An integrated control system and method for substation equipment

Abstract

The utility model provides an integrated control system of equipment in transformer substation, include: equipment access module is used to carry out data interaction with equipment in transformer substation through multiple communication protocols, data acquisition and processing module is used to obtain the electrical data, environmental data and equipment operation data in transformer substation in real time through multiple sensor equipment, and the electrical data, environmental data and equipment operation data are pretreated, fault diagnosis analysis module is used to analyze equipment state data, and equipment fault in transformer substation is automatically identified through multi sensor fusion and machine learning algorithm, intelligent control module is used to carry out collaborative control based on equipment operation state and preset logic, the utility model improves the operation efficiency and fault processing capacity of equipment in transformer substation through the integrated control of equipment, reduces manual operation intervention, improves the intelligent management level of transformer substation, has wide application prospect and economic value.

Description

TECHNICAL FIELD

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

[0002] Substations are the core components of power systems, with a wide variety of equipment including transformers, circuit breakers, busbars, capacitors, and arresters. As an important part of the power network, intelligent substations carry the transmission and distribution of electrical energy, and their safety and operational efficiency are crucial to the stable operation of the entire power system. The monitoring and management methods of traditional substations have been unable to meet the needs of modern power systems, and the following problems exist:

[0003] 1. System fragmentation: equipment control is scattered, leading to low management efficiency, difficulty in sharing data, and complex debugging and maintenance.

[0004] 2. Lack of real-time performance: there is a time lag in the collection and processing of equipment state 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, which cannot optimize the operating state.

[0006] 4. Strong dependence on fault diagnosis: traditional systems rely on manual analysis of equipment operating state, and the accuracy of diagnosis is limited. SUMMARY

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

[0008] To solve the above technical problems, the present application discloses the following technical solutions:

[0009] In a first aspect, the present application discloses an integrated control system for equipment in a substation, comprising: a device access module, a data collection and processing module, a fault diagnosis analysis module, an intelligent control module, and a human-computer interaction module; wherein:

[0010] The device access module is configured to interact with the equipment in the substation through multiple communication protocols;

[0011] The data collection and processing module is configured to acquire electrical data, environmental data, and equipment operating data in the substation in real time through multiple sensor devices, and preprocess the electrical data, environmental data, and equipment operating data;

[0012] The fault diagnosis analysis module is configured to analyze equipment state data and automatically identify equipment faults in the substation through multi-sensor fusion and machine learning algorithms;

[0013] An intelligent control module is configured to perform collaborative control based on the device operating state and preset logic.

[0014] Further, a device access module is configured to interact with devices in the substation through a plurality of communication protocols, including at least IEC 61850 protocol, Modbus protocol, and DNP3 protocol.

[0015] Further, a data acquisition and processing module is configured to acquire electrical data, environmental data, and device operating data in the substation in real time through a plurality of sensor devices, including: acquiring voltage and current electrical operating data of devices in the substation through electrical sensors; acquiring temperature, humidity, and pressure environmental data of devices in the substation through environmental sensors; and acquiring vibration, displacement, and operating state data of devices in the substation through operating state sensors.

[0016] Further, the data acquisition and processing module is configured to preprocess the electrical data, environmental data, and device operating data, including: data cleaning, data filling, and normalization processing; wherein the data cleaning method includes: removing duplicate data by identifying and deleting duplicate data; detecting abnormal values by statistical analysis algorithm to determine whether the abnormal values are error data, and if so, deleting or replacing the abnormal values with reasonable values; and determining missing data in the power quality data by using mean interpolation or median interpolation or most frequent value interpolation method.

[0017] Further, for numerical data, the mean value of the feature column is calculated and the missing values are replaced with the mean value, for classification data, the mode of the column is used to fill the missing values, and for time series data, the linear interpolation method is used to fill the missing values according to the linear relationship between the previous and subsequent values, to obtain the data filling power quality data; the Min-Max normalization or Z-score standardization method is used to normalize the filled power quality data; and the time domain and frequency domain analysis method is used to extract power quality abnormality features from the normalized power quality data.

