Control method and device for unattended equipment in power plants based on fuzzy logic

Abstract

The present invention provides a method and device for controlling unattended equipment in a power plant based on fuzzy logic, which relates to the technical field of power plant data processing, including constructing a complex network topology structure between power plant equipment based on a graph theory method according to the historical data of the connection relationship between the power plant equipment, and extracting features of the complex network topology structure to obtain network structure features; mapping the network structure features and the historical data of the state parameters to a fuzzy set, and constructing a feature vector matrix according to the fuzzy set; formulating fuzzy rules based on a density clustering algorithm according to the feature vector matrix and the expert experience rule base to obtain a fuzzy rule base; performing fuzzy reasoning according to the second information and the fuzzy rule base to obtain a fuzzy output, and controlling the power plant equipment according to the fuzzy output. The present invention enhances the adaptability and flexibility of the power plant equipment control method, and can respond to different operating states and environmental changes in a timely manner.

Description

Technical Field

[0001] The present invention relates to the technical field of power plant equipment data processing, and in particular to a power plant unattended equipment control method and device based on fuzzy logic. Background Art

[0002] Existing fuzzy control methods, especially in the face of nonlinear and highly uncertain power plant environments, have poor adaptability and are difficult to meet actual control needs. In addition, due to the complexity of power plant equipment operating conditions, fuzzy control methods often find it difficult to maintain a stable control effect, and are prone to control failure or over-adjustment. Relying on experience to adjust parameters: Many dynamic fuzzy control methods rely on the operator's experience to adjust parameters, which limits the universality and adaptability of the control method. Summary of the invention

[0003] The purpose of the present invention is to provide a method and device for controlling unattended equipment in a power plant based on fuzzy logic to improve the above problems. In order to achieve the above purpose, the technical solution adopted by the present invention is as follows:

[0004] In a first aspect, the present application provides a method for controlling unattended equipment in a power plant based on fuzzy logic, comprising:

[0005] Acquire first information, wherein the first information includes historical data of connection relationships between power plant devices, historical data of status parameters of each of the power plant devices, and a preset expert experience rule base, wherein the expert experience rule base includes control strategies for each of the power plant devices;

[0006] Acquire original data, historical original data of connection relationships between power plant equipment, and historical original data of status parameters of each of the power plant equipment;

[0007] Performing outlier detection on the historical original data based on a deep learning autoencoder to obtain first data;

[0008] Performing interpolation processing on the first data based on a high-order graph convolutional neural network to obtain second data;

[0009] The second data is normalized based on the maximum and minimum normalization method to obtain historical data of the connection relationship between the power plant equipment and historical data of the status parameters of each of the power plant equipment.

[0010] Acquire second information, wherein the second information includes real-time data of connection relationships between power plant devices and real-time data of status parameters of each of the power plant devices;

[0011] According to the historical data of the connection relationship between the power plant equipment, a complex network topology structure between the power plant equipment is constructed based on a graph theory method, and features of the complex network topology structure are extracted to obtain network structure features;

[0012] Mapping the network structure characteristics and the historical data of the state parameters to a fuzzy set, and constructing a feature vector matrix according to the fuzzy set;

[0013] According to the feature vector matrix and the expert experience rule base, fuzzy rules are formulated based on a density clustering algorithm to obtain a fuzzy rule base;

[0014] According to the second information and the fuzzy rule base, reasoning is performed based on a minimum-maximum fuzzy reasoning algorithm to obtain a fuzzy output, and the power plant equipment is controlled according to the fuzzy output.

[0015] In a second aspect, the present application also provides a fuzzy logic-based unattended equipment control device for a power plant, comprising:

[0016] A first acquisition module, the first acquisition module is used to acquire first information, the first information includes historical data of connection relationships between power plant equipment, historical data of status parameters of each of the power plant equipment, and a preset expert experience rule base, the expert experience rule base includes control strategies for each of the power plant equipment;

[0017] A second acquisition module, the second acquisition module is used to acquire second information, the second information including real-time data of connection relationships between power plant equipment and real-time data of status parameters of each of the power plant equipment;

[0018] A feature extraction module, wherein the feature extraction module is used to construct a complex network topology structure between the power plant equipment based on the historical data of the connection relationship between the power plant equipment and the graph theory method, and to extract features from the complex network topology structure to obtain network structure features;

[0019] A construction module, the construction module is used to map the historical data of the network structure characteristics and the state parameters to a fuzzy set, and construct a feature vector matrix according to the fuzzy set;

[0020] A formulation module, the formulation module is used to formulate fuzzy rules based on the density clustering algorithm according to the feature vector matrix and the expert experience rule base to obtain a fuzzy rule base;

[0021] An inference module is used to perform inference based on the second information and the fuzzy rule base based on a minimum-maximum fuzzy inference algorithm to obtain a fuzzy output, and control the power plant equipment according to the fuzzy output.

[0022] In a third aspect, the present application also provides a power plant unattended equipment control device based on fuzzy logic, comprising:

[0023] Memory for storing computer programs;

[0024] A processor is used to implement the steps of the power plant unattended equipment control method based on fuzzy logic when executing the computer program.

[0025] In a fourth aspect, the present application further provides a readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the above-mentioned fuzzy logic-based unattended power plant equipment control method are implemented.

