Fire early warning system and method for photovoltaic power station

Abstract

The invention discloses a fire early warning system and method for a photovoltaic power station, relates to the technical field of photovoltaic power generation, and solves the problem that abnormal temperature rise is possibly caused by a hot spot effect and line aging during long-term operation of a photovoltaic panel; therefore, the technical problems of low anomaly detection efficiency and low early warning timeliness of the photovoltaic panel caused by difficulty in timely detection and early warning of the photovoltaic panel with a large anomaly degree can be solved. Comprising the steps of obtaining a thermal imaging image of a photovoltaic panel; performing image analysis based on the thermal imaging image to obtain a corresponding photovoltaic panel abnormal area; obtaining structure data of the photovoltaic panel, and generating an abnormal score based on the abnormal region and the structure data; sorting the detection lines based on the abnormal scores, sequentially obtaining the detection data of the detection lines based on the sorting sequence, and obtaining the danger detection levels of the detection lines based on the analysis of the detection data; an alarm signal is generated based on the hazard detection level. The early warning time is greatly reduced, and the overall efficiency is improved.

Description

Technical Field

[0001] The present application belongs to the field of photovoltaic power generation technology, and specifically relates to a fire warning system and method for a photovoltaic power station. Background Art

[0002] A photovoltaic power station refers to a power generation system that utilizes solar energy, uses special materials such as crystalline silicon panels, inverters and other electronic components, is connected to the power grid and transmits electricity to the grid.

[0003] The prior art (CN118826633A) discloses a photovoltaic power station fault warning system, including: an environmental data monitoring module for monitoring and obtaining solar radiation intensity and temperature data and retrieving the attenuation coefficient; an ideal power generation module for calculating the ideal power generation; a regional label adding module for monitoring and obtaining the actual power generation of each photovoltaic sub-region, comparing the actual power generation with the ideal power generation, and adding a label to each photovoltaic sub-region; a warning region determination module for counting and analyzing the labels of the photovoltaic sub-region nearly N times, determining the warning sub-region and the corresponding hovering coordinates; an actual image acquisition module for obtaining the actual image of the sub-region; and a warning information generation module for overlapping and locating the actual image of the sub-region and the corresponding standard image of the sub-region, determining a number of photovoltaic panel groups, and analyzing the photovoltaic panel groups. In this way, the warning information and the fault location can be accurately determined.

[0004] The above-mentioned photovoltaic power station fault warning system obtains the solar radiation intensity and temperature data of the photovoltaic power generation area by monitoring, and calculates the ideal power generation power; at the same time, it monitors the actual power generation power, compares the actual power generation power with the ideal power generation power, and determines the warning sub-area and the corresponding hovering coordinates; according to the hovering coordinates, the drone reaches the hovering position to collect images and obtain the actual image of the sub-area; after retrieving the standard image of the sub-area and performing image processing, the actual image of the sub-area and the corresponding standard image of the sub-area are overlapped and positioned, so as to accurately determine the warning information; however, in actual applications, photovoltaic panels may cause abnormal heating due to hot spot effects, line aging and other problems during long-term operation. It is difficult to detect and warn photovoltaic panels with a large degree of abnormality in a timely manner, and a fire may occur in severe cases, which leads to low abnormality detection efficiency of photovoltaic panels and low timeliness of warning. Summary of the Invention

[0005] The present application aims to solve at least one of the technical problems existing in the prior art; to this end, the present application proposes a fire warning system and method for a photovoltaic power station, which is used to solve the problem that photovoltaic panels may heat up abnormally due to problems such as hot spot effect and line aging during long-term operation; as a result, it will be difficult to detect and warn photovoltaic panels with a large degree of abnormality in a timely manner, and in severe cases, a fire may occur, which will lead to the technical problem of low efficiency in abnormal detection of photovoltaic panels and low timeliness of warning.

[0006] To achieve the above objectives, the first aspect of the present application provides a fire early warning method for a photovoltaic power station, comprising: Acquire thermal imaging images of the photovoltaic panel; perform image analysis based on the thermal imaging images to obtain the corresponding abnormal areas of the photovoltaic panel; Acquiring structural data of the photovoltaic panel, and generating an abnormality score indicating the degree of abnormality of the photovoltaic panel based on the abnormal region and the structural data; The detection lines are sorted based on the abnormality scores, the detection data of the detection lines are sequentially acquired based on the sorting order, and the danger detection level of the detection lines is obtained based on the detection data analysis; and an alarm signal is generated based on the danger detection level.

