High-temperature safety valve heat dissipation protection system and method thereof

Abstract

The embodiment of the invention provides a heat dissipation protection system and method for a high-temperature safety valve. The method comprises the steps that state information and historical opening and closing information of the valve are converted into a node training data set; matching the safety valve position topology and the electromagnetic valve position topology with the node training data set to obtain a correlation coefficient matrix; inputting the correlation coefficient matrix into an input layer of an extreme learning machine model to obtain a first feature vector; inputting the security training data set as observation data into a hidden Markov model to obtain hidden Markov model parameters; constructing a hidden variable probability model according to the hidden Markov model parameters and the state information of the pipeline substances; obtaining predicted valve opening and closing probability values of the safety valve and the electromagnetic valve through the hidden variable probability model, and displaying the predicted valve opening and closing probability values of the safety valve and the electromagnetic valve; heat dissipation protection can be carried out on a pipeline corresponding to the safety valve in advance through a prediction result, and the system plays an important role in equipment safety and personal safety.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular, to a heat dissipation protection method for a high-temperature safety valve, a heat dissipation protection system for a high-temperature safety valve, a computer device, and a storage medium. Background Art

[0002] A safety valve is a special valve in which the closing member is in a normally closed state under the action of an external force. When the pressure of the medium in the equipment or pipeline rises above a specified value, the medium is discharged to the outside of the system to prevent the pressure of the medium in the pipeline or equipment from exceeding the specified value. The safety valve belongs to the category of automatic valves and is mainly used on boilers, pressure vessels, and pipelines to control the pressure not to exceed the specified value, playing an important role in protecting personal safety and equipment operation. However, the existing safety valves only determine whether to open or close according to the state of the corresponding pipeline, and the safety is limited. Summary of the Invention

[0003] In view of the above problems, embodiments of the present invention are proposed to provide a heat dissipation protection method for a high-temperature safety valve, a heat dissipation protection system for a high-temperature safety valve, a computer device, and a storage medium that overcome the above problems or at least partially solve the above problems.

[0004] To solve the above problems, embodiments of the present invention disclose a heat dissipation protection method for a high-temperature safety valve, including: Obtaining the position information of multiple safety valves and solenoid valves in a pipe network node, the state information of the corresponding pipeline substances, and the historical opening and closing information of the valves; wherein, the state information includes temperature information; Converting the position information of the multiple safety valves and solenoid valves into a safety valve position topology and a solenoid valve position topology; Converting the state information and the historical opening and closing information of the valves into a node training data set; Matching the safety valve position topology and the solenoid valve position topology with the node training data set to obtain a correlation coefficient matrix; Inputting the correlation coefficient matrix into the input layer of an extreme learning machine model to obtain a first feature vector; Training the first feature vector through a hidden layer to obtain a second feature vector, setting the parameters corresponding to the safety valve position topology and the solenoid valve position topology as the connection weights and thresholds of the hidden layer, and transmitting the second feature vector to the output layer to obtain a trained extreme learning machine model; Inputting the position information of new safety valves and solenoid valves and the corresponding state information of pipeline substances into the trained extreme learning machine model to obtain the output valve opening and closing information, and forming a safety training data set with the position information of the new safety valves and solenoid valves, the corresponding state information of pipeline substances, and the valve opening and closing information; Input the safety training data set as observed data into the hidden Markov model to obtain the hidden Markov model parameters; Construct a hidden variable probability model based on the hidden Markov model parameters and the state information of the pipeline substance; Obtain the predicted valve opening and closing probability values of the safety valve and the solenoid valve through the hidden variable probability model, and display the predicted valve opening and closing probability values of the safety valve and the solenoid valve.

[0005] Preferably, the conversion of the position information of the multiple safety valves and solenoid valves into the safety valve position topology and the solenoid valve position topology includes: Identify the position information of the safety valve from the pipeline network plane design drawing; Identify the position information of the solenoid valve from the pipeline network plane design drawing; Convert the position information of the safety valve into the safety valve position topology; Convert the position information of the solenoid valve into the solenoid valve position topology.

[0006] Preferably, the matching of the safety valve position topology and the solenoid valve position topology with the node training data set to obtain the correlation coefficient matrix includes: Convert the safety valve position topology and the solenoid valve position topology into sequence data; the sequence data includes valve sequence data; Identify the subset data in the node training data set corresponding to the safety valve and the solenoid valve pipelines, and the subset data includes state information and valve historical opening and closing information; Form a single matrix element with the valve sequence data and the corresponding subset data, form matrix rows or matrix columns through the elements, form the original matrix from the matrix rows or matrix columns, and obtain the correlation coefficient matrix through the original matrix.

[0007] Preferably, the training of the first eigenvector through the hidden layer to obtain the second eigenvector, setting the parameters corresponding to the safety valve position topology and the solenoid valve position topology as the link weights and thresholds of the hidden layer, and transmitting the second eigenvector to the output layer to obtain the trained extreme learning machine model includes: Set the valve sequence data corresponding to the safety valve position topology and the solenoid valve position topology as the initial value of the link weights of the hidden layer of the extreme learning machine model; Determine the maximum value in the sequence data as the threshold of the hidden layer of the extreme learning machine model; Train the first eigenvector through the hidden layer to obtain the second eigenvector; Transmit the second eigenvector to the output layer to obtain the trained extreme learning machine model.

[0008] Preferably, inputting the safety training data set as observation data into a hidden Markov model to obtain hidden Markov model parameters includes: Inputting the safety training data set as observation data into a hidden Markov model; When the number of iterations is zero, determining the first initial parameter, the second initial parameter, and the third initial parameter of the hidden Markov model; Performing iterative processing on the hidden Markov model for the first initial parameter, the second initial parameter, and the third initial parameter, and when the number of iterations reaches the maximum value, obtaining the hidden Markov model parameters.

[0009] Preferably, constructing a hidden variable probability model according to the hidden Markov model parameters and the state information of the pipeline substance includes: Constructing a hidden variable probability model through the hidden Markov model parameters, the state information of the pipeline substance, the position information of the safety valve and the solenoid valve, and the valve opening and closing information.