[0018] Further, a fault diagnosis analysis module is configured to analyze device state data and automatically identify device faults in the substation by using multi-sensor fusion and machine learning algorithms, including:

[0019] Based on the data fusion algorithm, data from different sensors is comprehensively analyzed to establish a correlation model between various types of data; and the specific method includes:

[0020] Extracting data features, using a neural network model to extract useful features from sensor data, which at least includes statistical quantities, frequency domain features, time domain features of the data;

[0021] Establishing a neural network, selecting a suitable neural network model according to the actual problem, at least including convolutional neural network, recurrent neural network, long short-term memory network (LSTM); Design the input layer, hidden layer and output layer structure of the neural network, and the activation function, optimization algorithm parameters.

[0022] Neural network training, dividing sensor data into training set, validation set and 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] Selecting a suitable loss function according to the nature of the task; For regression tasks, using mean square error as the loss function; For classification tasks, using cross-entropy loss function;

[0024] Optimizing the algorithm, the optimization algorithm at least includes gradient descent, Adam, RMSprop; Through forward propagation and back propagation, the weights of the network are constantly adjusted to minimize the loss function, cross-validation, regularization techniques and learning rate adjustment strategies are used in the training process to prevent overfitting, and the final fault identification model is obtained.

[0025] Further, the intelligent control module is used for collaborative control based on the device running state and the preset logic, and the specific method comprises:

[0026] Establishing a device dynamic model, which is used to describe how the running state of each device changes with time and input control signal; At least including the thermodynamic model of temperature control device, the speed-current relationship model of motor and the pressure-flow model of hydraulic device. Establishing a system state equation, using state variables (such as x1, x2, …, xn) to describe the device running state, establishing the system state equation: X”=f(x、u、t), wherein x is the state vector, u is the control input, and t is the time; Determine the control target and the constraint condition, define the control target, including the minimum energy consumption, the maximum efficiency or the minimum failure rate; Add constraint conditions to limit the device running range;

[0027] Formulate the preset logic and control rules, including the formulation of conditional trigger rules, which define the conditions for the collaborative operation of devices; Priority rule formulation, which defines the priority among devices; Optimization target rule formulation, which dynamically adjusts the device running state through optimization algorithm; Formulate the failure response logic, which is the processing rule when the device fails;

[0028] A cooperative control algorithm is formulated, and a control logic based on conditional rules is provided, including at least a decision tree, a state machine or a Boolean logic; control inputs of an optimization solving algorithm are optimized to achieve global optimization; the solving algorithm includes a linear programming algorithm, a nonlinear programming algorithm, a genetic algorithm and a particle swarm optimization algorithm; a reinforcement learning algorithm is used to enable the controller to learn an optimal cooperative strategy through trial and error, and an optimal control strategy is calculated in real time within a given prediction time window by optimizing an objective function.

[0029] Further, the integrated control system of the equipment in the substation further comprises a data storage and analysis module, which is used for storing historical data and performing trend analysis.

[0030] Further, the integrated control system of the equipment in the substation further comprises a human-computer interaction module, which is used for providing a graphical interface and mobile terminal access function, and realizing monitoring, configuration and remote operation of the equipment.

[0031] In the second aspect, the embodiments of the present application disclose an integrated control method of equipment in a substation, comprising:

[0032] Data interaction is performed with the equipment in the substation through multiple communication protocols;

[0033] Through multiple sensor devices, electrical data, environmental data and equipment operation data in the substation are acquired in real time, and the electrical data, the environmental data and the equipment operation data are preprocessed;

[0034] Based on the preprocessed electrical data, environmental data and equipment operation data, through multi-sensor fusion and machine learning algorithm, the equipment state data is analyzed, and the equipment fault in the substation is automatically identified;

[0035] Based on the equipment operation state and the preset logic, the equipment in the substation is cooperatively controlled.

