Underground fire early warning method and device, processor and electronic equipment

Abstract

The invention discloses an underground fire early warning method and device, a processor and electronic equipment. The method comprises the steps that the detection intensity of a plurality of underground detection devices at different moments is acquired, and the detection intensity is used for representing the intensity of detection signals obtained when the detection devices detect underground transformation devices at different moments; inputting the detection intensity into a target prediction model for prediction to obtain a prediction result; and in response to the fact that the possibility degree corresponding to the prediction result exceeds a preset possibility degree, a target early warning signal and a target early warning strategy are sent to the client, and the target early warning strategy is used for representing a rule for protecting the transformer equipment in response to the fact that the transformer equipment generates a fire disaster underground at the future moment. According to the invention, the technical problem of low early warning efficiency of underground fire is solved.

Description

Technical Field

[0001] The present invention relates to the field of electric power, and in particular to an underground fire early warning method, device, processor and electronic equipment. Background Art

[0002] At present, with the development of cities, the demand for electricity is also increasing, and underground transformer substations have become important infrastructure. However, underground transformer substations are relatively closed places with few people entering and leaving, and related detection methods or detectors are difficult to quickly and accurately issue fire alarms after a fire occurs, resulting in low early warning efficiency of underground fires.

[0003] With respect to the above-mentioned technical problem of low early warning efficiency of underground fires, no effective solution has been proposed so far. Summary of the invention

[0004] The embodiments of the present invention provide an underground fire early warning method, device, processor and electronic device to at least solve the technical problem of low efficiency of underground fire early warning.

[0005] According to one aspect of an embodiment of the present invention, there is provided an underground fire warning method, the method comprising: obtaining detection strengths of multiple detection devices located underground at different times, wherein the detection strength is used to represent the strength of detection signals obtained by the detection devices detecting transformer equipment located underground at different times; inputting the detection strength into a target prediction model for prediction to obtain a prediction result, wherein the target prediction model is used to represent a mapping relationship between the prediction result and the detection strength and the target weight of the detection device, and the prediction result is used to represent the degree of possibility of a fire occurring underground in the transformer equipment at a future moment; in response to the degree of possibility corresponding to the prediction result exceeding a preset degree of possibility, sending a target warning signal and a target warning strategy to a client, wherein the target warning strategy is used to represent rules for protecting the transformer equipment in response to a fire occurring underground in the transformer equipment at a future moment.

[0006] Optionally, the detection intensity is input into a target prediction model for prediction to obtain a prediction result, including: determining a target weight of the detection device; inputting the target weight and the detection intensity into the target prediction model for prediction to obtain a prediction result.

[0007] Optionally, determining a target weight of the detection device includes: inputting the detection intensity into an initial prediction model for prediction to obtain an initial prediction result, wherein the initial prediction model is used to represent a mapping relationship between the initial prediction result and the detection intensity and the initial weight of the detection device; in response to a possibility degree corresponding to the initial prediction result being less than a preset possibility degree, determining a target weight based on the initial weight.

[0008] Optionally, based on the initial weights, a target weight is determined, including: determining a first initial weight of a first detection device in the detection device and a second initial weight of a second detection device in the detection device, wherein the way the first detection device detects the transformer device is different from the way the second detection device detects the transformer device, and the initial weights include the first initial weight and the second initial weight; the first initial weight is merged into the second initial weight to obtain the target weight.

[0009] Optionally, the method also includes: in response to the possibility level corresponding to the initial prediction result exceeding a preset possibility level, determining the severity of a fire occurring underground in the transformer equipment at a future moment; determining a target warning signal and a target warning strategy corresponding to the severity; and sending a target warning signal and a target warning strategy corresponding to the severity to the client.

[0010] Optionally, in response to the possibility level corresponding to the prediction result exceeding the preset possibility level, a target warning signal and a target warning strategy are sent to the client, including: in response to the possibility level corresponding to the prediction result exceeding the preset possibility level, determining the severity of a fire underground in the transformer equipment at a future moment; determining a target warning signal and a target warning strategy corresponding to the severity; and sending a target warning signal and a target warning strategy corresponding to the severity to the client.

[0011] According to one aspect of an embodiment of the present invention, an underground fire warning device is provided, which may include: an acquisition unit, used to acquire the detection strength of multiple detection devices located underground at different times, wherein the detection strength is used to represent the strength of the detection signal obtained by the detection device detecting the transformer device located underground at different times; a prediction unit, used to input the detection strength into a target prediction model for prediction to obtain a prediction result, wherein the target prediction model is used to represent the mapping relationship between the prediction result and the detection strength and the target weight of the detection device, and the prediction result is used to represent the possibility of a fire occurring underground in the transformer device at a future moment; a sending unit, used to send a target warning signal and a target warning strategy to a client in response to the possibility corresponding to the prediction result exceeding a preset possibility, wherein the target warning strategy is used to represent the rules for protecting the transformer device in response to a fire occurring underground in the transformer device at a future moment.