[0026] The beneficial effects of the present invention are as follows: the present invention jointly extracts features of the complex network topology structure between power plant equipment and the state parameters of the power plant equipment, jointly captures changes in the connection relationship between equipment and changes in equipment state parameters, and uses these two features together for fuzzy reasoning based on a density clustering algorithm, which can enhance the adaptability and flexibility of the control method, and can timely perceive and respond to different operating states and environmental changes, thereby improving the adaptability and robustness of the method.

[0027] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or be understood by implementing the embodiments of the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description, claims, and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0029] Figure 1 It is a flow chart of a method for controlling unattended equipment in a power plant based on fuzzy logic according to an embodiment of the present invention;

[0030] Figure 2 A schematic diagram of control logic of unattended equipment in a power plant based on fuzzy logic according to an embodiment of the present invention;

[0031] Figure 3 It is a schematic diagram of the structure of the unattended equipment control device of a power plant based on fuzzy logic described in an embodiment of the present invention.

[0032] Markings in the figure: 800, unattended equipment control equipment of a power plant based on fuzzy logic; 801, processor; 802, memory; 803, multimedia component; 804, I / O interface; 805, communication component. DETAILED DESCRIPTION

[0033] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. The components of the embodiments of the present invention generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0034] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings. At the same time, in the description of the present invention, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0035] Embodiment 1:

[0036] This embodiment provides a method for controlling unattended equipment in a power plant based on fuzzy logic.

[0037] See also Figure 1 and Figure 2 , the figure shows that the method includes step S100, step S200, step S300, step S400, and step S500.

[0038] Step S100: Acquire first information, wherein the first information includes historical data of connection relationships between power plant equipment, historical data of status parameters of each of the power plant equipment, and a preset expert experience rule base, wherein the expert experience rule base includes control strategies for each of the power plant equipment;

[0039] Step S200: Acquire second information, wherein the second information includes real-time data of connection relationships between power plant devices and real-time data of status parameters of each of the power plant devices;

[0040] The connection relationship between the power plant equipment includes electrical connection: connection used to transmit electrical energy, such as cables, wires, busbars, etc.; mechanical connection: connection used to transmit mechanical energy, such as shafts, wheels, gears, transmission belts, etc.; hydraulic connection: connection used to transmit liquid energy, such as hydraulic pipes, pipe fittings, valves, etc.; pneumatic connection: connection used to transmit gas energy, such as air pipes, joints, pneumatic valves, etc.; sensor connection: connection used to transmit sensor signals, such as sensor cables, signal lines, etc.; communication connection: connection used to transmit data or control signals, such as network cables, communication cables, wireless communication equipment, etc.; thermal energy connection: connection used to transmit thermal energy, such as heat pipes, heat exchangers, thermal sensors, etc.

[0041] The closeness and association between power plant equipment can be measured by the connection relationship between them. For example, the generator is connected to the transformer through the transmission line, and the transformer is connected to the user. These physical connections reflect the closeness between the equipment. If the connection is close and stable, the degree of association between the equipment will be higher; for example, real-time data exchange is required between the equipment, such as voltage, current, power and other information. This information exchange reflects the degree of association between the equipment. If the information exchange is frequent and timely, it means that the degree of association between the equipment is high. For example, the generator generates electrical energy and transmits the electrical energy to the user end through the transformer and transmission line. These energy transfer processes also reflect the closeness and association between the equipment. If the energy transfer is efficient and stable, it means that the degree of association between the equipment is high. If the physical connection between the generator, transformer and transmission line is close and stable, and data exchange and energy transfer can be carried out in real time, then the closeness and association between them are high. On the contrary, if there is a loose connection, poor information transmission, and low energy transfer efficiency, it means that the closeness and association between the equipment is low.

[0042] The status parameters of power plant equipment include temperature, pressure and flow. During the operation of the power plant, the collection of temperature, pressure and flow data is to monitor and control the operating status of the power plant equipment, ensure the safe operation of the equipment, improve the power generation efficiency and extend the life of the equipment. In the unattended equipment control of the power plant, it is to ensure the safe, stable and efficient operation of the power plant.

[0043] The preset expert experience rule base includes the control strategies of each of the power plant equipment, and the preset expert experience rule base is set according to specific circumstances.

[0044] Obtaining first information includes: obtaining historical original data, historical original data on the connection relationship between power plant equipment, and historical original data on status parameters of each power plant equipment; performing outlier detection on the historical original data based on a deep learning autoencoder to obtain first data; performing interpolation processing on the first data based on a high-order graph convolutional neural network to obtain second data; performing data normalization processing on the second data based on a maximum-minimum normalization method to obtain the first information.

[0045] Outlier detection: Use deep learning-based autoencoders to perform outlier detection, identify and filter outlier data points. Set the loss function to the reconstruction error, such as the squared loss function.

[0046] Interpolation processing: Use the interpolation method based on high-order graph convolutional neural network to fill in the missing data. The high-order graph convolutional neural network learns the relationship between nodes in the graph structure and interpolates and predicts the missing nodes.

[0047] Data normalization: Apply the maximum and minimum normalization method to scale the data to the [0,1] interval.

