Electrical Fire Prediction Method, Device, Computer Program Product and Storage Medium

Abstract

The present invention discloses an electrical fire prediction method, device, computer program product and storage medium. The method includes: obtaining detection data detected by each detection node; obtaining the node probability of each of the detection nodes according to the detection data; inputting the node probability as evidence into a Bayesian network model, where the Bayesian network model is obtained according to at least two preset detection nodes and a conditional probability table corresponding to the parent nodes of each of the preset detection nodes; obtaining the probability of an electrical fire occurring at the top-level node corresponding to the detection node output by the Bayesian network model, so as to achieve early prediction before the occurrence of an electrical fire and avoid waste of resources.

Description

Technical Field

[0001] The present invention relates to the technical field of electrical safety, and in particular, to an electrical fire prediction method, device, computer program product, and storage medium. Background Art

[0002] When studying the causes of electrical fires in the prior art, it is usually to judge the causes leading to electrical fires after the fire occurs, and it is impossible to predict in advance before the electrical fire occurs, resulting in waste of resources. Summary of the Invention

[0003] Embodiments of the present application provide an electrical fire prediction method, device, computer program product, and storage medium, aiming to predict electrical fires in advance to avoid waste of resources.

[0004] Embodiments of the present application provide an electrical fire prediction method, including:

[0005] Obtaining detection data detected by each detection node;

[0006] Obtaining the node probability of each detection node according to the detection data;

[0007] Taking the node probability as evidence and inputting it into a Bayesian network model, where the Bayesian network model is obtained according to at least two preset detection nodes and the conditional probability tables corresponding to the parent nodes of each preset detection node;

[0008] Obtaining the probability of an electrical fire occurring at the top-level node corresponding to the detection node output by the Bayesian network model.

[0009] In one embodiment, the step of obtaining the node probability of each detection node according to the detection data includes:

[0010] Obtaining the detection data of the current detection node;

[0011] Performing fuzzification processing on the detection data of the current detection node to map the detection data of the detection node to the node probability of the detection node.

[0012] In one embodiment, the step of performing fuzzification processing on the detection data of the current detection node to map the detection data of the detection node to the node probability of the detection node includes:

[0013] Performing processing on the detection data of the current detection node by using a fuzzification processing formula to map the detection data of the current detection node to the node probability of the detection node, and the fuzzification processing formula is:

[0014]

[0015] Among them, the x represents a detection parameter, k is the coefficient of the detection parameter, c is the critical determination threshold of the detection parameter, and the detection data of each detection node includes at least one detection parameter.

[0016] In one embodiment, the step of obtaining the probability of an electrical fire occurring at the top-level node corresponding to the detection node output by the Bayesian network model includes:

[0017] Determine the elimination order of the respective parent nodes of the detection node;

[0018] According to the elimination order, the conditional probability distribution tables corresponding to the respective parent nodes of the detection node, and the node probability, determine the probability of an electrical fire occurring at the top-level node corresponding to the detection node.

[0019] In one embodiment, in the step of determining the probability of an electrical fire occurring at the top-level node corresponding to the detection node according to the elimination order, the conditional probability distribution tables corresponding to the respective parent nodes of the detection node, and the node probability, the probability of an electrical fire occurring at the top-level node corresponding to the detection node is determined according to the following inference formula, and the inference formula is:

[0020]

[0021] Among them, the X n-1 is the top-level node, the X 1 , X 2 , X 3 ,......, X n-2 are the respective parent nodes of the detection node, the m X1X2 is the intermediate result between the parent node X 1 and the parent node X 2 , and the defined elimination order is (X 1 , X 2 , X 3 ,......, X n-1 ).

[0022] In one embodiment, before the step of inputting the node probability as evidence into the Bayesian network model, the steps of generating the Bayesian network model include:

[0023] Obtain at least two preset detection nodes and the parent nodes of each preset detection node, and the preset detection node includes at least one parent node;

[0024] Determine the conditional probability table of the parent node of each preset detection node according to prior knowledge;

[0025] A Bayesian network model is obtained based on the conditional probability tables of each of the preset detection nodes and the parent nodes of the preset detection nodes.