[0012] According to another aspect of an embodiment of the present invention, a processor is further provided, wherein the processor is used to run a program, wherein when the program is run by the processor, the early warning method for underground fire in the embodiment of the present invention is executed.

[0013] According to another aspect of an embodiment of the present invention, there is also provided an electronic device, comprising: a memory storing an executable program; and a processor for running the program, wherein when the program is running, the early warning method for underground fire in each embodiment of the present invention is executed.

[0014] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the underground fire early warning method in the present invention.

[0015] According to another aspect of an embodiment of the present invention, a computer program product is further provided. The computer program product includes a computer program. When the computer program is executed by a processor, the early warning method for underground fire in the embodiment of the present invention is implemented.

[0016] According to another aspect of an embodiment of the present invention, a computer program product is also provided, including a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium is used to store a computer program, and when the computer program is executed by a processor, the early warning method for underground fires in the embodiment of the present invention is implemented.

[0017] According to another aspect of the embodiments of the present invention, the embodiments of the present application further provide a computer program, which, when executed by a processor, implements the underground fire early warning method in the above-mentioned embodiments of the present invention.

[0018] In an embodiment of the present invention, when an underground fire is warned, the detection strength of multiple detection devices located underground at different times can be obtained, that is, the strength of the detection signal obtained by the detection device detecting the transformer device located underground at different times can be obtained. The obtained detection strength is input into the target prediction model for prediction, and a prediction result can be obtained, that is, the possibility of a fire occurring underground in the transformer device at a future moment can be obtained, and in response to the possibility corresponding to the prediction result exceeding the preset possibility, a target warning signal and a target warning strategy are sent to the client, thereby achieving the purpose of quickly and accurately issuing a fire alarm after a fire occurs, thereby solving the technical problem of low warning efficiency of underground fires, and further achieving the technical effect of improving the warning efficiency of underground fires. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0020] Figure 1is a flow chart of an underground fire early warning method according to an embodiment of the present invention;

[0021] Figure 2 is a flow chart of a method for identifying a fire shielded by an underground transformer in a city according to an embodiment of the present invention;

[0022] Figure 3 It is a schematic diagram of an underground fire early warning device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0023] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only embodiments of a part of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0024] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0025] According to an embodiment of the present invention, a method for early warning of underground fires is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0026] Figure 1 : is a flow chart of an underground fire early warning method according to an embodiment of the present invention. The method may include the following steps:

[0027] Step S101, obtaining the detection strength of multiple detection devices underground at different times.

[0028] In the technical solution provided in the above step S101 of the present invention, the above detection intensity can be used to indicate the intensity of the detection signal obtained by the detection device detecting the transformer device located underground at different times.

[0029] In this embodiment, the above-mentioned voltage conversion device can be a transformer. The above-mentioned detection device can be different types of detectors, and the detectors can at least include: cable-type linear temperature-sensitive fire detectors, suction-type fire detectors, infrared reflection-type fire detectors, and image fire detectors, etc., which are only given as examples and are not specifically limited.

[0030] In this embodiment, the detection strength of multiple detection devices located underground at different times is obtained. Optionally, this embodiment controls multiple detection devices to perform real-time detection of the transformer device located underground at different times, and the detection strength can be obtained, that is, the strength of the detection signal obtained by the detection device detecting the transformer device located underground at different times can be obtained.

[0031] Step S102, inputting the detection intensity into the target prediction model for prediction to obtain a prediction result.

[0032] In the technical solution provided in step S102 of the present invention, the target prediction model can be used to represent the mapping relationship between the prediction result and the detection strength and the target weight of the detection device. The prediction result can be used to represent the possibility of a fire occurring underground in the transformer equipment at a future moment.

[0033] In this embodiment, after obtaining the detection strength of multiple detection devices located underground at different times, the detection strength is input into the target prediction model for prediction to obtain a prediction result. Optionally, this embodiment, based on obtaining the detection strength of multiple detection devices located underground at different times, inputs the obtained detection strength into the target prediction model for prediction, and outputs the predicted result through the output layer of the target prediction model. That is, through the output layer of the target prediction model, the possibility of a fire occurring underground in the transformer equipment at a future moment can be output.

[0034] Step S103, in response to the possibility level corresponding to the prediction result exceeding the preset possibility level, sending a target warning signal and a target warning strategy to the client.

[0035] In the technical solution provided in the above step S103 of the present invention, the above target warning strategy can be used to represent the rules for protecting the transformer equipment in response to a fire occurring underground in the transformer equipment at a future moment.

[0036] In this embodiment, the preset probability degree can be used to represent the fire alarm threshold. The target warning signal can be presented in at least one of the following forms: voice form, animation form, email form, and pop-up form, etc., which are only used as examples and are not specifically limited.