[0010] Preferably, obtaining the predicted valve opening and closing probability values of the safety valve and the solenoid valve through the hidden variable probability model and outputting the predicted valve opening and closing probability values includes: Solving the hidden variable probability model through the Viterbi algorithm to obtain the predicted valve opening and closing probability values of the safety valve and the solenoid valve, and displaying the predicted valve opening and closing probability values of the safety valve and the solenoid valve.

[0011] An embodiment of the present invention discloses a high-temperature safety valve heat dissipation protection system, including: A first acquisition module, configured to acquire the position information of a plurality of safety valves and solenoid valves at the pipe network node, the corresponding state information of the pipeline substance, and the valve historical opening and closing information; wherein, the state information includes temperature information; A first conversion module, configured to convert the position information of the plurality of safety valves and solenoid valves into a safety valve position topology and a solenoid valve position topology; A second conversion module, configured to convert the state information and the valve historical opening and closing information into a node training data set; A matching module, configured to match the safety valve position topology and the solenoid valve position topology with the node training data set to obtain a correlation coefficient matrix; A first input module, configured to input the correlation coefficient matrix into the input layer of an extreme learning machine model to obtain a first feature vector; A setting module, configured to obtain a second feature vector through training of the first feature vector by the hidden layer, set the parameters corresponding to the safety valve position topology and the solenoid valve position topology as the connection weights and thresholds of the hidden layer, and transmit the second feature vector to the output layer to obtain a trained extreme learning machine model; A composition module is used to input the position information of a new safety valve and solenoid valve and the corresponding state information of the pipeline substance into a trained extreme learning machine model to obtain the output valve opening and closing information, and form a safety training data set with the position information of the new safety valve and solenoid valve, the corresponding state information of the pipeline substance, and the valve opening and closing information. A second input module is used to input the safety training data set as observation data into a hidden Markov model to obtain hidden Markov model parameters. A construction module is used to construct a hidden variable probability model according to the hidden Markov model parameters and the state information of the pipeline substance. A display module is used to obtain the predicted valve opening and closing probability values of the safety valve and solenoid valve through the hidden variable probability model, and display the predicted valve opening and closing probability values of the safety valve and solenoid valve.

[0012] An embodiment of the present invention also discloses a computer device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the steps of the above-mentioned high-temperature safety valve heat dissipation protection are implemented.

[0013] An embodiment of the present invention also discloses a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned high-temperature safety valve heat dissipation protection are implemented.

[0014] The embodiments of the present invention have the following advantages: In an embodiment of the present invention, the method includes: obtaining position information of multiple safety valves and solenoid valves at pipeline nodes, corresponding state information of pipeline substances, and historical opening and closing information of the valves; wherein, the state information includes temperature information; converting the position information of the multiple safety valves and solenoid valves into a safety valve position topology and a solenoid valve position topology; converting the state information and the historical opening and closing information of the valves into a node training data set; matching the safety valve position topology and the solenoid valve position topology with the node training data set to obtain a correlation coefficient matrix; inputting the correlation coefficient matrix into the input layer of an extreme learning machine model to obtain a first feature vector; training the first feature vector through a hidden layer to obtain a second feature vector, setting the safety valve position topology and the solenoid valve position topology as the link weights and the thresholds of the hidden layer, transmitting the second feature vector to an output layer to obtain a trained extreme learning machine model; inputting position information of new safety valves and solenoid valves and corresponding state information of pipeline substances into the trained extreme learning machine model to obtain output valve opening and closing information, and forming a safety training data set with the position information of the new safety valves and solenoid valves, the corresponding state information of pipeline substances, and the valve opening and closing information; using the safety training data set as observed data and inputting it into a hidden Markov model to obtain hidden Markov model parameters; constructing a hidden variable probability model based on the hidden Markov model parameters and the state information of pipeline substances; obtaining predicted valve opening and closing probability values of the safety valves and solenoid valves through the hidden variable probability model, and displaying the predicted valve opening and closing probability values of the safety valves and solenoid valves; obtaining the probability of opening and closing of each valve, improving the accuracy of valve opening and closing prediction, displaying the probability values of opening and closing of each valve to the user, providing suggestions for valve opening and closing or predicting the valve operating state, improving the monitoring safety of the pipeline network, and being able to perform heat dissipation protection on the pipeline corresponding to the safety valve in advance through the prediction result, and the system plays an important role in equipment safety and personal safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0016] Figure 1 It is a flowchart of the steps of an embodiment of a high-temperature safety valve heat dissipation protection method according to an embodiment of the present invention; Figure 2 It is a schematic diagram of a solenoid valve position topology according to an embodiment of the present invention; Figure 3 It is a schematic diagram of a safety valve position topology according to an embodiment of the present invention; Figure 4 It is a structural block diagram of an embodiment of a high-temperature safety valve heat dissipation protection system according to an embodiment of the present invention; Figure 5 It is an internal structure diagram of a computer device according to an embodiment. Specific embodiments

[0017] In order to make the technical problems, technical solutions and beneficial effects solved by the embodiments of the present invention clearer, the following further details the embodiments of the present invention in conjunction with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0018] In the embodiments of the present invention, through the positions of two types of valves in the pipe network and the valve opening and closing history, after the secondary prediction operation of the extreme learning machine and the hidden Markov model, where the pipe network state and the valve opening and closing history are used as training samples to obtain the trained extreme learning machine, and then the output of the extreme learning machine and some original data are used as the input of the hidden Markov model to obtain the opening and closing probabilities of each valve, improving the accuracy of valve opening and closing prediction, displaying the opening and closing probability values of each valve to the user, providing suggestions for valve opening and closing or predicting the valve operating state, improving the monitoring safety of the pipe network, and through the prediction results, heat dissipation protection can be carried out in advance for the pipeline corresponding to the safety valve, and the system plays an important role in equipment safety and personal safety.