[0036] The above technical solutions provided by the embodiments of the present application have at least the following beneficial effects:

[0037] The application discloses a substation equipment integrated control system and method, and the system comprises an equipment access module, a data acquisition and processing module, a fault diagnosis analysis module, an intelligent control module and a man-machine interaction module; wherein: the equipment access module is used for data interaction with the substation equipment through multiple communication protocols; the data acquisition and processing module is used for real-time acquisition of electrical data, environmental data and equipment operation data in the substation through multiple sensor equipment, and the electrical data, the environmental data and the equipment operation data are preprocessed; the fault diagnosis analysis module is used for analyzing equipment state data and automatically identifying the substation equipment fault through multi-sensor fusion and machine learning algorithm; and the intelligent control module is used for collaborative control based on the equipment operation state and preset logic. The application improves the operation efficiency and fault processing capability of the substation equipment through the integrated control of the equipment, reduces manual operation intervention, improves the intelligent management level of the substation, and has wide application prospect and economic value.

[0038] The technical solutions of the application will be further described in detail below with reference to the drawings and examples. BRIEF DESCRIPTION OF DRAWINGS

[0039] The accompanying drawings are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and are used to explain the application, but do not constitute a limitation on the application. In the drawings:

[0040] Figure 1 For the structure diagram of the substation equipment integrated control system in the embodiment 1 of the application;

[0041] Figure 2 For the flow chart of the substation equipment integrated control method in the embodiment 2 of the application. DETAILED DESCRIPTION

[0042] The exemplary embodiments of the present disclosure will be described in detail with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided so that the present disclosure can be more thoroughly understood and the scope of the present disclosure can be accurately conveyed to those skilled in the art.

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

[0044] Embodiment 1

[0045] The application discloses a substation equipment integrated control system, which comprises an equipment access module, a data acquisition and processing module, a fault diagnosis analysis module, an intelligent control module and a man-machine interaction module. Figure 1The device access module is configured to interact with devices in the substation through multiple communication protocols; specifically, with the development of the intelligent power system, the substation automation system needs to be compatible with devices of different protocols for data interaction, and in this embodiment, the multiple communication protocols at least include the IEC 61850 protocol, the Modbus protocol and the DNP3 protocol.

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

[0047] The IEC 61850 protocol is an object-oriented protocol, and its main features include logical nodes (LN), abstract communication service interfaces (ACSI) and manufacturing message specification (MMS). The IEC 61850 protocol supports GOOSE (fast transmission message) and Sampled Values (sampled value transmission) communication. The MMS service interface is implemented for data interaction with intelligent electronic devices (IED) in the substation. The logical node (LN) model is used for hierarchical management of devices. Modbus is a simple master-slave protocol that supports serial and Ethernet communication modes and is commonly used in traditional industrial devices. Modbus supports Modbus RTU (based on serial port) and Modbus TCP (based on Ethernet). It 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 of the host station and the slave station. It supports event reporting functions for detecting device state changes. It supports data grouping and time synchronization functions.

[0048] The data acquisition and processing module is configured to acquire electrical data, environmental data and device operation data in the substation in real time through multiple sensor devices, and to preprocess the electrical data, environmental data and device operation data.

[0049] The electrical parameter sensor is configured to collect electrical operation data such as voltage and current in the substation. The environmental parameter sensor is configured to collect environmental data such as temperature, humidity and pressure. The operation state sensor is configured to monitor the vibration, displacement and operation state of the device.

[0050] The electrical data, environmental data and equipment operation data are preprocessed, specifically including data cleaning, data filling, normalization processing; the specific method of data cleaning includes: removing duplicate data by identifying and deleting duplicate data; detecting abnormal values by statistical analysis algorithm, judging whether the abnormal values are error data, if yes, deleting or replacing the abnormal values with reasonable values; adopting mean interpolation or median interpolation or most frequent value interpolation method to process missing values to determine the missing data in the power quality data.