[0026] In one embodiment, the step of obtaining a Bayesian network model based on the conditional probability tables of each of the preset detection nodes and the parent nodes of the preset detection nodes includes:

[0027] Based on prior knowledge, each of the preset detection nodes and the parent nodes of the preset detection nodes are sequentially subjected to discretization processing and sorting processing to obtain a set of detection nodes;

[0028] A Bayesian network model is obtained according to the sorted set of detection nodes and the conditional probability tables of the parent nodes of the preset detection nodes in the set of detection nodes.

[0029] In addition, to achieve the above object, the present invention also provides an electrical fire prediction device including: a memory, a processor, and an electrical fire prediction program stored on the memory and executable on the processor. When the electrical fire prediction program is executed by the processor, the steps of the above electrical fire prediction method are implemented.

[0030] In addition, to achieve the above object, the present invention also provides a computer program product. The computer program product includes an electrical fire prediction program. When the electrical fire prediction program is executed by a processor, the steps of the above electrical fire prediction method are implemented.

[0031] In addition, to achieve the above object, the present invention also provides a storage medium on which an electrical fire prediction program is stored. When the electrical fire prediction program is executed by a processor, the steps of the above electrical fire prediction method are implemented.

[0032] In the technical solution of an electrical fire prediction method, device, computer program product, and storage medium provided in the embodiments of the present application, by acquiring detection data detected by a detection node, converting the detection data into a node probability corresponding to the detection node, using the node probability as evidence and inputting it into a Bayesian network model, and inferring the probability of an electrical fire occurring at the top-level node corresponding to the detection node according to the node probability and the conditional probability tables corresponding to each detection node in the Bayesian network model. By the above method, the probability of an electrical fire occurring can be known in advance before the electrical fire occurs, thereby avoiding waste of resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 It is a schematic structural diagram of the hardware operating environment related to the embodiment solution of the present invention;

[0034] Figure 2 It is a schematic flowchart of the first embodiment of the electrical fire prediction method of the present invention;

[0035] Figure 3 It is a schematic flowchart of the second embodiment of the electrical fire prediction method of the present invention;

[0036] Figure 4 It is a schematic flowchart of the fourth embodiment of the electrical fire prediction method of the present invention;

[0037] Figure 5 It is a schematic flowchart of the sixth embodiment of the electrical fire prediction method of the present invention;

[0038] Figure 6 It is a schematic flowchart of the seventh embodiment of the electrical fire prediction method of the present invention;

[0039] Figure 7 It is a schematic diagram showing the Bayesian network model and conditional probability in the electrical fire prediction method of the present invention;

[0040] Figure 8 It is a schematic diagram of the inference of the variable elimination method of the Bayesian network model in the electrical fire prediction method of the present invention;

[0041] The realization, functional features and advantages of the object of the present invention will be further described in conjunction with the embodiments with reference to the accompanying drawings. The above accompanying drawings are only diagrams of one embodiment and not all of the invention. Detailed Embodiment

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

[0043] As Figure 1 shown, Figure 1 It is a schematic diagram of the structure of the hardware operating environment related to the embodiment solution of the present invention.

[0044] It should be noted that Figure 1 it can be a schematic diagram of the structure of the hardware operating environment of the electrical fire prediction device.

[0045] As Figure 1As shown, the electrical fire prediction device may include: a processor 1001, such as a CPU, a memory 1005, a user interface 1003, a network interface 1004, and a communication bus 1002. Among them, the communication bus 1002 is used to implement the connection and communication between these components. The user interface 1003 may include a display screen (Display) and an input unit such as a keyboard (Keyboard). Optionally, the user interface 1003 may further include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface). The memory 1005 may be a high-speed RAM memory or a stable memory (non-volatile memory), such as a disk memory. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0046] Those skilled in the art can understand that Figure 1 the structure of the electrical fire prediction device shown in

[0047] does not constitute a limitation on the electrical fire prediction device, and may include more or fewer components than shown in the figure, or combine certain components, or have a different component layout. Figure 1 As shown, the memory 1005, as a storage medium, may include an operating system, a network communication module, a user interface module, and an electrical fire prediction program. Among them, the operating system is a program that manages and controls the hardware and software resources of the electrical fire prediction device, and the operation of the electrical fire prediction program and other software or programs.

[0048] In Figure 1 the electrical fire prediction device shown, the user interface 1003 is mainly used to connect to a terminal and perform data communication with the terminal; the network interface 1004 is mainly used to connect to a background server and perform data communication with the background server; the processor 1001 may be used to call the electrical fire prediction program stored in the memory 1005.