[0019] Referring to Figure 1 , it shows a step flow chart of an embodiment of a high-temperature safety valve heat dissipation protection method according to an embodiment of the present invention, which specifically may include the following steps: Step 101, obtaining the position information of multiple safety valves and solenoid valves at the pipe network nodes, the state information of the corresponding pipeline substances, and the valve historical opening and closing information; wherein, the state information includes temperature information; In the embodiments of the present invention, the method is applied to a pipeline network system, which may include various pipelines, safety valves, solenoid valves, flow meters, and various sensors, etc. Safety valves, solenoid valves, etc. are respectively installed on various pipelines, and the pipeline network system is also connected through a terminal, and the terminal can obtain the information of various solenoid valves and sensors and control the operation of the solenoid valves or sensors through the control system of the pipeline network. The embodiments of the present invention do not impose too many restrictions on the structure and devices of the pipeline network; further, the terminal may be, but is not limited to, various personal computers, laptop computers, smart phones, tablet computers, and portable wearable devices. The embodiments of the present invention do not limit the specific type of the terminal, and the operating system of the terminal may include Android, Harmony OS, IOS, Windows Phone, Windows, etc. The present invention does not impose too many restrictions on this.

[0020] The pipeline network system can be composed of a variety of pipeline network nodes, and the pipeline network node can refer to the pipeline and the valves at both ends. The valve can be an electromagnetic valve or a safety valve. Further, the safety valve can include a mechanical safety valve or an electromagnetic safety valve. The embodiments of the present invention do not impose excessive restrictions on this; The position information can refer to the planar coordinates of the safety valve and the electromagnetic valve in the pipeline network plane design drawing; In addition, the state information of the pipeline substance can refer to the temperature information, humidity information, flow rate information, etc. of the pipeline content. The embodiments of the present invention do not impose excessive restrictions on this. Further, the pipeline content can be a gas, a liquid, etc. The embodiments of the present invention do not impose excessive restrictions on this; and the valve historical opening and closing information can include the number of times each valve is opened or closed, the reason for opening or closing, and the duration of opening or closing; Step 102, convert the position information of the multiple safety valves and electromagnetic valves into a safety valve position topology and an electromagnetic valve position topology; In the embodiments of the present invention, the conversion of the position information of the multiple safety valves and electromagnetic valves into a safety valve position topology and an electromagnetic valve position topology includes: identifying the position information of the safety valve from the pipeline network plane design drawing; identifying the position information of the electromagnetic valve from the pipeline network plane design drawing; Convert the position information of the safety valve into a safety valve position topology; Convert the position information of the electromagnetic valve into an electromagnetic valve position topology.

[0021] In the embodiments of the present invention, the position information of the safety valve and the electromagnetic valve are respectively identified from the pipeline network plane design drawing, and are respectively converted into a position topology diagram according to the position information of the two, as Figure 2 and Figure 3 shown. Classifying the valves increases the diversity of the samples, realizes the digitization of the valve positions such as electromagnetic valves, and is used for the training of the model and the setting of the initial parameters of the model, improving the training efficiency and matching of the model.

[0022] Step 103, convert the state information and the valve historical opening and closing information into a node training data set; Step 104, match the safety valve position topology and the electromagnetic valve position topology with the node training data set to obtain a correlation coefficient matrix; Further applied to the embodiments of the invention, the status information and the valve historical opening and closing information can also be converted into a node training data set, that is, the temperature information, humidity information, flow information of the pipeline content, the number of times each valve is opened or closed, the reason for opening or closing, and the duration of opening or closing are combined to form a node training data set; then the safety valve position topology and the solenoid valve position topology are matched with the node training data set to obtain a correlation coefficient matrix; Specifically in the embodiments of the present invention, the matching of the safety valve position topology and the solenoid valve position topology with the node training data set to obtain a correlation coefficient matrix includes: Converting the safety valve position topology and the solenoid valve position topology into sequence data; the sequence data includes valve sequence data; wherein, the valve sequence data may refer to the sequence information composed of the position information and serial number information of each valve and the connection relationship with other pipeline valves, and the embodiments of the present invention do not limit this too much; the connection relationship of the other pipeline valves is the serial number of the other pipeline valves and the pipeline number; Identifying subset data in the node training data set corresponding to the pipelines of the safety valve and the solenoid valve, and the subset data includes status information and valve historical opening and closing information; Combining the valve sequence data and the corresponding subset data into a single matrix element, and obtaining a correlation coefficient matrix through the single matrix element.

[0023] Further applied to the embodiments of the present invention, the elements in the correlation coefficient matrix may include status information, valve historical opening and closing information, and valve sequence data, and then form matrix rows or matrix columns through the elements, form an original matrix through the matrix rows or matrix columns, and obtain a correlation coefficient matrix through the original matrix; For example, the status information is A1, A2, A3, A4, the valve historical opening and closing information is b1, b2, b3, b4, and the valve sequence data is c1, c2, c3, c4, then the element may include (A1b1c1), and the matrix row or matrix column can be formed through the above elements. A certain matrix row may include (A1b1c1) (A2b2c3) (A3b3c3) (A4b4c4), and then form an original matrix through the matrix row or matrix column, calculate the correlation coefficient between the matrix rows or matrix columns, and eliminate the matrix rows or matrix columns with a correlation coefficient less than a preset threshold, and the remaining matrix rows or matrix column combinations are used as the correlation coefficient matrix, further eliminating invalid data and ensuring the accuracy of the model training data.