[0037] In this embodiment, after the detection intensity is input into the target prediction model for prediction and the prediction result is obtained, in response to the possibility degree corresponding to the prediction result exceeding the preset possibility degree, a target warning signal and a target warning strategy are sent to the client. Optionally, based on the prediction result, this embodiment judges the relationship between the possibility degree corresponding to the prediction result and the preset possibility degree, and if it is judged that the possibility degree corresponding to the prediction result exceeds the preset possibility degree, a target warning signal and a target warning strategy are sent to the client.

[0038] In the above steps S101 to S103 of the present application, when warning of underground fire, the detection strength of multiple detection devices located underground at different times can be obtained, that is, the strength of the detection signal obtained by the detection device detecting the transformer device located underground at different times can be obtained. The obtained detection strength is input into the target prediction model for prediction, and the prediction result can be obtained, that is, the possibility of a fire occurring underground in the transformer device at a future moment can be obtained, and in response to the possibility corresponding to the prediction result exceeding the preset possibility, the target warning signal and target warning strategy are sent to the client, thereby achieving the purpose of quickly and accurately issuing a fire alarm after the fire occurs, thereby solving the technical problem of low warning efficiency of underground fires, and further achieving the technical effect of improving the warning efficiency of underground fires.

[0039] The above method of this embodiment is further introduced below.

[0040] As an optional implementation method, step S102, inputting the detection intensity into the target prediction model for prediction to obtain a prediction result, includes: determining the target weight of the detection device; inputting the target weight and the detection intensity into the target prediction model for prediction to obtain a prediction result.

[0041] In this embodiment, after obtaining the detection strength of multiple detection devices in the underground at different times, the target weight of the detection device is determined. Optionally, this embodiment can determine the target weight of the detection device according to the initial weight of the detection device based on the detection strength of multiple detection devices in the underground at different times.

[0042] In this embodiment, after determining the target weight of the detection device, the target weight and the detection intensity are input into the target prediction model for prediction to obtain a prediction result. Optionally, on the basis of determining the target weight of the detection device, this embodiment inputs the determined target weight and the obtained detection intensity into the target prediction model for prediction, and outputs the predicted result through the output layer of the target prediction model. That is, through the output layer of the target prediction model, the possibility of a fire occurring underground in the transformer equipment at a future moment can be output.

[0043] In this embodiment, the target weight can be expressed as W j ′ The target weight can be calculated by the following formula (1), the weights of the cable-type linear heat-sensing fire detector, suction-type fire detector, and infrared reflection-type fire detector divided proportionally according to the correlation coefficient can be calculated by the following formulas (2) and (3), and the initial weights of the cable-type linear heat-sensing fire detector, suction-type fire detector, infrared reflection-type fire detector, and image fire detector can be calculated by the following formula (4):

[0044] W j ′ =W i +W j (1)

[0045]

[0046] Among them, W4 can be used to represent the weight assigned to the image fire detector. j It can be used to express the correlation coefficient between image fire detectors and cable-type linear temperature-sensitive fire detectors, suction fire detectors, and infrared reflection fire detectors, r k It can be used to represent the sum of the correlation coefficients between image fire detectors and cable-type linear heat-sensing fire detectors, suction fire detectors, and infrared reflection fire detectors. j It can be used to represent the role of the jth evaluation index (e.g., the alarm time of the jth detector) in the entire evaluation system. j The larger the value of , the greater the weight that the detector should be assigned. 1 and X 2 can be used to represent the response signals of the two detectors after recombination, and n can be used to represent the length of the time series.

[0047] In this embodiment, C in the above formula (4) j It can be calculated by the following formulas (5) to (7):

[0048]

[0049]

[0050] Optionally, the alarm time of each detector is used as an evaluation index, with a total of four evaluation indexes, to form an original index data matrix, which can be expressed by the following formula (8):

[0051]

[0052] Among them, x max Can be used to represent the maximum value of the alarm time of the detector in each column. min It can be used to represent the minimum value of the alarm time of the detector in each column. j It can be used to represent the standard deviation of the jth indicator. The larger the standard deviation, the greater the volatility of its value, the more information it can express, the higher the evaluation intensity in the evaluation system, and the greater the weight assigned. j It can be used to represent the conflict coefficient of indicator time. The smaller its value is, the closer the two are. In the later weight division, the weight distribution value can be reduced to a certain extent. ij It can be used to represent the correlation coefficient between various indicators. ij It can be used to represent the value of the jth evaluation index in the i-th non-shading fire experiment.

[0053] In this embodiment, the target prediction model can be expressed by the following formula (9):

[0054]

[0055] Among them, H j It can be used to indicate the detection strength of multiple detection devices underground at different times.