[0049] In this embodiment, the electrical fire prediction device includes: a memory 1005, a processor 1001, and an electrical fire prediction program stored on the memory and executable on the processor, where:

[0050] When the processor 1001 calls the electrical fire prediction program stored in the memory 1005, it performs the following operations:

[0051] Obtain the detection data detected by each detection node;

[0052] Obtain the node probability of each of the detection nodes according to the detection data;

[0053] Input the node probability as evidence into the Bayesian network model, which is obtained based on at least two preset detection nodes and the conditional probability tables corresponding to the parent nodes of each of the preset detection nodes;

[0054] Obtain the probability of an electrical fire occurring at the top-level node corresponding to the detection node output by the Bayesian network model.

[0055] When the processor 1001 calls the electrical fire prediction program stored in the memory 1005, the following operations are also performed:

[0056] Obtain the detection data of the current detection node;

[0057] Perform fuzzification processing on the detection data of the current detection node to map the detection data of the detection node to the node probability of the detection node.

[0058] When the processor 1001 calls the electrical fire prediction program stored in the memory 1005, the following operations are also performed:

[0059] Process the detection data of the current detection node using a fuzzification processing formula to map the detection data of the current detection node to the node probability of the detection node, and the fuzzification processing formula is:

[0060]

[0061] where x represents the detection parameter, k is the coefficient of the detection parameter, c is the critical determination threshold of the detection parameter, and the detection data of each detection node includes at least one detection parameter.

[0062] When the processor 1001 calls the electrical fire prediction program stored in the memory 1005, the following operations are also performed:

[0063] Determine the elimination order of the respective parent nodes of the detection node;

[0064] Based on the elimination order, the conditional probability distribution tables corresponding to the respective parent nodes of the detection node, and the node probability, determine the probability of an electrical fire occurring at the top-level node corresponding to the detection node.

[0065] When the processor 1001 calls the electrical fire prediction program stored in the memory 1005, the following operations are also performed:

[0066] Determine the probability of an electrical fire occurring at the top-level node corresponding to the detection node according to the following inference formula, and the inference formula is:

[0067]

[0068] where the Xn-1 is the top-level node, and the X 1 , X 2 , X 3 ,......, X n-2 are the respective parent nodes of the detection node, and the m X1X2 is the intermediate result between the parent node X 1 and the parent node X 2 . The defined elimination order is (X 1 , X 2 , X 3 ,......, X n-1 ).

[0069] When the processor 1001 calls the electrical fire prediction program stored in the memory 1005, the following operations are also performed:

[0070] Obtain at least two preset detection nodes and the parent nodes of each of the preset detection nodes, where the preset detection nodes include at least one parent node;

[0071] Determine the conditional probability table of the parent nodes of each of the preset detection nodes according to prior knowledge;

[0072] Obtain a Bayesian network model according to each of the preset detection nodes and the conditional probability table of the parent nodes of the preset detection nodes.

[0073] When the processor 1001 calls the electrical fire prediction program stored in the memory 1005, the following operations are also performed:

[0074] Perform discrete processing and sorting processing on each of the preset detection nodes and the parent nodes of the preset detection nodes in sequence based on prior knowledge to obtain a detection node set;

[0075] Obtain a Bayesian network model according to the sorted detection node set and the conditional probability table of the parent nodes of the preset detection nodes in the detection node set.

[0076] The embodiments of the present invention provide embodiments of an electrical fire prediction method. It should be noted that although the logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than here.

[0077] As Figure 2 shown, in the first embodiment of the present application, the electrical fire prediction method of the present application includes the following steps:

[0078] Step S110, obtain the detection data detected by each detection node;

[0079] Step S120, obtain the node probability of each of the detection nodes according to the detection data;

[0080] Step S130: Use the node probability as evidence and input it into a Bayesian network model, where the Bayesian network model is obtained according to at least two preset detection nodes and the conditional probability tables corresponding to the parent nodes of each of the preset detection nodes;

[0081] Step S140: Obtain the probability of an electrical fire occurring at the top-level node corresponding to the detection node output by the Bayesian network model.