[0048] Step S300: constructing a complex network topology structure between the power plant equipment based on the graph theory method according to the historical data of the connection relationship between the power plant equipment, and extracting features of the complex network topology structure to obtain network structure features;

[0049] According to the historical data of the connection relationship between the power plant equipment, a complex network topology structure between the power plant equipment is constructed based on the graph theory method, including:

[0050] Taking each of the power plant equipment as a node, and constructing a device node set according to each of the nodes;

[0051] Establishing edges between the power plant devices according to historical data of connection relationships between the power plant devices, wherein the connection relationships include physical connection, signal transmission, and data exchange;

[0052] A complex network topology structure between the power plant equipment is constructed according to the edges established between the node set and the power plant equipment.

[0053] Feature extraction is performed on the complex network topology structure to obtain network structure features, including:

[0054] constructing an adjacency matrix according to the complex network topology structure;

[0055] Acquire the number of nodes, the connection relationship between nodes, the number of triangles connected to each node, the number of shortest paths between nodes, and the number of shortest paths passing through each node according to the adjacency matrix;

[0056] Extracting the degree of each of the nodes according to the number of the nodes and the connection relationship between the nodes;

[0057] Extracting a clustering coefficient of each node according to the degree of the node and the number of triangles connected to each node;

[0058] The betweenness centrality of each of the nodes is extracted based on the number of shortest paths between the nodes and the number of shortest paths passing through each of the nodes.

[0059] The applicant found that in the process of controlling power plant equipment, not only the state parameters of the equipment need to be considered, but also the connection relationship between the equipment also affects the control of the power plant equipment. The specific analysis is as follows:

[0060] Node degree refers to the number of connections between a node and other nodes. In a power plant equipment network, the node degree will change with the connection status between the equipment. The applicant has analyzed the reasons for this change, including:

[0061] Device operating status changes: When the operating status of a device changes, such as turning it on or off, the degree of the nodes connected to it will also change accordingly;

[0062] Network topology adjustment: When the network topology of power plant equipment changes, such as adding, deleting or adjusting the connection relationship between equipment, the degree of the node will change;

[0063] Load changes: Changes in device load may affect its connection relationship with other devices, thereby affecting the degree of the node;

[0064] Failure or damage: Failure or damage of a device may cause changes in the connection status between it and other devices, thereby affecting the degree of the node;

[0065] In summary, changes in node degree may be caused by factors such as device operating status, network topology, load changes, and device failures.

[0066] The clustering coefficient is a measure of the closeness between nodes in a network. It describes the density of connections between node neighbors. In a power plant equipment network, the clustering coefficient changes with the network topology and the connection relationship between devices. The following are some possible reasons for changes in the clustering coefficient:

[0067] Network topology changes: When the topology of the power plant equipment network changes, such as adding, deleting, or reconnecting equipment, the node's neighbor node set may change, thus affecting the clustering coefficient;

[0068] Connection relationship changes: When the connection relationship between devices changes, such as adding or deleting a connection, the connection between the node's neighbor nodes may change, thereby affecting the clustering coefficient;

[0069] Load balancing adjustment: When the load balancing strategy between devices changes, the connection mode between devices may change, thus affecting the clustering coefficient of the nodes;

[0070] Device operating status changes: When the operating status of some devices changes, such as turning on or off, it may cause the connection status of nodes adjacent to these devices to change, thereby affecting the clustering coefficient.

[0071] In summary, changes in the clustering coefficient may be caused by changes in factors such as network topology, connection relationships, load balancing strategies, and device operating status.

[0072] In a power plant equipment network, betweenness centrality can change depending on the network topology and the connections between the equipment. Here are some possible reasons for changes in betweenness centrality:

[0073] Network topology changes: When the topology of a power plant equipment network changes, such as adding, removing, or reconnecting equipment, the communication paths between nodes may be altered, thus affecting the betweenness centrality.

[0074] Changes in key nodes: When key nodes in the network change, such as the importance of some nodes increases or decreases, the communication paths between nodes may change, thereby affecting the betweenness centrality.

[0075] Communication pattern changes: When the communication pattern between devices changes, such as changes in communication frequency or communication method, it may change the communication path between nodes, thereby affecting the betweenness centrality.

[0076] Network load changes: When the network load changes, such as the load of some nodes increases or decreases, it may affect the communication paths between nodes and thus affect the betweenness centrality.

[0077] In summary, changes in betweenness centrality may be caused by changes in factors such as network topology, key nodes, communication patterns, and network load.

[0078] The betweenness centrality of each of the nodes is extracted based on the number of shortest paths between the nodes and the number of shortest paths passing through each of the nodes.

[0079] Information is obtained, wherein the information includes connection relationships between power plant equipment, wherein the power plant equipment includes a generator (G1), a boiler (B1), a steam turbine (T1), and a cooling tower (C1).

[0080] According to the information, a complex network structure G = (V, E) between power plant equipment is constructed based on graph theory, and each power plant equipment is regarded as a node V i , where V represents the device node set and E represents the connection relationship between devices.