[0056] As an optional implementation method, determining the target weight of the detection device includes: inputting the detection intensity into an initial prediction model for prediction to obtain an initial prediction result; in response to the possibility level corresponding to the initial prediction result being less than a preset possibility level, determining the target weight based on the initial weight.

[0057] In this embodiment, the above initial prediction model can be used to represent the mapping relationship between the initial prediction result and the detection strength and the initial weight of the detection device.

[0058] In this embodiment, after obtaining the detection strength of multiple detection devices located underground at different times, the detection strength is input into the initial prediction model for prediction to obtain an initial prediction result. Optionally, this embodiment, based on obtaining the detection strength of multiple detection devices located underground at different times, inputs the obtained detection strength and the initial weight of the detection device into the initial prediction model for prediction, and outputs the predicted initial prediction result through the output layer of the initial prediction model. That is, through the output layer of the initial prediction model, the possibility of a fire occurring underground in the transformer equipment at a future moment can be output.

[0059] In this embodiment, after the detection intensity is input into the initial prediction model for prediction and the initial prediction result is obtained, in response to the possibility degree corresponding to the initial prediction result being less than the preset possibility degree, the target weight is determined based on the initial weight. Optionally, on the basis of obtaining the initial prediction result, this embodiment determines the relationship between the possibility degree corresponding to the initial prediction result and the preset possibility degree. If it is determined that the possibility degree corresponding to the initial prediction result is less than the preset possibility degree, the target weight of the detection device can be determined based on the initial weight of the detection device.

[0060] In this embodiment, the above initial prediction model can be expressed by the following formula (10):

[0061]

[0062] As an optional implementation method, based on the initial weight, determining the target weight includes: determining a first initial weight of a first detection device in the detection device and a second initial weight of a second detection device in the detection device; fusing the first initial weight into the second initial weight to obtain the target weight.

[0063] In this embodiment, the way in which the first detection device detects the transformer device may be different from the way in which the second detection device detects the transformer device. The initial weight may include a first initial weight and a second initial weight.

[0064] In this embodiment, after the detection score strength is input into the initial prediction model for prediction and the initial prediction result is obtained, the first initial weight of the first detection device in the detection device and the second initial weight of the second detection device in the detection device are determined. Optionally, based on the initial prediction result, this embodiment can determine the first initial weight of the first detection device in the detection device and the second initial weight of the second detection device in the detection device from the initial prediction model. Among them, the first detection device can be an image fire detector, and the second detection device can be a suction fire detector, an infrared reflection fire detector, and a cable-type linear temperature-sensing fire detector. The first initial weight can be represented by W4, and the second initial weight can be represented by W1, W2, and W3. This is only used as an example and is not specifically limited.

[0065] In this embodiment, after determining the first initial weight of the first detection device in the detection device and the second initial weight of the second detection device in the detection device, the first initial weight is fused to the second initial weight to obtain the target weight. Optionally, based on the determination of the first initial weight and the second initial weight, this embodiment performs a proportional division on the determined first initial weight, and fuses the divided first initial weight to the second initial weight, so as to obtain the target weight of the detection device. The above-mentioned proportional division process can be implemented by the above formula (2), and the above-mentioned fusion process can be implemented by the above formula (1).

[0066] As an optional implementation mode, the method also includes: in response to the possibility level corresponding to the initial prediction result exceeding the preset possibility level, determining the severity of a fire occurring underground in the transformer equipment at a future moment; determining a target warning signal and a target warning strategy corresponding to the severity; and sending a target warning signal and a target warning strategy corresponding to the severity to the client.

[0067] In this embodiment, in response to the possibility degree corresponding to the initial prediction result exceeding the preset possibility degree, the severity of the underground fire of the transformer equipment at a future moment is determined. Optionally, this embodiment determines the relationship between the possibility degree corresponding to the initial prediction result and the preset possibility degree, and if it is determined that the possibility degree corresponding to the initial prediction result exceeds the preset possibility degree, the severity of the underground fire of the transformer equipment at a future moment can be determined.

[0068] In this embodiment, in response to the possibility level corresponding to the initial prediction result exceeding the preset possibility level, after determining the severity of the fire occurring underground in the transformer equipment at a future moment, a target warning signal and a target warning strategy corresponding to the severity level are determined. Optionally, this embodiment can determine a target warning signal and a target warning strategy corresponding to the severity level based on the determination of the severity of the fire occurring underground in the transformer equipment at a future moment. For example, if the determined severity level is level I, a target warning signal and a target warning strategy corresponding to level I severity are determined; if the determined severity level is level II, a target warning signal and a target warning strategy corresponding to level II severity are determined. This is merely an example and is not specifically limited.

[0069] In this embodiment, after determining the target warning signal and target warning strategy corresponding to the severity, the target warning signal and target warning strategy corresponding to the severity are sent to the client. Optionally, this embodiment sends the target warning signal and target warning strategy corresponding to the severity to the client on the basis of determining the target warning signal and target warning strategy corresponding to the severity, and displays the target warning signal and the target warning strategy on the screen of the client.