[0082] In this embodiment, to solve the technical problem in the prior art that it is impossible to predict an electrical fire in advance, the present application designs a prediction method for an electrical fire. This prediction method for an electrical fire can be applied to indoor electrical fire prediction or outdoor electrical fire prediction. Taking indoor electrical fire prediction as an example, first, a Bayesian network structure is established based on prior knowledge, and the conditional probability tables of each detection node are constructed; then, after the Bayesian network structure is established, the detection data collected by the sensors of each detection node is read in real time, and the detection data is fuzzified to convert the detection data into the node probability corresponding to the detection node. The node probability is used as evidence and input into the Bayesian network model; finally, in the process of using the node probability as evidence and inputting it into the Bayesian network model, the probability of an electrical fire occurring at the top-level node is inferred by the variable elimination method.

[0083] In this embodiment, the Bayesian network model is obtained from at least two preset detection nodes and the conditional probability tables corresponding to the parent nodes of each of the preset detection nodes. The parameters of the Bayesian network model are represented by detection nodes. The state of each detection node generally represents detection data such as temperature and pressure that is continuously updated. Corresponding sensors can be set on each detection node to collect the detection data on the detection node, and then the detection data of each detection node is converted into the node probability corresponding to the detection node through fuzzification processing; after obtaining the node probability table corresponding to each detection node, the node probability table is used as evidence and input into the Bayesian network model, and the probability of an electrical fire occurring at the top-level node corresponding to the detection node is obtained through inference.

[0084] In this embodiment, the relationships between the detection nodes and the conditional probability table of each detection node can be obtained based on prior knowledge. The number of conditional probability tables is the same as the number of detection nodes in the Bayesian network. The conditional probability table is a multi-dimensional array, and its dimension is equal to the product of the number of node states, the number of evidence states in the detection node, and the number of evidences. All detection nodes in this Bayesian network model have two node states. For example, there are detection nodes A, B, and C. Among them, detection nodes A and B are the parent nodes of detection node C. Then, detection nodes A and B are the evidences of detection node C, and the number of evidences is 2. Then, the size of the conditional probability table of detection node C is 2*4, and the conditional probability table can be represented by the following table:

[0085]

[0086] Among them, taking P(C|A) as an example, when A does not occur, the probabilities of detection node C being in states 0 and 1 are 0.10 and 0.90 respectively. When A occurs, the probabilities of detection node C being in states 0 and 1 become 0.90 and 0.10 respectively.

[0087] In this embodiment, the process of reasoning using the Bayesian network model is essentially a process of obtaining the top-level node state information of the detection node based on the existing evidences. The reasoning methods include forward reasoning, backward reasoning, and explanatory reasoning. This application adopts the forward reasoning method, that is, determining the cause to infer all possible results. For example, there is a Figure 7 shown Bayesian network model and conditional probability table. Among them, D is the top-level node of the detection node, and the probability of the top-level node of the detection node is obtained according to prior knowledge:

[0088]

[0089] Obtain the evidences corresponding to the detection node, and use the evidences to perform reasoning calculations on the Bayesian network model to obtain the probability distribution of the detection node:

[0090]

[0091] According to the above technical solution, in this embodiment, by obtaining the detection data detected by the detection node, converting the detection data into the node probability corresponding to the detection node, inputting the node probability as an evidence into the Bayesian network model, and inferring the probability of the top-level node corresponding to the detection node having an electrical fire according to the node probability and the conditional probability table corresponding to each detection node in the Bayesian network model. By the above method, the probability of an electrical fire can be known in advance before the electrical fire occurs, thus avoiding waste of resources.

[0092] Such as Figure 3As shown in the figure, in the second embodiment of the present application, based on step S110 of the first embodiment, the second embodiment of the present application includes the following steps:

[0093] Step S111, obtaining the detection data of the current detection node;

[0094] Step S112, performing a fuzzification process on the detection data of the current detection node to map the detection data of the detection node to the node probability of the detection node.

[0095] In this embodiment, the process of obtaining the detection data of the current detection node is a real-time acquisition process. The detection data of the current detection node is obtained through sensors set on the detection node. The detection data corresponding to each detection node may be the same or different. The detection data may be temperature data, and the detection data may also be pressure data. The detection data may also be other data such as current.

[0096] In this embodiment, after obtaining the detection data of the detection node, a fuzzification process is performed on the detection data. The fuzzification process is a process of converting the detection data of the input quantity of the fuzzy controller into the corresponding fuzzy language variable value, that is, through the fuzzification process, the detection data is mapped to the probability of the occurrence of the detection node event, that is, the node probability of the detection node.

[0097] According to the above technical solution, this embodiment obtains the evidence source for the inference of the Bayesian network model by adopting the technical means of performing a fuzzification process on the detection data of the detection node to map the detection data of the detection node to the node probability of the detection node.

