Arc, flame review detection method, device, system and computer equipment

Abstract

The application relates to an electric arc, flame cross-check detection method, device, system and computer equipment. The method comprises the following steps: acquiring ultraviolet image data, visible light image data and ultraviolet intensity data of ambient light; in the case that an electric arc signal is detected based on the ultraviolet image data, and the comparison result of the intensity of the electric arc signal and the ultraviolet intensity data meets a first preset condition, it is determined that an electric arc event exists in the environment; in the case that no electric arc signal is detected based on the ultraviolet image data, and a flame feature is detected based on the visible light image data, the area of a rectangular frame corresponding to the flame feature is acquired; in the case that the number of frames in which the same flame feature exists reaches a preset threshold, and the area of the rectangular frame corresponding to the number of frames of the preset threshold and the ultraviolet intensity data continuously counted meet a second preset condition, it is determined that a flame event exists in the environment. The electric arc and the flame are distinguished and cross-verified, and the false positive rate is reduced.

Description

Technical Field

[0001] This application relates to the field of fire early warning technology, and in particular to an arc and flame verification detection method, device, system and computer equipment. Background Technology

[0002] Currently, existing methods for detecting electric arcs mainly rely on ultraviolet (UV) light tubes, while methods for detecting flames use visible light images verified by adding a UV light tube.

[0003] However, ultraviolet (UV) light tubes work by detecting UV radiation of specific wavelengths. Both open flames and electric arcs release high-intensity UV radiation during combustion or discharge. In particular, a significant portion of the UV light they produce overlaps, primarily concentrated between 185nm and 260nm, and UV light tubes are highly sensitive to this wavelength range. Therefore, when an electric arc or flame occurs, the UV light tube will detect a strong UV signal and trigger an alarm, making it difficult to distinguish between an arc and a flame. Summary of the Invention

[0004] This application provides a method, apparatus, system, and computer equipment for verifying and detecting electric arcs and flames, in order to solve the problem that the prior art cannot distinguish between detecting electric arcs and flames.

[0005] A method for verifying and detecting electric arcs and flames, comprising:

[0006] Acquire detection data of ambient light, including ultraviolet image data, visible light image data, and ultraviolet intensity data of ultraviolet light tube;

[0007] If an electric arc signal is detected based on the ultraviolet image data, and the comparison result between the intensity of the electric arc signal and the ultraviolet intensity data meets the first preset condition, it is determined that an electric arc event exists in the environment.

[0008] If no arc signal is detected in the ultraviolet image data and flame features are detected in the visible light image data, the area of ​​the rectangular frame corresponding to the flame features is obtained.

[0009] If the number of frames in which the same flame feature exists reaches a preset threshold, and the area of ​​the rectangular frame and the ultraviolet intensity data corresponding to the consecutively counted frames of the preset threshold meet a second preset condition, then it is determined that a flame event exists in the environment.

[0010] In another embodiment, determining that a flame event exists in the environment when the number of frames in which the same flame feature exists reaches a preset threshold, and the area of ​​the rectangular frame corresponding to the consecutively counted frames of the preset threshold and the ultraviolet intensity data satisfy a second preset condition, includes:

[0011] If the number of frames in which the same flame feature exists reaches a preset threshold, count the number of frames in which the ultraviolet intensity data and the area of ​​the rectangular frame satisfy the second preset condition;

[0012] If the number of frames reaches the preset threshold, it is determined to be a fire event.

[0013] In another embodiment, the second preset condition includes:

[0014] The ultraviolet intensity data of the current frame is greater than the preset intensity threshold;

[0015] The preset intensity threshold is the product of the square of the area of ​​the rectangle, the preset influence factor, and the preset intensity threshold per unit area.

