Intelligent distribution line environment monitoring and fault handling system and method for forest fire prevention

Abstract

The invention discloses an intelligent distribution line environment monitoring and fault handling system and method for forest fire prevention, and relates to the technical field of forest fire monitoring. A detailed environment monitoring data set P is collected in real time, and the environment monitoring data set P is introduced into a forest fire prevention risk grading evaluation algorithm; according to the method, the forest fire analysis index Fr of the line area is accurately calculated, detailed analysis of forest fire risks of different areas is realized, the risk levels of the distribution line area are accurately divided, a clear level evaluation result Rz is generated, and a summarized emergency response index Asum of the whole line is formed through summarizing. Therefore, the overall evaluation state of the current distribution line can be dynamically generated. According to the process, the forest fire prevention response capability of the system in a complex environment is remarkably improved, potential forest fire risks can be found and processed more timely and more effectively, and the defects that inspection response is not flexible and dynamic environment changes cannot be effectively handled in a traditional method are overcome.

Description

Technical Field

[0001] The present invention relates to the technical field of wildfire monitoring, and in particular to an intelligent power distribution line environment monitoring and fault handling system and method for wildfire prevention. Background Art

[0002] Wildfires, as a natural disaster, have occurred frequently around the world in recent years, especially against the backdrop of climate change and global warming, the frequency and intensity of wildfires have increased significantly. Wildfires are often accompanied by extreme weather conditions such as high temperatures, dryness, and strong winds, which make originally safe areas such as forests and mountains flammable and dangerous. Due to the rapid spread and widespread destructiveness of wildfires, they not only threaten human life and property, but also cause serious damage to the ecological environment and infrastructure, especially key facilities such as distribution lines. When wildfires spread to the vicinity of distribution lines, it is very likely to cause power outages or line damage, and even further expand the scale of the fire.

[0003] In the traditional monitoring system, wildfire prevention mainly relies on fixed monitoring nodes, such as temperature, humidity and wind speed sensors, and static maintenance strategies based on regular inspections. This static monitoring and prevention method has multiple defects. First, it cannot make flexible adjustments based on real-time environmental changes, especially in areas where the weather changes rapidly, and the wildfire risk level may change at any time. Secondly, the allocation of monitoring resources lacks flexibility and cannot give priority to areas with high wildfire risks, which may result in high-risk areas not receiving enough attention and low-risk areas consuming unnecessary monitoring resources. Due to the lack of intelligent dynamic zoning and response strategies for wildfire risks, the prediction of fire risks is delayed, making it difficult to take effective preventive measures in a timely manner. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention provides an intelligent distribution line environment monitoring and fault handling system and method for wildfire prevention, which solves the problems mentioned in the background technology.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: an intelligent distribution line environment monitoring and fault handling method for wildfire prevention, comprising the following steps:

[0006] S1, collect environmental data through several sensors integrated and deployed on the distribution lines, and perform preprocessing and integration to form an environmental monitoring data set P;

[0007] S2, substituting the acquired environmental detection data set P into the wildfire prevention risk grading assessment algorithm in real time to calculate the wildfire analysis index Fr of the distribution line area;

[0008] S3. Compare the obtained wildfire analysis index Fr with the preset risk level assessment threshold TZ to obtain a level assessment result Rz of the wildfire risk level of the distribution line area, and mark the current distribution line area according to the level assessment result Rz;

[0009] S4, after marking the current distribution line area according to the grade evaluation result Rz, dynamically adjust the inspection strategy frequency and inspection priority mark Xj of the current distribution line area, and obtain the adjusted inspection frequency Fz of the current distribution line area;

[0010] S5. Associate the grade assessment result Rz, priority mark Xj and inspection frequency Fz to generate the forest fire prevention emergency response index Az for the current distribution line area, and summarize it to generate the summary emergency response index Asum of the entire line, and match it with the preset line summary assessment threshold HZ to obtain the overall assessment status of the current distribution line.

[0011] Preferably, said S1 includes S11 and S12;

[0012] S11, collecting environmental data through several sensors integrated and deployed in the distribution line, wherein the sensor type includes temperature sensor, humidity sensor, wind speed sensor and surface temperature sensor, obtaining the ambient temperature Ta, relative humidity RH, wind speed value WS and surface temperature Ts, and then calculating the surface temperature gradient Gt through the ambient temperature Ta and the surface temperature Ts, and calculating the air environment dryness coefficient AD through the relative humidity RH and the ambient temperature Ta, to form the environmental data;

[0013] S12. Preprocess the environmental data, including data filtering and missing value filling, wherein the environmental data is preprocessed by using a sliding average filter, and the environmental data is preprocessed by using a linear interpolation method to fill in missing values. The environmental data after the data filtering and missing value filling preprocessing are integrated to form an environmental monitoring data set P, wherein the environmental monitoring data set P is specifically P={Ta, RH, WS, Ts, Gt, AD}, and the environmental monitoring data set P is marked with a collection timestamp and stored in a cloud database.