[0024] In the embodiments of the present invention, the correlation coefficient between the matrix rows or matrix columns can be calculated in various ways, such as calculating the correlation coefficient between the matrix rows or matrix columns by means of covariance and standard deviation, and the embodiments of the present invention do not limit this too much; Step 105: Input the correlation coefficient matrix into the input layer of the extreme learning machine model to obtain the first eigenvector; Step 106: Through the training of the first eigenvector passing through the hidden layer, obtain the second eigenvector. Set the safety valve position topology and the solenoid valve position topology as the connection weights and thresholds of the hidden layer, and transmit the second eigenvector to the output layer to obtain the trained extreme learning machine model; In the embodiment of the present invention, training data with high correlation, that is, the correlation coefficient matrix, can also be input into the input layer of the extreme learning machine model to obtain the first eigenvector. The extreme learning machine model mainly includes 1 input layer, a hidden layer, and 1 output layer; Through the training of the first eigenvector passing through the hidden layer, obtain the second eigenvector. Set the safety valve position topology and the solenoid valve position topology as the connection weights of the hidden layer and the threshold of the hidden layer, and transmit the second eigenvector to the output layer to obtain the trained extreme learning machine model, including: Set the valve sequence data corresponding to the safety valve position topology and the solenoid valve position topology as the initial value of the connection weights of the network nodes of this extreme learning machine model; alternatively, part of the data in the valve sequence data can also be set as the initial value of the connection weights of the network nodes of this extreme learning machine model. For example, set the serial number of the other pipeline valve and the pipeline number as the initial value of the connection weights of the network nodes of this extreme learning machine model, and map to the topological structure of the extreme learning machine model through two valve position topologies. The workload of model training is reduced, computing resources are saved, and the accuracy of model training is improved. The embodiment of the present invention does not limit this too much.

[0025] Determine the maximum value in the sequence data as the threshold of the network nodes of this extreme learning machine model; Through the training of the first eigenvector passing through the hidden layer, obtain the second eigenvector; Transmit the second eigenvector to the output layer to obtain the trained extreme learning machine model; By simulating the initial weight parameters of the hidden layer of the neural network through the topological position, the workload of model training is reduced, computing resources are saved, and the accuracy of model training is improved; This extreme learning machine model E can be expressed as follows: ; Among them, l represents the number of nodes in the hidden layer, represents the connection weight of the i-th node in the hidden layer, g(x) represents the activation function, x represents the sequence data of the correlation coefficient matrix, that is, the input of the model, represents the i-th weight value of the activation function, i = 1, 2, 3 ······ d, and d is a positive integer, Denote the \(i\)-th threshold of the activation function, where \(i = 1, 2, 3, \cdots, d\) and \(d\) is a positive integer.

[0026] Step 107: Input the position information of the new safety valve and solenoid valve and the corresponding state information of the pipeline substance into the trained extreme learning machine model to obtain the output valve opening and closing information. Combine the position information of the new safety valve and solenoid valve, the corresponding state information of the pipeline substance, and the valve opening and closing information to form a safety training data set. Step 108: Input the safety training data set as observation data into the hidden Markov model to obtain the hidden Markov model parameters. After obtaining the safety training data set, the safety training data set can be input as observation data into the hidden Markov model to obtain the hidden Markov model parameters. The Markov model parameters and the state information of the pipeline substance are used to construct a hidden variable probability model, and the Viterbi algorithm is used to solve the hidden variable probability model to obtain the probability of the predicted valve opening or closing. For example, if the probability of a certain solenoid valve closing in the next 1 hour is 80%, there may be abnormal fluctuations in the pipeline state, and a reminder message is sent to the user.

[0027] Specifically, in the embodiment of the present invention, the step of inputting the safety training data set as observation data into the hidden Markov model to obtain the hidden Markov model parameters includes: Input the safety training data set as observation data into the hidden Markov model. When the number of iterations is zero, determine the first initial parameter, the second initial parameter, and the third initial parameter of the hidden Markov model. Perform iterative processing on the hidden Markov model for the first initial parameter, the second initial parameter, and the third initial parameter. When the number of iterations reaches the maximum value, obtain the hidden Markov model parameters.

[0028] The first initial parameter refers to the transition probability matrix of the state information of the pipeline substance; the second initial parameter refers to the probability distribution matrix of the safety training data set; and the third initial parameter refers to the initial state probability distribution. Iterative processing is performed on the three initial parameters. When the number of iterations reaches the maximum value, obtain the iterated hidden Markov model parameters.

[0029] Step 109: Construct a hidden variable probability model according to the hidden Markov model parameters and the state information of the pipeline substance. Further applied to the embodiment of the present invention, the step of constructing a hidden variable probability model according to the hidden Markov model parameters and the state information of the pipeline substance includes: constructing a hidden variable probability model through the hidden Markov model parameters, the state information of the pipeline substance, the position information of the safety valve and solenoid valve, and the valve opening and closing information.

[0030] The latent variable probability model P is as follows ; where q represents the hidden state sequence of the valve opening and closing information, represents the set of hidden Markov model parameters, Y represents the valve opening and closing information corresponding to the state information of the pipeline substance, the positions of the safety valve and the solenoid valve, represents the probability generated by the situation of the hidden state sequence, represents the probability of the valve opening and closing information generated under the condition of q.

[0031] Step 110, obtain the predicted valve opening and closing probability values of the safety valve and the solenoid valve through the latent variable probability model, and display the predicted valve opening and closing probability values of the safety valve and the solenoid valve.

[0032] In the embodiment of the present invention, obtaining the predicted valve opening and closing probability values of the safety valve and the solenoid valve through the latent variable probability model and outputting the predicted valve opening and closing probability values includes: solving the latent variable probability model through the Viterbi algorithm to obtain the predicted valve opening and closing probability values of the safety valve and the solenoid valve, and displaying the predicted valve opening and closing probability values of the safety valve and the solenoid valve, and further analyzing and predicting through HMM to improve the prediction accuracy of the valve opening and closing.