[0016] In another embodiment, the first preset condition includes determining that an arc event exists in the environment when the comparison result of the arc signal intensity and the ultraviolet intensity data is greater than the dynamic screening threshold corresponding to the intensity of the arc signal, including:

[0017] The dynamic screening threshold is calculated based on the intensity of the electric arc signal;

[0018] When the ultraviolet intensity data is greater than the dynamic screening threshold, it is determined to be an electric arc event.

[0019] An arc and flame verification and detection device, comprising:

[0020] The data acquisition unit is used to acquire detection data of ambient light, including ultraviolet image data, visible light image data, and ultraviolet intensity data of the ultraviolet light tube.

[0021] A data processing unit, connected to the data acquisition unit, is configured to: determine that an arc event exists in the environment when an arc signal is detected based on the ultraviolet image data, and the comparison result of the arc signal intensity and the ultraviolet intensity data satisfies a first preset condition; acquire the area of ​​a rectangular frame corresponding to the flame feature when no arc signal is detected in the ultraviolet image data, but a flame feature is detected based on the visible light image data; and determine that a flame event exists in the environment when the number of frames in which the same flame feature exists reaches a preset threshold, and the area of ​​the rectangular frame corresponding to the number of consecutive frames at the preset threshold and the ultraviolet intensity data satisfy a second preset condition.

[0022] An arc and flame verification detection system, comprising:

[0023] The ultraviolet light tube module is used to collect ultraviolet intensity data in real time;

[0024] The ultraviolet image acquisition module is used to acquire ultraviolet image data in real time.

[0025] The visible light image acquisition module is used to acquire visible light image data and identify suspected flames within it using an artificial intelligence model;

[0026] Data processing module: Connected to the ultraviolet light tube module, ultraviolet image acquisition module, and visible light image acquisition module respectively, used to determine that an arc event exists in the environment when an arc signal is detected based on the ultraviolet image data, and the comparison result of the arc signal intensity and the ultraviolet intensity data meets a first preset condition; when no arc signal is detected in the ultraviolet image data, but a flame feature is detected based on the visible light image data, the area of ​​the rectangular frame corresponding to the flame feature is obtained; and when the number of frames in which the same flame feature exists reaches a preset threshold, and the area of ​​the rectangular frame corresponding to the number of consecutive frames at the preset threshold and the ultraviolet intensity data meet a second preset condition, the presence of a flame event in the environment is determined.

[0027] In another embodiment, the data processing module includes:

[0028] The multi-frame buffer and statistics unit is used to store multiple consecutive frames of data with the same flame feature and to perform statistical calculations.

[0029] In another embodiment, the data processing module includes:

[0030] A dynamic threshold unit is used to calculate a dynamic screening threshold based on the image arc intensity.

[0031] When the ultraviolet intensity data is greater than the dynamic screening threshold, it is determined to be an electric arc event.

[0032] A computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of any one of the above-described method embodiments.

[0033] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any one of the above-described method embodiments.

[0034] The aforementioned arc and flame verification detection methods, devices, systems, and computer equipment effectively eliminate non-arc ultraviolet interference such as lightning and welding by synchronously comparing arc signals from ultraviolet images with ultraviolet intensity data, significantly improving the accuracy of arc detection. Simultaneously, for flame detection, when no arc is detected in the ultraviolet image, a strategy combining preliminary identification using visible light image data with multi-frame statistical verification of ultraviolet intensity data is employed. By continuously tracking the flame target for multiple frames and analyzing the correlation between its area and ultraviolet intensity data, the system effectively distinguishes real flames from false alarm sources such as sunlight reflection and high-temperature equipment. Through these methods, accurate differentiation and cross-validation of arcs and flames are achieved, significantly reducing the false alarm rate caused by a single sensor. Attached Figure Description

[0035] To more clearly illustrate the technical solutions in the embodiments of this application or the conventional technology, the drawings used in the description of the embodiments or the conventional technology will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0036] Figure 1 This is a flowchart of an embodiment of an arc and flame verification detection method;

[0037] Figure 2 This is a flowchart of another embodiment of the arc and flame verification detection method;

[0038] Figure 3 This is a flowchart of another embodiment of the arc and flame verification detection method;

[0039] Figure 4 This is a schematic diagram of the unit connections of an arc and flame verification detection device according to an embodiment;

[0040] Figure 5 This is a schematic diagram of the module connection of an arc and flame verification detection system according to one embodiment.