[0051] In this embodiment, for numerical data, the mean value of the feature column is calculated, and the missing values are replaced with the mean value, for classification data, the mode of the column is used to fill in the missing values, for time series data, linear interpolation method is used to fill in according to the linear relationship between the front and rear values, to obtain the power quality data after data filling; Min-Max normalization or Z-score standardization method is adopted to normalize the power quality data after filling; time domain and frequency domain analysis method is adopted to extract power quality abnormal features from the normalized power quality data.

[0052] Through the data acquisition and processing module of this embodiment, multiple types of data acquisition are ensured, covering full-dimensional monitoring of electrical, environmental and equipment state, and the accuracy and consistency of data acquisition are improved.

[0053] The fault diagnosis analysis module is used to analyze the equipment state data by multi-sensor fusion and machine learning algorithm, and automatically identify the equipment fault 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 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, and often has the following problems:

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

[0055] Complex fault type: equipment faults often take many forms, and a single sensor cannot accurately diagnose them.

[0056] Fault warning is insufficient: the traditional system usually responds only after the fault occurs, and lacks forward-looking warning function.

[0057] Poor data correlation: equipment state data is scattered and comes from multiple different types of sensors, how to accurately integrate and analyze these data is a technical difficulty.

[0058] In this embodiment, the device state data is analyzed by multi-sensor fusion and machine learning algorithm to automatically identify the device fault in the substation, and the specific method comprises:

[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, and the specific method comprises:

[0060] Feature extraction, using neural network model to extract useful features from sensor data, the features at least include statistical quantity, frequency domain feature, time domain feature of data;

[0061] Establishment of neural network, according to the actual problem, select appropriate neural network model, at least including convolutional neural network, recurrent neural network, long short-term memory network (LSTM); Design the input layer, hidden layer and output layer structure of neural network, and the activation function, optimization algorithm parameter.

[0062] Neural network training, the sensor data is divided into training set, validation set and 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] According to the nature of the task, select appropriate loss function; For regression task, use mean square error as loss function; For classification task, use cross-entropy loss function;

[0064] Optimize the algorithm, the optimization algorithm at least includes gradient descent, Adam, RMSprop; Through forward propagation and back propagation, the weights of the network are constantly adjusted to minimize the loss function, in the training process, cross-validation, regularization techniques and learning rate adjustment strategy are used to prevent overfitting, and the final fault identification model is obtained.

[0065] Through the fault diagnosis analysis module of the 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 network can handle complex nonlinear relationship, thereby improving the accuracy of data fusion analysis.

[0066] Intelligent control module, used for collaborative control based on device running state and preset logic. Specifically, the collaborative control refers to coordinating and controlling the devices according to the real-time running state of multiple devices, combining with the preset logic and constraint conditions, to achieve the control method of system overall optimization or meeting specific target. The core idea of collaborative control is to establish a dynamic and feedback control system, real-time acquisition of device running state data (such as temperature, pressure, current, etc.), comparison with preset logic (control rules, objective function, constraint conditions, etc.). Through optimization algorithm and control strategy, the collaborative work between devices is realized.

[0067] In this embodiment, the intelligent control module is used for cooperative control based on the device operating state and preset logic, and the specific method includes:

[0068] A device dynamic model is established, which is used to describe how the operating state of each device changes over time and input control signals; at least including a thermodynamic model of temperature control equipment, a speed-current relationship model of motor and a pressure-flow model of hydraulic equipment. A system state equation is established, using state variables (such as x1, x2, …, xn) to describe the device operating state, and the system state equation is established: X” = f(x, u, t), wherein x is the state vector, u is the control input, and t is the time; determine the control target and the constraint condition, define the control target, including the minimum energy consumption, the maximum efficiency or the minimum failure rate; add constraint conditions to limit the device operating range;

[0069] Formulate preset logic and control rules, including the formulation of conditional trigger rules, which define the conditions for cooperative operation of devices; priority rule formulation, which defines the priority between devices; optimization target rule formulation, which dynamically adjusts the device operating state through optimization algorithm; fault response logic formulation, which is the processing rule when a device fails;

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

[0071] The intelligent control module of this embodiment is based on the cooperative control method of device operating state and preset logic, which realizes efficient cooperation between multiple devices by real-time monitoring of device state, reasonable design of preset logic and optimization of control strategy.