[0081] Analyze the physical connection relationship and mutual influence between each device. Based on these connection relationships, establish edges between devices to represent the connection relationship between devices. If there is a direct influence relationship between devices, establish an edge between the corresponding nodes. Based on the established connection relationship, construct an adjacency matrix A to represent the connection relationship between power plant equipment. The element a in the adjacency matrix A is ij Represents node V i To Node V j According to the adjacency matrix A, the number of triangles connected to node i, the number of shortest paths from node j to node l, and the number of shortest paths passing through node i are obtained.

[0082] The topological structure features (degree distribution, clustering coefficient, betweenness centrality) of the constructed complex network structure are extracted to calculate the degree k of each node. i , clustering coefficient C i and betweenness centrality B i .

[0083] Spend

[0084] Clustering coefficient

[0085] Betweenness Centrality

[0086] n is the total number of devices, k is the degree i is the number of devices directly connected to device i, and the clustering coefficient C i Measures the degree of connection between device i and its neighboring devices, betweenness centrality B i Indicates the degree to which device i acts as a bridge in the network structure. i is the number of triangles connected to node i, σ jl is the number of shortest paths from node j to node l, σ jl (i) is the number of shortest paths passing through node i.

[0087] Step S400: Mapping the network structure characteristics and the historical data of the state parameters to a fuzzy set, and constructing a feature vector matrix according to the fuzzy set;

[0088] The state parameters include the temperature, pressure and flow of power plant equipment, and the network structure characteristics and historical data of the state parameters are mapped to a fuzzy set, including:

[0089] Mapping the degrees of the nodes to a low-degree fuzzy set, a medium-degree fuzzy set and a high-degree fuzzy set, respectively, and setting the membership functions of the low-degree fuzzy set, the medium-degree fuzzy set and the high-degree fuzzy set, respectively;

[0090] Mapping the clustering coefficients to a low clustering coefficient fuzzy set, a medium clustering coefficient fuzzy set and a high clustering coefficient fuzzy set respectively, and setting the membership functions of the low clustering coefficient fuzzy set, the medium clustering coefficient fuzzy set and the high clustering coefficient fuzzy set respectively;

[0091] Mapping the betweenness centrality to a low betweenness centrality fuzzy set, a betweenness centrality fuzzy set, and a high betweenness centrality fuzzy set, respectively, and setting the membership functions of the low betweenness centrality fuzzy set, the betweenness centrality fuzzy set, and the high betweenness centrality fuzzy set, respectively;

[0092] Mapping the temperatures to a low temperature set, a medium temperature set and a high temperature set respectively, and setting the membership functions of the low temperature fuzzy set, the medium temperature fuzzy set and the high temperature fuzzy set respectively;

[0093] Mapping the pressure to a low pressure set, a medium pressure set and a high pressure set respectively, and setting the membership functions of the low pressure fuzzy set, the medium pressure fuzzy set and the high pressure fuzzy set respectively;

[0094] The traffic is mapped to a low traffic set, a medium traffic set and a high traffic set respectively, and the membership functions of the low traffic fuzzy set, the medium traffic fuzzy set and the high traffic fuzzy set are set respectively.

[0095] For the degree k of a node i , mapping it to low degree K L , Moderate K M and height K H Among the three fuzzy sets, the corresponding membership functions are and in:

[0096]

[0097]

[0098]

[0099] For the clustering coefficient C of the node i , mapping it to a low clustering coefficient C L , the clustering coefficient C M and high clustering coefficient CH Among the three fuzzy sets, the corresponding membership functions are and in:

[0100]

[0101]

[0102]

[0103] For the node betweenness centrality B i , mapping it to the low betweenness centrality B L , betweenness centrality B M and high betweenness centrality B H The three fuzzy sets and their corresponding membership functions are and in:

[0104]

[0105]

[0106]

[0107] For the device temperature T i , which is mapped to the low temperature T L , medium temperature T M and high temperature T H The three fuzzy sets and their corresponding membership functions are and in:

[0108]

[0109]

[0110]

[0111] For the equipment pressure P i , mapping it to the low voltage T L , Medium Pressure T M and high voltage T H The three fuzzy sets and their corresponding membership functions are and in:

[0112]

[0113]

[0114]

[0115] For device flow Q i , mapping it to the low flow Q L , Medium flow Q M and high flow Q H The three fuzzy sets and their corresponding membership functions are and in:

[0116]

[0117]

[0118]

[0119] If there are N devices in a power plant, each device has K1, K2, K3, K4...KN features (feature refers to degree k i , clustering coefficient C i and betweenness centrality B i , temperature, pressure and flow), map each feature to three fuzzy sets of low, medium and high, that is, they can respectively constitute K1*3 membership vectors, K2*3 membership vectors.... and so on to KN*3 membership vectors. Connecting the K1*3 membership vectors can form a K1*3-dimensional feature vector, connecting the K2*3 membership vectors can form a K2*3-dimensional feature vector... and so on to KN*3 membership vectors can form a KN*3-dimensional feature vector. Then arrange the feature vectors of all devices into a feature vector matrix, with rows representing each device and columns representing the feature vector of each device.

[0120] Step S500: formulating fuzzy rules based on the density clustering algorithm according to the feature vector matrix and the expert experience rule base to obtain a fuzzy rule base;

[0121] Clustering the feature vector matrix based on a density clustering algorithm to obtain a number of clusters;

[0122] The cluster is set as the condition part of the fuzzy rule, and the conclusion part of the fuzzy rule is determined according to the control strategy preset in the expert experience rule base to obtain the fuzzy rule;

[0123] A fuzzy rule base is constructed according to the fuzzy rules.

