Integrated control system and method for equipment in transformer substation

Abstract

An integrated control system for equipment in a transformer substation comprises an equipment access module used for carrying out data interaction with the equipment in the transformer substation through various communication protocols; the data acquisition and processing module is used for acquiring electrical data, environmental data and equipment operation data in the transformer substation in real time through various sensor equipment, and preprocessing the electrical data, the environmental data and the equipment operation data; the fault diagnosis and analysis module is used for analyzing equipment state data through multi-sensor fusion and a machine learning algorithm and automatically identifying equipment faults in the transformer substation; and the intelligent control module is used for performing cooperative control based on the equipment operation state and preset logic. Through integrated control of the equipment, the operation efficiency and fault processing capability of the equipment in the transformer substation are improved, manual operation intervention is reduced, the intelligent management level of the transformer substation is improved, and wide application prospects and economic values are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of transformer substations, and in particular to an integrated control system for equipment in a transformer substation. Background Art

[0002] Substations are the core components of power systems, and they have a wide variety of equipment, including transformers, circuit breakers, busbars, capacitors, lightning arresters, etc. As an important part of the power network, smart substations carry the transmission and distribution of electric energy. Their safety and operating efficiency are crucial to the stable operation of the entire power system. The monitoring and management methods of traditional substations can no longer meet the needs of modern power systems, and there are the following problems:

[0003] 1. System fragmentation: decentralized device control leads to low management efficiency, difficulty in data sharing, and complex debugging and maintenance.

[0004] 2. Lack of real-time performance: There is a time lag in the collection and processing of equipment status data, making it difficult to respond to faults in a timely manner.

[0005] 3. Lack of coordinated control: There is a lack of linkage control mechanism between devices, and the operating status cannot be optimized.

[0006] 4. Fault diagnosis is highly dependent: Traditional systems rely on manual analysis of equipment operating status, and diagnostic accuracy is limited. Summary of the invention

[0007] In view of the above problems, the present invention is proposed to provide an integrated control system and method for equipment in a substation that overcomes the above problems or at least partially solves the above problems.

[0008] In order to solve the above technical problems, the embodiments of the present application disclose the following technical solutions:

[0009] In a first aspect, an embodiment of the present invention discloses an integrated control system for equipment in a substation, including: an equipment access module, a data acquisition and processing module, a fault diagnosis and analysis module, an intelligent control module and a human-computer interaction module; wherein:

[0010] Equipment access module, used to exchange data with equipment in the substation through various communication protocols;

[0011] The data acquisition and processing module is used to obtain the electrical data, environmental data and equipment operation data in the substation in real time through various sensor devices, and pre-process the electrical data, environmental data and equipment operation data;

[0012] Fault diagnosis and analysis module, which is used to analyze equipment status data and automatically identify equipment faults in substations through multi-sensor fusion and machine learning algorithms;

[0013] Intelligent control module, used for coordinated control based on equipment operating status and preset logic.

[0014] Furthermore, the device access module is used to perform data interaction with the devices in the substation through multiple communication protocols, and the multiple communication protocols at least include IEC 61850 protocol, Modbus protocol and DNP3 protocol.

[0015] Furthermore, the data acquisition and processing module is used to obtain electrical data, environmental data and equipment operation data in the substation in real time through various sensor devices, specifically including: collecting voltage and current electrical operation data of equipment in the substation through electrical sensors; collecting temperature, humidity and pressure environmental data of equipment in the substation through environmental sensors; collecting vibration, displacement and operation status data of equipment in the substation through operation status sensors.

[0016] Furthermore, the data acquisition and processing module pre-processes the electrical data, environmental data and equipment operation data, specifically including: data cleaning, data filling, and normalization processing; wherein the specific method of data cleaning includes: deduplication of data by identifying and deleting duplicate data; detecting outliers by identifying outliers through statistical analysis algorithms, and determining whether the outliers are erroneous data, and if so, deleting or replacing the outliers with reasonable values; processing missing values ​​by using mean interpolation, median interpolation, or most frequent value interpolation methods, and determining missing data in the power quality data.

[0017] Furthermore, for numerical data, the mean of the feature column is calculated and the missing values ​​are replaced by the mean. For categorical data, the mode of the column is used to fill the missing values. For time series data, a linear interpolation method is used to fill the data according to the linear relationship between the previous and next values ​​to obtain the power quality data after data filling. The filled power quality data is normalized by using the Min-Max normalization or Z-score standardization method. The power quality abnormality features of the normalized power quality data are extracted by using time domain and frequency domain analysis methods.

