Dynamic cable temperature prediction and fire early warning method and system
Through the BP-LSTM algorithm model combined with the fuzzy logic algorithm, the cable temperature change trend is dynamically predicted and the warning level is adjusted, which solves the problem that the existing technology cannot be early warning and achieves higher warning accuracy and timeliness.
Patent Information
- Application Number
- CN202510189477.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-02-20
- Publication Date
- 2025-06-13
AI Technical Summary
Existing cable fire warning technologies cannot dynamically predict cable temperature changes, resulting in the inability to achieve early warning of cable fires.
The BP-LSTM algorithm model is used combined with the fuzzy logic algorithm to dynamically predict the cable temperature change trend, and the early warning level is adjusted through the fuzzy logic algorithm to achieve early warning of cable fire.
It improves the accuracy and timeliness of fire warnings, can effectively capture the long-term dependence and periodic patterns of cable temperature changes, reduce false alarms, and provide strong safety guarantees for the stable operation of the cable.
Smart Images
Figure CN120148210A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of cable monitoring, and in particular to a method and system for dynamic cable temperature prediction and fire warning. Background Art
[0002] As the "blood vessels" and "nerves" of modern society, cables play a crucial role in power transmission, information transfer, and energy distribution. However, cables are prone to thermal degradation under long-term load, which can lead to damage to the cable insulation layer, increase the risk of cable failures, and even cause fires. Once a cable fire occurs, the fire often spreads rapidly and is difficult to control because the insulation layer of the cable is mostly composed of combustible materials. The fire will produce high-temperature toxic smoke, seriously threatening the safety of personnel's lives and causing equipment damage, resulting in huge economic losses and social impacts. Existing cable fire warning technologies focus on monitoring cable temperatures, such as cable-type linear temperature sensors, fiber optic temperature sensors, etc. However, these technologies often cannot dynamically predict the changing trend of cable temperatures, and thus cannot achieve early warning of cable fires. Therefore, developing a new cable temperature prediction and fire warning model is of great significance for improving the safety and reliability of cable operation. Summary of the Invention
[0003] In view of the above existing problems, the present invention is proposed.
[0004] Therefore, the problem to be solved by the present invention is: how to solve the problem that existing cable fire warning technologies focus on monitoring cable temperatures, such as cable-type linear temperature sensors, fiber optic temperature sensors, etc., but these technologies often cannot dynamically predict the changing trend of cable temperatures, and thus cannot achieve early warning of cable fires.
[0005] To solve the above technical problems, the present invention provides the following technical solution: A method for dynamic cable temperature prediction and fire warning, including collecting data, constructing a BP-LSTM algorithm model to dynamically predict the changing trend of cable temperatures; constructing a fuzzy logic algorithm model; using the temperature prediction result and the temperature rising trend as fuzzy input variables, and using the fire warning level as a fuzzy output variable to conduct cable fire warning.
[0006] As a preferred solution of the method for dynamic cable temperature prediction and fire warning according to the present invention, wherein: the BP-LSTM algorithm model includes an input layer, an LSTM layer, a BP neural network hidden layer, and an output layer; the input layer is used to represent the factors affecting the change of cable temperature; the LSTM layer includes a forgetting gate, an input gate, an output gate, and a memory cell with a cyclic self-connection, and extracts the time dimension features of data changes according to historical node data; the BP neural network hidden layer is used to represent the weights and thresholds of the BP neural network; the output layer represents the predicted temperature value of the cable.
[0007] As a preferred embodiment of the dynamic cable temperature prediction and fire warning method of the present invention, the number of nodes in the input layer is 4, and the input variables are soil humidity, soil temperature, cable current-carrying capacity, and cable arrangement interval; the number of time steps in the LSTM layer is t, and the data of the past t time points are used to predict new values; the number of nodes in the output layer is 1, and the output variable is the predicted cable temperature value.
[0008] As a preferred embodiment of the dynamic cable temperature prediction and fire warning method of the present invention, the fuzzy logic algorithm model includes a fuzzy set, a membership function, fuzzy inference, a fuzzy discrimination rule base, and defuzzification; the fuzzy set is used to perform fuzzy processing on the input and output variables; the membership function is used to quantify the fuzziness of the input variables; the fuzzy inference maps the fuzzy membership degrees of the input variables to the fuzzy membership degrees of the output variables; the fuzzy discrimination rule base is used to make decisions according to different input fuzzy quantities; the defuzzification is used to convert the fuzzy output into a specific numerical value.