[0041] Explanation of reference numerals in the attached figures:

[0042] 401. Data acquisition unit; 402. Data processing unit; 501. Ultraviolet light tube module; 502. Ultraviolet image acquisition module; 503. Visible light image acquisition module; 504. Data processing module. Detailed Implementation

[0043] To facilitate understanding of this application, a more complete description will be provided below with reference to the accompanying drawings, which illustrate embodiments of the present application. However, the present application can be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided so that the disclosure of this application will be thorough and complete.

[0044] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application.

[0045] It is understood that the terms "first," "second," etc., used herein may be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish one element from another. For example, without departing from the scope of this application, a first resistor may be referred to as a second resistor, and similarly, a second resistor may be referred to as a first resistor. Both the first resistor and the second resistor are resistors, but they are not the same resistor.

[0046] It is understood that the term "connection" in the following embodiments should be understood as "electrical connection," "communication connection," etc., if the connected circuits, modules, units, etc., have electrical signal or data transmission with each other.

[0047] When used herein, the singular forms of “a,” “an,” and “the” may also include the plural forms unless the context clearly indicates otherwise. It should also be understood that the terms “comprising / including” or “having,” etc., specify the presence of the stated features, wholes, steps, operations, components, parts, or combinations thereof, but do not preclude the possibility of the presence or addition of one or more other features, wholes, steps, operations, components, parts, or combinations thereof. Meanwhile, the term “and / or” as used in this specification includes any and all combinations of the associated listed items.

[0048] like Figure 1 As shown, this application proposes a method for verifying and detecting electric arcs and flames, including steps 101, 102, 103 and 104.

[0049] 101. Acquire detection data of ambient light, the detection data including ultraviolet image data, visible light image data and ultraviolet intensity data of ultraviolet light tube.

[0050] Among them, ultraviolet image data, visible light image data, and ultraviolet intensity data of ultraviolet light tube can be collected by ultraviolet camera (for identifying ultraviolet light spots generated by electric arc), by visible light camera (for identifying visible features such as flames and smoke), and by ultraviolet light tube (reflecting the intensity of ultraviolet radiation in the environment), respectively.

[0051] 102. If an arc signal is detected based on the ultraviolet image data, and the comparison result between the intensity of the arc signal and the ultraviolet intensity data satisfies the first preset condition, it is determined that an arc event exists in the environment.

[0052] In this step, the acquired ultraviolet image data is analyzed in real time, and an image recognition algorithm is used to detect the presence of an electric arc signal. When a suspected electric arc spot area is detected in the ultraviolet image, the intensity feature value of that area is extracted as the electric arc signal intensity. Simultaneously, ultraviolet intensity data collected by the ultraviolet light tube at the same time is acquired. The electric arc signal intensity is compared with the ultraviolet intensity data to determine whether a first preset condition is met. If the first preset condition is met, it can be determined that an electric arc event exists in the environment.

[0053] 103. If no arc signal is detected in the ultraviolet image data and flame features are detected in the visible light image data, obtain the area of ​​the rectangular frame corresponding to the flame.

[0054] When a flame is detected in the visible light image data but no arc signal is detected in the ultraviolet image, the flame detection process begins. First, the visible light image data is analyzed, and a pre-trained deep learning model (such as YOLOv4) is used to identify suspected flames in the image. When the model detects a flame target, it outputs the position and size of the target's bounding box and calculates the area of ​​the bounding box.

[0055] 104. If the number of frames in which the same flame feature exists reaches a preset threshold, and the area of ​​the rectangular frame and the ultraviolet intensity data corresponding to the number of consecutive frames at the preset threshold meet the second preset condition, it is determined that a flame event exists in the environment.