[0124] The eigenvector matrix is ​​clustered based on a density clustering algorithm to obtain several clusters, including:

[0125] Preset parameters, including field radius and minimum number of samples;

[0126] Calculate the distance between each data point in the feature vector matrix based on the Euclidean distance;

[0127] Calculate the number of points within the domain radius for each of the data points;

[0128] Determine and compare the size between the number of points and the minimum number of samples, and if the number of points is not less than the minimum number of samples, mark the data point as a core point;

[0129] According to the core points, all the data points are divided into different clusters based on density directness and density connectivity.

[0130] The specific steps are as follows:

[0131] Calculate the distance between each data point in the feature vector matrix based on the Euclidean distance;

[0132] Based on the preset domain radius and minimum number of samples, the neighborhood radius ∈ determines the neighborhood range of a point, and the minimum number of samples MinPts defines the number of samples in the minimum neighborhood of a core point;

[0133] For each data point X i , calculate the number of points in the area with ∈ as the radius, recorded as N ∈ (X i ), if N ∈ (X i )≥MinPts, then X i Mark as core point.

[0134] If you click X j At point X i ∈ is in the neighborhood of X i is the core point, then X j With X i Density direct.

[0135] If there exists a sample sequence p1,p2,...,p n , so that p1=X i , p n =X j , and for any p k , p k+1 The density reaches p k , then X i With X j Density connected.

[0136] Determine which points are density-direct or density-connected. Based on the relationship between density-direct and density-connected, we divide the data points into different clusters.

[0137] The following is the formal representation of fuzzy rules:

[0138] Rule 1:

[0139] Condition part: The device status belongs to cluster 1;

[0140] Conclusion: Adopt control strategy A;

[0141] This rule can be expressed as follows:

[0142] IF the device status belongs to cluster 1 THEN adopt control strategy A.

[0143] Rule 2:

[0144] Condition part: The device status belongs to cluster 2;

[0145] Conclusion: Adopt control strategy B;

[0146] This rule can be expressed as follows:

[0147] IF the device status belongs to cluster 2 THEN adopt control strategy B.

[0148] Rule 3:

[0149] Condition part: The device status belongs to cluster 3;

[0150] Conclusion: Adopt control strategy C;

[0151] This rule can be expressed as follows:

[0152] IF the device status belongs to cluster 3 THEN adopt control strategy C.

[0153] Step S600: Perform fuzzy reasoning according to the second information and the fuzzy rule base to obtain a fuzzy output, and control the power plant equipment according to the fuzzy output.

[0154] Matching the second information with the fuzzy rules in the fuzzy rule base, and calculating the corresponding matching degree;

[0155] Determine a fuzzy output according to the matching degree;

[0156] The fuzzy output is defuzzified into a real-time control strategy, and the power plant equipment is controlled according to the real-time control strategy.

[0157] Fuzzification input: The input value, i.e., the second information, is converted into the membership of the corresponding fuzzy set through the corresponding membership function. This involves mapping the actual value to a membership value on each fuzzy set.

[0158] Matching fuzzy rules: For each fuzzy rule, match the input fuzzy value with the fuzzy conditions in the rule. This involves comparing the membership of the input value with the membership of the corresponding fuzzy set in the rule.

[0159] Calculate the matching degree: For each fuzzy rule, use the minimum operation, that is, take the minimum value of the membership of the input value as the matching degree. For example, if the condition of a rule contains two input variables, whose membership degrees are 0.6 and 0.8 respectively, then the matching degree is min(0.6,0.8)=0.6.

[0160] Reasoning process: Determine the fuzzy output of each output variable based on the matching degree of the rule. The membership value of the fuzzy output is associated with the matching degree of the rule. For example, if the matching degree of a rule is 0.6 and its output is "strong", the membership value of the output variable "strong" is 0.6.

[0161] Aggregate fuzzy output: Aggregate the fuzzy outputs of all rules to get the fuzzy output of the system. Use the maximum operation in the fuzzy logic operation rules to aggregate the fuzzy output. This means taking the maximum membership value of each output variable as the aggregated membership value.

[0162] Defuzzification: Finally, the aggregated fuzzy output is converted into a specific output value through a defuzzification method. The defuzzification method can be weighted average, center method, maximum method, etc.

[0163] The power plant unattended equipment control method further includes:

[0164] Constructing a state space according to the real-time network structure characteristics and the real-time data of the state parameters;

[0165] Constructing an action space according to the expert experience rule base;

[0166] designing a reward function according to equipment stability, energy utilization efficiency and equipment loss of the power plant equipment;

[0167] According to the state space, the action space and the reward function, training a Q value table based on a Q learning algorithm;

[0168] Iteratively updating the Q value table based on a Q learning update rule according to the second information and the real-time control strategy until a preset stop iteration condition is reached to obtain an updated Q value table;

[0169] The action with the highest Q value in the updated Q value table is taken as the optimal control strategy.

