operation state of equipment and changes in the external environment.

[0006] With the increasing prominence of energy problems and the continuous enhancement of environmental awareness, it is urgent to reduce the energy consumption of power engineering equipment and improve energy utilization efficiency. Developing a management system and method that can real-time monitor the operation state of equipment, accurately analyze energy consumption, and intelligently generate and dynamically adjust energy-saving strategies not only reduces power consumption and saves energy costs but also has important significance for reducing environmental pollution and promoting the sustainable development of the power industry. This need has prompted continuous innovation and development of related technologies to meet the dual requirements of efficient energy utilization and environmental protection. Summary of the Invention

[0007] An intelligent energy-saving management system and method for power engineering equipment proposed by the present invention are used to solve the problems mentioned in the above prior art.

[0008] To achieve the above object, the present invention adopts the following technical solution: An intelligent energy-saving management system for power engineering equipment, which is composed of a data acquisition subsystem, a data analysis and processing subsystem, an intelligent decision-making generation subsystem, a control execution subsystem, and a feedback optimization subsystem: The data acquisition subsystem is equipped with a variety of high-precision sensors, which are used to comprehensively and real-time collect various operation data of power engineering equipment, covering the voltage, current, power factor, surface temperature of the equipment, humidity of the operation environment, and status information such as startup, stop, and standby of the equipment. The collected data is recorded at a preset time interval to ensure the timeliness and integrity of the data.

[0009] The data analysis and processing subsystem is connected to the data acquisition subsystem through a high-speed data bus and receives the collected operation data. This subsystem uses advanced data mining algorithms and machine learning technologies to deeply analyze the data. On the one hand, it mines the potential laws and characteristics in the data and identifies the typical operation modes of the equipment under different working conditions; on the other hand, by establishing an energy consumption analysis model, it accurately analyzes the energy consumption distribution and change trend of the equipment.

[0010] The intelligent decision-making generation subsystem is connected to the data analysis and processing subsystem. According to the analysis results and preset energy-saving goals and strategies, it uses a multi-objective optimization algorithm to generate the optimal energy-saving control decision. The decision content includes adjusting the start and stop times of the equipment, setting operation parameters, etc., to minimize the energy consumption of the equipment and maximize the operation efficiency.

[0011] The control execution subsystem is connected to the intelligent decision-making generation subsystem, receives the generated control decision, and converts it into specific control instructions to perform real-time regulation on the power engineering equipment through the control interface. This subsystem has the ability of fast response and precise control to ensure that the equipment can operate stably according to the decision requirements.

[0012] The feedback optimization subsystem is respectively connected to the control execution subsystem and the data analysis and processing subsystem, and real-time collects the operation data of the equipment after executing the control decision. By comparing the energy consumption data before and after energy saving and using the energy-saving effect evaluation formula (where E represents the evaluation value of the energy-saving effect, is the energy consumption before the implementation of the energy-saving measure, is the energy consumption after the implementation of the energy-saving measure) to evaluate the energy-saving effect. According to the evaluation results, the preset energy-saving strategies and goals are dynamically adjusted and optimized.

[0013] Furthermore, it also includes a data storage and management subsystem. The data storage and management subsystem adopts distributed file system and database technologies to interact with the data acquisition subsystem and the data analysis and processing subsystem. It is responsible for storing the collected original operation data, data analysis results, system configuration information, etc. At the same time, it has data backup, recovery and data security encryption functions, and uses symmetric encryption algorithms to encrypt data to prevent data leakage and loss, ensuring the security and reliability of data. In addition, this subsystem also supports functions such as fast data query and statistical analysis, providing data support for the operation and management of the system.

[0014] Furthermore, it also includes a communication and network subsystem, which supports multiple communication protocols such as Ethernet, RS-485, ZigBee, etc., to achieve stable data transmission between the subsystems of the system and between the system and power engineering equipment. It adopts a hierarchical network architecture design, including a field device layer, a control layer and a management layer, to improve the communication efficiency and reliability of the system. At the same time, it has network security protection mechanisms such as firewalls and intrusion detection systems to prevent external network attacks and ensure the normal operation of the system.