[0070] As an optional implementation method, step S103, in response to the possibility level corresponding to the prediction result exceeding the preset possibility level, sending a target warning signal and a target warning strategy to the client, includes: in response to the possibility level corresponding to the prediction result exceeding the preset possibility level, determining the severity of a fire underground in the transformer equipment at a future moment; determining a target warning signal and a target warning strategy corresponding to the severity; and sending a target warning signal and a target warning strategy corresponding to the severity to the client.

[0071] In this embodiment, after the detection intensity is input into the target prediction model for prediction and the prediction result is obtained, in response to the possibility degree corresponding to the prediction result exceeding the preset possibility degree, the severity of the underground fire of the transformer equipment at the future moment is determined. Optionally, based on the prediction result, this embodiment determines the relationship between the possibility degree corresponding to the prediction result and the preset possibility degree. If it is determined that the possibility degree corresponding to the prediction result exceeds the preset possibility degree, the severity of the underground fire of the transformer equipment at the future moment can be determined.

[0072] In this embodiment, in response to the possibility level corresponding to the prediction result exceeding the preset possibility level, after determining the severity of the underground fire of the transformer equipment at a future moment, a target warning signal and a target warning strategy corresponding to the severity level are determined. Optionally, this embodiment can determine a target warning signal and a target warning strategy corresponding to the severity level based on the determination of the severity level. For example, if the determined severity level is level I, a target warning signal and a target warning strategy corresponding to level I severity are determined; if the determined severity level is level II, a target warning signal and a target warning strategy corresponding to level II severity are determined. This is only an example and is not specifically limited.

[0073] In this embodiment, after determining the target warning signal and target warning strategy corresponding to the severity, the target warning signal and target warning strategy corresponding to the severity are sent to the client. Optionally, this embodiment sends the target warning signal and target warning strategy corresponding to the severity to the client on the basis of obtaining the target warning signal and target warning strategy, and displays the target warning signal and target warning strategy on the screen of the client.

[0074] In an embodiment of the present invention, when an underground fire is warned, the detection strength of multiple detection devices located underground at different times can be obtained, that is, the strength of the detection signal obtained by the detection device detecting the transformer device located underground at different times can be obtained. The obtained detection strength is input into the target prediction model for prediction, and a prediction result can be obtained, that is, the possibility of a fire occurring underground in the transformer device at a future moment can be obtained, and in response to the possibility corresponding to the prediction result exceeding the preset possibility, a target warning signal and a target warning strategy are sent to the client, thereby achieving the purpose of quickly and accurately issuing a fire alarm after a fire occurs, thereby solving the technical problem of low warning efficiency of underground fires, and further achieving the technical effect of improving the warning efficiency of underground fires.

[0075] The technical solution of the embodiment of the present invention is illustrated below in conjunction with preferred implementation modes.

[0076] At present, with the development of cities, the demand for electricity is also increasing, and underground transformer substations have become important infrastructure. However, underground transformer substations are relatively closed places with few people entering and leaving, and related detection methods or detectors are difficult to quickly and accurately issue fire alarms after a fire occurs, resulting in low early warning efficiency of underground fires.

[0077] In order to solve the above technical problems, an embodiment of the present invention proposes an underground fire early warning method, which inputs the detection strength of multiple detection devices at different times in the underground into the target prediction model for prediction, and obtains the prediction result. If the degree of possibility represented by the prediction result exceeds the preset degree of possibility, the target early warning signal and the target early warning strategy are sent to the client, thereby achieving the purpose of quickly and accurately issuing a fire alarm after the fire occurs, thereby solving the technical problem of low early warning efficiency of underground fires, and further achieving the technical effect of improving the early warning efficiency of underground fires.

[0078] In this embodiment, the method for identifying fires caused by underground transformers in cities can be used to obtain the possibility of fires occurring underground in transformer equipment at a future moment. Figure 2 FIG. 4 is a flow chart of a method for identifying a fire shielded by an underground transformer in a city according to an embodiment of the present invention. Figure 2 As shown, the method may include the following steps:

[0079] Step S201, using the objective weighting method (CRITIC) to construct the original indicator data matrix.

[0080] In the technical solution provided in step S201 of the present invention, the detector data is collected under the non-shielded fire test to form the original indicator data matrix of the objective weighting method (CRITIC). Assuming that n experimental conditions are carried out, the alarm time of each detector under these n experiments is used as an evaluation index, with a total of four evaluation indexes, to form the original indicator data matrix shown in the above formula (4).

[0081] After the objective weighting method (CRITIC) is used to construct the original indicator data matrix, the process proceeds to step S202 to normalize the constructed original indicator data matrix to obtain the initial weight of each indicator.