[0018] Furthermore, the fault diagnosis and analysis module is used to analyze the equipment status data through multi-sensor fusion and machine learning algorithms to automatically identify equipment faults in the substation. The specific methods include:

[0019] Based on the data fusion algorithm, the data from different sensors are comprehensively analyzed to establish the correlation model between various types of data; the specific methods include:

[0020] Extracting data features: using a neural network model to extract useful features from sensor data, wherein the features include at least statistics, frequency domain features, and time domain features of the data;

[0021] Establish a neural network and select a suitable neural network model based on actual problems, including at least convolutional neural network, recurrent neural network, and long short-term memory network (LSTM); design the input layer, hidden layer, and output layer structure of the neural network, as well as the activation function and optimization algorithm parameters.

[0022] Neural network training, dividing sensor data into a training set, a validation set and a test set; the training set is used for model training, the validation set is used for adjusting hyperparameters, and the test set is used for evaluating the generalization ability of the model;

[0023] Choose an appropriate loss function based on the nature of the task; for regression tasks, use mean square error as the loss function; for classification tasks, use cross entropy loss function;

[0024] The algorithm is optimized, and the optimization algorithm includes at least gradient descent, Adam, and RMSprop; the weight of the network is continuously adjusted through forward propagation and back propagation to minimize the loss function. During the training process, cross-validation, regularization technology, and learning rate adjustment strategy are used to prevent overfitting, so as to obtain the final fault recognition model.

[0025] Furthermore, the intelligent control module is used to perform coordinated control based on the equipment operation status and preset logic, and the specific method includes:

[0026] Establish a dynamic model of the equipment, which is used to describe how the operating state of each device changes with time and input control signals; at least include a thermodynamic model of the temperature control device, a speed-current relationship model of the motor, and a pressure-flow model of the hydraulic device. Establish a system state equation, use state variables (such as x1, x2, ..., xn) to describe the operating state of the equipment, and establish a system state equation: X" = f(x, u, t), where x is the state vector, u is the control input, and t is time; determine the control objectives and constraints, and define the control objectives, including minimizing energy consumption, maximizing efficiency, or minimizing failure rate; add constraints to limit the operating range of the equipment;

[0027] Formulate preset logic and control rules, including the formulation of conditional trigger rules, which define the conditions for the coordinated operation of equipment; the formulation of priority rules, which define the priority between equipment; the formulation of optimization target rules, which dynamically adjust the equipment operation status through optimization algorithms; the formulation of fault response logic, which is the processing rule of the response logic when a device fails;

[0028] Formulate a collaborative control algorithm, a control logic based on conditional rules, including at least a decision tree, a state machine or Boolean logic; optimize the control input of the solution algorithm to achieve global optimality; the solution algorithm includes a linear programming algorithm, a nonlinear programming algorithm, a genetic algorithm and a particle swarm optimization algorithm; use a reinforcement learning algorithm to allow the controller to learn the optimal collaborative strategy through trial and error, and calculate the optimal control strategy in real time within a given prediction time window by optimizing the objective function.

[0029] Furthermore, an integrated control system for equipment in a substation also includes a data storage and analysis module, which is used to store historical data and perform trend analysis.

[0030] Furthermore, an integrated control system for equipment in a substation also includes a human-computer interaction module, which is used to provide a graphical interface and mobile terminal access function to achieve monitoring, configuration and remote operation of the equipment.

[0031] In a second aspect, an embodiment of the present invention discloses an integrated control method for equipment in a substation, including:

[0032] Interact with substation equipment via multiple communication protocols;

[0033] Through a variety of sensor devices, electrical data, environmental data and equipment operation data in the substation are acquired in real time, and the electrical data, environmental data and equipment operation data are pre-processed;

[0034] Based on the pre-processed electrical data, environmental data and equipment operation data, the equipment status data is analyzed through multi-sensor fusion and machine learning algorithms to automatically identify equipment faults in the substation;

[0035] Based on the equipment operating status and preset logic, the equipment in the substation is coordinated and controlled.