[0015] Furthermore, the data analysis and processing subsystem uses the long short-term memory network (LSTM) model in deep learning to perform time series analysis on the operation data of the equipment. By learning and training historical data, a prediction model of equipment energy consumption is established , where is the predicted equipment energy consumption, are the past energy consumption data of the equipment, are the past operation status data of the equipment, are the environmental parameters of the equipment operation. This model can accurately predict the energy consumption of the equipment in the future for a period of time, providing a basis for intelligent decision-making.

[0016] Furthermore, the training process of the LSTM model uses the mean squared error loss function (where is the actual equipment energy consumption value, is the equipment energy consumption value predicted by the model, is the number of samples) for optimization. Through the backpropagation algorithm, the weights and biases of the model are continuously adjusted to minimize the prediction error of the model and improve the prediction accuracy of the model.

[0017] Further, the intelligent decision-making generation subsystem adopts a multi-objective optimization strategy based on genetic algorithms to generate energy-saving control decisions. This strategy takes the minimization of equipment energy consumption, the maximization of equipment operation efficiency, and the extension of equipment service life as optimization objectives, considering the operation constraint conditions and real-time operation status of the equipment. Through the selection, crossover, and mutation operations of genetic algorithms, the optimal combination of control parameters is searched in the solution space. Its fitness function (where is the energy consumption reduction rate, is the operation efficiency improvement rate, is the equipment service life extension rate, , , are the corresponding weight coefficients, and ) is used to evaluate the quality of each solution.

[0018] Further, the feedback optimization subsystem adopts a fuzzy adaptive control algorithm to dynamically adjust the energy-saving strategy. According to the energy-saving effect evaluation results and the changes in the equipment operation status, the adjustment direction and amplitude of the energy-saving strategy are determined through a fuzzy inference mechanism. The fuzzy rule base is established based on expert experience and historical data, taking the energy-saving rate deviation e and the energy-saving rate deviation change rate Δe as input variables, and the energy-saving strategy adjustment parameter Δp as the output variable. Through the processes of fuzzification, fuzzy inference, and defuzzification, the adaptive optimization of the energy-saving strategy is realized, improving the energy-saving effect and adaptability of the system.

[0019] Further, a method for an intelligent energy-saving management system for power engineering equipment includes the following steps: S1. Data acquisition stage: Use various sensors in the data acquisition subsystem to collect the operation data of power engineering equipment in real time and store it at preset time intervals.

[0020] S2. Data analysis and processing stage: Transmit the collected data to the data analysis and processing subsystem, use the LSTM model of deep learning for time series analysis, establish an equipment energy consumption prediction model, and simultaneously mine the operation mode and energy consumption characteristics of the equipment.

[0021] S3. Intelligent decision-making generation stage: The intelligent decision-making generation subsystem generates the optimal energy-saving control decision according to the data analysis results and the preset energy-saving goals, adopting a multi-objective optimization strategy based on genetic algorithms.

[0022] S4. Control execution stage: The control execution subsystem receives the decision instruction, converts it into a specific control signal, and performs real-time regulation on the power engineering equipment.

[0023] S5. Feedback optimization stage: The feedback optimization subsystem collects the operation data of the device after executing the control decision, calculates the energy-saving rate through the energy-saving effect evaluation formula, and uses the fuzzy adaptive control algorithm to dynamically adjust and optimize the energy-saving strategy.

[0024] Furthermore, the data analysis and processing stage further includes a data preprocessing step. The raw data collected is cleaned to remove noise data and outliers; the normalization processing method is adopted to unify different types of data into the same numerical range to improve the training effect and analysis accuracy of the model. At the same time, feature extraction is performed on the processed data, and features closely related to the device energy consumption and operation status are selected as the input of the model to reduce the data dimension and improve the calculation efficiency.