[0009] As a preferred embodiment of the dynamic cable temperature prediction and fire warning method of the present invention, the temperature prediction results include defining four fuzzy levels for the cable temperature as low, medium, high, and extremely high; the temperature rising trend includes defining three fuzzy levels for the trend of cable temperature change as stable, rising, and sharply rising; and defining three fuzzy levels for the warning level of fire risk as low, medium, and high.
[0010] As a preferred embodiment of the dynamic cable temperature prediction and fire warning method of the present invention, making decisions according to different input fuzzy quantities includes that if the temperature level is low and the temperature trend is stable, the warning level is low; if the temperature level is medium and the temperature trend is rising, the warning level is medium; if the temperature level is high and the temperature trend is rising, the warning level is high; if the temperature level is extremely high and the temperature trend is sharply rising, the warning level is high.
[0011] As a preferred embodiment of the dynamic cable temperature prediction and fire warning method of the present invention, converting the fuzzy output into a specific numerical value includes performing fuzzy inference using the minimum rule to obtain a fuzzy output, and performing defuzzification using the centroid method to convert the temperature level and the temperature change trend into a quantitative result of fire risk warning.
[0012] Another object of the present invention is to provide a system for the dynamic cable temperature prediction and fire warning method, which can solve the problem of dynamic cable temperature prediction and fire warning by constructing a dynamic cable temperature prediction and fire warning system.
[0013] To solve the above technical problems, the present invention provides the following technical solution: A dynamic cable temperature prediction and fire warning system, including a temperature prediction module, a fuzzy logic algorithm model module, a warning module, and a wireless transmission module; the temperature prediction module is used to collect data, construct a BP-LSTM algorithm model, and dynamically predict the changing trend of cable temperature; the fuzzy logic algorithm model module is used to construct a fuzzy logic algorithm model; the warning module is used to define the temperature prediction result and the temperature rising trend as fuzzy input variables, and define the fire warning level as a fuzzy output variable to conduct cable fire warning; the wireless transmission module sends the warning information to the monitoring center to achieve remote real-time monitoring and predict the changing trend of cable temperature.
[0014] A computer device, including a memory and a processor, where the memory stores a computer program, and when the processor executes the computer program, it implements the steps of the above-mentioned dynamic cable temperature prediction and fire warning method.
[0015] A computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the above-mentioned dynamic cable temperature prediction and fire warning method.
[0016] The beneficial effects of the present invention are as follows: The dynamic cable temperature prediction and fire warning method provided by the present invention aims to solve the deficiency of the existing cable fire warning technology in terms of dynamic timeliness. This model combines the advantages of the BP neural network and the LSTM network. By using the input layer to represent the factors affecting cable temperature, the LSTM layer to extract time series features, and the hidden layer of the BP neural network to handle non-linear problems, finally, the output layer predicts the cable temperature. In addition, the model combines the fuzzy logic algorithm. Through fuzzy sets, membership functions, fuzzy inference, a fuzzy discrimination rule base, and defuzzification processing, the warning level is dynamically adjusted to improve the accuracy and timeliness of the warning. The present invention can not only effectively capture the long-term dependence relationship and periodic pattern of cable temperature changes, but also handle the uncertainty and ambiguity problems in cable fire warning, reduce false alarms, and provide a strong safety guarantee for the stable operation of the cable. Through the wireless transmission module, this model can achieve remote real-time monitoring, predict the changing trend of cable temperature, and thus realize the early warning of cable fire in the very early stage to ensure the safe and stable operation of the power system. Description of the Drawings
[0017] In order to more clearly illustrate the technical solutions of 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, without creative efforts, other drawings can be obtained based on these drawings.
[0018] Figure 1 Flow chart of a dynamic cable temperature prediction and fire warning method provided for the first embodiment of the present invention.
[0019] Figure 2 Structure diagram of a dynamic cable temperature prediction and fire warning system provided for the second embodiment of the present invention.
[0020] Figure 3 COMSOL single-core cable model and simulation result diagram of a dynamic cable temperature prediction and fire warning method provided for the third embodiment of the present invention.