[0056] The system continuously tracks the same suspected flame target across multiple frames. When the number of consecutive frames in which the flame target appears reaches a preset threshold N (e.g., N=10 frames), the area of ​​the bounding box and the corresponding ultraviolet intensity data for each of these N frames are acquired. Based on a preset second condition, the bounding box area and ultraviolet intensity data of these N frames are comprehensively evaluated. When the second preset condition is met, a real flame event is confirmed in the environment, triggering a flame alarm.

[0057] This embodiment effectively eliminates non-arc ultraviolet interference such as lightning and welding by synchronously comparing the arc signal in the image with ultraviolet intensity data, significantly improving the accuracy of arc detection. Simultaneously, for flame detection, a strategy combining preliminary identification from visible light images with multi-frame statistical verification of ultraviolet intensity data is employed. Even when no arc is detected in the ultraviolet image, the flame target is tracked continuously for multiple frames, and the correlation between its area and ultraviolet intensity data is analyzed, effectively distinguishing real flames from false alarm sources such as sunlight reflection and high-temperature equipment. Through this collaborative mechanism, accurate differentiation and cross-validation of arcs and flames are achieved, significantly reducing the false alarm rate caused by a single sensor, making it suitable for fire early warning in unattended scenarios such as photovoltaic power plants.

[0058] In another embodiment, such as Figure 2 As shown, step 104 includes: step 201 and step 202.

[0059] 201. When the number of frames in which the same flame feature exists reaches a preset threshold, count the number of frames in which the ultraviolet intensity data and the area of ​​the rectangular frame satisfy the second preset condition.

[0060] 202. If the number of frames reaches a preset threshold, it is determined to be a flame event.

[0061] When a suspected flame target is detected by the visible light image data through a deep learning model, the target is tracked continuously for multiple frames. The detection data for N consecutive frames is stored; in this embodiment, N can be 10. For each frame, the area of ​​its bounding box and the corresponding ultraviolet intensity data are collected. Within a frame, when the ultraviolet intensity data and the bounding box area meet a second preset condition, the frame counter is incremented by 1 from a value of 0. When the frame counter finally reaches a preset judgment threshold, it is determined to be a flame event.

[0062] Because false alarm sources exist, such as sunlight reflection and moving light sources, several frames of visible light image data may contain "suspected flame" images. Therefore, a threshold needs to be set. Only when the value exceeds this threshold is it confirmed as a real flame event, thus preventing false alarms caused by interference from false alarm sources in a very short period of time. Therefore, this embodiment improves the accuracy of flame event judgment and the reliability of fire early warning by setting a threshold.

[0063] In another embodiment, the second preset condition includes:

[0064] The ultraviolet intensity data of the current frame is greater than a preset intensity threshold, wherein the preset intensity threshold is the product of the square of the area of ​​the rectangle, a preset influence factor, and a preset intensity threshold per unit area.

[0065] The formula for calculating the preset intensity threshold can be expressed as:

[0066]

[0067] in This represents the intensity threshold per unit area of ​​the flame during statistical analysis. This represents the influence factor of flame size on ultraviolet radiation intensity, and its value ranges from 0 to 1. This represents the area of ​​the rectangular frame containing the flame in that frame. In this embodiment, The default value is 3, but it is understandable that the above values ​​can be set according to the actual situation.

[0068] After obtaining the ultraviolet intensity data of the current frame, the ultraviolet intensity data and the preset intensity threshold corresponding to the current frame obtained by the above calculation formula are combined. If the ultraviolet intensity data is greater than the preset intensity threshold, the comparison will be made. Then the operation frame counter starts incrementing by 1 from a value of 0.

[0069] Repeat the above operation. After statistical analysis of the detection data of multiple consecutive frames, obtain the final value of the frame counter. When the final value is greater than the judgment threshold, it is confirmed that there is a flame event in the environment.