[0072] In some preferred embodiments, the integrated control system of the equipment in the substation further comprises a data storage and analysis module for storing historical data and performing trend analysis. Specifically, the data storage and analysis module plays a crucial role in modern data processing systems. It is mainly responsible for storing a large amount of historical data and revealing potential trends and patterns in the data through in-depth analysis of these data. The data storage and analysis module needs to be able to process and store a large amount of historical data. These data can 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 comprises a human-computer interaction module for providing a graphical interface and mobile terminal access function to realize monitoring, configuration and remote operation of the equipment.

[0074] The integrated control system of the equipment in the substation disclosed in this embodiment comprises: an equipment access module, a data acquisition and processing module, a fault diagnosis analysis module, an intelligent control module and a human-computer interaction module; wherein: the equipment access module is used for data interaction with the equipment in the substation through multiple communication protocols; the data acquisition and processing module is used for real-time acquisition of electrical data, environmental data and equipment operation data in the substation through multiple sensor devices, and preprocessing of the electrical data, environmental data and equipment operation data; the fault diagnosis analysis module is used for analyzing equipment state data and automatically identifying equipment faults in the substation through multi-sensor fusion and machine learning algorithm; the intelligent control module is used for collaborative control based on equipment operation state and preset logic. The present application improves the operation efficiency and fault handling capability of the equipment in the substation through integrated control of the equipment, reduces manual operation intervention, improves the intelligent management level of the substation, and has wide application prospect and economic value.

[0075] Embodiment 2

[0076] Based on the same inventive concept, the present disclosure also provides an integrated control method of equipment in a substation, which comprises: Figure 2 , comprising:

[0077] S100. Data interaction with the equipment in the substation through multiple communication protocols;

[0078] S200. Real-time acquisition of electrical data, environmental data and equipment operation data in the substation through multiple sensor devices, and preprocessing of the electrical data, environmental data and equipment operation data;

[0079] S300. Based on the pre-processed electrical data, environmental data and equipment operation data, through multi-sensor fusion and machine learning algorithm, the equipment state data is analyzed, and the equipment fault in the substation is automatically identified;

[0080] S400. Based on the equipment operation state and the preset logic, the equipment in the substation is cooperatively controlled.

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

[0082] It should be understood that the specific order or hierarchy of steps in the disclosed processes should not be interpreted as reflecting an essential sequence for the methods. Based on design preference, 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 appended method claims recite the elements of the various steps in an exemplary order, and are not intended to be limited to the specific order or hierarchy presented.

[0083] In the above detailed description, various features are combined in a single embodiment for simplicity. This disclosure should not be interpreted as reflecting an intention that the claimed subject matter requires more features than those expressly stated in each claim. Rather, as reflected by the appended claims, the invention is in a state of less than all of the features of the disclosed single embodiment. Therefore, the appended claims are hereby expressly incorporated into the detailed description, in which each claim independently stands as a separate preferred embodiment of the invention.

[0084] Those skilled in the art will further understand that the various illustrative logical blocks, modules, circuits, and algorithm steps described in connection with the embodiments herein can be implemented as electronic hardware, computer software, or combinations thereof. To clearly illustrate the interchangeability of hardware and software, various illustrative components, blocks, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends on the particular application and design constraints imposed on the overall system. Skilled artisans can implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present disclosure.

[0085] The steps of a method or algorithm described in connection with the embodiments disclosed herein can be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module can reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor such that the processor can read information from, and write information to, the storage medium. In the alternative, the storage medium can be integral to the processor. The processor and the storage medium can reside in an ASIC. The ASIC can reside in a user terminal. In the alternative, the processor and the storage medium can reside as discrete components in a user terminal.