[0021] Figure 4 Cable temperature prediction model diagram based on BP-LSTM algorithm of a dynamic cable temperature prediction and fire warning method provided for the third embodiment of the present invention.
[0022] Figure 5 Cable fire warning model diagram based on fuzzy logic algorithm of a dynamic cable temperature prediction and fire warning method provided for the third embodiment of the present invention.
[0023] In the figure: 100, temperature prediction module; 200, fuzzy logic algorithm model module; 300, warning module; 400, wireless transmission module. Detailed implementation manners
[0024] To make the above objects, features and advantages of the present invention more obvious and understandable, the following detailed description of the specific implementation manners of the present invention will be given in conjunction with the accompanying drawings of the specification.
[0025] In the following description, many specific details are set forth to fully understand the present invention. However, the present invention can also be implemented in other ways different from those described herein. Those skilled in the art can make similar extensions without departing from the connotation of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.
[0026] Example 1, referring to Figure 1 , which is the first embodiment of the present invention. This embodiment provides a dynamic cable temperature prediction and fire warning method, including: collecting data, constructing a BP-LSTM algorithm model, dynamically predicting the changing trend of cable temperature; constructing a fuzzy logic algorithm model; defining the temperature prediction result and the temperature rising trend as fuzzy input variables, and defining the fire warning level as a fuzzy output variable to conduct cable fire warning.
[0027] Cables play a crucial role in the power system, responsible for safely and efficiently transmitting electrical energy from power generation stations to various power consumption points. Once a cable fails, it may lead to a power supply interruption, affecting industrial production and residents' lives, causing huge economic losses and social impacts. Cable fires are particularly dangerous. They not only cause power supply interruptions but may also trigger a chain reaction. The high temperature and toxic smoke generated by cable fires spread rapidly and are difficult to control, posing a direct threat to personnel safety. At the same time, they will also damage the structure of the cable itself, requiring expensive repair and replacement costs. In addition, cable fires may also cause environmental problems, such as the release of toxic substances, having a long-term impact on the ecological environment. Therefore, preventing cable fires and ensuring the safe operation of cables are important tasks in the power industry.
[0028] Existing cable fire warning technologies focus on monitoring cable temperature, such as cable-type linear temperature sensors, fiber optic temperature sensors, etc. However, these technologies often cannot dynamically predict the changing trend of cable temperature, and thus cannot achieve early warning of cable fires.
[0029] The present invention precisely aims at the problem of the lack of dynamic timeliness in existing cable fire warning technologies, and proposes a dynamic cable temperature prediction and fire warning model based on the BP-LSTM and fuzzy logic algorithms. This model applies the BP-LSTM algorithm to predict the changing trend of temperature, combines the fuzzy logic algorithm to adjust the warning level, and then sends the warning information to the monitoring center through a wireless transmission module to achieve remote real-time monitoring and predict the changing trend of cable temperature, thereby improving the accuracy and timeliness of fire warning.
[0030] S1. Collect data, construct a BP-LSTM algorithm model, and dynamically predict the changing trend of cable temperature.
[0031] The BP-LSTM algorithm model includes an input layer, an LSTM layer, a hidden layer of the BP neural network, and an output layer; the input layer is used to represent the factors affecting the change of cable temperature; the LSTM layer includes a forgetting gate, an input gate, an output gate, and a memory cell with a recurrent self-connection, and extracts the time dimension features of data changes according to historical node data; the hidden layer of the BP neural network is used to represent the weights and thresholds of the BP neural network; the output layer represents the predicted temperature value of the cable.
[0032] S2. Construct a fuzzy logic algorithm model.
[0033] The fuzzy logic algorithm model includes a fuzzy set, a membership function, fuzzy inference, a fuzzy discrimination rule base, and defuzzification; the fuzzy set is used to perform fuzzy processing on input and output variables; the membership function is used to quantify the fuzziness of input variables; fuzzy inference maps the fuzzy membership degrees of input variables to the fuzzy membership degrees of output variables; the fuzzy discrimination rule base is used to make decisions according to different input fuzzy quantities; defuzzification is used to convert the fuzzy output into a specific numerical value.
[0034] S3. Define the temperature prediction result and the temperature rising trend as fuzzy input variables, and define the fire warning level as a fuzzy output variable to conduct cable fire warning.