[0025] Furthermore, in the feedback optimization stage, when the deviation of the energy-saving rate exceeds the preset threshold range, the system enters the rapid adjustment mode. In the rapid adjustment mode, the fuzzy adaptive control algorithm increases the change amplitude of the adjustment parameter to accelerate the adjustment speed of the energy-saving strategy so that the energy-saving rate can reach the target value as soon as possible. When the energy-saving rate approaches the target value, the system enters the fine adjustment mode, reduces the change amplitude of the adjustment parameter, and performs precise fine-tuning to ensure the best balance between the energy-saving effect and the operation stability of the device.

[0026] Compared with the existing technologies, the beneficial effects of the present invention are as follows: In terms of energy saving, the system collects the operation data of the device in real time and uses advanced data analysis and machine learning algorithms to accurately identify the operation mode and energy consumption characteristics of the device. Based on this, the intelligent decision-making generation subsystem adopts a multi-objective optimization strategy to generate the optimal energy-saving control decision, and can adjust the operation parameters of the device in a timely manner according to the real-time operation status of the device and the changes in the external environment, avoiding the occurrence of excessive energy consumption and idling of the device. Through practical application verification, the system can effectively reduce the energy consumption of power engineering equipment, improve the energy-saving rate, and significantly save electric power resources and energy costs.

[0027] In terms of management efficiency, the system realizes the intelligent and automated management of power engineering equipment. The data acquisition subsystem can collect the operation data of the device in real time and comprehensively, reducing the workload and error of manual inspection. The data analysis and processing subsystem deeply mines and analyzes a large amount of data, providing an accurate basis for energy-saving decision-making. The control execution subsystem can quickly and accurately execute the control decision to realize the real-time regulation of the device. The feedback optimization subsystem dynamically adjusts the energy-saving strategy according to the energy-saving effect evaluation result, making the system always maintain the optimal energy-saving state. The entire management process is efficient and accurate, greatly improving the management efficiency of power engineering equipment.

[0028] In terms of adaptability and stability, the system adopts a variety of advanced technologies and has strong adaptability and stability. The LSTM model of deep learning can accurately predict the energy consumption of the device and adapt to the changes in the operating conditions of the device. The multi-objective optimization strategy based on genetic algorithm and the fuzzy adaptive control algorithm can dynamically adjust the energy-saving strategy according to different device types and operating environments to ensure that the system can achieve the best energy-saving effect in various situations. At the same time, the system has a perfect communication and network subsystem and data storage and management subsystem, which guarantees the safe transmission and storage of data and improves the stability and reliability of the system.

[0029] In addition, the system also has good scalability and compatibility. The system supports a variety of communication protocols and device interfaces and can be seamlessly connected to different types of power engineering equipment. At the same time, the software architecture of the system adopts a modular design, which is convenient for function expansion and upgrade and can meet the diverse needs of future power engineering equipment management. Brief Description of the Drawings

[0030] Figure 1 It is a schematic block diagram of an intelligent energy-saving management system for power engineering equipment proposed by the present invention; Figure 2 It is a schematic block diagram of an intelligent energy-saving management method for power engineering equipment proposed by the present invention; Figure 3 It is a comparison chart of the energy-saving effect of an intelligent energy-saving management system for power engineering equipment proposed by the present invention; Figure 4 It is a verification chart of the energy consumption prediction model of an intelligent energy-saving management system for power engineering equipment proposed by the present invention. Detailed Embodiments

[0031] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0032] In the description of the present invention, it should be understood that the orientation or positional relationship indicated by the terms "center", "longitudinal", "transverse", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", etc. is based on the orientation or positional relationship shown in the drawings, and is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as a limitation to the present invention.

[0033] In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of the said features. In the description of the present invention, the meaning of "a plurality" is two or more, unless otherwise specifically defined. In addition, the terms "mounted", "connected" and "coupled" should be understood in a broad sense. For example, it may be a fixed connection, a detachable connection or an integral connection; it may be a mechanical connection or an electrical connection; it may be directly connected or indirectly connected through an intermediate medium, and it may be the communication inside two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances. The present invention will be further described in detail below with reference to the drawings.