[0036] The beneficial effects of the above technical solution provided by the embodiment of the present invention include at least:

[0037] The present invention discloses an integrated control system and method for equipment in a substation, the system comprising: an equipment access module, a data acquisition and processing module, a fault diagnosis and analysis module, an intelligent control module and a human-computer interaction module; wherein: the equipment access module is used to interact with the equipment in the substation through a variety of communication protocols; the data acquisition and processing module is used to obtain the electrical data, environmental data and equipment operation data in the substation in real time through a variety of sensor devices, and pre-process the electrical data, environmental data and equipment operation data; the fault diagnosis and analysis module is used to analyze the equipment status data through multi-sensor fusion and machine learning algorithms, and automatically identify equipment faults in the substation; the intelligent control module is used to perform collaborative control based on the equipment operation status and preset logic. The present invention improves the operating efficiency and fault handling capability of the equipment in the substation through the integrated control of the equipment, reduces manual operation intervention, and improves the intelligent management level of the substation, and has broad application prospects and economic value.

[0038] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0040] Figure 1 This is a structural diagram of an integrated control system for equipment in a substation in Embodiment 1 of the present invention;

[0041] Figure 2 This is a flow chart of an integrated control method for equipment in a substation in Embodiment 2 of the present invention. DETAILED DESCRIPTION

[0042] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0043] In order to solve the problems existing in the prior art, an embodiment of the present invention provides an integrated control system and method for equipment in a substation.

[0044] Example 1

[0045] The present invention discloses an integrated control system for equipment in a substation. Figure 1, including: equipment access module, data acquisition and processing module, fault diagnosis and analysis module, intelligent control module and human-computer interaction module; among which:

[0046] The device access module is used to interact with the devices in the substation through multiple communication protocols. Specifically, with the intelligent development of the power system, the substation automation system needs to be compatible with devices of different protocols for data interaction. In this embodiment, the multiple communication protocols include at least IEC 61850 protocol, Modbus protocol and DNP3 protocol.

[0047] Among them, IEC 61850 is an object-oriented protocol, and its main features include logical nodes (LN), abstract communication service interface (ACSI) and manufacturing message description (MMS). The IEC 61850 protocol supports GOOSE (fast transmission message) and Sampled Values ​​(sampled value transmission) communication. Implement the MMS service interface for data interaction with the intelligent electronic device (IED) of the substation. Hierarchical management of devices is performed through the logical node (LN) model. Modbus is a simple master-slave protocol that supports both serial port and Ethernet communication modes and is commonly used in traditional industrial equipment. Modbus supports Modbus RTU (based on serial port) and Modbus TCP (based on Ethernet). Provides register data parsing functions, including input registers and holding registers. DNP3 is a distributed protocol that supports event-driven communication and timestamp data transmission. DNP3 implements the master-slave communication mode. Supports event reporting function for detecting changes in device status. Supports data grouping and time synchronization functions.

[0048] The data acquisition and processing module is used to obtain the electrical data, environmental data and equipment operation data in the substation in real time through various sensor devices, and pre-process the electrical data, environmental data and equipment operation data;

[0049] Among them, electrical parameter sensors: used to collect electrical operation data such as voltage and current in the substation. Environmental parameter sensors: used to collect environmental data such as temperature, humidity, pressure, etc. Operation status sensors: used to monitor the vibration, displacement and operation status of the equipment.

[0050] Among them, the electrical data, environmental data and equipment operation data are preprocessed, specifically including: data cleaning, data filling, and normalization processing; wherein the specific method of data cleaning includes: deduplication of data by identifying and deleting duplicate data; detecting outliers by identifying outliers through statistical analysis algorithms, and judging whether the outliers are erroneous data, if they are erroneous data, deleting or replacing the outliers with reasonable values; using mean interpolation, median interpolation, or most frequent value interpolation methods to process missing values, and determine the missing data in the power quality data.

[0051] In this embodiment, for numerical data, the mean of the feature column is calculated and the missing values ​​are replaced by the mean. For categorical data, the mode of the column is used to fill the missing values. For time series data, a linear interpolation method is used to fill the data according to the linear relationship between the previous and next values ​​to obtain the power quality data after data filling. The filled power quality data is normalized by using the Min-Max normalization or Z-score standardization method. The normalized power quality data is analyzed by using the time domain and frequency domain analysis methods to extract power quality abnormality features.