[0035] In step S1 of the present invention, an algorithm model combining a BP neural network and an LSTM is provided for cable temperature prediction. It includes an input layer for characterizing the factors affecting the change of cable temperature; an LSTM layer including a forgetting gate, an input gate, an output gate, and a memory cell with a recurrent self-connection, which is used to extract the time dimension features of data changes according to historical node data; a BP neural network hidden layer for characterizing the weights and thresholds of the BP neural network; and an output layer for the predicted temperature value of the cable. The cable temperature prediction problem is a complex, non-linear, and dynamically changing problem. Compared with a single BP neural network prediction model, the BP-LSTM model is more suitable for predicting cable temperature. It combines the ability of the BP neural network to handle non-linear problems with the advantages of the LSTM network in processing time series data, and can effectively capture the long-term dependence relationship and periodic pattern in the cable temperature change. This hybrid model can not only avoid overfitting and improve the generalization ability of the model, but also has a memory and forgetting mechanism, which can dynamically adjust the prediction according to historical data, thus showing higher accuracy and adaptability in real-time monitoring and predicting cable temperature.
[0036] Furthermore, determine the number of nodes in the input layer for characterizing the factors affecting the change of cable temperature. Therefore, the number of nodes in the input layer is determined to be 4, and the input variables are soil humidity, soil temperature, cable current-carrying capacity, and cable arrangement interval respectively.
[0037] Furthermore, set the time step t of the LSTM, which represents predicting a new value using the data of the past t time points.
[0038] Furthermore, set the weight and bias parameters of the LSTM forgetting gate, input gate, and output gate to improve the LSTM structure.
[0039] Furthermore, set the number of nodes in the hidden layer of the LSTM and use its output as the input of the BP neural network.
[0040] Furthermore, determine the number of nodes in the hidden layer of the BP neural network. The selection of the number of nodes in the hidden layer determines whether a normally working BP neural network can be established.
[0041] Furthermore, set the neural network parameters, including the connection weights between the input layer and the hidden layer, the connection weights between the hidden layer and the output layer, and the thresholds of the hidden layer and the output layer, to improve the neural network structure.
[0042] Further, determine the number of nodes in the output layer. Since the output layer represents the cable temperature prediction result, the number of nodes in the output layer is determined to be 1, and the output variable is the predicted cable temperature value.
[0043] In step S2 of the present invention, a fuzzy logic algorithm model is provided for cable fire warning. It includes a fuzzy set for fuzzifying input and output variables; a membership function for quantifying the fuzziness of input variables and describing the belonging degree of each input value in a certain fuzzy set; fuzzy reasoning for mapping the fuzzy membership degrees of input variables to those of output variables to obtain a fuzzified fire warning level; a fuzzy discrimination rule base for making decisions based on different input fuzzy quantities; and defuzzification for converting the fuzzified output into a specific numerical value to obtain a clear fire warning risk. Cable fire warning has the characteristics of complex multi-factor correlation, non-linearity, and high uncertainty. The fuzzy logic algorithm can just handle problems of uncertainty and fuzziness, and has strong anti-interference ability, reducing false alarms, thus improving the accuracy and reliability of fire warning.
[0044] Further, define the temperature prediction result and the temperature rising trend as fuzzy input variables, and define the fire warning level as a fuzzy output variable.
[0045] In step S3 of the present invention, define the fuzzification levels of cable temperature, which are divided into four fuzzy sets: low (L), medium (M), high (H), and very high (VH).
[0046] Further, define the fuzzification levels of the trend of cable temperature change, which are divided into three fuzzy sets: stable (S), rising (R), and sharply rising (SR).
[0047] Further, define the fuzzification levels of the warning levels of fire risks, which are divided into three fuzzy sets: low (L), medium (M), and high (H).
[0048] Further, define the membership functions of each input variable.
[0049] Further, formulate a fuzzy discrimination rule base. The fuzzy discrimination rules usually have the following form: IF (a set of conditions) THEN (deduce a set of results). The specific rules are as follows: If the temperature level is low and the temperature trend is stable, the warning level is low; if the temperature level is medium and the temperature trend is rising, the warning level is medium; if the temperature level is high and the temperature trend is rising, the warning level is high; if the temperature level is very high and the temperature trend is sharply rising, the warning level is high.
[0050] Further, the minimum rule is used for fuzzy reasoning to obtain a fuzzy output, and the centroid method is used for defuzzification, so as to convert the temperature level and the temperature change trend into a quantitative result of fire risk warning for actual monitoring and early warning.