[0082] In the technical solution provided in the above step S202 of the present invention, the original data is normalized. According to the processing requirements, the evaluation index is the response time, and the inverse processing is selected. The calculation formula is the above formula (5). Then, the variability of each index is calculated in the form of standard deviation, where the calculation formula is the above formula (6). Next, the conflict between each index and the amount of information of each index are calculated, where the calculation formula is the above formula (7). Finally, the weight of each index is calculated, where the calculation formula is the above formula (4).

[0083] After the constructed original indicator data matrix is ​​processed to obtain the initial weight of each indicator, step S203 is entered to assign a grade to each detector at different times based on the alarm threshold of each detector and the detection intensity of each detector.

[0084] In the technical solution provided in step S203 of the present invention, grading scores are carried out according to the set alarm thresholds of each detector. That is, when a certain detector reaches the set alarm threshold and exceeds the set alarm threshold, the scoring score of this detector is 100. At time t1, when a certain detector reaches a certain value range, additional scoring is carried out, and the detection signals of the detector before the alarm time are divided into several levels. Combining the weights of each criterion index, the possible risk value of a fire occurring at time t1 can be calculated, and a certain threshold is set. If it is greater than this threshold, it is regarded as a fire occurring.

[0085] In this embodiment, the above-mentioned score assignment and grading may include the following steps:

[0086] Step S2031, assuming that at time t, when the detector reaches its set alarm threshold or is greater than this value, the score is recorded as 100, then its score at time t1 (t1 < t) is recorded as other values less than 100. The detection signals of the detector at each moment before it reaches the alarm threshold are divided into multiple levels according to a certain value range to obtain the score values H at each moment. j 。

[0087] After assigning scores and grading each detector at different times based on the alarm thresholds of each detector and the detection intensity of each detector, steps S204 and S205 are entered. According to the score assignment and grading results and combined with the weights, the possible risk value A of a fire occurring is calculated, and it is judged whether the calculated possible risk value A of a fire occurring is greater than the fire alarm threshold set according to experience.

[0088] In this embodiment, after obtaining the score values H at each moment j After that, step S2032 is entered. According to the weights obtained in step S202 and combined with the score values H of the detector obtained in step S2031 j , the possible value of a fire occurring at time t1 can be calculated, where the specific calculation formula can be as shown in the above formula (10).

[0089] If the calculated possible risk value A of a fire occurring is greater than the fire alarm threshold set according to experience, step S206 is entered to determine that a fire occurs underground in the transformer at a future time. If the calculated possible risk value A of a fire occurring is less than or equal to the fire alarm threshold set according to experience, step S207 is entered to calculate the correlation coefficient between the image fire detector and the other three detectors under non-occluded fire using a correlation coefficient model (for example, the Pearson model).

[0090] In the technical solution provided in step S207 of the present invention, calculating the correlation coefficient between the image fire detector and the other three detectors under non-occluded fire using a correlation coefficient model may include the following steps:

[0091] Step S2071, when step S205 determines that no fire has occurred, the signals of each fire detector obtained from the simulation experiment under non-shielded fire are processed.

[0092] After processing the fire detector signals obtained from the non-obstructed fire simulation experiment, proceed to step S2072, use the fire detector signals processed in step S2071 as input data, and use the Pearson correlation coefficient calculation model to calculate the correlation coefficient value between the image fire detector and the other three fire detectors, where the calculation formula can be shown as above formula (3).

[0093] After using the correlation coefficient model to calculate the correlation coefficient between the image fire detector and the other three detectors under non-obstructed fire, proceed to step S208 to re-divide the initial weights of the detectors based on the correlation coefficient between the image fire detector and the other three detectors.

[0094] After the initial weights of the detectors are redivided in proportion to the correlation coefficients between the image fire detectors and the other three detectors, step S209 and step S210 are entered to recalculate the possible risk value A' of the fire occurrence based on the target weights obtained by the division, and to determine whether the recalculated possible risk value A' of the fire occurrence is greater than the fire alarm threshold set according to experience.

[0095] In the technical solution provided in the above step S210 of the present invention, according to the above formula (2), according to the correlation coefficient r between the image detector and other detectors j (j=4, 5, 6), and the weights of the image detectors are divided into the remaining three detectors. Substituting the obtained new weight distribution into the above formula (9), the possible risk value A' of fire occurrence can be recalculated.

[0096] If the recalculated fire risk value A' is greater than the fire alarm threshold value set according to experience, the process proceeds to step S211 to determine whether the transformer will have an underground fire in the future. If the recalculated fire risk value A' is less than or equal to the fire alarm threshold value set according to experience, the process proceeds to step S212 to determine whether the transformer will not have an underground fire in the future.