[0014] Preferably, S2 includes S21 and S22;

[0015] S21, normalizing the environmental detection data set P acquired in real time, converting the data in the environmental detection data set P to a range of 0 to 1, specifically by calculating each data in the environmental detection data set P with the maximum and minimum values ​​in the historical data of the cloud database, obtaining the normalized environmental detection data set Pnorm = {Tanorm, RHnorm, WSnorm, Tsnorm, Gtnorm, ADnorm} after normalization, and then performing standardization conversion on the normalized environmental detection data set Pnorm, including using a zero mean unit variance standardization method to convert it into a distribution state with 0 as the mean and 1 as the standard deviation, to form a standardized environmental detection data set Pstd = {Tastd, RHstd, WSstd, Tsstd, Gtstd, ADstd};

[0016] Among them, in the normalized environment detection data set Pnorm, Tanorm represents the normalized ambient temperature, RHnorm represents the normalized relative humidity, WSnorm represents the normalized wind speed value, Tsnorm represents the normalized surface temperature, Gtnorm represents the normalized surface temperature gradient, and ADnorm represents the normalized air environment dryness coefficient;

[0017] In the standardized environmental detection data set Pstd, Tastd represents the standardized ambient temperature, RHstd represents the standardized relative humidity, WSstd represents the standardized wind speed value, Tsstd represents the standardized surface temperature, Gtstd represents the standardized surface temperature gradient, and ADstd represents the standardized air environment dryness coefficient.

[0018] Preferably, S22, establishing a wildfire prevention risk grading assessment algorithm based on a linear weighted model, substituting the standardized environmental detection data set Pstd into the wildfire prevention risk grading assessment algorithm, and calculating the wildfire analysis index Fr of the distribution line area;

[0019] The wildfire analysis index Fr is obtained by the following calculation formula:

[0020] Fr=f1*Tastd+f2*RHstd+f3*WSstd+f4*Tsstd+f5*Gtstd+f6*ADstd;

[0021] Wherein, f1, f2, f3, f4, f5 and f6 respectively represent the standardized ambient temperature Tastd, the standardized relative humidity RHstd, the standardized wind speed value WSstd, the standardized surface temperature Tsstd, the standardized surface temperature gradient Gtstd, and the preset weight value of the standardized air environment dryness coefficient ADstd;

[0022] Among them, f1+f2+f3+f4+f5+f6=1, and the specific value is set by the user.

[0023] Preferably, said S3 includes S31 and S32;

[0024] S31, comparing the obtained wildfire analysis index Fr with a preset risk level assessment threshold TZ, to obtain a level assessment result Rz of the wildfire risk level of the distribution line area;

[0025] The grade evaluation result Rz is obtained by the following comparison method:

[0026]

[0027] When the wildfire analysis index Fr is less than the risk level assessment threshold TZ, the level assessment result Rz of the first level is obtained, and at this time the level assessment result Rz=1;

[0028] When the wildfire analysis index Fr ≥ the risk level assessment threshold TZ, the second level assessment result Rz is obtained, and at this time the level assessment result Rz=2;

[0029] When the wildfire analysis index Fr≥twice the risk level assessment threshold TZ, the third level assessment result Rz is obtained, and at this time the level assessment result Rz=3.

[0030] Preferably, S32, marking the current distribution line area according to the level assessment result Rz, and the specific marking method is that when the level assessment result R=1, the risk status of the current distribution line area is marked as normal, the inspection frequency is not adjusted, and the priority mark Xj=1 of the priority of the current distribution line area is marked;

[0031] When the level assessment result Rz=2, the risk status of the current distribution line area is marked as abnormal, the preset inspection frequency is adjusted to twice the inspection frequency, and the priority mark Xj=2 for marking the priority of the current distribution line area;

[0032] When the level assessment result Rz=3, the risk status of the current distribution line area is marked as warning, the preset inspection frequency is adjusted to five times the inspection frequency, and relevant personnel are simultaneously prompted to go to the current distribution line area for inspection, and the priority mark Xj=5 of the current distribution line area is marked.

[0033] Preferably, the S4 includes S41;

[0034] S41, marking the current distribution line area according to the grade evaluation result Rz and the priority mark Xj, and then dynamically adjusting the inspection frequency F0 preset in the inspection strategy frequency of the current distribution line area;

[0035] When Rz=1, the preset inspection frequency F0 in the inspection strategy frequency of the current distribution line area is not adjusted, and the preset inspection strategy frequency is executed according to the inspection frequency F0;

[0036] When Rz=2, obtain the priority mark Xj=2, adjust the inspection frequency F0 preset in the inspection strategy frequency of the current distribution line area, and obtain the adjusted inspection frequency Fz, which is obtained by the calculation formula Fz=F0*Xj;

[0037] When Rz=3, the priority mark Xj=5 is obtained, and the inspection frequency F0 preset in the inspection strategy frequency of the current distribution line area is adjusted to obtain the adjusted inspection frequency Fz, which is obtained by the calculation formula Fz=F0*Xj.

[0038] Preferably, said S5 includes S51 and S52;

[0039] S51, associating the level assessment result Rz, the priority mark Xj and the inspection frequency Fz to generate a forest fire prevention emergency response index Az for the current distribution line area;

[0040] The preventive emergency response index Az is obtained by the following calculation formula:

[0041]

[0042] Wherein, a1, a2 and a3 represent the preset weight values ​​of the grade evaluation result Rz, the priority mark Xj and the inspection frequency Fz respectively, and a1+a2+a3=1, λ represents the normalization coefficient, which specifically maps the preventive emergency response index Az to the preset range.