[0170] Compared with the prior art, the present invention has the following advantages:

[0171] Comprehensively consider the relationship and status information between devices: By using network topology characteristics and device status parameter characteristics together for fuzzy reasoning, the connection relationship and status information between devices can be comprehensively considered. By analyzing the topology characteristics, the dependency and influence between devices can be understood; and through the device status parameter characteristics, the real-time operating status of the device can be obtained. In this way, fuzzy reasoning can more comprehensively consider the mutual influence between devices and improve the accuracy and reliability of decision-making.

[0172] Enhance the adaptability of the system: The connection relationship and topology between devices may change with time and environment, and the device state parameters will also change with the change of the device operation state. Using these two characteristics together for fuzzy reasoning can enhance the adaptability and flexibility of the system, enabling the system to perceive and respond to different operation states and environmental changes in a timely manner, thereby improving the adaptability and robustness of the system.

[0173] Improve the comprehensiveness and intelligence of decision-making: Using topological structure characteristics and equipment status parameter characteristics together for fuzzy reasoning can make the decision-making process more comprehensive and intelligent. By comprehensively considering the connection relationship and status information between devices, the system can generate more comprehensive and reasonable decisions, thereby realizing intelligent control and management of power plant equipment.

[0174] Reduce misjudgment and improve efficiency: Using topological structure characteristics and equipment status parameter characteristics together for fuzzy reasoning can reduce the possibility of misjudgment and improve the accuracy and efficiency of decision-making. By comprehensively considering different information sources, the system can more accurately judge the operating status and health of the equipment and take corresponding measures in a timely manner, thereby reducing the risk of system failure and downtime and improving the operating efficiency and stability of the system.

[0175] In summary, using the complex network topology structure characteristics and equipment status parameter characteristics between power plant equipment for fuzzy reasoning can give full play to the advantages of various information, improve the accuracy and intelligence level of decision-making, and provide a more comprehensive and effective solution for the control and management of power plant equipment.

[0176] Embodiment 2:

[0177] This embodiment provides a fuzzy logic-based unattended equipment control device for a power plant, the device comprising:

[0178] A first acquisition module, the first acquisition module is used to acquire first information, the first information includes historical data of connection relationships between power plant equipment, historical data of status parameters of each of the power plant equipment, and a preset expert experience rule base, the expert experience rule base includes control strategies for each of the power plant equipment;

[0179] A second acquisition module, the second acquisition module is used to acquire second information, the second information including real-time data of connection relationships between power plant equipment and real-time data of status parameters of each of the power plant equipment;

[0180] A feature extraction module, wherein the feature extraction module is used to construct a complex network topology structure between the power plant equipment based on the historical data of the connection relationship between the power plant equipment and the graph theory method, and to extract features from the complex network topology structure to obtain network structure features;

[0181] A construction module, the construction module is used to map the historical data of the network structure characteristics and the state parameters to a fuzzy set, and construct a feature vector matrix according to the fuzzy set;

[0182] A formulation module, the formulation module is used to formulate fuzzy rules based on the density clustering algorithm according to the feature vector matrix and the expert experience rule base to obtain a fuzzy rule base;

[0183] An inference module is used to perform inference based on the second information and the fuzzy rule base based on a minimum-maximum fuzzy inference algorithm to obtain a fuzzy output, and control the power plant equipment according to the fuzzy output.

[0184] It should be noted that, regarding the device in the above embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment of the method, and will not be elaborated here.

[0185] Embodiment 3:

[0186] Corresponding to the above method embodiment, this embodiment also provides a power plant unattended equipment control device based on fuzzy logic. The power plant unattended equipment control device based on fuzzy logic described below and the power plant unattended equipment control method based on fuzzy logic described above can be referenced to each other.

[0187] Figure 3 FIG. 8 is a block diagram of a power plant unattended equipment control device 800 based on fuzzy logic according to an exemplary embodiment. Figure 3 As shown, the fuzzy logic-based power plant unattended equipment control device 800 may include: a processor 801 and a memory 802. The fuzzy logic-based power plant unattended equipment control device 800 may also include one or more of a multimedia component 803, an I / O interface 804, and a communication component 805.

[0188] The processor 801 is used to control the overall operation of the fuzzy logic-based power plant unattended equipment control device 800 to complete all or part of the steps in the above-mentioned fuzzy logic-based power plant unattended equipment control method. The memory 802 is used to store various types of data to support the operation of the fuzzy logic-based power plant unattended equipment control device 800, and these data may include, for example, instructions for any application or method operating on the fuzzy logic-based power plant unattended equipment control device 800, and application-related data, such as contact data, sent and received messages, pictures, audio, video, etc. The memory 802 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, disk or optical disk. The multimedia component 803 may include a screen and an audio component. The screen may be, for example, a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signal may be further stored in the memory 802 or sent via the communication component 805. The audio component also includes at least one speaker for outputting audio signals. The I / O interface 804 provides an interface between the processor 801 and other interface modules, and the above-mentioned other interface modules can be keyboards, mice, buttons, etc. These buttons can be virtual buttons or physical buttons. The communication component 805 is used for wired or wireless communication between the unattended equipment control device 800 of the power plant based on fuzzy logic and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G or 4G, or a combination of one or more of them, so the corresponding communication component 805 can include: Wi-Fi module, Bluetooth module, NFC module.

