Intelligent monitoring method, system and device for coal pile temperature based on dual-spectrum and medium

Abstract

The present application belongs to the field of intelligent monitoring, and discloses a coal pile temperature intelligent monitoring method, system, device and medium based on dual spectrum, which comprises the following steps: obtaining the coal pile area recognition result of each collection visual angle of the coal yard according to the visible light image and the infrared image under each collection visual angle of the coal yard, and through a preset coal pile recognition semantic segmentation model; obtaining the surface temperature of each partition coal pile under each collection visual angle of the coal yard according to the partition information of the coal yard, the coal pile area recognition result under each collection visual angle and the infrared image; obtaining the internal temperature of each partition coal pile under each collection visual angle of the coal yard according to the environmental data of the coal yard and the surface temperature of each partition coal pile under each collection visual angle, and through a preset internal-external temperature relationship fitting function of the coal pile; and integrating the internal temperature of each partition coal pile under each collection visual angle of the coal yard to obtain the internal temperature of each partition coal pile of the coal yard. The visible light image and the infrared image are used to realize the accurate extraction of the coal pile area, improve the monitoring accuracy, realize the timely discovery of dangerous situations, and reduce the occurrence of false positives.

Description

Technical Field

[0001] This invention belongs to the field of intelligent monitoring and relates to a method, system, equipment and medium for intelligent monitoring of coal pile temperature based on dual spectrum. Background Technology

[0002] Thermal power generation is the backbone of electricity production. The rapid development of new energy power generation and the need to ensure the supply of electricity for production and daily life place high demands on power plants to maintain sufficient and high-quality coal reserves in order to ensure a reliable power supply while shaving off peak loads and filling valleys. This places high demands on coal storage at power plants. Whether stored in the open or indoors, coal stored for extended periods is prone to oxidation, leading to increased internal temperatures and a risk of spontaneous combustion. Therefore, it is necessary to strengthen early warning systems for spontaneous combustion of coal piles to avoid significant economic losses and safety hazards.

[0003] Currently, monitoring the temperature of stored coal mostly relies on manually setting up temperature measuring rods, which can achieve accurate measurement of the internal temperature of the coal pile, but the workload is heavy. Some coal yards also use infrared thermal imagers to monitor the temperature of target areas in real time; however, because the preset area is used, the temperature measurement system cannot respond promptly to real-time changes on site, and suffers from the disadvantages of on-site environmental interference and weak monitoring capability of the core high-temperature area of ​​the coal pile. Summary of the Invention

[0004] The purpose of this invention is to overcome the shortcomings of the prior art, which is that the manual placement of temperature measuring rods is labor-intensive when monitoring the temperature of coal piles in real time, and that the use of infrared thermal imagers in real time is subject to on-site environmental interference and has weak monitoring capability of the core high-temperature area of ​​the coal pile. The invention provides a method, system, equipment and medium for intelligent monitoring of coal pile temperature based on dual spectrum.

[0005] To achieve the above objectives, the present invention employs the following technical solution:

[0006] In a first aspect, the present invention provides a method for intelligent monitoring of coal pile temperature based on dual-spectrum, comprising:

[0007] Acquire environmental data, zoning information, and visible light and infrared images from several acquisition angles of the coal yard;

[0008] Based on the visible light and infrared images from various acquisition angles in the coal yard, the coal pile area identification results are obtained from various acquisition angles in the coal yard through a preset coal pile identification semantic segmentation model.

[0009] Based on the zoning information of the coal yard, the coal pile area identification results and infrared images from each acquisition perspective, the surface temperature of the coal pile in each zone of the coal yard from each acquisition perspective is obtained.

[0010] Based on the environmental data of the coal yard and the surface temperature of the coal piles in each zone from various acquisition perspectives, the internal temperature of the coal piles in each zone from each acquisition perspective is obtained and integrated using a preset fitting function for the relationship between the internal and external temperatures of the coal piles, thus obtaining the internal temperature of the coal piles in each zone of the coal yard.

[0011] Optionally, the environmental data may include one or more of the following: ambient temperature, wind speed, and air humidity.

[0012] Optionally, the step of obtaining the surface temperature of each coal pile in each zone under each acquisition viewpoint, based on the coal yard's zoning information, the coal pile area identification results from each acquisition perspective, and the infrared image, includes:

[0013] Based on the coal yard zoning information, the coal yard zoning identification results are marked on the visible light images and infrared images from each acquisition perspective of the coal yard, thus obtaining the coal yard zoning identification results from each acquisition perspective; and based on the infrared images from each acquisition perspective of the coal yard, the thermal imaging temperature data from each acquisition perspective of the coal yard are obtained.

[0014] Boolean operations are performed on the coal pile area identification results, coal yard zoning identification results, and thermal imaging temperature data from various acquisition perspectives in the coal yard to obtain the surface temperature of the coal pile in each zone from each acquisition perspective.