[0070] In this embodiment, the judgment threshold can be set based on the value of N. For example, it can be set to 0.8 times N. When the final value of the frame counter is greater than this value, it is confirmed that there is a fire event in the environment.

[0071] This embodiment provides a computational basis for confirming flame events by setting a preset intensity threshold, enabling refined verification of flame detection. Compared to a fixed threshold, the dynamic threshold in this embodiment can adaptively adjust the judgment criteria according to the actual size of the flame: for larger flames, a higher ultraviolet intensity requirement is allowed to avoid misclassifying large-area interference sources as flames; for smaller flames, a lower ultraviolet intensity threshold is used to prevent missing small initial flames. This mechanism improves the accuracy and adaptability of flame detection.

[0072] In another embodiment, the first preset condition includes that the ultraviolet intensity data is greater than the dynamic screening threshold corresponding to the intensity of the arc signal. If the comparison result between the intensity of the arc signal and the ultraviolet intensity data satisfies the first preset condition, it is determined that an arc event exists in the environment. Figure 3 As shown, it includes: step 301 and step 302.

[0073] 301. Calculate the dynamic screening threshold based on the intensity of the electric arc signal;

[0074] 302. When the ultraviolet intensity data is greater than the dynamic screening threshold, it is determined to be an electric arc event.

[0075] When a suspected electric arc signal is detected in ultraviolet image data, the feature value of the electric arc signal is extracted as the electric arc signal intensity. The system generates a dynamic screening threshold based on a preset formula. In this embodiment, the formula for calculating the dynamic screening threshold is:

[0076]

[0077] in, This study identifies the influencing factors between the detection of electric arc intensity and the intensity of the ultraviolet light tube based on ultraviolet image analysis. The dynamic screening threshold can be adaptively adjusted by setting the influencing factor as the arc signal intensity changes in the current frame: when the detected arc signal is strong, the dynamic threshold is increased to eliminate strong interference; when the arc signal is weak, the dynamic threshold is decreased to maintain sensitivity to small arcs.

[0078] Acquire ultraviolet intensity data at the same time. When the following conditions are met:

[0079]

[0080] If the current arc signal is detected, it is determined to be a real arc event, and an arc alarm is triggered; otherwise, the current arc signal is determined to be a false alarm (such as lightning, welding interference, etc.), and no alarm is triggered.

[0081] This embodiment introduces a dynamic screening threshold mechanism to achieve refined verification of electric arc events. The dynamic screening threshold calculation can adaptively adjust the judgment standard based on the intensity of the electric arc signal detected in the image: when a strong electric arc signal is detected in the image, the ultraviolet intensity data must reach a higher level before confirmation, effectively eliminating false alarms caused by strong interference sources, and further improving the accuracy and anti-interference capability of electric arc detection. It is especially suitable for scenarios with complex electromagnetic environments and natural light interference, such as photovoltaic power plants.

[0082] This application also proposes an arc and flame verification detection device, such as Figure 4 As shown, it includes: a data acquisition unit 401 and a data processing unit 402.

[0083] The data acquisition unit 401 is used to acquire detection data of ambient light, including ultraviolet image data, visible light image data and ultraviolet intensity data of the ultraviolet light tube;

[0084] Specifically, the data acquisition unit 401 is connected to the ultraviolet camera, the visible light camera, and the ultraviolet light tube, respectively, and receives in real time ultraviolet image data collected by the ultraviolet camera, visible light image data collected by the visible light camera, and ultraviolet intensity data output by the ultraviolet light tube.

[0085] The data acquisition unit 401 performs time synchronization and alignment on the received data to ensure that ultraviolet image, visible light image data and ultraviolet intensity data at the same time can be correlated, providing an accurate data foundation for subsequent processing.