[0007] Preferably, performing image analysis based on the thermal imaging image to obtain the abnormal area of ​​the photovoltaic panel includes: Obtain a thermal imaging image, input the thermal imaging image into the image segmentation model to obtain a cell image and cell number, obtain the average pixel value of each pixel in the cell image, and query the corresponding imaging temperature based on the average value; Determine whether the imaging temperature is greater than a set temperature threshold, and if so, mark the cell as an abnormal cell; if not, mark the cell as a normal cell; The areas where each continuous abnormal cell is located are obtained in sequence and marked as abnormal areas of the photovoltaic panel.

[0008] Preferably, the temperature threshold is obtained by: S1: Obtaining the imaging temperature of each cell of the photovoltaic panel; S2: round up all imaging temperatures and obtain the mode of the rounded imaging temperatures; S3: Determine whether the mode is less than the maximum temperature value set for the photovoltaic panel; if yes, proceed to S5; if not, proceed to S4; S4: Obtain the imaging temperature of each cell on adjacent photovoltaic panels on the same detection circuit; jump to S2; S5: Setting the mode as a temperature threshold.

[0009] Preferably, the image segmentation model is obtained by training an artificial intelligence model, including: Acquire a plurality of photovoltaic panel thermal imaging images, and a plurality of corresponding cell images and cell numbers; the cell images are images of regions where each cell is located, manually separated from the photovoltaic panel thermal imaging images; and integrate the photovoltaic panel thermal imaging images, the plurality of corresponding cell images, and the cell numbers into a plurality of sets of training data and test data; The artificial intelligence model is trained using training data, and the trained artificial intelligence model is tested using test data, ultimately obtaining an image segmentation model whose input is a thermal imaging image of a photovoltaic panel and whose output is a number of corresponding cell images and cell numbers; wherein the artificial intelligence model includes a BP neural network model and an RBF neural network model.

[0010] Preferably, generating the abnormality score based on abnormal region and structure data comprises: Extracting the cell numbers of each cell line and each cell from the structural data; obtaining a number of abnormal cells on each cell line; obtaining the imaging temperature of each abnormal cell and the shortest distance from the cell to the cell at the boundary of the corresponding abnormal area; generating an abnormal state score of the abnormal battery cell based on the imaging temperature and the shortest distance; Summing up the abnormal status scores of the abnormal cells on a cell line to obtain an abnormality score for the cell line; The abnormality score of each cell circuit is obtained in sequence, and the maximum abnormality score is used as the abnormality score of the photovoltaic panel.

[0011] Preferably, generating the abnormal state score based on the imaging temperature and the shortest distance includes: Obtain the total number of abnormal cells YS in the abnormal area where the abnormal cell is located; mark the imaging temperature as CW; and mark the shortest distance as ZJ; By formula The abnormal state score YCPF is calculated; CWmax represents the maximum imaging temperature; ZA represents the unit distance value; γ1 and γ2 represent the proportional coefficients; the proportional coefficients can be dynamically adjusted according to the influence of the parameters of the abnormal area; Preferably, the sorting of the detection circuits based on the anomaly score includes: Obtaining the anomaly score of each photovoltaic panel on the detection line, and performing a weighted summation of the anomaly scores of the photovoltaic panels on the same detection line to obtain the anomaly score of the detection line; Obtain the anomaly score of each detection line in turn; sort each detection line in descending order.