[0015] Optionally, the fitting function for the relationship between the internal and external temperatures of the coal pile is obtained in the following manner:

[0016] Acquire historical surface temperature data, historical internal temperature data, and historical environmental data of the coal pile;

[0017] Based on historical surface temperature data, historical internal temperature data, and historical environmental data of the coal pile, one or more of the following models are used: a regression model based on a recurrent neural network, a time series prediction model, and a segmented linear regression model to fit the relationship between the surface temperature and environmental data of the coal pile and the internal temperature of the coal pile. The model with the best fitting result is used as the preset fitting function for the relationship between the internal and external temperatures of the coal pile.

[0018] Optionally, the internal temperature includes the highest internal temperature and the average internal temperature; obtaining and integrating the internal temperatures of each zone of the coal pile from each acquisition perspective in the coal yard to obtain the internal temperatures of each zone of the coal pile in the coal yard includes:

[0019] The highest temperature inside each zone of the coal pile under each collection perspective is taken as the highest temperature inside each zone of the coal pile in the coal yard; the average temperature inside each zone of the coal pile under each collection perspective is taken as the average temperature inside each zone of the coal pile after area weighting.

[0020] Optional, also includes:

[0021] The system visualizes environmental data from the coal yard, as well as visible light and infrared images from several acquisition perspectives.

[0022] Visualize the coal pile area identification results from various acquisition perspectives in the coal yard;

[0023] The system visualizes the surface temperature of coal piles in each zone from various acquisition perspectives, the internal temperature of coal piles in each zone from various acquisition perspectives, and the internal temperature of coal piles in each zone of the coal yard.

[0024] Optional, also includes:

[0025] Based on the internal temperature of the coal piles in each zone of the coal yard, when the internal temperature of the coal pile in the current zone exceeds the preset temperature warning threshold, the preset graded warning judgment indicators are combined to generate graded warning information for the current zone.

[0026] In a second aspect, the present invention provides a dual-spectrum intelligent monitoring system for coal pile temperature, comprising:

[0027] The data acquisition module is used to acquire environmental data, zoning information, and visible light and infrared images from several acquisition angles of the coal yard.

[0028] The identification module is used to obtain the coal pile area identification results from each acquisition view of the coal yard based on the visible light and infrared images from each acquisition view of the coal yard, through a preset coal pile identification semantic segmentation model;

[0029] The surface temperature determination module is used to obtain the surface temperature of each coal pile in each zone under each acquisition angle based on the zoning information of the coal yard, the coal pile area identification results under each acquisition angle and the infrared image.

[0030] The internal temperature determination module is used to obtain the internal temperature of each zone of the coal pile under each acquisition perspective based on the environmental data of the coal yard and the surface temperature of each zone of the coal pile from each acquisition perspective. It uses a preset fitting function for the internal and external temperature relationship of the coal pile to obtain the internal temperature of each zone of the coal pile in the coal yard.

[0031] In a third aspect, the present invention provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the above-described intelligent monitoring method for coal pile temperature based on dual spectrum.

[0032] In a fourth aspect, the present invention provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the above-described intelligent monitoring method for coal pile temperature based on dual spectra.

[0033] Compared with the prior art, the present invention has the following beneficial effects:

[0034] This invention relates to a dual-spectrum intelligent coal pile temperature monitoring method. By using visible light and infrared images from various acquisition angles within the coal yard, and employing a pre-defined semantic segmentation model for coal pile identification, it obtains coal pile area identification results from each acquisition angle. The use of visible light and infrared images enables precise extraction of coal pile areas, eliminating the influence of factors such as coal yard buildings, equipment, and personnel on the infrared temperature measurement results. Simultaneously, by using environmental data and the surface temperature of each zone of the coal pile, and based on a pre-defined fitting function for the internal and external temperature relationship of the coal pile, it achieves accurate prediction of the internal temperature of each zone of the coal pile. This improves the monitoring accuracy of the coal pile temperature, enabling timely detection of dangerous situations and reducing false alarms. Attached Figure Description

[0035] Figure 1 This is a flowchart of the intelligent coal pile temperature monitoring method based on dual spectrum according to an embodiment of the present invention.

[0036] Figure 2 This is a structural block diagram of a dual-spectrum intelligent coal pile temperature monitoring system according to an embodiment of the present invention. Detailed Implementation

[0037] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0038] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0039] The present invention will now be described in further detail with reference to the accompanying drawings:

[0040] See Figure 1In one embodiment of the present invention, a method for intelligent monitoring of coal pile temperature based on dual spectrum is provided, comprising the following steps:

[0041] S1: Acquire environmental data, zoning information, and visible light and infrared images from several acquisition angles of the coal yard.

[0042] S2: Based on the visible light and infrared images from various acquisition angles in the coal yard, the coal pile area identification results are obtained from various acquisition angles in the coal yard through a preset coal pile identification semantic segmentation model.

[0043] S3: Based on the zoning information of the coal yard and the coal pile area identification results and infrared images from each acquisition perspective, the surface temperature of the coal pile in each zone of the coal yard from each acquisition perspective is obtained.