[0034] Refer to Figures 1-4 : An intelligent energy-saving management system and method for power engineering equipment, which consists of a data acquisition subsystem, a data analysis and processing subsystem, an intelligent decision-making generation subsystem, a control execution subsystem, a feedback optimization subsystem, a data storage and management subsystem, and a communication and network subsystem. Each subsystem cooperates with each other to achieve the intelligent energy-saving management of power engineering equipment.

[0035] Data acquisition subsystem: The data acquisition subsystem is the data source basis of the entire system. To ensure comprehensive, accurate and real-time acquisition of the operation information of power engineering equipment, a variety of high-precision sensors are installed at key parts of the equipment. For example, voltage sensors and current sensors are installed in the circuit of the equipment to monitor the voltage and current values of the equipment in real time; temperature sensors are installed on the surface of the equipment to obtain the temperature change during the operation of the equipment; humidity sensors are installed in the operating environment of the equipment to monitor the impact of environmental humidity on the operation of the equipment. At the same time, through the status monitoring device, the operation status information such as the start, stop and standby of the equipment is accurately recorded.

[0036] These sensors and monitoring devices collect and record data at preset time intervals (such as every 5 minutes) to ensure the timeliness and integrity of the data. The collected data is sent in the form of digital signals through the data transmission line to the data storage and management subsystem for preliminary storage, providing a basis for subsequent data analysis and processing.

[0037] Data analysis and processing subsystem: After receiving a large amount of operation data from the data acquisition subsystem, this subsystem first performs data preprocessing operations. Using data cleaning algorithms, noise and outliers in the data are removed. For example, by setting a reasonable threshold range, data outside the normal range is marked as outliers and corrected or removed. Then, a normalization processing method is adopted to unify data of different types and ranges into the same numerical interval. For example, data such as voltage and current is normalized to the [0, 1] interval to improve the training effect and accuracy of subsequent analysis models.

[0038] After completing data preprocessing, a long short-term memory network (LSTM) model in deep learning is used to perform time series analysis on the operation data of the device. By learning and training the historical operation data of the device, a prediction model for device energy consumption is established , where is the predicted device energy consumption, is the past energy consumption data of the device, is the past operation status data of the device, is the environmental parameter of the device operation.

[0039] During the training process, the mean squared error loss function (where is the actual device energy consumption value, is the device energy consumption value predicted by the model, is the number of samples) is used to evaluate the prediction error of the model, and the weights and biases of the model are continuously adjusted through the backpropagation algorithm to minimize the prediction error of the model, thereby improving the prediction accuracy of the model. At the same time, data mining techniques are used to mine potential laws and features in the data, identify typical operation modes of the device under different working conditions, and provide a basis for intelligent decision-making.

[0040] The intelligent decision-making generation subsystem generates the optimal energy-saving control decision by adopting a multi-objective optimization strategy based on the genetic algorithm according to the analysis results of the data analysis and processing subsystem and the preset energy-saving goals and strategies. This strategy takes the minimization of device energy consumption, the maximization of device operation efficiency, and the extension of device service life as optimization goals, while considering the operation constraint conditions and real-time operation status of the device.

[0041] In specific implementation, first, the solution space is determined, that is, all possible combinations of control parameters. Then, through the selection, crossover, and mutation operations of the genetic algorithm, the optimal combination of control parameters is continuously searched in the solution space. The fitness function (where is the energy consumption reduction rate, is the operation efficiency improvement rate, is the equipment service life extension rate, , , are the corresponding weight coefficients, and ) is used to evaluate the quality of each solution. Finally, the optimal energy-saving control decision for power engineering equipment is generated, such as adjusting the start-stop time of the equipment and setting the operation parameters.