[0051] Example 2, referring to Figure 2 , which is the second embodiment of the present invention. Different from the previous embodiment, it provides a dynamic cable temperature prediction and fire warning system, including: a temperature prediction module 100, a fuzzy logic algorithm model module 200, a warning module 300, and a wireless transmission module 400.
[0052] The temperature prediction module 100 is used to collect data, construct a BP-LSTM algorithm model, and dynamically predict the cable temperature change trend.
[0053] The fuzzy logic algorithm model module 200 is used to construct a fuzzy logic algorithm model.
[0054] The warning module 300 is used to define the temperature prediction result and the temperature rising trend as fuzzy input variables, and define the fire warning level as a fuzzy output variable to conduct cable fire warning.
[0055] The wireless transmission module 400 sends the warning information to the monitoring center to realize remote real-time monitoring and predict the cable temperature change trend.
[0056] If the above functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The foregoing storage medium includes: USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical disks and other various media that can store program codes.
[0057] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a definite sequence list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device), or used in combination with these instruction execution systems, apparatuses, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
[0058] More specific examples (non-exhaustive list) of computer-readable media include the following: an electrical connection portion with one or more wirings (electronic device), a portable computer diskette (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpretation, or otherwise processing as appropriate, and then stored in a computer memory.
[0059] It should be understood that various parts of the present invention can be implemented using hardware, software, firmware, or combinations thereof. In the above-described embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application-specific integrated circuits having appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.
[0060] Example 3, referring to Figures 3 to 5 , is the third embodiment of the present invention, which is different from the previous two embodiments in that it makes a detailed description of the implementation steps adopted in the present invention.
[0061] Referring to Figure 3 , the present invention uses COMSOL simulation software to build a cable model to obtain the change data of the cable temperature under different conditions such as soil humidity, soil temperature, cable current-carrying capacity, and cable arrangement interval, and uses this as the data set for the algorithm.
[0062] Firstly, the cable geometric model is built, and a horizontally placed single-core cable directly buried in the soil is selected as the simulation object. The single-core cable structure consists of a conductor layer, an insulation layer, a semiconductor layer, a metal sheath layer and an outer sheath.
[0063] Use the material library that comes with COMSOL to define the material properties of each layer and set parameters such as soil moisture, soil temperature, cable current carrying capacity, and cable arrangement spacing.
[0064] After meshing, the electromagnetic-thermal coupling physical field is set up, and the corresponding boundary conditions are set to calculate the temperature change results.
[0065] Reference Figure 4 The BP-LSTM cable temperature prediction algorithm model provided by the present invention combines the BP neural network with the LSTM, including an input layer, an LSTM layer, a BP neural network hidden layer, and an output layer.
[0066] The number of input layer nodes is determined to be 4 as needed, and the input variables are soil moisture Hsoil, cable current carrying capacity I, soil temperature Tsoil, and cable arrangement interval d.
[0067] According to the needs, the number of nodes in the model output layer is determined to be 1, and the output variables are the predicted temperature values of the cable;
[0068] The data set is normalized, and the formula is as follows:
[0069]
[0070] Among them, X is the original sample data, max is the maximum value of the sample data, min is the minimum value of the sample data, and X' is the normalized data.
[0071] Set the time step number t to 10 and use the data from the past 10 time points to predict the output.
[0072] Based on multiple adjustments, the optimal number of LSTM layer nodes H=64 is selected.
[0073] The LSTM layer is responsible for processing sequence data and extracting temporal dependencies. For each time step t, the LSTM calculation includes the following steps:
[0074] For the forget gate:
[0075] f t =σ(W f ·[H t-1 ,X t ]+b f )
[0076] Among them, W f is the weight matrix of the forget gate, bf is the bias term of the forget gate, and σ is the Sigmoid activation function.
[0077] For the input gate:
[0078] i t = σ(W i · [H t-1 , X t + b i )
[0079]
[0080] where W i , b i are the weights and bias of the input gate, W c , b c are the weights and bias of the candidate memory cell, and tanh is the hyperbolic tangent activation function.
[0081] Then update the memory cell state:
[0082]
[0083] C t is the current memory cell state.