[0052] Through the data collection and processing module of this embodiment, various types of data collection are guaranteed, covering full-dimensional monitoring of electrical, environmental and equipment status, and improving the accuracy and consistency of data collection.

[0053] The fault diagnosis and analysis module is used to analyze the equipment status data through multi-sensor fusion and machine learning algorithms, and automatically identify equipment faults in the substation. Specifically, the substation is an important part of the power system, and the normal operation of its equipment directly affects the stability of the power grid and the safe supply of electricity. With the continuous expansion of the scale of the power system, the number of substation equipment is large and the operating environment is complex. The traditional equipment fault diagnosis method relies on manual inspection and regular maintenance, which often has the following problems:

[0054] Fault detection delay: Due to the wide distribution of substation equipment, manual inspection cannot detect faults in real time.

[0055] Complex fault types: Equipment failures often manifest themselves in multiple forms, which are difficult to accurately diagnose with a single sensor.

[0056] Insufficient fault warning: Traditional systems usually only respond after a fault occurs and lack forward-looking warning capabilities.

[0057] Poor data correlation: Equipment status data is scattered and comes from many different types of sensors. How to accurately integrate and analyze this data is a technical difficulty.

[0058] In this embodiment, the method for analyzing the equipment status data and automatically identifying equipment failures in the substation through multi-sensor fusion and machine learning algorithms includes:

[0059] Based on the data fusion algorithm, the data from different sensors are comprehensively analyzed to establish the correlation model between various types of data; the specific methods include:

[0060] Feature extraction, using a neural network model to extract useful features from sensor data, the features at least include data statistics, frequency domain features, and time domain features;

[0061] Establish a neural network and select a suitable neural network model based on actual problems, including at least convolutional neural network, recurrent neural network, and long short-term memory network (LSTM); design the input layer, hidden layer, and output layer structure of the neural network, as well as the activation function and optimization algorithm parameters.

[0062] Neural network training, dividing sensor data into a training set, a validation set and a test set; the training set is used for model training, the validation set is used for adjusting hyperparameters, and the test set is used for evaluating the generalization ability of the model;

[0063] Choose an appropriate loss function based on the nature of the task; for regression tasks, use mean square error as the loss function; for classification tasks, use cross entropy loss function;

[0064] The algorithm is optimized, and the optimization algorithm includes at least gradient descent, Adam, and RMSprop; the weight of the network is continuously adjusted through forward propagation and back propagation to minimize the loss function. During the training process, cross-validation, regularization technology, and learning rate adjustment strategy are used to prevent overfitting, so as to obtain the final fault recognition model.

[0065] Through the fault diagnosis and analysis module of this embodiment, effective features can be automatically extracted from the data of multiple sensors, avoiding the tedious steps of manually designing features in traditional methods. At the same time, neural networks can handle complex nonlinear relationships, thereby improving the accuracy of data fusion analysis.

[0066] The intelligent control module is used for collaborative control based on the operating status of the equipment and preset logic. Specifically, the collaborative control refers to a control method that coordinates the equipment according to the real-time operating status of multiple devices and combines preset logic and constraints to achieve the overall optimal system or meet specific goals. The core idea of ​​collaborative control is to establish a dynamic, feedback control system to obtain equipment operating status data (such as temperature, pressure, current, etc.) in real time and compare it with preset logic (control rules, objective functions, constraints, etc.). Collaborative work between devices is achieved through optimization algorithms and control strategies.

[0067] In this embodiment, the intelligent control module is used to perform collaborative control based on the device operating status and preset logic. The specific method includes:

[0068] Establish a dynamic model of the equipment, which is used to describe how the operating state of each device changes with time and input control signals; at least include a thermodynamic model of the temperature control device, a speed-current relationship model of the motor, and a pressure-flow model of the hydraulic device. Establish a system state equation, use state variables (such as x1, x2, ..., xn) to describe the operating state of the equipment, and establish a system state equation: X" = f(x, u, t), where x is the state vector, u is the control input, and t is time; determine the control objectives and constraints, and define the control objectives, including minimizing energy consumption, maximizing efficiency, or minimizing failure rate; add constraints to limit the operating range of the equipment;