[0086] The data processing unit 402, connected to the data acquisition unit 401, is used to determine that an arc event exists in the environment when an arc signal is detected from the ultraviolet image data and the comparison result of the arc signal intensity and the ultraviolet intensity data meets a first preset condition; when no arc signal is detected from the ultraviolet image data, but a flame is detected from the visible light image data, it acquires the area of ​​the rectangular frame corresponding to the flame in the current frame and the ultraviolet intensity data; and when the number of frames in which the same flame feature exists reaches a preset threshold, and the area of ​​the rectangular frame and the ultraviolet intensity data corresponding to the number of consecutive frames at the preset threshold meet a second preset condition, it determines that a flame event exists in the environment. Detailed operation steps can be found in the foregoing embodiments and will not be repeated here.

[0087] This embodiment achieves synchronous acquisition of multi-source data through a data acquisition unit and collaborative detection and verification of electric arcs and flames through a data processing unit, forming a complete electric arc and flame verification and detection device. This device has high integration and fast response speed, and can be deployed in unattended scenarios such as photovoltaic power plants to achieve all-weather fire early warning.

[0088] This application also proposes an arc and flame verification detection system, such as Figure 5 As shown, it includes: an ultraviolet light tube module 501, an ultraviolet image acquisition module 502, a visible light image acquisition module 503, and a data processing module 504.

[0089] The UV light tube module 501 is used to collect UV intensity data in real time.

[0090] The UV phototube module 501 can use a UV phototube, which is sensitive to the UV band (180nm-280nm) in the solar blind zone, and can effectively eliminate UV interference from sunlight. Its output is an analog voltage signal or a digital signal, reflecting the real-time intensity of ambient UV radiation.

[0091] An ultraviolet image acquisition module 502 is used to acquire ultraviolet image data in real time. Exemplarily, the ultraviolet image acquisition module 502 includes:

[0092] Ultraviolet camera: Employs a solar-blind ultraviolet imaging device to acquire ultraviolet images of the environment;

[0093] Embedded image processing unit: performs real-time analysis of ultraviolet images, uses image recognition algorithms to detect the presence of electric arc spots in the image, and outputs the arc signal intensity and location information when an electric arc is detected.

[0094] A visible light image acquisition module 503 is used to acquire visible light image data and identify suspected flames within it using an artificial intelligence model. In this embodiment, the module includes:

[0095] Visible light camera: Real-time acquisition of ambient visible light image data;

[0096] AI processing unit: Deploys pre-trained deep learning models to perform real-time analysis of visible light image data, detects flame targets in the image, and outputs the position and area of ​​the flame rectangle.

[0097] Data processing module 504: Connected to the ultraviolet light tube module 501, the ultraviolet image acquisition module 502, and the visible light image acquisition module 503 respectively, used to determine that an arc event exists in the environment when an arc signal is detected from the ultraviolet image data and the comparison result of the arc signal intensity and the ultraviolet intensity data meets a first preset condition; when no arc signal is detected from the ultraviolet image data and a flame is detected from the visible light image data, to obtain the area of ​​the rectangular frame corresponding to the flame in the current frame and the ultraviolet intensity data; and when the number of frames with the same flame feature reaches a preset threshold and the area of ​​the rectangular frame and the ultraviolet intensity data corresponding to the number of consecutive frames at the preset threshold meet a second preset condition, to determine that a flame event exists in the environment.

[0098] The workflow of the data processing module can be referred to the steps in the foregoing embodiments, and will not be repeated here.

[0099] This embodiment integrates an ultraviolet light tube module, an ultraviolet image acquisition module, a visible light image acquisition module, and a data processing module into a single unit, forming a complete arc and flame verification and detection system. This system can acquire multi-source data in real time, perform fusion analysis and verification judgment through the data processing module, and achieve accurate differentiation and reliable early warning of arcs and flames. It is particularly suitable for unattended scenarios such as photovoltaic power plants.

[0100] In another embodiment, the data processing module includes:

[0101] The multi-frame buffer and statistics unit is used to store multiple consecutive frames of data of the same suspected flame target and perform statistical calculations.