[0084] For the output gate:
[0085] o t = σ(W o · [H t-1 , X t + b o )
[0086] H t = o t * tanh(C t )
[0087] where W o , b o are the weights and bias of the output gate, and H t is the output of the LSTM hidden layer.
[0088] Take the output of the LSTM hidden layer as the input of the BP neural network, so determine that the number of nodes in the input layer of the BP neural network n1 = 64.
[0089] Determine the number of nodes in the hidden layer of the BP neural network according to the empirical formula. The formula is as follows:
[0090]
[0091] where n H is the number of nodes in the hidden layer, n 1is the number of input nodes, n 2 is the number of output nodes, n is an integer between 1 and 10, so the number of hidden layer nodes is determined to be 10.
[0092] After determining the number of nodes in each layer of the neural network, it is necessary to input the previous data of the thermogravimetric analyzer to train the neural network model. Using the forward propagation of the neural network, continuously loop and iterate. The specific steps are as follows:
[0093] Initialization, select the maximum allowable error Emax of the model, and initialize each parameter to small random values.
[0094] Calculate the output of the hidden layer:
[0095]
[0096] Among them, is the weight matrix from the input layer to the hidden layer, is the bias term of the hidden layer.
[0097] Calculate the output of the output layer:
[0098]
[0099] Among them, is the predicted cable temperature value, is the weight matrix from the input layer to the hidden layer, b (2) is the bias term of the output layer.
[0100] Select the mean square error (MSE) as the loss function and calculate the error between the predicted value and the actual value:
[0101]
[0102] Among them, is the actual cable temperature value, N is the number of sample data;
[0103] Perform multiple iterations until the loss converges or the error is less than the maximum allowable error.
[0104] Referring to Figure 4 , the present invention provides a fuzzy logic algorithm model for dealing with cable fire warning problems with characteristics such as multi-factor complex correlation, high nonlinearity, and high uncertainty, including defining fuzzy sets, membership functions, and fuzzy discrimination rule bases, so as to perform fuzzy reasoning and defuzzification processing to obtain clear fire warning risks and improve the accuracy and reliability of fire warning.
[0105] Define the temperature prediction result and the temperature rising trend as fuzzy input variables, and define the fire warning level as a fuzzy output variable.
[0106] Define the cable temperature Tlevel The fuzzification levels are divided into four fuzzy sets: low (L), medium (M), high (H), and very high (VH).
[0107] Define the cable temperature change trend T trend The fuzzification levels are divided into three fuzzy sets: stable (S), rising (R), and sharply rising (SR).
[0108] Define the warning level P of the fire risk warning The fuzzification levels are divided into three fuzzy sets: low (L), medium (M), and high (H).
[0109] Then use the triangular membership function to define the membership functions of the input variables.
[0110] For the cable temperature T level :
[0111] Low (L): When the temperature is below 20°C, it is a low risk:
[0112]
[0113] Medium (M): The temperature is in the range of 40 - 60°C:
[0114]
[0115] High (H): The temperature is in the range of 60 - 80°C:
[0116]
[0117] Very high (VH): The temperature is above 80°C:
[0118]
[0119] ② For the cable temperature change trend T trend :
[0120] Stable (S): The temperature change trend is close to 0 or negative.
[0121]
[0122] Rising (R): The temperature change trend is in the range of 0.5 - 1:
[0123]
[0124] Sharply rising (SR): The temperature change trend is above 1:
[0125]
[0126] Then, formulate a fuzzy discrimination rule base. Fuzzy discrimination rules usually have the following form: IF (a set of conditions) THEN (deduce a set of results). The specific rules are as follows:
[0127] If the temperature level is low and the temperature trend is stable, the warning level is low. If the temperature level is medium and the temperature trend is rising, the warning level is medium. If the temperature level is high and the temperature trend is rising, the warning level is high. If the temperature level is extremely high and the temperature trend is rising sharply, the warning level is high.
[0128] Furthermore, use the minimum rule to perform Mamdani fuzzy inference to obtain a fuzzy output:
[0129] μ output = min(μ TempLevel , μ Trend )
[0130] μ output represents the output membership degree of this rule, that is, the fuzzy membership degree of the fire warning level. μ TempLevel represents the membership degree of the input variable "temperature level", and μ Trend represents the membership degree of the input variable "temperature change trend".