[0069] Formulate preset logic and control rules, including the formulation of conditional trigger rules, which define the conditions for the coordinated operation of equipment; the formulation of priority rules, which define the priority between equipment; the formulation of optimization target rules, which dynamically adjust the equipment operation status through optimization algorithms; the formulation of fault response logic, which is the processing rule of the response logic when a device fails;

[0070] Formulate a collaborative control algorithm, a control logic based on conditional rules, including at least a decision tree, a state machine or Boolean logic; optimize the control input of the solution algorithm to achieve global optimality; the solution algorithm includes a linear programming algorithm, a nonlinear programming algorithm, a genetic algorithm and a particle swarm optimization algorithm; use a reinforcement learning algorithm to allow the controller to learn the optimal collaborative strategy through trial and error, and calculate the optimal control strategy in real time within a given prediction time window by optimizing the objective function.

[0071] The intelligent control module of this embodiment realizes efficient collaboration among multiple devices based on a collaborative control method of device operating status and preset logic by real-time monitoring of device status, reasonable design of preset logic and optimization of control strategy.

[0072] In some preferred embodiments, an integrated control system for equipment in a substation further includes a data storage and analysis module, which is used to store historical data and perform trend analysis. Specifically, the data storage and analysis module plays a vital role in modern data processing systems. It is mainly responsible for storing a large amount of historical data, and through in-depth analysis of these data, it reveals the potential trends and patterns in the data. The data storage and analysis module needs to be able to process and store a large amount of historical data. These data may come from different sources, such as sensors, user input, external databases, etc. The data storage and analysis module uses a distributed storage system or a cloud storage solution to ensure the scalability and reliability of the data.

[0073] In some embodiments, the integrated control system further includes a human-computer interaction module, which is used to provide a graphical interface and mobile terminal access function to achieve monitoring, configuration and remote operation of the device.

[0074] The present embodiment discloses an integrated control system for equipment in a substation, the system comprising: an equipment access module, a data acquisition and processing module, a fault diagnosis and analysis module, an intelligent control module and a human-computer interaction module; wherein: the equipment access module is used to interact with the equipment in the substation through a variety of communication protocols; the data acquisition and processing module is used to obtain the electrical data, environmental data and equipment operation data in the substation in real time through a variety of sensor devices, and pre-process the electrical data, environmental data and equipment operation data; the fault diagnosis and analysis module is used to analyze the equipment status data through multi-sensor fusion and machine learning algorithms, and automatically identify equipment faults in the substation; the intelligent control module is used to perform collaborative control based on the equipment operation status and preset logic. The present invention improves the operating efficiency and fault handling capability of the equipment in the substation through the integrated control of the equipment, reduces manual operation intervention, and improves the intelligent management level of the substation, and has broad application prospects and economic value.

[0075] Example 2

[0076] Based on the same inventive concept, the embodiment of the present disclosure also provides an integrated control method for equipment in a substation, such as Figure 2 ,include:

[0077] S100. Interact with substation equipment via multiple communication protocols;

[0078] S200. Acquire electrical data, environmental data and equipment operation data in the substation in real time through a variety of sensor devices, and pre-process the electrical data, environmental data and equipment operation data;

[0079] S300. Based on the pre-processed electrical data, environmental data and equipment operation data, the equipment status data is analyzed through multi-sensor fusion and machine learning algorithms to automatically identify equipment faults in the substation;

[0080] S400. Based on the equipment operating status and preset logic, coordinate control of the equipment in the substation.

[0081] Among them, the specific working method of an integrated control method for equipment in a substation has been described in detail in Example 1, and will not be repeated in this embodiment.

[0082] It should be understood that the specific order or hierarchy of steps in the disclosed process is an example of an exemplary method. Based on design preferences, it should be understood that the specific order or hierarchy of steps in the process can be rearranged without departing from the scope of protection of the present disclosure. The attached method claims present the elements of the various steps in an exemplary order and are not intended to be limited to the specific order or hierarchy described.

[0083] In the above detailed description, various features are grouped together in a single embodiment to simplify the disclosure. This method of disclosure should not be interpreted as reflecting an intention that the embodiments of the claimed subject matter require more features than are clearly stated in each claim. On the contrary, as reflected in the appended claims, the invention is in a state of having less than all the features of the disclosed individual embodiments. Therefore, the appended claims are hereby expressly incorporated into the detailed description, with each claim standing on its own as a separate preferred embodiment of the invention.