[0042] The control execution subsystem receives the control decision generated by the intelligent decision-making subsystem and converts it into specific control instructions. This subsystem is connected to the power engineering equipment through a control interface and has the ability of fast response and precise control.

[0043] For example, for motor equipment, the motor speed is adjusted according to the decision instruction; for lighting equipment, its switch state and brightness adjustment are controlled. During the execution of the control instruction, the operation state of the equipment is monitored in real time to ensure that the equipment operates stably according to the decision requirements. If an abnormal situation occurs during the control process, such as equipment failure or operation parameters exceeding the safety range, the system will issue an alarm in time and take corresponding emergency measures.

[0044] The feedback optimization subsystem is responsible for collecting the equipment operation data after the control execution subsystem executes the control decision, and calculates the energy-saving rate through the energy-saving effect evaluation formula (where E represents the evaluation value of the energy-saving effect, is the energy consumption before the implementation of the energy-saving measure, is the energy consumption after the implementation of the energy-saving measure) to evaluate the energy-saving effect. According to the evaluation results, the fuzzy adaptive control algorithm is used to dynamically adjust and optimize the energy-saving strategy.

[0045] The fuzzy adaptive control algorithm takes the energy-saving rate deviation e and the energy-saving rate deviation change rate Δe as input variables, and takes the energy-saving strategy adjustment parameter Δp as the output variable. According to the preset fuzzy rule base, through the processes of fuzzification, fuzzy inference, and defuzzification, the adjustment direction and amplitude of the energy-saving strategy are determined. When the energy-saving rate deviation e exceeds the preset threshold range, the system enters the fast adjustment mode, increases the change amplitude of the adjustment parameter, and speeds up the adjustment speed of the energy-saving strategy; when the energy-saving rate approaches the target value, the system enters the fine adjustment mode, reduces the change amplitude of the adjustment parameter, and performs precise fine-tuning to ensure the best balance between the energy-saving effect and the equipment operation stability.

[0046] The data storage and management subsystem uses a distributed file system and database technology to store and manage the collected original operation data, data analysis results, and system configuration information, etc. This subsystem has functions of data backup, recovery, and data security encryption, and uses a symmetric encryption algorithm to encrypt the data to prevent data leakage and loss.

[0047] At the same time, the system supports functions of rapid data query and statistical analysis, providing data support for the operation and management of the system. For example, operation and maintenance personnel can quickly query the historical operation data and energy consumption of equipment through the system interface, conduct statistical analysis and report generation, so as to timely discover the operation problems and energy-saving potential of the equipment.

[0048] The communication and network subsystem supports multiple communication protocols, such as Ethernet, RS - 485, ZigBee, etc., to achieve stable data transmission between the subsystems of the system and between the system and power engineering equipment. It adopts a hierarchical network architecture design, including the field device layer, control layer, and management layer, to improve the communication efficiency and reliability of the system.

[0049] At the field device layer, sensors and monitoring devices transmit the collected data to the control layer through corresponding communication interfaces; the control layer is responsible for preliminary data processing and forwarding; the management layer conducts centralized management and monitoring of the entire system. At the same time, the system has a network security protection mechanism, such as a firewall, intrusion detection system, etc., to prevent external network attacks and ensure the normal operation of the system.

[0050] In the present invention, in the data collection stage, various sensors in the data collection subsystem are used to collect the operation data of power engineering equipment in real time, including information such as voltage, current, power factor, temperature, humidity, and the operation status of the equipment. The collected data is stored at preset time intervals and stored in the data storage and management subsystem, providing basic data for subsequent data analysis and processing.

[0051] In the present invention, in the data analysis and processing stage, the collected data is transmitted from the data storage and management subsystem to the data analysis and processing subsystem. First, data preprocessing is performed, including operations such as data cleaning and normalization, to remove noise and outliers and unify the data range. Then, the LSTM model of deep learning is used for time series analysis to establish an equipment energy consumption prediction model , where is the predicted equipment energy consumption, is the past energy consumption data of the equipment, is the past operation status data of the equipment, They are the environmental parameters for the operation of the device. Meanwhile, data mining technology is used to mine the operation mode and energy consumption characteristics of the device, identify the typical operation modes of the device under different working conditions, and provide a basis for intelligent decision-making. When training the LSTM model, the mean squared error loss function is used to optimize the model, where is the actual energy consumption value of the device, is the energy consumption value of the device predicted by the model, and n is the number of samples.