[0043] Preferably, S52, summarize the emergency response index Az of the current distribution line, generate the summary emergency response index Asum of the entire line, and match it with the preset line summary evaluation threshold HZ to obtain the evaluation status of the entire current distribution line;

[0044] The summary emergency response index Asum is obtained by the following calculation formula:

[0045]

[0046] Where n represents the total number of distribution line partitions, z represents the distribution line of the zth area, Wz represents the preset weight value of the zth area, and 0<Wz≤1, and the specific value is set by the user;

[0047] The overall evaluation status of the current distribution line is obtained by the following matching method:

[0048] When the summary emergency response index Asum is less than the line summary assessment threshold HZ, the overall status of the current distribution line is obtained as a qualified state, and the overall current distribution line is marked as green, prompting relevant personnel that there is no abnormality;

[0049] When the summary emergency response index Asum ≥ the line summary assessment threshold HZ, the overall status of the current distribution line is obtained as unqualified, and the current distribution line is marked as yellow to prompt relevant personnel to pay attention;

[0050] When the summary emergency response index Asum ≥ twice the line summary assessment threshold HZ, the overall status of the current distribution line is obtained as a warning state, and the current distribution line is marked as red, prompting relevant personnel to eliminate abnormal situations, including using drone-related methods to eliminate the situation.

[0051] An intelligent power distribution line environment monitoring and fault handling system for wildfire prevention, comprising a data acquisition module, a wildfire prevention classification module, a marking module, a priority assessment module and an overall feedback module;

[0052] The data acquisition module collects environmental data through several sensors integrated and deployed in the power distribution line, and performs preprocessing and integration to form an environmental monitoring data set P;

[0053] The wildfire prevention classification module substitutes the environmental detection data set P into the wildfire prevention risk classification assessment algorithm to calculate the wildfire analysis index Fr of the distribution line area;

[0054] The marking module compares the obtained wildfire analysis index Fr with a preset risk level assessment threshold TZ to obtain a level assessment result Rz of the wildfire risk level of the distribution line area, and marks the current distribution line area according to the level assessment result Rz;

[0055] The priority evaluation module marks the current distribution line area according to the level evaluation result Rz, and then dynamically adjusts the inspection strategy frequency and inspection priority priority mark Xj of the current distribution line area to obtain the adjusted inspection frequency Fz of the current distribution line area;

[0056] The overall feedback module associates the grade assessment result Rz, priority mark Xj and inspection frequency Fz to generate the forest fire prevention emergency response index Az for the current distribution line area, and summarizes it to generate the overall line summary emergency response index Asum, and matches it with the preset line summary assessment threshold HZ to obtain the overall assessment status of the current distribution line.

[0057] The present invention provides an intelligent power distribution line environment monitoring and fault handling system and method for wildfire prevention, which has the following beneficial effects:

[0058] (1) By collecting detailed environmental monitoring data sets P in real time and introducing the environmental monitoring data sets P into the wildfire prevention risk grading assessment algorithm, the wildfire analysis index Fr of the line area is accurately calculated, and the detailed analysis of wildfire risks in different areas is realized. The risk level of the distribution line area is accurately divided, and a clear grade assessment result Rz is generated. The high-risk areas are marked, providing a basis for the priority treatment of high-risk areas. The grade assessment results Rz, priority marks Xj and inspection frequency Fz of each area are associated to generate the prevention emergency response index Az of each area, and the summary emergency response index Asum of the entire line is summarized. In this way, the overall assessment status of the current distribution line can be dynamically generated. This process significantly improves the wildfire prevention response capability of the system in complex environments, and can discover and deal with potential wildfire risks more timely and effectively, overcoming the shortcomings of the traditional method of inflexible inspection response and inability to effectively respond to dynamic environmental changes.

[0059] (2) By comparing the wildfire analysis index Fr with the risk level assessment threshold TZ, the system can quickly and accurately generate the level assessment result Rz, achieving accurate assessment under different risk levels. The risk status of the distribution line area is intelligently marked, which not only clarifies the risk level, but also accurately allocates inspection resources by adjusting the priority mark Xj, thereby achieving reasonable allocation of resources and improving the real-time monitoring of high-risk areas. This method effectively reduces the waste of resources under the traditional fixed inspection cycle through intelligent inspection frequency adjustment and risk classification management, and ensures priority response in high-risk areas, thereby greatly improving the accuracy and efficiency of wildfire prevention.

[0060] (3) By weighting the evaluation result Rz, priority mark Xj, and inspection frequency Fz, the preventive emergency response index Az for each area is generated and summarized into the summary emergency response index Asum. By comparing it with the line summary evaluation threshold HZ, the risk status of the entire line can be quickly judged. This hierarchical evaluation mechanism effectively avoids the problems of fuzzy risk status assessment and inability to respond in a timely manner in traditional methods, ensuring that risks from local areas to the entire line can be accurately and dynamically monitored, thereby significantly improving the system's emergency handling capabilities and the execution efficiency of prevention strategies. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Figure 1 A schematic diagram of the steps of an intelligent power distribution line environment monitoring and fault handling method for wildfire prevention according to the present invention;

[0062] Figure 2 The present invention is a schematic diagram of a block diagram of an intelligent power distribution line environment monitoring and fault handling system for wildfire prevention. DETAILED DESCRIPTION

[0063] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0064] Example 1

[0065] The present invention provides an intelligent power distribution line environment monitoring and fault handling method for wildfire prevention. Figure 1 , including the following steps:

[0066] S1, collect environmental data through several sensors integrated and deployed on the distribution lines, and perform preprocessing and integration to form an environmental monitoring data set P;

[0067] S2, substituting the acquired environmental detection data set P into the wildfire prevention risk grading assessment algorithm in real time to calculate the wildfire analysis index Fr of the distribution line area;

[0068] S3. Compare the obtained wildfire analysis index Fr with the preset risk level assessment threshold TZ to obtain a level assessment result Rz of the wildfire risk level of the distribution line area, and mark the current distribution line area according to the level assessment result Rz;

[0069] S4, after marking the current distribution line area according to the grade evaluation result Rz, dynamically adjust the inspection strategy frequency and inspection priority mark Xj of the current distribution line area, and obtain the adjusted inspection frequency Fz of the current distribution line area;

[0070] S5. Associate the grade assessment result Rz, priority mark Xj and inspection frequency Fz to generate the forest fire prevention emergency response index Az for the current distribution line area, and summarize it to generate the summary emergency response index Asum of the entire line, and match it with the preset line summary assessment threshold HZ to obtain the overall assessment status of the current distribution line.

[0071] In this embodiment, through the integrated deployment of multiple sensors in step S1, key environmental data is collected in real time and preprocessed and integrated, ensuring the comprehensiveness and accuracy of the data, and forming a detailed environmental monitoring data set P. Then, through S2, the environmental monitoring data set P is introduced into the wildfire prevention risk grading assessment algorithm, and the wildfire analysis index Fr of the line area is accurately calculated, realizing the detailed analysis of wildfire risks in different areas. The following S3 compares the wildfire analysis index Fr with the preset risk level assessment threshold TZ, accurately divides the risk level of the distribution line area, generates a clear level assessment result Rz, and marks the high-risk area, providing a basis for the priority treatment of high-risk areas. On this basis, S4 can intelligently optimize the allocation of inspection resources through the dynamic adjustment of the level assessment result Rz, priority mark Xj and inspection frequency Fz, and further improve the overall prevention and emergency response efficiency of the line. Through S5, the system associates the level assessment results Rz, priority mark Xj and inspection frequency Fz of each area, generates the prevention emergency response index Az for each area, and summarizes the summary emergency response index Asum of the overall line. The index is matched with the preset line summary assessment threshold HZ, so that the overall assessment status of the current distribution line can be dynamically generated. This process significantly improves the system's wildfire prevention and response capabilities in complex environments, and can more timely and effectively discover and deal with potential wildfire risks, overcoming the shortcomings of traditional methods in terms of inflexible inspection response and inability to effectively respond to dynamic environmental changes.

[0072] Example 2

[0073] This embodiment is explained in Example 1, please refer to Figure 1 , specifically: the S1 includes S11 and S12;

[0074] S11, collecting environmental data through several sensors integrated and deployed in the distribution line, wherein the sensor type includes temperature sensor, humidity sensor, wind speed sensor and surface temperature sensor, obtaining the ambient temperature Ta, relative humidity RH, wind speed value WS and surface temperature Ts, and then calculating the surface temperature gradient Gt through the ambient temperature Ta and the surface temperature Ts, and calculating the air environment dryness coefficient AD through the relative humidity RH and the ambient temperature Ta, to form the environmental data;

[0075] S12. Preprocess the environmental data, including data filtering and missing value filling, wherein the environmental data is preprocessed by using a sliding average filter, and the environmental data is preprocessed by using a linear interpolation method to fill in missing values. The environmental data after the data filtering and missing value filling preprocessing are integrated to form an environmental monitoring data set P, wherein the environmental monitoring data set P is specifically P={Ta, RH, WS, Ts, Gt, AD}, and the environmental monitoring data set P is marked with a collection timestamp and stored in a cloud database.

[0076] The S2 includes S21 and S22;

[0077] S21, normalizing the environmental detection data set P acquired in real time, converting the data in the environmental detection data set P to a range of 0 to 1, specifically by calculating each data in the environmental detection data set P with the maximum and minimum values ​​in the historical data of the cloud database, obtaining the normalized environmental detection data set Pnorm = {Tanorm, RHnorm, WSnorm, Tsnorm, Gtnorm, ADnorm} after normalization, and then performing standardization conversion on the normalized environmental detection data set Pnorm, including using a zero mean unit variance standardization method to convert it into a distribution state with 0 as the mean and 1 as the standard deviation, to form a standardized environmental detection data set Pstd = {Tastd, RHstd, WSstd, Tsstd, Gtstd, ADstd};

[0078] Among them, in the normalized environment detection data set Pnorm, Tanorm represents the normalized ambient temperature, RHnorm represents the normalized relative humidity, WSnorm represents the normalized wind speed value, Tsnorm represents the normalized surface temperature, Gtnorm represents the normalized surface temperature gradient, and ADnorm represents the normalized air environment dryness coefficient;

[0079] In the standardized environmental detection data set Pstd, Tastd represents the standardized ambient temperature, RHstd represents the standardized relative humidity, WSstd represents the standardized wind speed value, Tsstd represents the standardized surface temperature, Gtstd represents the standardized surface temperature gradient, and ADstd represents the standardized air environment dryness coefficient.