[0102] When the visible light image acquisition module detects a suspected flame target, the multi-frame buffer and statistics unit assigns a unique identifier (ID) to the target and establishes a corresponding data buffer. The buffer size is set to store N consecutive frames of data; in this embodiment, N=10.

[0103] For each frame, the multi-frame buffer and statistics unit stores the following data:

[0104] The area of ​​the rectangular frame containing the flame target in the current frame, the ultraviolet intensity data corresponding to the current frame, and the timestamp of the current frame.

[0105] When a new frame of data arrives, the multi-frame buffer and statistics unit update the buffer using the first-in-first-out principle, always retaining the latest N frames of data to ensure the timeliness of the statistical data.

[0106] For the latest N frames of data that are retained, the multi-frame buffer and statistics unit is also used to perform statistical calculations as in step 104 of the method in the above embodiments, which will not be described again here.

[0107] This embodiment achieves continuous tracking and data accumulation statistics of suspected flame targets by setting up multi-frame buffers and statistical units, ensuring the timeliness of the data. This unit, as a core component of the data processing module, provides a reliable data foundation for the accurate judgment of flame events.

[0108] In another embodiment, the data processing module includes:

[0109] A dynamic threshold unit is used to calculate a dynamic screening threshold based on the image arc intensity.

[0110] When the ultraviolet intensity data is greater than the dynamic screening threshold, it is determined to be an electric arc event.

[0111] If the ultraviolet image acquisition module detects a suspected electric arc signal, the feature value of the electric arc signal is extracted as the electric arc signal intensity. The result is then output to the dynamic thresholding unit, which calculates the dynamic screening threshold for the current frame based on the intensity of the arc signal. In this embodiment, the formula for calculating the dynamic screening threshold is:

[0112]

[0113] in, This study identifies the influencing factors between the detection of electric arc intensity and the intensity of the ultraviolet light tube based on ultraviolet image analysis. The dynamic screening threshold can be adaptively adjusted by setting the influencing factor as the arc signal intensity changes in the current frame: when the detected arc signal is strong, the dynamic threshold is increased to eliminate strong interference; when the arc signal is weak, the dynamic threshold is decreased to maintain sensitivity to small arcs.

[0114] Acquire ultraviolet intensity data at the same time. When the following conditions are met:

[0115]

[0116] If the current arc signal is detected, it is determined to be a real arc event, and an arc alarm is triggered; otherwise, the current arc signal is determined to be a false alarm (such as lightning, welding interference, etc.), and no alarm is triggered.

[0117] This embodiment introduces a dynamic threshold unit, which adaptively adjusts the threshold for arc verification. Compared to a fixed threshold, the dynamic screening threshold changes in real time based on the detected arc signal strength. For example, strong arcs require higher ultraviolet intensity data verification to effectively eliminate strong interference; weak arcs use a lower threshold to prevent missed detection. Therefore, the accuracy and anti-interference capability of arc detection can be improved.

[0118] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the method described in the above method embodiment.

[0119] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described in the above method embodiment.

[0120] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of the method described in the above method embodiments.

[0121] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory, magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0122] In the description of this specification, references to terms such as "some embodiments," "other embodiments," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative descriptions of the above terms do not necessarily refer to the same embodiments or examples.

[0123] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0124] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these modifications and improvements all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for verifying and detecting electric arcs and flames, characterized in that, include: Acquire detection data of ambient light, including ultraviolet image data, visible light image data, and ultraviolet intensity data of ultraviolet light tube; If an electric arc signal is detected based on the ultraviolet image data, and the comparison result between the intensity of the electric arc signal and the ultraviolet intensity data meets the first preset condition, it is determined that an electric arc event exists in the environment. If no arc signal is detected in the ultraviolet image data and flame features are detected in the visible light image data, the area of ​​the rectangular frame corresponding to the flame features is obtained. If the number of frames in which the same flame feature exists reaches a preset threshold, and the area of ​​the rectangular frame and the ultraviolet intensity data corresponding to the consecutively counted frames of the preset threshold meet a second preset condition, then it is determined that a flame event exists in the environment.