[0033] In an embodiment of the present invention, the method includes: obtaining the position information of multiple safety valves and solenoid valves at the pipe network nodes, the state information of the corresponding pipeline substances, and the historical opening and closing information of the valves; wherein, the state information includes temperature information; converting the position information of the multiple safety valves and solenoid valves into a safety valve position topology and a solenoid valve position topology; converting the state information and the historical opening and closing information of the valves into a node training data set; matching the safety valve position topology and the solenoid valve position topology with the node training data set to obtain a correlation coefficient matrix; inputting the correlation coefficient matrix into the input layer of an extreme learning machine model to obtain a first feature vector; training the first feature vector through a hidden layer to obtain a second feature vector, setting the safety valve position topology and the solenoid valve position topology as the link weights and the thresholds of the hidden layer, transmitting the second feature vector to an output layer to obtain a trained extreme learning machine model; inputting the position information of new safety valves and solenoid valves and the corresponding state information of the pipeline substances into the trained extreme learning machine model to obtain the output valve opening and closing information, and forming a safety training data set with the position information of the new safety valves and solenoid valves, the corresponding state information of the pipeline substances, and the valve opening and closing information; using the safety training data set as observation data and inputting it into a hidden Markov model to obtain hidden Markov model parameters; constructing a hidden variable probability model based on the hidden Markov model parameters and the state information of the pipeline substances; obtaining the predicted valve opening and closing probability values of the safety valves and solenoid valves through the hidden variable probability model, and displaying the predicted valve opening and closing probability values of the safety valves and solenoid valves; obtaining the probabilities of opening and closing of each valve, improving the accuracy of valve opening and closing prediction, displaying the opening and closing probability values of each valve to the user, providing suggestions for valve opening and closing or predicting the valve operating state, improving the monitoring safety of the pipe network, and enabling heat dissipation protection for the pipeline corresponding to the safety valve in advance through the prediction result, and the system plays an important role in equipment safety and personal safety.

[0034] It should be noted that for the method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that the embodiments of the present invention are not limited by the described action sequences, because according to the embodiments of the present invention, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily essential for the embodiments of the present invention.

[0035] Referring to Figure 4 , a structural block diagram of an embodiment of a high-temperature safety valve heat dissipation protection system according to an embodiment of the present invention is shown, which may specifically include the following modules: The first acquisition module 301 is configured to acquire the position information of multiple safety valves and solenoid valves at the pipe network nodes, the state information of the corresponding pipeline substances, and the historical opening and closing information of the valves; wherein, the state information includes temperature information; The first conversion module 302 is configured to convert the position information of the multiple safety valves and solenoid valves into a safety valve position topology and a solenoid valve position topology; The second conversion module 303 is configured to convert the state information and the historical opening and closing information of the valves into a node training data set; The matching module 304 is configured to match the safety valve position topology and the solenoid valve position topology with the node training data set to obtain a correlation coefficient matrix; The first input module 305 is configured to input the correlation coefficient matrix into the input layer of the extreme learning machine model to obtain a first feature vector; The setting module 306 is configured to train the first feature vector through the hidden layer to obtain a second feature vector, set the parameters corresponding to the safety valve position topology and the solenoid valve position topology as the connection weights and thresholds of the hidden layer, and transmit the second feature vector to the output layer to obtain a trained extreme learning machine model; The composition module 307 is configured to input the position information of the new safety valve and solenoid valve and the corresponding state information of the pipeline substances into the trained extreme learning machine model to obtain the output valve opening and closing information, and compose the position information of the new safety valve and solenoid valve, the corresponding state information of the pipeline substances, and the valve opening and closing information into a safety training data set; The second input module 308 is configured to input the safety training data set as observation data into the hidden Markov model to obtain hidden Markov model parameters; The construction module 309 is configured to construct a hidden variable probability model according to the hidden Markov model parameters and the state information of the pipeline substances; The display module 310 is configured to obtain the predicted valve opening and closing probability values of the safety valve and the solenoid valve through the hidden variable probability model, and display the predicted valve opening and closing probability values of the safety valve and the solenoid valve.

[0036] Preferably, the first conversion module includes: The first identification sub-module is configured to identify the position information of the safety valve from the pipeline network plane design drawing; The second identification sub-module is configured to identify the position information of the solenoid valve from the pipeline network plane design drawing; The first conversion sub-module is configured to convert the position information of the safety valve into a safety valve position topology; The second conversion sub-module is configured to convert the position information of the solenoid valve into a solenoid valve position topology.

[0037] Preferably, the matching module includes: A first conversion sub-module for converting the safety valve position topology and the solenoid valve position topology into sequence data; the sequence data includes valve sequence data; A third identification sub-module for identifying subset data in the node training data set of the pipeline corresponding to the safety valve and the solenoid valve, the subset data including status information and valve historical opening and closing information; A correlation coefficient matrix sub-module for forming a single matrix element from the valve sequence data and the corresponding subset data, forming a matrix row or a matrix column through the elements, forming an original matrix from the matrix row or the matrix column, and obtaining a correlation coefficient matrix from the original matrix.

[0038] Preferably, the setting module includes: A setting sub-module for setting the valve sequence data corresponding to the safety valve position topology and the solenoid valve position topology as the initial value of the link weight of the hidden layer of the extreme learning machine model; A determination sub-module for determining the maximum value in the sequence data as the threshold of the hidden layer of the extreme learning machine model; A training sub-module for obtaining a second feature vector through training of the first feature vector passing through the hidden layer; A transmission sub-module for transmitting the second feature vector to the output layer to obtain a trained extreme learning machine model.

[0039] Preferably, the second input module includes: An input sub-module for inputting the safety training data set as observation data into the hidden Markov model; A determination sub-module for determining the first initial parameter, the second initial parameter, and the third initial parameter of the hidden Markov model when the number of iterations is zero; An iterative processing sub-module for performing iterative processing of the hidden Markov model on the first initial parameter, the second initial parameter, and the third initial parameter, and obtaining the hidden Markov model parameters when the number of iterations reaches the maximum value.

[0040] Preferably, the construction module includes: A construction sub-module for constructing a hidden variable probability model through the hidden Markov model parameters, the state information of the pipeline substance, the position information of the safety valve and the solenoid valve, and the valve opening and closing information.

[0041] Preferably, obtaining the predicted valve opening and closing probability values of the safety valve and the solenoid valve through the hidden variable probability model and displaying the predicted valve opening and closing probability values of the safety valve and the solenoid valve includes: A display sub-module is used to solve the hidden variable probability model through the Viterbi algorithm, obtain the predicted valve opening and closing probability values of the safety valve and the solenoid valve, and display the predicted valve opening and closing probability values of the safety valve and the solenoid valve.

[0042] For the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple. For the relevant parts, refer to the partial description of the method embodiment.