[0086] For a software implementation, the techniques described herein can be implemented with modules (e.g., procedures, functions, and so on) that perform the functions described herein. The software codes can be stored in memory units and executed by processors. The memory unit can be implemented within the processor or external to the processor, in which case it can be communicatively coupled to the processor via various means as is known in the art.

[0087] The above description includes one or more examples of the embodiments. Of course, not all possible combinations of components or methods described above can be described- the one of ordinary skill will recognize that further combinations and permutations of the embodiments described herein are possible. Accordingly, the embodiments described herein are intended to embrace all such alterations, modifications and variations that fall within the scope of the appended claims. Further, the term "comprising" as used in the specification and in the claims is to be construed as meaning "including", "consisting of", or "consisting essentially of", as the case can be, in accordance with the interpretation of the term "comprising" in the patent law of various jurisdictions. In addition, the use of any of the terms "or", "and", and "and / or" as used in the claims are to be construed as "non-exclusive or", "and", and "and / or", respectively.

Claims

1. An integrated control system for equipment in a substation, characterized by, Comprise: Device access module, data acquisition and processing module, fault diagnosis analysis module, intelligent control module; wherein: Device access module, for data interaction with devices in the substation through multiple communication protocols; Data acquisition and processing module, for real-time acquisition of electrical data, environmental data and device operation data in the substation through multiple sensor devices, and preprocessing of the electrical data, environmental data and device operation data; Fault diagnosis analysis module, for analyzing device state data and automatically identifying device faults in the substation through multi-sensor fusion and machine learning algorithm; Intelligent control module, for collaborative control based on device operating state and preset logic, the specific method comprising: Establishing a device dynamic model, the device dynamic model is used to describe how the operating state of each device changes with time and input control signal; at least including the thermodynamic model of temperature control device, the speed-current relationship model of motor and the pressure-flow model of hydraulic equipment; Establishing system state equation, using state variables (such as x1, x2,..., xn) to describe the device operating state, establishing system state equation: X”=f(x, u, t), wherein, x is state vector, u is control input, t is time; Determine the control target and the constraint condition, define the control target, including the minimum energy consumption, the maximum efficiency or the minimum failure rate; Add constraint conditions to limit the device operating range; Formulate preset logic and control rules, including the formulation of conditional trigger rules, which define the conditions for device collaborative operation; priority rule formulation, which defines the priority among devices; optimization target rule formulation, which dynamically adjusts the device operating state through optimization algorithm; fault response logic formulation, which defines the processing rules when a device fails; Formulate collaborative control algorithm based on conditional rule control logic, at least including decision tree, state machine or Boolean logic; solve the control input through optimization algorithm to achieve global optimization; the solving algorithm includes linear programming algorithm, nonlinear programming algorithm, genetic algorithm and particle swarm optimization algorithm; use reinforcement learning algorithm to let the controller learn the optimal collaborative strategy through trial and error, and calculate the optimal control strategy in real time within a given prediction time window through the optimization objective function.

2. An integrated control system for substation equipment as recited in claim 1, wherein, Device access module, for data interaction with devices in the substation through multiple communication protocols, the multiple communication protocols at least include IEC61850 protocol, Modbus protocol and DNP3 protocol.

3. An integrated control system for substation equipment as recited in claim 1, wherein, Data acquisition and processing module, for real-time acquisition of electrical data, environmental data and device operation data in the substation through multiple sensor devices, specifically including: collecting voltage, current electrical operation data of devices in the substation through electrical sensors; collecting temperature, humidity, pressure environmental data of devices in the substation through environmental sensors; collecting vibration, displacement and operating state data of devices in the substation through operating state sensors.

4. An integrated control system for substation equipment as recited in claim 1, wherein, A 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. The data cleaning method specifically includes: removing duplicate data by identification and deletion; detecting outliers using statistical analysis algorithms, determining whether the outliers are error data, and if so, deleting or replacing the outliers with reasonable values; and using mean interpolation, median interpolation, or most frequent value interpolation methods to handle missing values and determine missing data in the power quality data.