[0012] Preferably, obtaining the danger detection level based on the detection data analysis includes: Extracting various detection parameters from the detection data; the detection parameters include current, voltage, etc. of the detection circuit; Compare the detection parameter with its corresponding preset threshold; when the detection parameter is within the range of the corresponding threshold, the danger detection level is recorded as a low danger level; when the detection parameter exceeds the corresponding threshold, the danger detection level is recorded as a high danger level; Preferably, generating the alarm signal based on the danger detection level includes: When the danger detection level is a low danger level, a check signal is generated; When the danger detection level is a high danger level, a danger signal is generated; A second embodiment of the present application provides a fire warning system for a photovoltaic power station, comprising: Abnormal area division module: obtains thermal imaging images of photovoltaic panels; performs image analysis based on the thermal imaging images to obtain the corresponding abnormal areas of photovoltaic panels; Data analysis module: obtains the structural data of the photovoltaic panel and generates an abnormality score to indicate the degree of abnormality of the photovoltaic panel based on the abnormal area and structural data; Line warning module: sorts each detection line based on the anomaly score, obtains the detection data of each detection line in sequence based on the sorting order, and obtains the danger detection level of the detection line based on the detection data analysis; generates an alarm signal based on the danger detection level.

[0013] Compared with the prior art, the present invention has the following advantages: 1. This application obtains a thermal imaging image of a photovoltaic panel; performs image analysis based on the thermal imaging image to obtain an abnormal area corresponding to the photovoltaic panel; obtains structural data of the photovoltaic panel, and generates an abnormality score representing the degree of abnormality of the photovoltaic panel based on the abnormal area and structural data; sorts each detection line based on the abnormality score, sequentially obtains detection data of each detection line based on the sorting order, and obtains a danger detection level of the detection line based on the detection data analysis; generates an alarm signal based on the danger detection level; sorts the detection lines from high to low according to the abnormality score, and prioritizes warning processing for detection lines with high scores, thereby greatly reducing warning time and improving overall efficiency; 2. The temperature threshold optimization detection accuracy in this application is generated by statistically analyzing the mode of the imaging temperature and combining it with the data of adjacent photovoltaic panels to avoid misjudgment caused by environmental interference, significantly improving the accuracy and adaptability of abnormality recognition. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0015] Figure 1 This is a schematic diagram of the principles of this application; Figure 2 This is a system diagram of this application. DETAILED DESCRIPTION

[0016] The following will clearly and completely describe the technical solutions of this application in conjunction with the embodiments. Obviously, the embodiments described are only a part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0017] See also Figure 1 The first embodiment of the present application provides a fire warning method for a photovoltaic power station, comprising: Acquire thermal imaging images of photovoltaic panels; Image analysis is performed based on thermal imaging images to obtain the corresponding abnormal areas of the photovoltaic panels; Acquire the structural data of the photovoltaic panel, which is the structural data of the photovoltaic panel's circuits and components, including the solar cells and the circuit connections between them; generate an abnormality score indicating the degree of abnormality of the photovoltaic panel based on the abnormal area and structural data; Each detection line is sorted based on the anomaly score, where a detection line is a line connecting several photovoltaic panels in series. The detection data of each detection line is obtained in sequence based on the sorting order. The detection data are various detection parameters detected on the detection line. The detection parameters include the current, voltage, etc. of the detection line. The danger detection level of the detection line is obtained based on the detection data analysis. An alarm signal is generated based on the danger detection level.

[0018] Specifically, the abnormal area of ​​the photovoltaic panel is obtained by performing image analysis based on the thermal imaging image, including: Obtain a thermal imaging image, input the thermal imaging image into the image segmentation model to obtain a cell image and cell number, obtain the average pixel value of each pixel in the cell image, and query the corresponding imaging temperature based on the average value; Determine whether the imaging temperature is greater than a set temperature threshold, and if so, mark the cell as an abnormal cell; if not, mark the cell as a normal cell; The areas where each continuous abnormal cell is located are obtained in sequence and marked as abnormal areas of the photovoltaic panel.

[0019] In this embodiment, it is necessary to explain that the average value of the pixel values ​​of each pixel point in the cell image is obtained, the corresponding imaging temperature is queried based on the average value, and the imaging temperature is compared with the temperature threshold to thereby determine whether the cell has an abnormality. The abnormal photovoltaic panel area refers to the area where the photovoltaic panel has an abnormal condition. The imaging temperature refers to the temperature value obtained after processing the cell image. Specifically, the temperature threshold is obtained by: S1: Obtaining the imaging temperature of each cell of the photovoltaic panel; S2: round up all imaging temperatures and obtain the mode of the rounded imaging temperatures; S3: Determine whether the mode is less than the maximum temperature value set for the photovoltaic panel; if yes, proceed to S5; if not, proceed to S4; S4: Obtain the imaging temperature of each cell on adjacent photovoltaic panels on the same detection circuit; jump to S2; S5: Setting the mode as a temperature threshold.