[0097] In this embodiment, the detection strength of multiple detection devices in the underground at different times is input into the target prediction model for prediction, and a prediction result can be obtained. If the probability degree represented by the prediction result exceeds the preset probability degree, a target warning signal and a target warning strategy are sent to the client, thereby achieving the purpose of quickly and accurately issuing a fire alarm after a fire occurs, thereby solving the technical problem of low warning efficiency of underground fires, and further achieving the technical effect of improving the warning efficiency of underground fires.

[0098] According to an embodiment of the present invention, an early warning device for underground fire is also provided. It should be noted that the early warning device for underground fire can be used to execute an early warning method for underground fire in the embodiment.

[0099] Figure 3 FIG. 1 is a schematic diagram of an underground fire early warning device according to an embodiment of the present invention. Figure 3 As shown, the underground fire warning device 300 may include: an acquisition unit 301 , a prediction unit 302 and a sending unit 303 .

[0100] The acquisition unit 301 is used to acquire the detection strength of multiple detection devices located underground at different times, wherein the detection strength is used to represent the strength of the detection signal obtained by the detection device when detecting the transformer device located underground at different times.

[0101] The prediction unit 302 is used to input the detection intensity into the target prediction model for prediction to obtain a prediction result, wherein the target prediction model is used to represent the mapping relationship between the prediction result and the detection intensity and the target weight of the detection equipment, and the prediction result is used to represent the possibility of a fire occurring underground in the transformer equipment at a future moment.

[0102] The sending unit 303 is used to send a target warning signal and a target warning strategy to the client in response to the possibility level corresponding to the prediction result exceeding the preset possibility level, wherein the target warning strategy is used to represent the rules for protecting the transformer equipment in response to a fire occurring underground in the transformer equipment at a future moment.

[0103] Optionally, the prediction unit 302 may include: a first determination module, used to determine the target weight of the detection device; a prediction module, used to input the target weight and the detection strength into a target prediction model for prediction to obtain a prediction result.

[0104] Optionally, the first determination module may include: a prediction submodule, used to input the detection intensity into an initial prediction model for prediction to obtain an initial prediction result, wherein the initial prediction model is used to represent the mapping relationship between the initial prediction result and the detection intensity and the initial weight of the detection device; a determination submodule, used to determine the target weight based on the initial weight in response to the possibility degree corresponding to the initial prediction result being less than a preset possibility degree.

[0105] Optionally, the determination submodule can determine the target weight based on the initial weight by performing the following steps: determining a first initial weight of a first detection device in the detection device and a second initial weight of a second detection device in the detection device, wherein the way in which the first detection device detects the transformer device is different from the way in which the second detection device detects the transformer device, and the initial weights include the first initial weight and the second initial weight; fusing the first initial weight into the second initial weight to obtain the target weight.

[0106] Optionally, the underground fire warning device 300 may also include: a first determination unit, used to determine the severity of a fire occurring underground in the transformer equipment at a future moment in response to the possibility level corresponding to the initial prediction result exceeding a preset possibility level; a second determination unit, used to determine a target warning signal and a target warning strategy corresponding to the severity level; and a first sending unit, used to send a target warning signal and a target warning strategy corresponding to the severity level to the client.

[0107] Optionally, the sending unit 303 may include: a second determination module, used to determine the severity of a fire occurring underground in the transformer equipment at a future moment in response to the degree of possibility corresponding to the prediction result exceeding a preset degree of possibility; a third determination module, used to determine a target warning signal and a target warning strategy corresponding to the severity; and a sending module, used to send a target warning signal and a target warning strategy corresponding to the severity to the client.

[0108] In this embodiment, an acquisition unit is used to obtain the detection strength of multiple detection devices located underground at different times, wherein the detection strength is used to represent the strength of the detection signal obtained by the detection device detecting the transformer device located underground at different times; a prediction unit is used to input the detection strength into a target prediction model for prediction to obtain a prediction result, wherein the target prediction model is used to represent the mapping relationship between the prediction result and the detection strength and the target weight of the detection device, and the prediction result is used to represent the possibility of a fire occurring underground in the transformer device at a future moment; a sending unit is used to send a target warning signal and a target warning strategy to a client in response to the possibility corresponding to the prediction result exceeding a preset possibility, wherein the target warning strategy is used to represent the rules for protecting the transformer device in response to a fire occurring underground in the transformer device at a future moment, thereby achieving the purpose of quickly and accurately issuing a fire alarm after a fire occurs, thereby solving the technical problem of low warning efficiency of underground fires, and further achieving the technical effect of improving the warning efficiency of underground fires.

[0109] According to an embodiment of the present invention, a processor is further provided, the processor being used to run a program, wherein the program, when run by the processor, executes the early warning method for underground fire in the embodiment.

[0110] According to an embodiment of the present invention, there is also provided an electronic device, comprising: a memory storing an executable program; and a processor for running the program, wherein the early warning method for underground fire in the embodiment is executed when the program is running.

[0111] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the underground fire early warning method in the embodiment.