[0052] In the present invention, in the intelligent decision generation stage, according to the analysis results of the data analysis and processing subsystem and the preset energy-saving target, a multi-objective optimization strategy based on the genetic algorithm is adopted to generate the optimal energy-saving control decision. In this process, the operation constraint conditions and real-time operation status of the device are considered, and the minimization of device energy consumption, the maximization of device operation efficiency, and the extension of device service life are taken as the optimization objectives. Through the selection, crossover, and mutation operations of the genetic algorithm, the optimal combination of control parameters is searched in the solution space. The fitness function is used to evaluate the quality of each solution.

[0053] In the present invention, the control execution subsystem receives the control decision instruction generated by the intelligent decision generation subsystem, converts it into a specific control signal, and performs real-time regulation on the power engineering device through the control interface. During the regulation process, the operation status of the device is monitored in real time to ensure that the device operates stably according to the decision requirements. If an abnormal situation occurs, an alarm is issued in a timely manner and emergency measures are taken.

[0054] In the present invention, the feedback optimization subsystem collects the operation data of the device after the control execution subsystem executes the control decision, calculates the energy-saving rate through the energy-saving effect evaluation formula to evaluate the energy-saving effect. According to the evaluation results, a fuzzy adaptive control algorithm is adopted to dynamically adjust and optimize the energy-saving strategy. When the deviation e of the energy-saving rate exceeds the preset threshold, it enters the fast adjustment mode; when the energy-saving rate approaches the target value, it enters the fine adjustment mode to ensure the best balance between the energy-saving effect and the operation stability of the system.

[0055] A method based on the intelligent energy-saving management system for power engineering devices is also disclosed in the present invention, including the following steps: S1. Data acquisition stage: Various sensors in the data acquisition subsystem are used to collect the operation data of the power engineering device in real time and store it at preset time intervals.

[0056] S2. Data analysis and processing stage: The collected data is transmitted to the data analysis and processing subsystem, and the time series analysis is carried out using the LSTM model of deep learning to establish an energy consumption prediction model for the device, and at the same time, the operation mode and energy consumption characteristics of the device are mined.

[0057] S3. Intelligent Decision Generation Phase: The intelligent decision generation subsystem generates the optimal energy-saving control decision by adopting a multi-objective optimization strategy based on the genetic algorithm according to the data analysis results and the preset energy-saving goals.

[0058] S4. Control Execution Phase: The control execution subsystem receives the decision instruction, converts it into specific control signals, and performs real-time regulation on the power engineering equipment.

[0059] S5. Feedback Optimization Phase: The feedback optimization subsystem collects the operation data of the equipment after executing the control decision, calculates the energy-saving rate through the energy-saving effect evaluation formula, and dynamically adjusts and optimizes the energy-saving strategy by adopting the fuzzy adaptive control algorithm.

[0060] Refer to Figure 3 , this figure compares the energy consumption of power engineering equipment such as motors, transformers, lighting equipment, and air-conditioning equipment before and after implementing the energy-saving management system of the present invention. It can be intuitively seen from the figure that after implementing the energy-saving management system, the energy consumption of various equipment has been significantly reduced. This shows that the system of the present invention can effectively reduce the energy consumption of power engineering equipment, verifies its energy-saving effect, and strongly illustrates that the system can effectively reduce energy waste and improve energy utilization efficiency in practical applications.