[0080] S22, establishing a wildfire prevention risk grading assessment algorithm based on a linear weighted model, substituting the standardized environmental detection data set Pstd into the wildfire prevention risk grading assessment algorithm, and calculating the wildfire analysis index Fr of the distribution line area;

[0081] The wildfire analysis index Fr is obtained by the following calculation formula:

[0082] Fr=f1*Tastd+f2*RHstd+f3*WSstd+f4*Tsstd+f5*Gtstd+f6*ADstd;

[0083] Wherein, f1, f2, f3, f4, f5 and f6 respectively represent the standardized ambient temperature Tastd, the standardized relative humidity RHstd, the standardized wind speed value WSstd, the standardized surface temperature Tsstd, the standardized surface temperature gradient Gtstd, and the preset weight value of the standardized air environment dryness coefficient ADstd;

[0084] Among them, f1+f2+f3+f4+f5+f6=1, and the specific value is set by the user.

[0085] In this embodiment, a detailed environmental data set P is obtained through multi-type sensor collection of S11 and S12, such as temperature sensor, humidity sensor and wind speed sensor, and the environmental data is preprocessed by sliding average filtering and linear interpolation to ensure the integrity and accuracy of the data. On this basis, S21 normalizes and standardizes the environmental monitoring data set P, so that the dimensions of the data are consistent during the analysis process, reducing the deviation of different parameters on the analysis results, and further optimizing the accuracy of risk assessment. Through the linear weighted model established in S22, the standardized environmental detection data set Pstd is substituted into the wildfire prevention risk grading assessment algorithm to generate the wildfire analysis index Fr. This method effectively combines historical data with real-time acquisition data, and calculates the influence of each environmental parameter through preset weight values, providing a flexible and adjustable risk assessment framework. This dynamic data normalization and standardization processing mechanism enables the system to quickly adapt to environmental changes and customize adjustments according to different user needs, significantly improving the flexibility and prediction accuracy of wildfire prevention strategies, ensuring that the system can be intelligently adjusted under changing environmental conditions, and reducing the blind spots of potential wildfires.

[0086] Example 3

[0087] This embodiment is explained in Example 1, please refer to Figure 1 , specifically: S3 includes S31 and S32;

[0088] S31, comparing the obtained wildfire analysis index Fr with a preset risk level assessment threshold TZ, to obtain a level assessment result Rz of the wildfire risk level of the distribution line area;

[0089] The grade evaluation result Rz is obtained by the following comparison method:

[0090]

[0091] When the wildfire analysis index Fr is less than the risk level assessment threshold TZ, the level assessment result Rz of the first level is obtained, and at this time the level assessment result Rz=1;

[0092] When the wildfire analysis index Fr ≥ the risk level assessment threshold TZ, the second level assessment result Rz is obtained, and at this time the level assessment result Rz=2;

[0093] When the wildfire analysis index Fr≥twice the risk level assessment threshold TZ, the third level assessment result Rz is obtained, and at this time the level assessment result Rz=3.

[0094] S32, marking the current distribution line area according to the level assessment result Rz, and the specific marking method is that when the level assessment result R=1, the risk status of the current distribution line area is marked as normal, the inspection frequency is not adjusted, and the priority mark Xj of the current distribution line area is marked as 1;

[0095] When the level assessment result Rz=2, the risk status of the current distribution line area is marked as abnormal, the preset inspection frequency is adjusted to twice the inspection frequency, and the priority mark Xj=2 for marking the priority of the current distribution line area;

[0096] When the level assessment result Rz=3, the risk status of the current distribution line area is marked as warning, the preset inspection frequency is adjusted to five times the inspection frequency, and relevant personnel are simultaneously prompted to go to the current distribution line area for inspection, and the priority mark Xj=5 of the current distribution line area is marked.

[0097] The S4 includes S41;

[0098] S41, marking the current distribution line area according to the grade evaluation result Rz and the priority mark Xj, and then dynamically adjusting the inspection frequency F0 preset in the inspection strategy frequency of the current distribution line area;

[0099] When Rz=1, the preset inspection frequency F0 in the inspection strategy frequency of the current distribution line area is not adjusted, and the preset inspection strategy frequency is executed according to the inspection frequency F0;

[0100] When Rz=2, obtain the priority mark Xj=2, adjust the inspection frequency F0 preset in the inspection strategy frequency of the current distribution line area, and obtain the adjusted inspection frequency Fz, which is obtained by the calculation formula Fz=F0*Xj;

[0101] When Rz=3, the priority mark Xj=5 is obtained, and the inspection frequency F0 preset in the inspection strategy frequency of the current distribution line area is adjusted to obtain the adjusted inspection frequency Fz, which is obtained by the calculation formula Fz=F0*Xj.

[0102] In this implementation, by comparing the wildfire analysis index Fr with the risk level assessment threshold TZ, the system can quickly and accurately generate the level assessment result Rz, and divide it into three levels, thus achieving accurate assessment under different risk levels. Then, S32 further intelligently marks the risk status of the distribution line area according to the level assessment result Rz, not only clarifies the risk level, but also accurately allocates the inspection resources by adjusting the priority mark Xj, thereby achieving reasonable allocation of resources. On this basis, S41 provides a dynamic inspection frequency adjustment strategy for different risk levels. According to the level assessment result Rz and the priority mark Xj, the system automatically and flexibly adjusts the preset inspection frequency F0 to ensure that the inspection frequency is increased to five times the normal frequency under a higher risk state, greatly shortening the inspection cycle, thereby enhancing the real-time monitoring of high-risk areas. This method effectively reduces the waste of resources under the traditional fixed inspection cycle through intelligent inspection frequency adjustment and risk classification management, and ensures priority response in high-risk areas, thereby greatly improving the accuracy and efficiency of wildfire prevention.