[0084] Those skilled in the art will also appreciate that the various illustrative logic blocks, modules, circuits, and algorithmic steps described in conjunction with the embodiments herein can all be implemented as electronic hardware, computer software, or a combination thereof. In order to clearly illustrate the interchangeability between hardware and software, various illustrative components, blocks, modules, circuits, and steps are generally described above around their functions. Whether such functions are implemented as hardware or software depends on specific applications and the design constraints imposed on the entire system. A skilled person can implement the described functions in an alternative manner for each specific application, but such implementation decisions should not be interpreted as departing from the scope of protection of the present disclosure.

[0085] The steps of the method or algorithm described in conjunction with the embodiments herein may be directly embodied as hardware, a software module executed by a processor, or a combination thereof. The software module may be located in a RAM memory, a flash memory, a ROM memory, an EPROM memory, an EEPROM memory, a register, a hard disk, a mobile disk, a CD-ROM, or any other form of storage medium well known in the art. An exemplary storage medium is connected to the processor so that the processor can read information from the storage medium and can write information to the storage medium. Of course, the storage medium may also be an integral part of the processor. The processor and the storage medium may be located in an ASIC. The ASIC may be located in a user terminal. Of course, the processor and the storage medium may also be present in a user terminal as discrete components.

[0086] For software implementation, the techniques described in this application can be implemented with modules (e.g., procedures, functions, etc.) that perform the functions described in this application. These software codes can be stored in a memory unit and executed by a processor. The memory unit can be implemented within the processor or outside the processor. In the latter case, it is coupled to the processor in a communication manner via various means, which are well known in the art.

[0087] The above description includes examples of one or more embodiments. Of course, it is impossible to describe all possible combinations of components or methods for the purpose of describing the above embodiments, but it should be recognized by those skilled in the art that the various embodiments may be further combined and arranged. Therefore, the embodiments described herein are intended to cover all such changes, modifications and variations that fall within the scope of protection of the appended claims. In addition, with respect to the term "comprising" used in the specification or claims, the word is covered in a manner similar to the term "including", just as "including," is explained as a transitional word in the claims. In addition, any term "or" used in the specification of the claims is intended to mean "non-exclusive or".

Claims

1. An integrated control system for equipment in a substation, characterized in that: include: Equipment access module, data acquisition and processing module, fault diagnosis and analysis module, intelligent control module; among which: Equipment access module, used to exchange data with equipment in the substation through various communication protocols; The data acquisition and processing module is used to obtain the electrical data, environmental data and equipment operation data in the substation in real time through various sensor devices, and pre-process the electrical data, environmental data and equipment operation data; Fault diagnosis and analysis module, which is used to analyze equipment status data and automatically identify equipment faults in substations through multi-sensor fusion and machine learning algorithms; Intelligent control module, used for coordinated control based on equipment operating status and preset logic.

2. An integrated control system for equipment in a substation as claimed in claim 1, characterized in that: The device access module is used to exchange data with the devices in the substation through multiple communication protocols, and the multiple communication protocols at least include IEC61850 protocol, Modbus protocol and DNP3 protocol.

3. The integrated control system for equipment in a substation according to claim 1, characterized in that: The data acquisition and processing module is used to obtain the electrical data, environmental data and equipment operation data in the substation in real time through a variety of sensor devices, including: collecting the voltage and current electrical operation data of the equipment in the substation through electrical sensors; collecting the temperature, humidity and pressure environmental data of the equipment in the substation through environmental sensors; collecting the vibration, displacement and operation status data of the equipment in the substation through operation status sensors.

4. The integrated control system for equipment in a substation according to claim 1, characterized in that: The data acquisition and processing module pre-processes the electrical data, environmental data and equipment operation data, specifically including: data cleaning, data filling, and normalization processing; wherein the specific method of data cleaning includes: deduplication of data by identifying and deleting duplicate data; detecting outliers by identifying outliers through statistical analysis algorithms, and determining whether the outliers are erroneous data. If they are erroneous data, the outliers are deleted or replaced with reasonable values; missing value processing is performed by using mean interpolation, median interpolation, or most frequent value interpolation methods to determine the missing data in the power quality data.