[0061] Refer to Figure 4 , this figure is used to verify the accuracy of the energy consumption prediction model. Through comparison, it can be judged whether the energy consumption prediction model accurately predicts the future energy consumption of the equipment. If the fitting degree between the actual data and the predicted data is relatively high, it indicates that the model can more accurately predict the energy consumption of the equipment, provides a reliable basis for the intelligent decision generation subsystem, and further ensures that the system formulates reasonable energy-saving strategies according to the prediction results to effectively control the energy consumption of the equipment.

[0062] Through the specific implementation of the above system and method, intelligent energy-saving management of power engineering equipment can be realized, the energy consumption of the equipment can be effectively reduced, the energy utilization efficiency can be improved, and at the same time, the stable operation of the equipment can be guaranteed and the service life can be extended.

[0063] The above is only a preferred specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention, according to the technical solution and inventive concept of the present invention, makes equivalent substitutions or changes, and should be covered by the protection scope of the present invention.

Claims

1. An intelligent energy-saving management system for electric power engineering equipment, characterized in that: It includes data acquisition subsystem, data analysis and processing subsystem, intelligent decision making subsystem, control execution subsystem and feedback optimization subsystem; The data acquisition subsystem is equipped with sensors for real-time acquisition of operating data of power engineering equipment, and the acquired data is recorded at preset time intervals; The data analysis and processing subsystem is connected to the data acquisition subsystem via a data bus, receives the collected operation data, uses data mining algorithms and machine learning techniques to conduct in-depth analysis of the data, and analyzes the energy consumption distribution and change trend of the equipment by establishing an energy consumption analysis model; The intelligent decision making subsystem is connected to the data analysis and processing subsystem, and uses a multi-objective optimization algorithm to generate the optimal energy-saving control decision based on the analysis results and preset energy-saving goals and strategies; The control execution subsystem is connected to the intelligent decision making subsystem, receives the generated control decisions, and converts them into specific control instructions, and performs real-time control of the power engineering equipment through the control interface; The feedback optimization subsystem is connected to the control execution subsystem and the data analysis and processing subsystem respectively, collects the operation data of the equipment after executing the control decision in real time, and uses the energy saving effect evaluation formula by comparing the energy consumption data before and after energy saving. Evaluate the energy-saving effect, where E represents the evaluation value of the energy-saving effect, is the energy consumption before the implementation of energy-saving measures, In order to evaluate the energy consumption after the implementation of energy-saving measures, the preset energy-saving strategies and goals are dynamically adjusted and optimized according to the evaluation results.

2. The intelligent energy-saving management system for electric power engineering equipment according to claim 1 is characterized in that: It also includes a data storage and management subsystem, which uses a distributed file system and database technology to interact with the data acquisition subsystem and the data analysis and processing subsystem to store the collected original operating data, data analysis results, and system configuration information. It also has data backup, recovery, and data security encryption functions, and uses a symmetric encryption algorithm to encrypt data to prevent data leakage and loss. It also supports rapid data query and statistical analysis functions to provide data support for system operation and management.

3. The intelligent energy-saving management system for electric power engineering equipment according to claim 1 is characterized in that: It also includes communication and network subsystems, which support multiple communication protocols, including Ethernet, RS-485, and ZigBee, to achieve stable data transmission between system subsystems and between the system and power engineering equipment; it adopts a layered network architecture design, including field equipment layer, control layer, and management layer, to improve the communication efficiency and reliability of the system. At the same time, it has network security protection mechanisms, including firewalls and intrusion detection systems, to prevent external network attacks.

4. The intelligent energy-saving management system for electric power engineering equipment according to claim 1 is characterized in that: The data analysis and processing subsystem uses the long short-term memory network (LSTM) model in deep learning to perform time series analysis on the equipment's operating data; by learning and training historical data, a prediction model for equipment energy consumption is established. ,in To predict the energy consumption of the equipment, is the past energy consumption data of the equipment, The past operating status data of the equipment. The environmental parameters for equipment operation are used to accurately predict the energy consumption of the equipment in the future and provide a basis for intelligent decision-making.