[0043] For the specific limitations of the high-temperature safety valve heat dissipation protection system, reference can be made to the limitations of the high-temperature safety valve heat dissipation protection method in the above text, which will not be elaborated here. Each module in the above high-temperature safety valve heat dissipation protection system can be implemented in whole or in part by software, hardware, and their combination. The above-mentioned modules can be embedded in the processor of the computer device in hardware form or be independent of it, or can be stored in the memory of the computer device in software form, so as to facilitate the processor to call and execute the operations corresponding to the above modules.

[0044] The above-provided high-temperature safety valve heat dissipation protection system can be used to execute the high-temperature safety valve heat dissipation protection method provided in any of the above embodiments, and has corresponding functions and beneficial effects.

[0045] In one embodiment, a computer device is provided. The computer device can be a terminal, and its internal structure diagram can be as Figure 5 shown. The computer device includes a processor, a memory, a network interface, a display screen, and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal through a network connection. The computer program, when executed by the processor, implements a high-temperature safety valve heat dissipation protection method. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covering the display screen, or a button, a trackball, or a touchpad provided on the housing of the computer device, or an external keyboard, touchpad, or mouse, etc.

[0046] Those skilled in the art can understand that Figure 5 the structure shown in

[0047] In one embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory. When the processor executes the computer program, the following steps are implemented: Obtain the position information of multiple safety valves and solenoid valves at the pipe network nodes, the state information of the corresponding pipeline substances, and the historical opening and closing information of the valves; wherein, the state information includes temperature information; Convert the position information of the multiple safety valves and solenoid valves into a safety valve position topology and a solenoid valve position topology; Convert the state information and the historical opening and closing information of the valves into a node training data set; Match the safety valve position topology and the solenoid valve position topology with the node training data set to obtain a correlation coefficient matrix; Input the correlation coefficient matrix into the input layer of the extreme learning machine model to obtain a first feature vector; Through the training of the first feature vector passing through the hidden layer, obtain a second feature vector. Set the parameters corresponding to the safety valve position topology and the solenoid valve position topology as the connection weights and thresholds of the hidden layer, and transmit the second feature vector to the output layer to obtain a trained extreme learning machine model; Input the position information of the new safety valve and solenoid valve and the corresponding state information of the pipeline substances into the trained extreme learning machine model to obtain the output valve opening and closing information. Combine the position information of the new safety valve and solenoid valve, the corresponding state information of the pipeline substances, and the valve opening and closing information to form a safety training data set; Use the safety training data set as observation data and input it into the hidden Markov model to obtain the hidden Markov model parameters; Construct a hidden variable probability model according to the hidden Markov model parameters and the state information of the pipeline substances; Obtain the predicted valve opening and closing probability values of the safety valve and the solenoid valve through the hidden variable probability model, and display the predicted valve opening and closing probability values of the safety valve and the solenoid valve.

[0048] Preferably, the conversion of the position information of the multiple safety valves and solenoid valves into a safety valve position topology and a solenoid valve position topology includes: Identify the position information of the safety valve from the pipeline network plane design drawing; Identify the position information of the solenoid valve from the pipeline network plane design drawing; Convert the position information of the safety valve into a safety valve position topology; Convert the position information of the solenoid valve into a solenoid valve position topology.

[0049] Preferably, the matching of the safety valve position topology and the solenoid valve position topology with the node training data set to obtain a correlation coefficient matrix includes: Converting the safety valve position topology and the solenoid valve position topology into sequence data; the sequence data includes valve sequence data; Identifying subset data in the node training data set of the pipelines corresponding to the safety valve and the solenoid valve, the subset data including status information and valve historical opening and closing information; Combining the valve sequence data and the corresponding subset data into a single matrix element, forming matrix rows or matrix columns through the elements, forming an original matrix from the matrix rows or matrix columns, and obtaining a correlation coefficient matrix from the original matrix.

[0050] Preferably, the training of the first eigenvector through the hidden layer to obtain a second eigenvector, setting the parameters corresponding to the safety valve position topology and the solenoid valve position topology as the connection weights and thresholds of the hidden layer, and transmitting the second eigenvector to the output layer to obtain a trained extreme learning machine model includes: Setting the valve sequence data corresponding to the safety valve position topology and the solenoid valve position topology as the initial value of the connection weights of the hidden layer of this extreme learning machine model; Determining the maximum value in the sequence data as the threshold of the hidden layer of this extreme learning machine model; Training the first eigenvector through the hidden layer to obtain a second eigenvector; Transmitting the second eigenvector to the output layer to obtain a trained extreme learning machine model.

[0051] Preferably, the inputting of the safety training data set as observed data into the hidden Markov model to obtain hidden Markov model parameters includes: Inputting the safety training data set as observed data into the hidden Markov model; At the iteration count of zero, determining the first initial parameter, the second initial parameter, and the third initial parameter of the hidden Markov model; Performing iterative processing on the hidden Markov model for the first initial parameter, the second initial parameter, and the third initial parameter, and when the iteration count reaches the maximum value, obtaining the hidden Markov model parameters.

[0052] Preferably, the constructing of a hidden variable probability model according to the hidden Markov model parameters and the status information of the pipeline substance includes: Constructing a hidden variable probability model through the hidden Markov model parameters, the status information of the pipeline substance, the position information of the safety valve and the solenoid valve, and the valve opening and closing information.

[0053] Preferably, obtaining the predicted valve opening and closing probability values of the safety valve and the solenoid valve through the latent variable probability model and outputting the predicted valve opening and closing probability values includes: Solving the latent variable probability model through the Viterbi algorithm to obtain the predicted valve opening and closing probability values of the safety valve and the solenoid valve, and presenting the predicted valve opening and closing probability values of the safety valve and the solenoid valve.