[0020] In another embodiment, the temperature threshold is obtained by: S1: Obtaining the imaging temperature of each cell of the photovoltaic panel; S2: round up all imaging temperatures and obtain the mode of the rounded imaging temperatures; S3: Determine whether the mode is less than the maximum temperature value set for the photovoltaic panel; if yes, proceed to S5; if not, proceed to S4; S4: Obtain the imaging temperature of each cell on other photovoltaic panels closest to the photovoltaic panel; jump to S2; S5: Setting the mode as a temperature threshold.

[0021] In another embodiment, the temperature threshold is obtained by: S1: Obtaining the imaging temperature of each cell of the photovoltaic panel; S2: round up all imaging temperatures and obtain the mode of the rounded imaging temperatures; S3: Determine whether the mode is less than the maximum temperature value set for the photovoltaic panel; if yes, proceed to S5; if not, proceed to S4; S4: Obtain the imaging temperature of each cell on other photovoltaic panels that are closest to the photovoltaic panel and have the same model as the photovoltaic panel; jump to S2; S5: Setting the mode as a temperature threshold.

[0022] Specifically, the image segmentation model is obtained by training an artificial intelligence model, including: Acquire a plurality of photovoltaic panel thermal imaging images, and a plurality of corresponding cell images and cell numbers; the cell images are images of regions where each cell is located, manually separated from the photovoltaic panel thermal imaging images; and integrate the photovoltaic panel thermal imaging images, the plurality of corresponding cell images, and the cell numbers into a plurality of sets of training data and test data; The artificial intelligence model is trained using training data, and the trained artificial intelligence model is tested using test data, ultimately obtaining an image segmentation model whose input is a thermal imaging image of a photovoltaic panel and whose output is a number of corresponding cell images and cell numbers; wherein the artificial intelligence model includes a BP neural network model and an RBF neural network model.

[0023] Specifically, generating the abnormality score based on the abnormal region and structure data includes: Extracting the cell numbers of each cell line and each cell from the structural data; obtaining a number of abnormal cells on each cell line; obtaining the imaging temperature of each abnormal cell and the shortest distance from the cell to the cell at the boundary of the corresponding abnormal area; generating an abnormal state score of the abnormal battery cell based on the imaging temperature and the shortest distance; Summing up the abnormal status scores of the abnormal cells on a cell line to obtain an abnormality score for the cell line; The abnormality score of each cell circuit is obtained in sequence, and the maximum abnormality score is used as the abnormality score of the photovoltaic panel.

[0024] The abnormality score refers to the quantitative index of the abnormality of the photovoltaic panel; the abnormal state score refers to the quantitative index of the abnormal battery cell; the structural data is the structural data of the circuit and components of the photovoltaic panel, including the circuit connection relationship between the battery cells and them; the abnormal area refers to the abnormal area of ​​the photovoltaic panel.

[0025] Specifically, generating the abnormal state score based on the imaging temperature and the shortest distance includes: Obtain the total number of abnormal cells YS in the abnormal area where the abnormal cell is located; mark the imaging temperature as CW; and mark the shortest distance as ZJ; By formula The abnormal state score YCPF is calculated; CWmax represents the maximum imaging temperature; ZA represents the unit distance value; γ1 and γ2 represent the proportional coefficients; the proportional coefficients can be dynamically adjusted according to the influence of the parameters of the abnormal area; In this embodiment, it is necessary to explain that the above formula illustrates the relationship between the abnormal state score and the number of abnormal cells, the imaging temperature, and the shortest distance. When the imaging temperature is higher, it means that the temperature of the cells inside the photovoltaic panel is higher, and a hot spot effect may occur. The more abnormal cells there are, the more heat accumulation will be aggravated, and the scope of influence of the hot spot phenomenon will be expanded. The longer the shortest distance among the abnormal cells is, the closer the cell is to the center of the abnormal area. The greater the probability of abnormality of the corresponding cell, the higher the corresponding abnormal state score.