[0131] Use the centroid method for defuzzification to convert the fuzzy output into a specific warning level value P warning :
[0132]
[0133] x i is the possible value of the disaster warning level (represented by the numerical values of low, medium, and high), and μ i is the corresponding membership degree.
[0134] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not restrictive. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered by the scope of the claims of the present invention.
Claims
1. A dynamic cable temperature prediction and fire warning method, characterized in that: include, Collect data, build a BP-LSTM algorithm model, and dynamically predict the cable temperature change trend; Construct fuzzy logic algorithm model; The temperature prediction results and the temperature rising trend are defined as fuzzy input variables, and the fire warning level is defined as a fuzzy output variable to carry out cable fire warning.
2. A dynamic cable temperature prediction and fire warning method as claimed in claim 1, characterized in that: The BP-LSTM algorithm model includes an input layer, an LSTM layer, a BP neural network hidden layer and an output layer; The input layer is used to characterize the factors that affect the temperature change of the cable; The LSTM layer includes a forget gate, an input gate, an output gate, and a cyclic self-connected memory cell, and extracts the time dimension characteristics of data changes according to historical node data; The hidden layer of the BP neural network is used to characterize the weight and threshold of the BP neural network; The output layer represents the predicted temperature value of the cable.
3. A dynamic cable temperature prediction and fire warning method as claimed in claim 2, characterized in that: The number of nodes in the input layer is 4, and the input variables are soil moisture, soil temperature, cable current carrying capacity, and cable arrangement interval; The time step number of the LSTM layer is t, and the data of the past t time points are used to predict the new value; The number of nodes in the output layer is 1, and the output variable is the predicted temperature value of the cable.
4. A dynamic cable temperature prediction and fire warning method as claimed in claim 3, characterized in that: The fuzzy logic algorithm model includes fuzzy sets, membership functions, fuzzy reasoning, fuzzy discrimination rule base and defuzzification; The fuzzy sets are used to perform fuzzification processing on input and output variables; The membership function is used to quantify the fuzziness of the input variable; The fuzzy reasoning maps the fuzzy membership of the input variable to the fuzzy membership of the output variable; The fuzzy discrimination rule base is used to make decisions according to different input fuzzy quantities; The defuzzification is used to convert the fuzzified output into a specific numerical value.
5. A dynamic cable temperature prediction and fire warning method as claimed in claim 4, characterized in that: The temperature prediction result includes defining the fuzzy level of the cable temperature as four levels: low, medium, high, and very high; The temperature rising trend includes defining the fuzzy levels of the cable temperature change trend as stable, rising, and sharp rising; The fuzzy levels of early warning levels for fire risk are defined as low, medium, and high.
6. A dynamic cable temperature prediction and fire warning method as claimed in claim 5, characterized in that: The decision making according to different input fuzzy quantities includes that if the temperature level is low and the temperature trend is stable, the warning level is low; If the temperature level is medium and the temperature trend is rising, the warning level is medium; If the temperature level is high and the temperature trend is rising, the warning level is high; If the temperature level is extremely high and the temperature trend is rising sharply, the warning level is high.
7. A dynamic cable temperature prediction and fire warning method as claimed in claim 6, characterized in that: The conversion of the fuzzy output into a specific numerical value includes using the minimum rule to perform fuzzy reasoning to obtain the fuzzy output, and using the centroid method to perform defuzzification processing to convert the temperature level and temperature change trend into a quantitative result of the fire risk warning.
8. A system using a dynamic cable temperature prediction and fire warning method as claimed in any one of claims 1 to 7, characterized in that: It comprises a temperature prediction module (100), a fuzzy logic algorithm model module (200), an early warning module (300) and a wireless transmission module (400); The temperature prediction module (100) is used to collect data, build a BP-LSTM algorithm model, and dynamically predict the cable temperature change trend; The fuzzy logic algorithm model module (200) is used to construct a fuzzy logic algorithm model; The early warning module (300) is used to define the temperature prediction result and the temperature rising trend as fuzzy input variables, and define the fire warning level as a fuzzy output variable, so as to carry out cable fire early warning; The wireless transmission module (400) sends the warning information to the monitoring center to achieve remote real-time monitoring and predict the cable temperature change trend.
9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of a dynamic cable temperature prediction and fire warning 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 a dynamic cable temperature prediction and fire warning method according to any one of claims 1 to 7 are implemented.