[0189] In an exemplary embodiment, the fuzzy logic-based power plant unattended equipment control device 800 can be implemented by one or more application-specific integrated circuits (Application Specific Integrated Circuit, referred to as ASIC), digital signal processors (Digital Signal Processor, referred to as DSP), digital signal processing devices (Digital Signal Processing Device, referred to as DSPD), programmable logic devices (Programmable Logic Device, referred to as PLD), field programmable gate arrays (Field Programmable Gate Array, referred to as FPGA), controllers, microcontrollers, microprocessors or other electronic components to execute the above-mentioned fuzzy logic-based power plant unattended equipment control method.

[0190] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, and when the program instructions are executed by a processor, the steps of the above-mentioned power plant unattended equipment control method based on fuzzy logic are implemented. For example, the computer-readable storage medium can be the above-mentioned memory 802 including program instructions, and the above-mentioned program instructions can be executed by the processor 801 of the power plant unattended equipment control device 800 based on fuzzy logic to complete the above-mentioned power plant unattended equipment control method based on fuzzy logic.

[0191] Embodiment 4:

[0192] Corresponding to the above method embodiment, a readable storage medium is also provided in this embodiment. The readable storage medium described below and the fuzzy logic-based unmanned equipment control method for a power plant described above can refer to each other.

[0193] A readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the fuzzy logic-based power plant unattended equipment control method of the above method embodiment.

[0194] The readable storage medium may specifically be a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, or other readable storage medium that can store program codes.

[0195] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

[0196] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for controlling unattended equipment in a power plant based on fuzzy logic, characterized in that: include: Acquire first information, wherein the first information includes historical data of connection relationships between power plant devices, historical data of status parameters of each of the power plant devices, and a preset expert experience rule base, wherein the expert experience rule base includes control strategies for each of the power plant devices; Acquire second information, wherein the second information includes real-time data of connection relationships between power plant devices and real-time data of status parameters of each of the power plant devices; According to the historical data of the connection relationship between the power plant equipment, a complex network topology structure between the power plant equipment is constructed based on a graph theory method, and features of the complex network topology structure are extracted to obtain network structure features; Mapping the network structure characteristics and the historical data of the state parameters to a fuzzy set, and constructing a feature vector matrix according to the fuzzy set; According to the feature vector matrix and the expert experience rule base, fuzzy rules are formulated based on a density clustering algorithm to obtain a fuzzy rule base; Perform fuzzy reasoning according to the second information and the fuzzy rule base to obtain a fuzzy output, and control the power plant equipment according to the fuzzy output; Wherein, fuzzy reasoning is performed according to the second information and the fuzzy rule base to obtain a fuzzy output, and the power plant equipment is controlled according to the fuzzy output: Matching the second information with the fuzzy rules in the fuzzy rule base, and calculating the corresponding matching degree; Determine a fuzzy output according to the matching degree; The fuzzy output is defuzzified into a real-time control strategy, and the power plant equipment is controlled according to the real-time control strategy.

2. The fuzzy logic-based unattended power plant equipment control method according to claim 1, characterized in that ,According to the historical data of the connection relationship between the power plant equipment, a complex network topology structure between the power plant equipment is constructed based on the graph theory method, including: Taking each of the power plant equipment as a node, and constructing a device node set according to each of the nodes; Establishing edges between the power plant devices according to historical data of connection relationships between the power plant devices, wherein the connection relationships include physical connection, signal transmission, and data exchange; A complex network topology structure between the power plant equipment is constructed according to the edges established between the node set and the power plant equipment.

3. The fuzzy logic-based unattended power plant equipment control method according to claim 1, characterized in that , extract features from the complex network topology to obtain network structure features, including: constructing an adjacency matrix according to the complex network topology structure; Acquire the number of nodes, the connection relationship between nodes, the number of triangles connected to each node, the number of shortest paths between nodes, and the number of shortest paths passing through each node according to the adjacency matrix; Extracting the degree of each of the nodes according to the number of the nodes and the connection relationship between the nodes; Extracting a clustering coefficient of each node according to the degree of the node and the number of triangles connected to each node; The betweenness centrality of each of the nodes is extracted based on the number of shortest paths between the nodes and the number of shortest paths passing through each of the nodes.

4. The fuzzy logic-based unattended power plant equipment control method according to claim 3 is characterized in that ,The state parameters include the temperature, pressure and flow of the power plant equipment, and the historical data of the network structure characteristics and the state parameters are mapped to fuzzy sets, including: Mapping the degrees of the nodes to a low-degree fuzzy set, a medium-degree fuzzy set and a high-degree fuzzy set, respectively, and setting the membership functions of the low-degree fuzzy set, the medium-degree fuzzy set and the high-degree fuzzy set, respectively; Mapping the clustering coefficients to a low clustering coefficient fuzzy set, a medium clustering coefficient fuzzy set and a high clustering coefficient fuzzy set respectively, and setting the membership functions of the low clustering coefficient fuzzy set, the medium clustering coefficient fuzzy set and the high clustering coefficient fuzzy set respectively; Mapping the betweenness centrality to a low betweenness centrality fuzzy set, a betweenness centrality fuzzy set, and a high betweenness centrality fuzzy set, respectively, and setting the membership functions of the low betweenness centrality fuzzy set, the betweenness centrality fuzzy set, and the high betweenness centrality fuzzy set, respectively; Mapping the temperatures to a low temperature set, a medium temperature set and a high temperature set respectively, and setting the membership functions of the low temperature fuzzy set, the medium temperature fuzzy set and the high temperature fuzzy set respectively; Mapping the pressure to a low pressure set, a medium pressure set and a high pressure set respectively, and setting the membership functions of the low pressure fuzzy set, the medium pressure fuzzy set and the high pressure fuzzy set respectively; The traffic is mapped to a low traffic set, a medium traffic set and a high traffic set respectively, and the membership functions of the low traffic fuzzy set, the medium traffic fuzzy set and the high traffic fuzzy set are set respectively.