5. An integrated control system of substation equipment according to claim 4, wherein, For numerical data, the mean value of the feature column is calculated, and the missing values are replaced with the mean value. For categorical data, the mode of the column is used to fill in the missing values. For time series data, linear interpolation is used to fill in the missing values based on the linear relationship between the previous and subsequent values. The normalized power quality data is obtained after filling in the data. Min-Max normalization or Z-score standardization methods are used to normalize the filled power quality data. Time and frequency domain analysis methods are used to extract power quality anomaly features from the normalized power quality data.

6. An integrated control system for substation equipment as recited in claim 1, wherein, A fault diagnosis analysis module analyzes equipment state data and automatically identifies substation equipment faults through multi-sensor fusion and machine learning algorithms. The specific methods include: Based on data fusion algorithms, data from different sensors is analyzed comprehensively to establish a correlation model between various types of data. The specific methods include: Extracting data features, using neural network models to extract useful features from sensor data, including at least statistical quantities, frequency domain features, and time domain features. Establishing a neural network, selecting an appropriate neural network model based on the actual problem, including at least convolutional neural networks, recurrent neural networks, and long short-term memory networks (LSTM). Designing 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 training, validation, and test sets. The training set is used for model training, the validation set is used to adjust hyperparameters, and the test set is used to evaluate the generalization ability of the model. Selecting an appropriate loss function based on the nature of the task. For regression tasks, using mean squared error as the loss function. For classification tasks, using cross-entropy loss function. Optimizing the algorithm, including at least gradient descent, Adam, and RMSprop. Continuously adjusting the network weights through forward propagation and backpropagation to minimize the loss function. Using cross-validation, regularization techniques, and learning rate adjustment strategies to prevent overfitting during the training process to obtain the final fault identification model.

7. An integrated control system for substation equipment as recited in claim 1, wherein, A data storage and analysis module is also included, which is used to store historical data and perform trend analysis.

8. An integrated control system for substation equipment as recited in claim 1, wherein, A human-computer interaction module is also included, which provides a graphical interface and mobile terminal access function to realize monitoring, configuration, and remote operation of the equipment.

9. A method of integrated control of equipment in a substation, characterized by, This includes: Interacting with substation equipment through various communication protocols; Real-time acquisition of electrical data, environmental data and equipment operation data in the substation through various sensor devices, preprocessing of the electrical data, environmental data and equipment operation data; Based on the preprocessed electrical data, environmental data and equipment operation data, through multi-sensor fusion and machine learning algorithm, analyze the equipment state data, automatically identify the equipment fault in the substation; Based on the equipment operation state and the preset logic, the equipment in the substation is cooperatively controlled, and the specific method includes: Establishing a dynamic model of the equipment, which is used to describe how the operation state of each equipment changes with time and input control signal; at least including the thermodynamic model of temperature control equipment, the speed-current relationship model of motor and the pressure-flow model of hydraulic equipment; establishing a system state equation, using state variables (such as x1, x2,..., xn) to describe the equipment operation state, establishing a system state equation: X”=f(x, u, t), wherein x is the state vector, u is the control input, and t is the time; determining the control target and the constraint condition, defining the control target, including the minimum energy consumption, the maximum efficiency or the minimum failure rate; adding constraint conditions to limit the equipment operation range; Formulate the preset logic and control rules, including the formulation of conditional trigger rules, which define the conditions for cooperative operation of equipment; priority rule formulation, which defines the priority among equipment; optimization target rule formulation, which dynamically adjusts the equipment operation state through optimization algorithm; fault response logic formulation, which is the processing rule when the equipment fails; Formulate the cooperative control algorithm based on the control logic of the conditional rule, at least including decision tree, state machine or Boolean logic; solve the control input through optimization algorithm to achieve global optimization; the solving algorithm includes linear programming algorithm, nonlinear programming algorithm, genetic algorithm and particle swarm optimization algorithm; use reinforcement learning algorithm to let the controller learn the optimal cooperative strategy through trial and error, and calculate the optimal control strategy in real time within a given prediction time window through the optimization objective function.

Images