5. The intelligent energy-saving management system for electric power engineering equipment according to claim 4 is characterized in that: The training process of the LSTM model adopts the mean square error loss function Optimize, where is the actual energy consumption value of the equipment, is the equipment energy consumption value predicted by the model, is the number of samples; the weights and biases of the model are continuously adjusted through the back propagation algorithm to minimize the prediction error of the model and improve the prediction accuracy of the model.

6. The intelligent energy-saving management system for electric power engineering equipment according to claim 1 is characterized in that: The intelligent decision-making subsystem adopts a multi-objective optimization strategy based on genetic algorithm to generate energy-saving control decisions. This strategy takes minimizing equipment energy consumption, maximizing equipment operating efficiency and extending equipment service life as optimization goals, taking into account the operating constraints and real-time operating status of the equipment; through the selection, crossover and mutation operations of the genetic algorithm, the optimal control parameter combination is searched in the solution space, and its fitness function Used to evaluate the quality of each solution, is the energy consumption reduction rate, To improve the operating efficiency, is the equipment service life extension rate, , , is the corresponding weight coefficient, and .

7. The intelligent energy-saving management system for electric power engineering equipment according to claim 1 is characterized in that: The feedback optimization subsystem adopts a fuzzy adaptive control algorithm to dynamically adjust the energy-saving strategy. According to the energy-saving effect evaluation results and the changes in the equipment operation status, the adjustment direction and amplitude of the energy-saving strategy are determined through the fuzzy reasoning mechanism. The fuzzy rule base is established based on expert experience and historical data. The energy-saving rate deviation e and the energy-saving rate deviation change rate Δe are used as input variables, and the energy-saving strategy adjustment parameter Δp is used as the output variable. Through the fuzzification, fuzzy reasoning and defuzzification process, the adaptive optimization of the energy-saving strategy is realized.

8. A method for intelligent energy-saving management system for electric power engineering equipment based on any one of claims 1 to 7, characterized in that: The following steps are involved: S1, data collection stage: using various sensors in the data collection subsystem to collect the operation data of the power engineering equipment in real time and store it at preset time intervals; S2, data analysis and processing stage: the collected data is transmitted to the data analysis and processing subsystem, and the LSTM model of deep learning is used to perform time series analysis, establish an equipment energy consumption prediction model, and at the same time explore the operation mode and energy consumption characteristics of the equipment; S3, intelligent decision generation stage: the intelligent decision generation subsystem generates the optimal energy-saving control decision based on the multi-objective optimization strategy based on genetic algorithm according to the data analysis results and the preset energy-saving target; S4, control execution stage: The control execution subsystem receives the decision instructions, converts them into specific control signals, and performs real-time control on the power engineering equipment; S5, feedback optimization stage: The feedback optimization subsystem collects the operating data after the equipment executes the control decision, calculates the energy saving rate through the energy-saving effect evaluation formula, and uses the fuzzy adaptive control algorithm to dynamically adjust and optimize the energy-saving strategy.

9. The method of intelligent energy-saving management system for electric power engineering equipment according to claim 8, characterized in that: The data analysis and processing stage also includes a data preprocessing step, in which the collected raw data is cleaned to remove noise data and outliers; a normalization processing method is used to unify different types of data into the same numerical range to improve the training effect and analysis accuracy of the model; at the same time, feature extraction is performed on the processed data, and features closely related to equipment energy consumption and operating status are selected as model inputs to reduce data dimensions and improve computing efficiency.

10. The method of intelligent energy-saving management system for electric power engineering equipment according to claim 8, characterized in that: In the feedback optimization stage, when the energy saving rate deviation exceeds the preset threshold range, the system enters the fast adjustment mode. In the fast adjustment mode, the fuzzy adaptive control algorithm increases the change range of the adjustment parameters, speeds up the adjustment speed of the energy saving strategy, and makes the energy saving rate reach the target value; when the energy saving rate is close to the target value, the system enters the adjustment mode, reduces the change range of the adjustment parameters, and ensures that the system achieves a balance between energy saving effect and equipment operation stability.

Images