[0103] Example 4

[0104] This embodiment is explained in Example 1, please refer to Figure 1 , specifically: the S5 includes S51 and S52;

[0105] S51, associating the level assessment result Rz, the priority mark Xj and the inspection frequency Fz to generate a forest fire prevention emergency response index Az for the current distribution line area;

[0106] The preventive emergency response index Az is obtained by the following calculation formula:

[0107]

[0108] Wherein, a1, a2 and a3 represent the preset weight values ​​of the grade evaluation result Rz, the priority mark Xj and the inspection frequency Fz respectively, and a1+a2+a3=1, λ represents the normalization coefficient, which specifically maps the preventive emergency response index Az to the preset range.

[0109] S52, summarizing the emergency response index Az of the current distribution line, generating the summary emergency response index Asum of the entire line, and matching it with the preset line summary evaluation threshold HZ to obtain the evaluation status of the entire current distribution line;

[0110] The summary emergency response index Asum is obtained by the following calculation formula:

[0111]

[0112] Where n represents the total number of distribution line partitions, z represents the distribution line of the zth area, Wz represents the preset weight value of the zth area, and 0<Wz≤1, and the specific value is set by the user;

[0113] The overall evaluation status of the current distribution line is obtained by the following matching method:

[0114] When the summary emergency response index Asum is less than the line summary assessment threshold HZ, the overall status of the current distribution line is obtained as a qualified state, and the overall current distribution line is marked as green, prompting relevant personnel that there is no abnormality;

[0115] When the summary emergency response index Asum ≥ the line summary assessment threshold HZ, the overall status of the current distribution line is obtained as unqualified, and the current distribution line is marked as yellow to prompt relevant personnel to pay attention;

[0116] When the summary emergency response index Asum ≥ twice the line summary assessment threshold HZ, the overall status of the current distribution line is obtained as a warning state, and the current distribution line is marked as red, prompting relevant personnel to eliminate abnormal situations, including using drone-related methods to eliminate the situation.

[0117] In this embodiment, by weighted association of the level assessment result Rz, the priority mark Xj and the inspection frequency Fz, the preventive emergency response index Az of each area is generated. The index not only comprehensively considers the risk level, inspection priority and frequency of each area, but also maps it to a controllable range through the standardization coefficient, thereby ensuring the uniformity and comparability of the index. Then, S52 summarizes the preventive emergency response index Az of each area into a summary emergency response index Asum, and compares it with the line summary assessment threshold HZ to quickly judge the risk status of the entire line. The biggest advantage of this method is that through the hierarchical management of the summary emergency response index Asum, it can provide accurate risk warnings for the entire line in real time and dynamically. When the summary emergency response index Asum is lower than the line summary assessment threshold HZ, the system automatically marks the line as qualified and prompts the relevant personnel that there is no abnormality; when the index exceeds the threshold, the system promptly issues an early warning, marks the line as yellow or red, and further prompts the relevant personnel to take necessary emergency measures in a high-risk state, such as eliminating abnormalities through drone inspections. This hierarchical assessment mechanism effectively avoids the problems of vague risk status assessment and inability to respond in a timely manner in traditional methods, ensuring that risks from local areas to overall lines can be accurately and dynamically monitored, thereby significantly improving the system's emergency response capabilities and the efficiency of implementing prevention strategies.

[0118] Example 5

[0119] An intelligent power distribution line environment monitoring and fault handling system for wildfire prevention, please refer to Figure 2 ,Specifically: including data collection module, wildfire prevention classification module, marking module, priority assessment module and overall feedback module;

[0120] The data acquisition module collects environmental data through several sensors integrated and deployed in the power distribution line, and performs preprocessing and integration to form an environmental monitoring data set P;

[0121] The wildfire prevention classification module substitutes the environmental detection data set P into the wildfire prevention risk classification assessment algorithm to calculate the wildfire analysis index Fr of the distribution line area;

[0122] The marking module compares the obtained wildfire analysis index Fr with a preset risk level assessment threshold TZ to obtain a level assessment result Rz of the wildfire risk level of the distribution line area, and marks the current distribution line area according to the level assessment result Rz;

[0123] The priority evaluation module marks the current distribution line area according to the level evaluation result Rz, and then dynamically adjusts the inspection strategy frequency and inspection priority priority mark Xj of the current distribution line area to obtain the adjusted inspection frequency Fz of the current distribution line area;

[0124] The overall feedback module associates the grade assessment result Rz, priority mark Xj and inspection frequency Fz to generate the forest fire prevention emergency response index Az for the current distribution line area, and summarizes it to generate the overall line summary emergency response index Asum, and matches it with the preset line summary assessment threshold HZ to obtain the overall assessment status of the current distribution line.