[0098] The following is the third embodiment of the present application. Based on step S112 of the second embodiment, the second embodiment of the present application includes:

[0099] Step S1121, processing the detection data of the current detection node by using a fuzzification formula to map the detection data of the current detection node to the node probability of the detection node. The fuzzification formula is:

[0100] In this embodiment, after obtaining the detection data of the current detection node, the detection data of the current detection node is fuzzified by using the fuzzification formula, so that the detection data of the current detection node is mapped to the node probability of the detection node. The fuzzification formula is Wherein, x represents a detection parameter, k is the coefficient of the detection parameter, c is the critical determination threshold of the detection parameter, the detection data of each detection node includes at least one detection parameter, and the detection data can be detection data such as temperature or current. When the detection data is current, the detection parameter can be at least one of small wire diameter and high load; the values of the fuzzy processing formula within the domain are all restricted within the interval (0, 1). When the detection data is temperature, when the node probability of the detection data is closer to 1, it indicates a higher temperature, and when the node probability of the detection data is closer to 0, it indicates a lower temperature.

[0101] In the technical solution of this embodiment, the fuzzy processing formula is adopted to obtain the node probability corresponding to the detection node in real time.

[0102] As Figure 4 shown, in the fourth embodiment of the present application, based on step S140 of the second embodiment, the fourth embodiment of the present application includes the following steps:

[0103] Step S141, determining the elimination order of each parent node of the detection node;

[0104] Step S142, determining the probability of an electrical fire occurring in the top-level node corresponding to the detection node according to the elimination order, the conditional probability distribution tables corresponding to each parent node of the detection node, and the node probability.

[0105] In this embodiment, during the reasoning process of the Bayesian network model, variables need to be added to reason out the probability of an electrical fire occurring in the top-level node corresponding to the detection node. At the same time, the variable elimination method is used to eliminate the added variables to obtain the probability of an electrical fire occurring in the top-level node corresponding to the detection node. For example, as Figure 8 shown, the variable elimination method is used to obtain the probability of an electrical fire occurring in detection node E. Specifically, by adding variables A, B, C, and D to obtain the probability of an electrical fire occurring in detection node E, then the probability of an electrical fire occurring in detection node E is:

[0106]

[0107] Determine the elimination order (A, B, C, D) of each parent node of the detection node. Then, according to the elimination order, the conditional probability distribution tables corresponding to each parent node of the detection node, and the node probability, determine the probability of an electrical fire occurring in the top-level node corresponding to the detection node as:

[0108]

[0109] In this embodiment, according to the above technical solution, by determining the elimination order of each parent node of the detection node, and determining the probability of an electrical fire occurring in the top-level node corresponding to the detection node according to the elimination order, the conditional probability distribution tables corresponding to each parent node of the detection node, and the node probability, the probability of an electrical fire occurring is determined by the variable elimination method.

[0110] The following is the fifth embodiment of the present application. Based on step S142 of the fourth embodiment, the fifth embodiment of the present application includes:

[0111] Step S1421, determining the probability of an electrical fire occurring in the top-level node corresponding to the detection node according to the following inference formula, and the inference formula is:

[0112]

[0113] In this embodiment, the top-level node is defined as X n-1 , and each parent node of the detection node is respectively X 1 , X 2 , X 3 ,......, X n-2 , where m X1X2 is the intermediate result between the parent node X 1 and the parent node X 2 . The defined elimination order is (X 1 , X 2 , X 3 ,......, X n-1 ), then the probability of an electrical fire occurring in the top-level node corresponding to the detection node can be determined according to the following inference formula, and the inference formula is:

[0114] The probability of an electrical fire occurring in the top-level node corresponding to the detection node, and the inference formula is:

[0115]

[0116] In the technical solution of this embodiment, by using the inference formula designed in the present application, the probability of an electrical fire occurring in the top-level node corresponding to the detection node is obtained, and the efficiency of determining the probability of an electrical fire occurring is improved.

[0117] As Figure 5 shown, in the sixth embodiment of the present application, before step S120 of the first embodiment, the sixth embodiment of the present application includes the following steps:

[0118] Step S210, obtaining at least two preset detection nodes and the parent nodes of each of the preset detection nodes, and the preset detection nodes include at least one parent node;

[0119] Step S220: Determine the conditional probability tables of the parent nodes of each of the preset detection nodes according to prior knowledge;

[0120] Step S230: Obtain a Bayesian network model according to each of the preset detection nodes and the conditional probability tables of the parent nodes of the preset detection nodes.