[0026] Specifically, the sorting of the detection lines based on the anomaly score includes: Obtaining the anomaly score of each photovoltaic panel on the detection line, and performing a weighted summation of the anomaly scores of the photovoltaic panels on the same detection line to obtain the anomaly score of the detection line; Obtain the anomaly score of each detection line in turn; sort each detection line in descending order.

[0027] In this embodiment, it should be explained that the various detection lines are sorted from largest to smallest. The larger the abnormality score of the detection line, the greater the probability of abnormality in the detection line, which indicates that the performance of the photovoltaic panels on the line is poor and may be prone to failure. Therefore, the detection line with the highest abnormality score is given priority for early warning processing; Specifically, the hazard detection level is obtained based on the analysis of the detection data, including: Extracting various detection parameters from the detection data; the detection parameters include current, voltage, etc. of the detection circuit; Compare the detection parameter with its corresponding preset threshold; when the detection parameter is within the range of the corresponding threshold, the danger detection level is recorded as a low danger level; when the detection parameter exceeds the corresponding threshold, the danger detection level is recorded as a high danger level; Danger detection level refers to the classification of the degree of danger of the detection line; Specifically, generating the alarm signal based on the danger detection level includes: When the danger detection level is a low danger level, a check signal is generated; When the danger detection level is a high danger level, a danger signal is generated; See also Figure 2 The second embodiment of the present application provides a fire warning system for a photovoltaic power station, including: Abnormal area division module: obtains thermal imaging images of photovoltaic panels; performs image analysis based on the thermal imaging images to obtain the corresponding abnormal areas of photovoltaic panels; Data analysis module: obtains the structural data of the photovoltaic panel and generates an abnormality score to indicate the degree of abnormality of the photovoltaic panel based on the abnormal area and structural data; Line warning module: sorts each detection line based on the anomaly score, obtains the detection data of each detection line in sequence based on the sorting order, and obtains the danger detection level of the detection line based on the detection data analysis; generates an alarm signal based on the danger detection level.

[0028] Some of the data in the above formula are calculated by removing the dimensions and taking their numerical values. The formula is a formula that is closest to the actual situation obtained by software simulation of a large amount of collected data; the preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained through simulation of a large amount of data.

[0029] The working principle of the present application is as follows: obtaining a thermal imaging image of a photovoltaic panel; performing image analysis based on the thermal imaging image to obtain the corresponding abnormal area of ​​the photovoltaic panel; obtaining the structural data of the photovoltaic panel, and generating an abnormality score representing the degree of abnormality of the photovoltaic panel based on the abnormal area and the structural data; sorting each detection line based on the abnormality score, obtaining the detection data of each detection line in sequence based on the sorting order, and obtaining the danger detection level of the detection line based on the detection data analysis; generating an alarm signal based on the danger detection level; sorting the detection lines from high to low according to the abnormality scores, and giving priority to early warning processing for detection lines with high scores, which greatly reduces the warning time and improves the overall efficiency.

[0030] The above embodiments are only used to illustrate the technical method of the present application and are not intended to limit it. Although the present application has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present application can be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present application.

Claims

1. A fire warning method for a photovoltaic power station, characterized in that: Acquire thermal imaging images of the photovoltaic panel; perform image analysis based on the thermal imaging images to obtain the corresponding abnormal areas of the photovoltaic panel; Acquiring structural data of the photovoltaic panel, and generating an abnormality score indicating the degree of abnormality of the photovoltaic panel based on the abnormal region and the structural data; Sorting each detection line based on the anomaly score, sequentially acquiring detection data of each detection line based on the sorting order, and obtaining a danger detection level of the detection line based on the detection data analysis; An alarm signal is generated based on the hazard detection level.

2. A fire warning method for a photovoltaic power station according to claim 1, characterized in that: The method for obtaining the abnormal area of ​​the photovoltaic panel includes: Obtain a thermal imaging image, input the thermal imaging image into the image segmentation model to obtain a cell image and cell number, obtain the average pixel value of each pixel in the cell image, and query the corresponding imaging temperature based on the average value; Determine whether the imaging temperature is greater than a set temperature threshold, and if so, mark the cell as an abnormal cell; if not, mark the cell as a normal cell; The areas where each continuous abnormal cell is located are obtained in sequence and marked as abnormal areas of the photovoltaic panel.