[0125] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent power distribution line environment monitoring and fault handling method for wildfire prevention, characterized in that: The following steps are involved: S1, collect environmental data through several sensors integrated and deployed on the distribution lines, and perform preprocessing and integration to form an environmental monitoring data set P; S2, substituting the acquired environmental detection data set P into the wildfire prevention risk grading assessment algorithm in real time to calculate the wildfire analysis index Fr of the distribution line area; S3. Compare the obtained wildfire analysis index Fr with the preset risk level assessment threshold TZ to obtain a level assessment result Rz of the wildfire risk level of the distribution line area, and mark the current distribution line area according to the level assessment result Rz; S4, after marking the current distribution line area according to the grade evaluation result Rz, dynamically adjust the inspection strategy frequency and inspection priority mark Xj of the current distribution line area, and obtain the adjusted inspection frequency Fz of the current distribution line area; S5. Associate the grade assessment result Rz, priority mark Xj and inspection frequency Fz to generate the forest fire prevention emergency response index Az for the current distribution line area, and summarize it to generate the summary emergency response index Asum of the entire line, and match it with the preset line summary assessment threshold HZ to obtain the overall assessment status of the current distribution line.

2. According to claim 1, a smart power distribution line environment monitoring and fault handling method for forest fire prevention is characterized in that: Said S1 includes S11 and S12; S11, collecting environmental data through several sensors integrated and deployed in the distribution line, wherein the sensor type includes temperature sensor, humidity sensor, wind speed sensor and surface temperature sensor, obtaining the ambient temperature Ta, relative humidity RH, wind speed value WS and surface temperature Ts, and then calculating the surface temperature gradient Gt through the ambient temperature Ta and the surface temperature Ts, and calculating the air environment dryness coefficient AD through the relative humidity RH and the ambient temperature Ta, to form the environmental data; S12. Preprocess the environmental data, including data filtering and missing value filling, wherein the environmental data is preprocessed by using a sliding average filter, and the environmental data is preprocessed by using a linear interpolation method to fill in missing values. The environmental data after the data filtering and missing value filling preprocessing are integrated to form an environmental monitoring data set P, wherein the environmental monitoring data set P is specifically P={Ta, RH, WS, Ts, Gt, AD}, and the environmental monitoring data set P is marked with a collection timestamp and stored in a cloud database.

3. The intelligent power distribution line environment monitoring and fault handling method for forest fire prevention according to claim 2 is characterized in that: The S2 includes S21 and S22; S21, normalizing the environmental detection data set P acquired in real time, converting the data in the environmental detection data set P to a range of 0 to 1, specifically by calculating each data in the environmental detection data set P with the maximum and minimum values ​​in the historical data of the cloud database, obtaining the normalized environmental detection data set Pnorm = {Tanorm, RHnorm, WSnorm, Tsnorm, Gtnorm, ADnorm} after normalization, and then performing standardization conversion on the normalized environmental detection data set Pnorm, including using a zero mean unit variance standardization method to convert it into a distribution state with 0 as the mean and 1 as the standard deviation, to form a standardized environmental detection data set Pstd = {Tastd, RHstd, WSstd, Tsstd, Gtstd, ADstd}; Among them, in the normalized environment detection data set Pnorm, Tanorm represents the normalized ambient temperature, RHnorm represents the normalized relative humidity, WSnorm represents the normalized wind speed value, Tsnorm represents the normalized surface temperature, Gtnorm represents the normalized surface temperature gradient, and ADnorm represents the normalized air environment dryness coefficient; In the standardized environmental detection data set Pstd, Tastd represents the standardized ambient temperature, RHstd represents the standardized relative humidity, WSstd represents the standardized wind speed value, Tsstd represents the standardized surface temperature, Gtstd represents the standardized surface temperature gradient, and ADstd represents the standardized air environment dryness coefficient.

4. The intelligent power distribution line environment monitoring and fault handling method for forest fire prevention according to claim 3 is characterized in that: S22, establishing a wildfire prevention risk grading assessment algorithm based on a linear weighted model, substituting the standardized environmental detection data set Pstd into the wildfire prevention risk grading assessment algorithm, and calculating the wildfire analysis index Fr of the distribution line area; The wildfire analysis index Fr is obtained by the following calculation formula: Fr=f1*Tastd+f2*RHstd+f3*WSstd+f4*Tsstd+f5*Gtstd+f6*ADstd; Wherein, f1, f2, f3, f4, f5 and f6 respectively represent the standardized ambient temperature Tastd, the standardized relative humidity RHstd, the standardized wind speed value WSstd, the standardized surface temperature Tsstd, the standardized surface temperature gradient Gtstd, and the preset weight value of the standardized air environment dryness coefficient ADstd; Among them, f1+f2+f3+f4+f5+f6=1, and the specific value is set by the user.

5. The intelligent power distribution line environment monitoring and fault handling method for forest fire prevention according to claim 4 is characterized in that: The S3 includes S31 and S32; S31, comparing the obtained wildfire analysis index Fr with a preset risk level assessment threshold TZ, to obtain a level assessment result Rz of the wildfire risk level of the distribution line area; The grade evaluation result Rz is obtained by the following comparison method: When the wildfire analysis index Fr is less than the risk level assessment threshold TZ, the level assessment result Rz of the first level is obtained, and at this time the level assessment result Rz=1; When the wildfire analysis index Fr ≥ the risk level assessment threshold TZ, the second level assessment result Rz is obtained, and at this time the level assessment result Rz=2; When the wildfire analysis index Fr≥twice the risk level assessment threshold TZ, the third level assessment result Rz is obtained, and at this time the level assessment result Rz=3.