5. An integrated control system for equipment in a substation as claimed in claim 4, characterized in that: For numerical data, the mean of the feature column is calculated and the missing values ​​are replaced with the mean. For categorical data, the missing values ​​are filled with the mode of the column. For time series data, the linear interpolation method is used to fill the data according to the linear relationship between the previous and next values ​​to obtain the power quality data after data filling. The filled power quality data is normalized by using the Min-Max normalization or Z-score normalization method. Time domain and frequency domain analysis methods are used to extract power quality abnormality features from normalized power quality data.

6. The integrated control system for equipment in a substation according to claim 1, characterized in that: The fault diagnosis and analysis module is used to analyze equipment status data and automatically identify equipment faults in the substation through multi-sensor fusion and machine learning algorithms. The specific methods include: Based on the data fusion algorithm, the data from different sensors are comprehensively analyzed to establish the correlation model between various types of data; the specific methods include: Extracting data features: using a neural network model to extract useful features from sensor data, wherein the features include at least statistics, frequency domain features, and time domain features of the data; Establish a neural network and select the appropriate neural network model according to the actual problem, including at least convolutional neural network, recurrent neural network, and long short-term memory network (LSTM); design the input layer, hidden layer and output layer structure of the neural network, as well as the activation function and optimization algorithm parameters; Neural network training, dividing sensor data into a training set, a validation set and a test set; the training set is used for model training, the validation set is used for adjusting hyperparameters, and the test set is used for evaluating the generalization ability of the model; Choose an appropriate loss function based on the nature of the task; for regression tasks, use mean square error as the loss function; for classification tasks, use cross entropy loss function; The algorithm is optimized, and the optimization algorithm includes at least gradient descent, Adam, and RMSprop; the weight of the network is continuously adjusted through forward propagation and back propagation to minimize the loss function. During the training process, cross-validation, regularization technology, and learning rate adjustment strategy are used to prevent overfitting, so as to obtain the final fault recognition model.

7. The integrated control system for equipment in a substation according to claim 1, characterized in that: Intelligent control module, used for coordinated control based on equipment operating status and preset logic, the specific methods include: Establish a dynamic model of the equipment, which is used to describe how the operating state of each equipment changes with time and input control signals; at least including a thermodynamic model of the temperature control equipment, a speed-current relationship model of the motor, and a pressure-flow model of the hydraulic equipment; establish a system state equation, use state variables (such as x1, x2, ..., xn) to describe the equipment operating state, and establish a system state equation: X" = f(x, u, t), where x is the state vector, u is the control input, and t is time; determine the control objectives and constraints, and define the control objectives, including minimizing energy consumption, maximizing efficiency, or minimizing failure rate; add constraints to limit the operating range of the equipment; Formulate preset logic and control rules, including the formulation of conditional trigger rules, which define the conditions for the coordinated operation of equipment; the formulation of priority rules, which define the priority between equipment; the formulation of optimization target rules, which dynamically adjust the equipment operation status through optimization algorithms; the formulation of fault response logic, which is the processing rule of the response logic when a device fails; Formulate a collaborative control algorithm, a control logic based on conditional rules, including at least a decision tree, a state machine or Boolean logic; optimize the control input of the solution algorithm to achieve global optimality; the solution algorithm includes a linear programming algorithm, a nonlinear programming algorithm, a genetic algorithm and a particle swarm optimization algorithm; use a reinforcement learning algorithm to allow the controller to learn the optimal collaborative strategy through trial and error, and calculate the optimal control strategy in real time within a given prediction time window by optimizing the objective function.

8. An integrated control system for equipment in a substation as claimed in claim 1, characterized in that: It also includes a data storage and analysis module, which is used to store historical data and perform trend analysis.

9. An integrated control system for equipment in a substation as claimed in claim 1, characterized in that: It also includes a human-computer interaction module, which is used to provide a graphical interface and mobile terminal access function to achieve monitoring, configuration and remote operation of the device.

10. An integrated control method for equipment in a substation, characterized in that: include: Interact with substation equipment via multiple communication protocols; Through a variety of sensor devices, electrical data, environmental data and equipment operation data in the substation are acquired in real time, and the electrical data, environmental data and equipment operation data are pre-processed; Based on the pre-processed electrical data, environmental data and equipment operation data, the equipment status data is analyzed through multi-sensor fusion and machine learning algorithms to automatically identify equipment faults in the substation; Based on the equipment operating status and preset logic, the equipment in the substation is coordinated and controlled.

Images