[0121] In this embodiment, the Bayesian network model is obtained from at least two preset detection nodes and the parent nodes of the preset detection nodes. Each preset detection node includes at least one parent node. Determine the conditional probability tables of the parent nodes of each preset detection node according to prior knowledge; after obtaining the conditional probability tables of the parent nodes of each preset detection node, construct a Bayesian network model according to each of the preset detection nodes and the conditional probability tables of the parent nodes of the preset detection nodes.

[0122] According to the above technical solution of this embodiment, since the technical means of obtaining at least two preset detection nodes and the parent nodes of each of the preset detection nodes, determining the conditional probability tables of the parent nodes of each of the preset detection nodes according to prior knowledge, and obtaining a Bayesian network model according to each of the preset detection nodes and the conditional probability tables of the parent nodes of the preset detection nodes are adopted, the construction of the Bayesian network model is realized.

[0123] As Figure 6 shown, in the seventh embodiment of the present application, based on step S230 of the sixth embodiment, the seventh embodiment of the present application includes the following steps:

[0124] Step S231: Perform discrete processing and sorting processing on each of the preset detection nodes and the parent nodes of the preset detection nodes in sequence based on prior knowledge to obtain a detection node set;

[0125] Step S232: Obtain a Bayesian network model according to the sorted detection node set and the conditional probability tables of the parent nodes of the preset detection nodes in the detection node set.

[0126] In this embodiment, before constructing the Bayesian network model, obtain the positions of each of the preset detection nodes and the parent nodes of the preset detection nodes, and perform discrete processing on each of the preset detection nodes and the parent nodes of the preset detection nodes in sequence based on prior knowledge; after the discrete processing, perform sorting processing on the positions of each of the preset detection nodes and the parent nodes of the preset detection nodes after the discrete processing to obtain a sorted detection node set; after obtaining the sorted detection node set, obtain a Bayesian network model according to the conditional probability tables of each of the preset detection nodes and the parent nodes of each of the preset detection nodes in the sorted detection node set.

[0127] In this embodiment, according to the above technical solution, since the detection node set is obtained by successively performing discrete processing and sorting processing on each of the preset detection nodes and the parent nodes of the preset detection nodes based on prior knowledge, and the Bayesian network model is obtained according to the sorted detection node set and the conditional probability table of the parent nodes of the preset detection nodes in the detection node set, the construction of the Bayesian network model is realized.

[0128] Based on the same inventive concept, an embodiment of the present application further provides a computer program product. The computer program product includes an electrical fire prediction program. When the electrical fire prediction program is executed by a processor, it realizes each step of the electrical fire prediction as described above and can achieve the same technical effect. To avoid repetition, it will not be elaborated here.

[0129] Since the computer program product provided by the embodiment of the present application is the computer program product adopted for implementing the method of the embodiment of the present application, based on the method introduced in the embodiment of the present application, those skilled in the art can understand the specific structure and variations of the computer program product, so it will not be elaborated here. Any computer program product adopted for the method of the embodiment of the present application falls within the scope of protection of the present application.

[0130] Based on the same inventive concept, an embodiment of the present application further provides a storage medium. The storage medium stores an electrical fire prediction program. When the electrical fire prediction program is executed by a processor, it realizes each step of the electrical fire prediction as described above and can achieve the same technical effect. To avoid repetition, it will not be elaborated here.

[0131] Since the storage medium provided by the embodiment of the present application is the storage medium adopted for implementing the method of the embodiment of the present application, based on the method introduced in the embodiment of the present application, those skilled in the art can understand the specific structure and variations of the storage medium, so it will not be elaborated here. Any storage medium adopted for the method of the embodiment of the present application falls within the scope of protection of the present application.

[0132] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, 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 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 storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0133] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and combinations of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to the processors of general-purpose computers, special-purpose computers, embedded processors, or other programmable data processing devices to generate a machine, such that the instructions executed by the processors of the computer or other programmable data processing devices produce means for implementing the functions specified in one flow Figure 1 one flow or multiple flows and / or blocks Figure 1 or means for implementing the functions specified in one block or multiple blocks.