2. The method according to claim 1, characterized in that, When the number of frames containing the same flame feature reaches a preset threshold, and the area of ​​the rectangular frame and the ultraviolet intensity data corresponding to the consecutively counted frames at the preset threshold meet a second preset condition, it is determined that a flame event exists in the environment, including: If the number of frames in which the same flame feature exists reaches a preset threshold, count the number of frames in which the ultraviolet intensity data and the area of ​​the rectangular frame satisfy the second preset condition; If the number of frames reaches the preset threshold, it is determined to be a fire event.

3. The method according to claim 2, characterized in that, The second preset condition includes: The ultraviolet intensity data of the current frame is greater than the preset intensity threshold; The preset intensity threshold is the product of the square of the area of ​​the rectangle, the preset influence factor, and the preset intensity threshold per unit area.

4. The method according to claim 1, characterized in that, The first preset condition includes determining that an arc event exists in the environment when the ultraviolet intensity data is greater than the dynamic screening threshold corresponding to the intensity of the arc signal, and the comparison result between the intensity of the arc signal and the ultraviolet intensity data meets the first preset condition. The dynamic screening threshold is calculated based on the intensity of the electric arc signal; When the ultraviolet intensity data is greater than the dynamic screening threshold, it is determined to be an electric arc event.

5. An arc and flame verification and detection device, characterized in that, include: The data acquisition unit is used to acquire detection data of ambient light, including ultraviolet image data, visible light image data, and ultraviolet intensity data of the ultraviolet light tube. A data processing unit, connected to the data acquisition unit, is configured to: determine that an arc event exists in the environment when an arc signal is detected based on the ultraviolet image data, and the comparison result of the arc signal intensity and the ultraviolet intensity data satisfies a first preset condition; acquire the area of ​​a rectangular frame corresponding to the flame feature when no arc signal is detected in the ultraviolet image data, but a flame feature is detected based on the visible light image data; and determine that a flame event exists in the environment when the number of frames in which the same flame feature exists reaches a preset threshold, and the area of ​​the rectangular frame corresponding to the number of consecutive frames at the preset threshold and the ultraviolet intensity data satisfy a second preset condition.

6. An arc and flame verification detection system, characterized in that, include: The ultraviolet light tube module is used to collect ultraviolet intensity data in real time; The ultraviolet image acquisition module is used to acquire ultraviolet image data in real time. The visible light image acquisition module is used to acquire visible light image data and identify suspected flames within it using an artificial intelligence model; Data processing module: Connected to the ultraviolet light tube module, ultraviolet image acquisition module, and visible light image acquisition module respectively, used to determine that an arc event exists in the environment when an arc signal is detected based on the ultraviolet image data, and the comparison result of the arc signal intensity and the ultraviolet intensity data meets a first preset condition; when no arc signal is detected in the ultraviolet image data, but a flame feature is detected based on the visible light image data, the area of ​​the rectangular frame corresponding to the flame feature is obtained; and when the number of frames in which the same flame feature exists reaches a preset threshold, and the area of ​​the rectangular frame corresponding to the number of consecutive frames at the preset threshold and the ultraviolet intensity data meet a second preset condition, the presence of a flame event in the environment is determined.

7. The system according to claim 6, characterized in that, The data processing module includes: The multi-frame buffer and statistics unit is used to store multiple consecutive frames of data with the same flame feature and to perform statistical calculations.

8. The system according to claim 6, characterized in that, The data processing module includes: A dynamic threshold unit is used to calculate a dynamic screening threshold based on the image arc intensity. When the ultraviolet intensity data is greater than the dynamic screening threshold, it is determined to be an electric arc event.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 4.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 4.

Images