5. The fuzzy logic-based unattended power plant equipment control method according to claim 4 is characterized in that ,The state parameters include the temperature, pressure and flow of the power plant equipment, and the historical data of the network structure characteristics and the state parameters are mapped to fuzzy sets, including: For the degree k of a node i , mapping it to low degree K L , Moderate K M and height K H Among the three fuzzy sets, the corresponding membership functions are and in: For the clustering coefficient C of the node i , mapping it to a low clustering coefficient C L , the clustering coefficient C M and high clustering coefficient C H Among the three fuzzy sets, the corresponding membership functions are and in: For the betweenness centrality of a node B i , mapping it to the low betweenness centrality B L , betweenness centrality B M and high betweenness centrality B H The three fuzzy sets and their corresponding membership functions are and in: For the device temperature T i , which is mapped to the low temperature T L , medium temperature T M and high temperature T H The three fuzzy sets and their corresponding membership functions are and in: For the equipment pressure P i , mapping it to the low voltage T L , Medium Pressure T M and high voltage T H The three fuzzy sets and their corresponding membership functions are and in: For device flow Q i , mapping it to the low flow Q L , medium flow Q M and high flow Q H The three fuzzy sets and their corresponding membership functions are and in:

6. The fuzzy logic-based unattended power plant equipment control method according to claim 1 or 4, characterized in that: Constructing a feature vector matrix according to the fuzzy set includes: Acquire all the membership vectors of each of the power plant equipment according to the fuzzy sets of each of the power plant equipment and the membership functions corresponding to the fuzzy sets; Connecting all the membership vectors of the power plant equipment to form a feature vector of the power plant equipment; The eigenvectors of all the devices are arranged to form an eigenvector matrix, wherein the rows of the eigenvector matrix represent each of the power plant devices, and the columns represent the eigenvectors of each of the power plant devices.

7. The fuzzy logic-based unattended power plant equipment control method according to claim 1, characterized in that ,According to the eigenvector matrix, fuzzy rules are formulated based on the density clustering algorithm to obtain the fuzzy rule base, including Clustering the feature vector matrix based on a density clustering algorithm to obtain a number of clusters; The cluster is set as the condition part of the fuzzy rule, and the conclusion part of the fuzzy rule is determined according to the control strategy preset in the expert experience rule base to obtain the fuzzy rule; A fuzzy rule base is constructed according to the fuzzy rules.

8. The fuzzy logic-based unattended power plant equipment control method according to claim 1, characterized in that , obtain the first information, including: Acquire historical original data, historical original data on connection relationships between power plant equipment, and historical original data on status parameters of each of the power plant equipment; Performing outlier detection on the historical original data based on a deep learning autoencoder to obtain first data; Performing interpolation processing on the first data based on a high-order graph convolutional neural network to obtain second data; The second data is normalized based on the maximum and minimum normalization method to obtain the first information.

9. A fuzzy logic-based unattended equipment control device for a power plant, characterized in that: include: A first acquisition module, the first acquisition module is used to acquire first information, the first information includes historical data of connection relationships between power plant equipment, historical data of status parameters of each of the power plant equipment, and a preset expert experience rule base, the expert experience rule base includes control strategies for each of the power plant equipment; A second acquisition module, the second acquisition module is used to acquire second information, the second information including real-time data of connection relationships between power plant devices and real-time data of status parameters of each of the power plant devices; A feature extraction module, wherein the feature extraction module is used to construct a complex network topology structure between the power plant equipment based on the historical data of the connection relationship between the power plant equipment and the graph theory method, and to extract features from the complex network topology structure to obtain network structure features; A construction module, the construction module is used to map the historical data of the network structure characteristics and the state parameters to a fuzzy set, and construct a feature vector matrix according to the fuzzy set; A formulation module, the formulation module is used to formulate fuzzy rules based on the density clustering algorithm according to the feature vector matrix and the expert experience rule base to obtain a fuzzy rule base; An inference module, the inference module is used to perform fuzzy inference according to the second information and the fuzzy rule base to obtain a fuzzy output, and control the power plant equipment according to the fuzzy output; Wherein, fuzzy reasoning is performed according to the second information and the fuzzy rule base to obtain a fuzzy output, and the power plant equipment is controlled according to the fuzzy output: Matching the second information with the fuzzy rules in the fuzzy rule base, and calculating the corresponding matching degree; Determine a fuzzy output according to the matching degree; The fuzzy output is defuzzified into a real-time control strategy, and the power plant equipment is controlled according to the real-time control strategy.

Images