3. A fire warning method for a photovoltaic power station according to claim 2, characterized in that: The temperature threshold is obtained by: S1: Obtaining the imaging temperature of each cell of the photovoltaic panel; S2: round up all imaging temperatures and obtain the mode of the rounded imaging temperatures; S3: Determine whether the mode is less than the maximum temperature value set for the photovoltaic panel; if yes, proceed to S5; if not, proceed to S4; S4: Obtain the imaging temperature of each cell on adjacent photovoltaic panels on the same detection circuit; jump to S2; S5: Setting the mode as a temperature threshold.

4. A fire warning method for a photovoltaic power station according to claim 2, characterized in that: The image segmentation model acquisition method includes: Acquire a number of photovoltaic panel thermal imaging images, and a number of corresponding cell images and cell numbers; integrate the photovoltaic panel thermal imaging images, and the number of corresponding cell images and cell numbers into a number of sets of training data and test data; Finally, we obtain an image segmentation model whose input is the thermal imaging image of the photovoltaic panel and whose output is the corresponding several cell images and cell numbers.

5. A fire warning method for a photovoltaic power station according to claim 1, characterized in that: Generating the anomaly score based on the abnormal region and structure data; comprising: Extracting the cell numbers of each cell line and each cell from the structural data; obtaining a number of abnormal cells on each cell line; obtaining the imaging temperature of each abnormal cell and the shortest distance from the cell to the cell at the boundary of the corresponding abnormal area; generating an abnormal state score of the abnormal battery cell based on the imaging temperature and the shortest distance; Summing up the abnormal status scores of the abnormal cells on a cell line to obtain an abnormality score for the cell line; The abnormality score of each cell circuit is obtained in sequence, and the maximum abnormality score is used as the abnormality score of the photovoltaic panel.

6. A fire warning method for a photovoltaic power station according to claim 2, characterized in that: Generating the abnormal state score based on the imaging temperature and the shortest distance includes: Obtain the total number of abnormal cells YS in the abnormal area where the abnormal cell is located; mark the imaging temperature as CW; and mark the shortest distance as ZJ; By formula The abnormal state score YCPF is calculated; CWmax represents the maximum imaging temperature; ZA represents the unit distance value; γ1 and γ2 represent the proportional coefficients.

7. A fire warning method for a photovoltaic power station according to claim 1, characterized in that: The sorting of the detection lines based on the anomaly score includes: Obtaining the anomaly score of each photovoltaic panel on the detection line, and performing a weighted summation of the anomaly scores of the photovoltaic panels on the same detection line to obtain the anomaly score of the detection line; Obtain the anomaly score of each detection line in turn; sort each detection line in descending order.

8. A fire warning method for a photovoltaic power station according to claim 7, characterized in that: The hazard detection level is obtained based on the analysis of the detection data, including: Extract each detection parameter from the detection data; compare the detection parameter with its corresponding preset threshold; when the detection parameter is within the range of the corresponding threshold, the danger detection level is recorded as a low danger level; when the detection parameter exceeds the corresponding threshold, the danger detection level is recorded as a high danger level.

9. The fire warning method for a photovoltaic power station according to claim 1, characterized in that: Generating the alarm signal based on the danger detection level comprises: When the danger detection level is a low danger level, a check signal is generated; When the danger detection level is a high danger level, a danger signal is generated.

10. A fire warning system for a photovoltaic power station, applied to the operation of a fire warning method for a photovoltaic power station according to any one of claims 1 to 9; characterized in that: The following steps are involved: Abnormal area division module: obtains thermal imaging images of photovoltaic panels; performs image analysis based on the thermal imaging images to obtain the corresponding abnormal areas of photovoltaic panels; Data analysis module: obtains the structural data of the photovoltaic panel and generates an abnormality score to indicate the degree of abnormality of the photovoltaic panel based on the abnormal area and structural data; Line warning module: sorts each detection line based on the anomaly score, obtains the detection data of each detection line in sequence based on the sorting order, and obtains the danger detection level of the detection line based on the detection data analysis; An alarm signal is generated based on the hazard detection level.

Images