[0134] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory produce a manufactured article including instruction means that implement the functions specified in one flow Figure 1 one flow or multiple flows and / or blocks Figure 1 or means for implementing the functions specified in one block or multiple blocks.

[0135] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, so that the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one flow Figure 1 one flow or multiple flows and / or blocks Figure 1 or means for implementing the functions specified in one block or multiple blocks.

[0136] It should be noted that in the claims, any reference signs placed between parentheses shall not be construed as limiting the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present invention can be implemented by means of hardware including several different elements and by means of a suitably programmed computer. In the unit claims listing several means, several of these means can be embodied by the same item of hardware. The use of the words first, second, and third, etc. does not denote any order. These words can be interpreted as names.

[0137] Although the preferred 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 concept. Therefore, the appended claims are intended to be construed as including the preferred embodiments and all changes and modifications falling within the scope of the present invention.

[0138] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these modifications and variations.

Claims

1. An electrical fire prediction method, characterized in that, the electrical fire prediction method includes: Obtaining the detection data detected by each detection node; Obtaining the node probability of each of the detection nodes according to the detection data; Taking the node probability as evidence and inputting it into a Bayesian network model, where the Bayesian network model is obtained according to at least two preset detection nodes and the conditional probability tables corresponding to the parent nodes of each of the preset detection nodes; Determining the elimination order of the parent nodes of each of the detection nodes; According to the elimination order, the conditional probability distribution tables corresponding to the parent nodes of each of the detection nodes, and the node probabilities of each of the detection nodes, determining the probability of an electrical fire occurring in the top-level node corresponding to the detection node; wherein, the probability of an electrical fire occurring in the top-level node corresponding to the detection node is determined according to the following inference formula, and the inference formula is: Among them, the X n-1 is the top-level node, and the X 1 , X 2 , X 3 ,......, X n-2 are the respective parent nodes of the detection node. The m X1X2 is the intermediate result between the parent node X 1 and the parent node X 2 . The defined elimination order is (X 1 , X 2 , X 3 ,......, X n-1 ).

2. The method according to claim 1, characterized in that, the step of obtaining the node probability of each of the detection nodes according to the detection data includes: Obtaining the detection data of the current detection node; Performing a fuzzification process on the detection data of the current detection node to map the detection data of the detection node to the node probability of the detection node.

3. The method according to claim 2, characterized in that, the step of performing a fuzzification process on the detection data of the current detection node to map the detection data of the detection node to the node probability of the detection node includes: Performing a process on the detection data of the current detection node using a fuzzification formula to map the detection data of the current detection node to the node probability of the detection node, and the fuzzification formula is: wherein, x represents a detection parameter, k is the coefficient of the detection parameter, c is the critical determination threshold of the detection parameter, and the detection data of each detection node includes at least one detection parameter.

4. The method according to claim 1, characterized in that, before the step of taking the node probability as evidence and inputting it into a Bayesian network model, the step of generating the Bayesian network model includes: Obtaining at least two preset detection nodes and the parent nodes of each of the preset detection nodes, where the preset detection nodes include at least one parent node; Determining the conditional probability tables of the parent nodes of each of the preset detection nodes according to prior knowledge; Obtaining a Bayesian network model according to each of the preset detection nodes and the conditional probability tables of the parent nodes of the preset detection nodes.

5. The method according to claim 4, characterized in that, the step of obtaining a Bayesian network model according to each of the preset detection nodes and the conditional probability tables of the parent nodes of the preset detection nodes includes: Performing a discrete process and a sorting process on each of the preset detection nodes and the parent nodes of the preset detection nodes in sequence based on prior knowledge to obtain a detection node set; Obtaining a Bayesian network model according to the sorted detection node set and the conditional probability tables of the parent nodes of the preset detection nodes in the detection node set.

6. An electrical fire prediction device, characterized in that, The electrical fire prediction device includes: a memory, a processor, and an electrical fire prediction program stored on the memory and executable on the processor. When the electrical fire prediction program is executed by the processor, the steps of the electrical fire prediction method according to any one of claims 1-5 are implemented.

7. A computer program product, characterized in that the computer program product includes an electrical fire prediction program. When the electrical fire prediction program is executed by a processor, each step of the electrical fire prediction method according to any one of claims 1-5 is implemented.

8. A storage medium, characterized in that an electrical fire prediction program is stored thereon. When the electrical fire prediction program is executed by a processor, the steps of the electrical fire prediction method according to any one of claims 1-5 are implemented.

Images