[0054] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented: Obtaining the position information of multiple safety valves and solenoid valves at the pipeline network nodes, the state information of the corresponding pipeline substances, and the historical valve opening and closing information; wherein, the state information includes temperature information; Converting the position information of the multiple safety valves and solenoid valves into a safety valve position topology and a solenoid valve position topology; Converting the state information and the historical valve opening and closing information into a node training data set; Matching the safety valve position topology and the solenoid valve position topology with the node training data set to obtain a correlation coefficient matrix; Inputting the correlation coefficient matrix into the input layer of the extreme learning machine model to obtain a first feature vector; Training the first feature vector through the hidden layer to obtain a second feature vector, setting the parameters corresponding to the safety valve position topology and the solenoid valve position topology as the connection weights and thresholds of the hidden layer, and transmitting the second feature vector to the output layer to obtain a trained extreme learning machine model; Inputting the position information of the new safety valve and solenoid valve and the corresponding state information of the pipeline substances into the trained extreme learning machine model to obtain the output valve opening and closing information, and forming a safety training data set with the position information of the new safety valve and solenoid valve, the corresponding state information of the pipeline substances, and the valve opening and closing information; Using the safety training data set as observation data and inputting it into the hidden Markov model to obtain hidden Markov model parameters; Constructing a latent variable probability model according to the hidden Markov model parameters and the state information of the pipeline substances; Obtaining the predicted valve opening and closing probability values of the safety valve and the solenoid valve through the latent variable probability model, and presenting the predicted valve opening and closing probability values of the safety valve and the solenoid valve.

[0055] Preferably, converting the position information of the multiple safety valves and solenoid valves into a safety valve position topology and a solenoid valve position topology includes: Identifying the position information of the safety valve from the pipeline network plane design drawing; Identify the position information of the solenoid valve from the pipeline network layout drawing; Convert the position information of the safety valve into a safety valve position topology; Convert the position information of the solenoid valve into a solenoid valve position topology.

[0056] Preferably, matching the safety valve position topology and the solenoid valve position topology with the node training data set to obtain a correlation coefficient matrix, including: Convert the safety valve position topology and the solenoid valve position topology into sequence data; the sequence data includes valve sequence data; Identify the subset data in the node training data set corresponding to the pipeline of the safety valve and the solenoid valve, and the subset data includes status information and valve historical opening and closing information; Form a single matrix element with the valve sequence data and the corresponding subset data, form matrix rows or matrix columns through the elements, form an original matrix with the matrix rows or matrix columns, and obtain a correlation coefficient matrix through the original matrix.

[0057] Preferably, training the first eigenvector through a hidden layer to obtain a second eigenvector, setting the parameters corresponding to the safety valve position topology and the solenoid valve position topology as the link weights and thresholds of the hidden layer, and transmitting the second eigenvector to the output layer to obtain a trained extreme learning machine model, including: Set the valve sequence data corresponding to the safety valve position topology and the solenoid valve position topology as the initial value of the link weights of the hidden layer of this extreme learning machine model; Determine the maximum value in the sequence data as the threshold of the hidden layer of this extreme learning machine model; Train the first eigenvector through the hidden layer to obtain a second eigenvector; Transmit the second eigenvector to the output layer to obtain a trained extreme learning machine model.

[0058] Preferably, inputting the safety training data set as observation data into a hidden Markov model to obtain hidden Markov model parameters, including: Input the safety training data set as observation data into a hidden Markov model; When the number of iterations is zero, determine the first initial parameter, the second initial parameter, and the third initial parameter of the hidden Markov model; Perform iterative processing on the hidden Markov model for the first initial parameter, the second initial parameter, and the third initial parameter, and when the number of iterations reaches the maximum value, obtain the hidden Markov model parameters.

[0059] Preferably, constructing a hidden variable probability model based on the hidden Markov model parameters and the state information of the pipeline substance includes: Constructing a hidden variable probability model through the hidden Markov model parameters, the state information of the pipeline substance, the position information of the safety valve and the solenoid valve, and the valve opening and closing information.

[0060] Preferably, obtaining the predicted valve opening and closing probability values of the safety valve and the solenoid valve through the hidden variable probability model and outputting the measured valve opening and closing probability values includes: Solving the hidden variable probability model through the Viterbi algorithm to obtain the predicted valve opening and closing probability values of the safety valve and the solenoid valve, and displaying the predicted valve opening and closing probability values of the safety valve and the solenoid valve.

[0061] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the various embodiments provided in the present application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0062] Each embodiment in this specification is described in a progressive manner. The key point of each embodiment is to illustrate the differences from other embodiments. The same or similar parts among the various embodiments can be referred to each other.

[0063] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, an apparatus, or a computer program product. Therefore, the embodiments of the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the embodiments of the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memory, CD-ROM, optical memory, etc.) that contain computer-usable program code.

[0064] The embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of the apparatus, terminal device (system), and computer program product according to the embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram, as well as the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing terminal devices generate an apparatus for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0065] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing terminal device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including an instruction method that implements the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0066] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device, such that a series of operation steps are executed on the computer or other programmable terminal device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable terminal device provide steps for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0067] Although the preferred embodiments of the embodiments of the present invention have been described, those skilled in the art can make additional changes and modifications once they learn the basic creative concepts. Therefore, the appended claims are intended to be construed as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present invention.

[0068] Finally, it should also be noted that in this text, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "including", "comprising" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, device, article or terminal device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, device, article or terminal device. Without further limitation, an element defined by the statement "including one..." does not exclude the existence of additional identical elements in the process, device, article or terminal device including the said element.

[0069] The above has introduced in detail a heat dissipation protection method for a high-temperature safety valve, a heat dissipation protection system for a high-temperature safety valve, a computer device and a storage medium provided by the present invention. Specific examples are used in this text to elaborate on the principle and implementation manner of the present invention. The description of the above embodiments is only used to help understand the method and its core idea of the present invention; at the same time, for those of ordinary skill in the art, according to the idea of the present invention, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present invention.