6. The intelligent power distribution line environment monitoring and fault handling method for forest fire prevention according to claim 5 is characterized in that: S32, marking the current distribution line area according to the level assessment result Rz, and the specific marking method is that when the level assessment result R=1, the risk status of the current distribution line area is marked as normal, the inspection frequency is not adjusted, and the priority mark Xj of the current distribution line area is marked as 1; When the level assessment result Rz=2, the risk status of the current distribution line area is marked as abnormal, the preset inspection frequency is adjusted to twice the inspection frequency, and the priority mark Xj=2 for marking the priority of the current distribution line area; When the level assessment result Rz=3, the risk status of the current distribution line area is marked as warning, the preset inspection frequency is adjusted to five times the inspection frequency, and relevant personnel are simultaneously prompted to go to the current distribution line area for inspection, and the priority mark Xj=5 of the current distribution line area is marked.

7. The intelligent power distribution line environment monitoring and fault handling method for forest fire prevention according to claim 1, characterized in that: The S4 includes S41; S41, marking the current distribution line area according to the grade evaluation result Rz and the priority mark Xj, and then dynamically adjusting the inspection frequency F0 preset in the inspection strategy frequency of the current distribution line area; When Rz=1, the preset inspection frequency F0 in the inspection strategy frequency of the current distribution line area is not adjusted, and the preset inspection strategy frequency is executed according to the inspection frequency F0; When Rz=2, obtain the priority mark Xj=2, adjust the inspection frequency F0 preset in the inspection strategy frequency of the current distribution line area, and obtain the adjusted inspection frequency Fz, which is obtained by the calculation formula Fz=F0*Xj; When Rz=3, the priority mark Xj=5 is obtained, and the inspection frequency F0 preset in the inspection strategy frequency of the current distribution line area is adjusted to obtain the adjusted inspection frequency Fz, which is obtained by the calculation formula Fz=F0*Xj.

8. The intelligent power distribution line environment monitoring and fault handling method for forest fire prevention according to claim 7 is characterized in that: The S5 includes S51 and S52; S51, associating the level assessment result Rz, the priority mark Xj and the inspection frequency Fz to generate a forest fire prevention emergency response index Az for the current distribution line area; The preventive emergency response index Az is obtained by the following calculation formula: Wherein, a1, a2 and a3 represent the preset weight values ​​of the grade evaluation result Rz, the priority mark Xj and the inspection frequency Fz respectively, and a1+a2+a3=1, λ represents the normalization coefficient, which specifically maps the preventive emergency response index Az to the preset range.

9. The intelligent power distribution line environment monitoring and fault handling method for wildfire prevention according to claim 1, characterized in that: S52, summarizing the emergency response index Az of the current distribution line, generating the summary emergency response index Asum of the entire line, and matching it with the preset line summary evaluation threshold HZ to obtain the evaluation status of the entire current distribution line; The summary emergency response index Asum is obtained by the following calculation formula: Where n represents the total number of distribution line partitions, z represents the distribution line of the zth area, Wz represents the preset weight value of the zth area, and 0<Wz≤1, and the specific value is set by the user; The overall evaluation status of the current distribution line is obtained by the following matching method: When the summary emergency response index Asum is less than the line summary assessment threshold HZ, the overall status of the current distribution line is obtained as a qualified state, and the overall current distribution line is marked as green, prompting relevant personnel that there is no abnormality; When the summary emergency response index Asum ≥ the line summary assessment threshold HZ, the overall status of the current distribution line is obtained as unqualified, and the current distribution line is marked as yellow to prompt relevant personnel to pay attention; When the summary emergency response index Asum ≥ twice the line summary assessment threshold HZ, the overall status of the current distribution line is obtained as a warning state, and the current distribution line is marked as red, prompting relevant personnel to eliminate abnormal situations, including using drone-related methods to eliminate the situation.

10. An intelligent power distribution line environment monitoring and fault handling system for wildfire prevention, applied to an intelligent power distribution line environment monitoring and fault handling method for wildfire prevention as claimed in any one of claims 1 to 9, characterized in that: It includes data collection module, wildfire prevention classification module, marking module, priority assessment module and overall feedback module; The data acquisition module collects environmental data through several sensors integrated and deployed in the power distribution line, and performs preprocessing and integration to form an environmental monitoring data set P; The wildfire prevention classification module substitutes the environmental detection data set P into the wildfire prevention risk classification assessment algorithm to calculate the wildfire analysis index Fr of the distribution line area; The marking module compares the obtained wildfire analysis index Fr with a preset risk level assessment threshold TZ to obtain a level assessment result Rz of the wildfire risk level of the distribution line area, and marks the current distribution line area according to the level assessment result Rz; The priority evaluation module marks the current distribution line area according to the level evaluation result Rz, and then dynamically adjusts the inspection strategy frequency and inspection priority priority mark Xj of the current distribution line area to obtain the adjusted inspection frequency Fz of the current distribution line area; The overall feedback module associates the grade assessment result Rz, priority mark Xj and inspection frequency Fz to generate the forest fire prevention emergency response index Az for the current distribution line area, and summarizes it to generate the overall line summary emergency response index Asum, and matches it with the preset line summary assessment threshold HZ to obtain the overall assessment status of the current distribution line.

Images