[0112] According to an embodiment of the present invention, a computer program product is further provided. The computer program product includes a computer program. When the computer program is executed by a processor, the early warning method for underground fire in the embodiment is implemented.

[0113] According to an embodiment of the present invention, a computer program product is also provided, including a non-volatile computer-readable storage medium, the non-volatile computer-readable storage medium is used to store a computer program, and when the computer program is executed by a processor, the early warning method for underground fire in the embodiment is implemented.

[0114] According to an embodiment of the present invention, a computer program is also provided. When the computer program is executed by a processor, the early warning method for underground fire in the embodiment is implemented.

[0115] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0116] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0117] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0118] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed over multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0119] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0120] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the relevant technology or the whole or part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, referred to as Read-Only Memory), random access memory (RAM, referred to as Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0121] The above are only preferred embodiments of the present invention. It should be pointed out that, for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. An early warning method for underground fire, characterized in that: include: Acquire detection strengths of multiple detection devices located underground at different times, wherein the detection strengths are used to represent the strengths of detection signals obtained by the detection devices detecting the transformer devices located underground at the different times; The detection intensity is input into a target prediction model for prediction to obtain a prediction result, wherein the target prediction model is used to represent a mapping relationship between the prediction result and the detection intensity and the target weight of the detection device, and the prediction result is used to represent the possibility of a fire occurring in the underground of the transformer device at a future moment; In response to the possibility level corresponding to the prediction result exceeding the preset possibility level, a target warning signal and a target warning strategy are sent to the client, wherein the target warning strategy is used to represent the rules for protecting the transformer equipment in response to the fire occurring underground in the transformer equipment at the future moment.

2. The method according to claim 1, characterized in that The detection intensity is input into the target prediction model for prediction to obtain prediction results, including: determining a target weight of the detection device; The target weight and the detection strength are input into the target prediction model for prediction to obtain the prediction result.

3. The method according to claim 2, characterized in that Determining a target weight of the detection device includes: Inputting the detection score into an initial prediction model for prediction to obtain an initial prediction result, wherein the initial prediction model is used to represent a mapping relationship between the initial prediction result and the detection strength and the initial weight of the detection device; In response to the possibility level corresponding to the initial prediction result being less than the preset possibility level, the target weight is determined based on the initial weight.

4. The method according to claim 3, characterized in that Determining the target weight based on the initial weight includes: Determine a first initial weight of a first detection device among the detection devices and a second initial weight of a second detection device among the detection devices, wherein the first detection device detects the transformer device in a manner different from the second detection device detects the transformer device, and the initial weights include the first initial weight and the second initial weight; The first initial weight is fused to the second initial weight to obtain the target weight.

5. The method according to claim 3, characterized in that: The method further comprises: In response to the possibility level corresponding to the initial prediction result exceeding the preset possibility level, determining the severity of the fire occurring in the underground of the transformer equipment at the future time; Determining the target warning signal and the target warning strategy corresponding to the severity; The target warning signal and the target warning strategy corresponding to the severity are sent to the client.

6. The method according to claim 1, characterized in that In response to the possibility degree corresponding to the prediction result exceeding a preset possibility degree, sending a target warning signal and a target warning strategy to the client, including: In response to the possibility level corresponding to the prediction result exceeding the preset possibility level, determining the severity of the fire occurring in the underground of the transformer equipment at the future moment; Determining the target warning signal and the target warning strategy corresponding to the severity; The target warning signal and the target warning strategy corresponding to the severity are sent to the client.

7. An underground fire warning device, characterized in that: include: An acquisition unit, used to acquire detection strengths of multiple detection devices located underground at different times, wherein the detection strengths are used to represent the strengths of detection signals obtained by the detection devices detecting the transformer devices located underground at the different times; A prediction unit, used for inputting the detection intensity into a target prediction model for prediction to obtain a prediction result, wherein the target prediction model is used to represent a mapping relationship between the prediction result and the detection intensity and the target weight of the detection device, and the prediction result is used to represent the possibility of a fire occurring in the underground of the transformer device at a future moment; A sending unit is used to send a target warning signal and a target warning strategy to a client in response to the possibility level corresponding to the prediction result exceeding a preset possibility level, wherein the target warning strategy is used to represent rules for protecting the transformer equipment in response to the fire occurring in the underground of the transformer equipment at the future moment.

8. A processor, characterized in that: The processor is used to run a program, wherein the program, when run by the processor, executes the underground fire early warning method according to any one of claims 1 to 6.

9. An electronic device, characterized in that: include: A memory storing an executable program; A processor is used to run the program, wherein the program, when running, executes the underground fire early warning method described in any one of claims 1 to 6.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored executable program, wherein when the executable program is run, the device where the storage medium is located is controlled to execute the underground fire early warning method according to any one of claims 1 to 6.

Images