Claims

1. A heat dissipation protection method for a high-temperature safety valve, characterized in that, Including: Obtaining the position information of multiple safety valves and solenoid valves at the pipe network nodes, the state information of the corresponding pipeline substances, and the historical opening and closing information of the valves; wherein, the state information includes temperature information; Converting the position information of the multiple safety valves and solenoid valves into a safety valve position topology and a solenoid valve position topology; Converting the state information and the historical opening and closing information of the valves into a node training data set; Matching the safety valve position topology and the solenoid valve position topology with the node training data set to obtain a correlation coefficient matrix; Inputting the correlation coefficient matrix into the input layer of the extreme learning machine model to obtain a first feature vector; Training the first feature vector through the hidden layer to obtain a second feature vector, setting the parameters corresponding to the safety valve position topology and the solenoid valve position topology as the connection weights and thresholds of the hidden layer, and transmitting the second feature vector to the output layer to obtain a trained extreme learning machine model; Inputting the position information of the new safety valve and solenoid valve and the corresponding state information of the pipeline substances into the trained extreme learning machine model to obtain the output valve opening and closing information, and forming a safety training data set with the position information of the new safety valve and solenoid valve, the corresponding state information of the pipeline substances, and the valve opening and closing information; Taking the safety training data set as observation data and inputting it into the hidden Markov model to obtain the hidden Markov model parameters; Constructing a hidden variable probability model according to the hidden Markov model parameters and the state information of the pipeline substances; Obtaining the predicted valve opening and closing probability values of the safety valve and the solenoid valve through the hidden variable probability model, and displaying the predicted valve opening and closing probability values of the safety valve and the solenoid valve.

2. The method according to claim 1, characterized in that, The converting the position information of the multiple safety valves and solenoid valves into a safety valve position topology and a solenoid valve position topology includes: Identifying the position information of the safety valve from the pipeline network plane design drawing; Identifying the position information of the solenoid valve from the pipeline network plane design drawing; Converting the position information of the safety valve into a safety valve position topology; Converting the position information of the solenoid valve into a solenoid valve position topology.

3. The method according to claim 1, wherein The matching the safety valve position topology and the solenoid valve position topology with the node training data set to obtain a correlation coefficient matrix includes: Converting the safety valve position topology and the solenoid valve position topology into sequence data; the sequence data includes valve sequence data; Identifying the subset data in the node training data set corresponding to the pipes of the safety valve and the solenoid valve, and the subset data includes state information and historical opening and closing information of the valves; Forming a single matrix element with the valve sequence data and the corresponding subset data, forming matrix rows or matrix columns through the elements, forming an original matrix with the matrix rows or matrix columns, and obtaining a correlation coefficient matrix through the original matrix.

4. The method according to claim 3, wherein The training the first feature vector through the hidden layer to obtain a second feature vector, setting the parameters corresponding to the safety valve position topology and the solenoid valve position topology as the connection weights and thresholds of the hidden layer, and transmitting the second feature vector to the output layer to obtain a trained extreme learning machine model includes: Set the valve sequence data corresponding to the safety valve position topology and the solenoid valve position topology as the initial value of the connection weights of the hidden layer of the extreme learning machine model; Determine the maximum value in the sequence data as the threshold of the hidden layer of the extreme learning machine model; Through the training of the first feature vector passing through the hidden layer, obtain the second feature vector; Transmit the second feature vector to the output layer to obtain the trained extreme learning machine model.

5. The method according to claim 3, characterized in that, The inputting the safety training data set as observation data into the hidden Markov model to obtain the hidden Markov model parameters includes: Input the safety training data set as observation data into the hidden Markov model; At the iteration count of zero, determine the first initial parameter, the second initial parameter, and the third initial parameter of the hidden Markov model; Perform iterative processing on the hidden Markov model for the first initial parameter, the second initial parameter, and the third initial parameter. When the iteration count reaches the maximum value, obtain the hidden Markov model parameters.

6. The method according to claim 4, wherein The constructing the hidden variable probability model according to the hidden Markov model parameters and the state information of the pipeline substance includes: Construct the hidden variable probability model through the hidden Markov model parameters, the state information of the pipeline substance, the positions of the safety valve and the solenoid valve, and the valve opening and closing information.

7. The method according to claim 6, characterized in that The obtaining the predicted valve opening and closing probability values of the safety valve and the solenoid valve through the hidden variable probability model and outputting the predicted valve opening and closing probability values includes: Solve the hidden variable probability model through the Viterbi algorithm to obtain the predicted valve opening and closing probability values of the safety valve and the solenoid valve, and display the predicted valve opening and closing probability values of the safety valve and the solenoid valve.

8. A high-temperature safety valve heat dissipation protection system, characterized in that, Includes: The first acquisition module is used to acquire the position information of multiple safety valves and solenoid valves at the pipe network nodes, the corresponding state information of the pipeline substance, and the valve historical opening and closing information; wherein, the state information includes temperature information; The first conversion module is used to convert the position information of the multiple safety valves and solenoid valves into the safety valve position topology and the solenoid valve position topology; The second conversion module is used to convert the state information and the valve historical opening and closing information into the node training data set; The matching module is used to match the safety valve position topology and the solenoid valve position topology with the node training data set to obtain the correlation coefficient matrix; The first input module is used to input the correlation coefficient matrix into the input layer of the extreme learning machine model to obtain the first feature vector; The setting module is used to obtain the second feature vector through the training of the first feature vector passing through the hidden layer, set the parameters corresponding to the safety valve position topology and the solenoid valve position topology as the connection weights and thresholds of the hidden layer, and transmit the second feature vector to the output layer to obtain the trained extreme learning machine model; The composition module is used to input the position information of the new safety valve and solenoid valve and the corresponding state information of the pipeline substance into the trained extreme learning machine model to obtain the output valve opening and closing information, and compose the position information of the new safety valve and solenoid valve, the corresponding state information of the pipeline substance, and the valve opening and closing information into the safety training data set; A second input module, configured to input the security training data set as observation data into a hidden Markov model to obtain hidden Markov model parameters; A construction module, configured to construct a hidden variable probability model according to the hidden Markov model parameters and the state information of the pipeline substance; A display module, configured to obtain predicted valve opening and closing probability values of a safety valve and a solenoid valve through the hidden variable probability model, and display the predicted valve opening and closing probability values of the safety valve and the solenoid valve.

9. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, the steps of the high-temperature safety valve heat dissipation protection method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, the steps of the high-temperature safety valve heat dissipation protection method according to any one of claims 1 to 7 are implemented.

Images