[0044] S4: Based on the environmental data of the coal yard and the surface temperature of each zone of the coal pile under each collection perspective, the internal temperature of each zone of the coal pile under each collection perspective is obtained and integrated through the preset internal and external temperature relationship fitting function of the coal pile, so as to obtain the internal temperature of each zone of the coal pile in the coal yard.

[0045] This invention relates to a dual-spectrum intelligent coal pile temperature monitoring method. By using visible light and infrared images from various acquisition angles within the coal yard, and employing a pre-defined semantic segmentation model for coal pile identification, it obtains coal pile area identification results from each acquisition angle. The use of visible light and infrared images enables precise extraction of coal pile areas, eliminating the influence of factors such as coal yard buildings, equipment, and personnel on the infrared temperature measurement results. Simultaneously, by using environmental data and the surface temperature of each zone of the coal pile, and based on a pre-defined fitting function for the internal and external temperature relationship of the coal pile, it achieves accurate prediction of the internal temperature of each zone of the coal pile. This improves the monitoring accuracy of the coal pile temperature, enabling timely detection of dangerous situations and reducing false alarms.

[0046] In one possible implementation, several dual-spectrum thermal imaging cameras can be deployed near the coal yard boundary to acquire visible light and infrared images from multiple viewing angles. Typically, two or more dual-spectrum thermal imaging cameras are used. Environmental data for the coal yard can be obtained by deploying small weather stations within the coal yard. The acquired environmental data generally includes ambient temperature, wind speed, and air humidity, with sampling intervals typically no less than 15 minutes.

[0047] In one possible implementation, coal pile area identification addresses two issues: first, identifying the location of the coal pile from monitoring footage; and second, determining the coal yard zoning for different coal piles. The former enables accurate temperature measurement of the coal body, while the latter enables accurate location of natural risk points. Due to the frequent changes in coal yard unloading operations, semantic segmentation deep learning algorithms are suitable for coal pile area identification.

[0048] Based on the above, the pre-defined semantic segmentation model for coal pile identification can be constructed as follows:

[0049] 1. Adjust the frame rate of the visible light image to be an integer multiple of the frame rate of the infrared image (25Hz), and extract the visible light image and infrared image from the same time period as samples. At the same time, crop the visible light image according to the shooting range of the infrared image to ensure that the content captured by the two images corresponds completely.

[0050] 2. Obtain image data under different meteorological conditions as much as possible, including but not limited to: coal piles under direct sunlight on sunny days, coal piles under diffused sunlight on sunny days, cloudy days, rainy or snowy days, foggy days, and infrared images during the day and night.

[0051] 3. Use open-source intelligent annotation tools such as Labelme or EISeg to annotate only the coal areas in the samples, and convert the dataset format to Pascal VOC or COCO.

[0052] 4. Based on models such as FCN, DeepLab v3, and SegNet, we carried out the optimization design of semantic segmentation algorithms suitable for infrared images.

[0053] 5. Compare the performance of different candidate models, with accuracy as the main evaluation indicator, select the appropriate model as the final semantic segmentation model, and save the corresponding training weight data to obtain the preset semantic segmentation model for coal pile recognition.

[0054] In this process, when the coal pile area identification results are obtained from the visible light and infrared images collected from various angles of the coal yard, the coal pile identification semantic segmentation model can be triggered to run and update the coal pile area identification results by capturing events that cause significant changes in the monitoring screen, such as coal unloading, bucket wheel excavator, personnel, and coal unloading truck movement.

[0055] Specifically, visible light and infrared images are received at a fixed frame rate. During the day, the visible light image is used as the basis, and at night, the infrared image is used as the basis. Edge detection is performed on the images to determine the similarity of edges between consecutive images. If the similarity exceeds a threshold, the coal pile recognition semantic segmentation model is triggered. For example, an image is captured and edge detected once per minute. The binary edge image is divided into several blocks, and each block is scaled to 8*8 pixels. The pixel ranking list of the scaled-down binary image is calculated, i.e., the hash value of that partition. The hash values ​​are compared with the hash values ​​obtained at different times. When at least one hash value differs from the previous one by a preset range, it is considered that there is a significant difference between the two images, and the coal pile recognition semantic segmentation model is triggered. It is also agreed that the coal pile recognition semantic segmentation model will be automatically triggered once every ten minutes.

[0056] In one possible implementation, obtaining the surface temperature of each coal pile in each acquisition view from the coal yard based on the coal yard's zoning information, the coal pile area identification results from each acquisition view, and the infrared image includes: marking the coal yard zoning identification results on the visible light and infrared images from each acquisition view of the coal yard based on the coal yard's zoning information to obtain the coal yard zoning identification results from each acquisition view; obtaining the thermal imaging temperature data from each acquisition view of the coal yard based on the infrared images from each acquisition view; and performing Boolean operations based on the coal pile area identification results, coal yard zoning identification results, and thermal imaging temperature data from each acquisition view of the coal yard to obtain the surface temperature of each coal pile in each acquisition view of the coal yard.

[0057] Specifically, based on the coal yard zoning construction, different coal yard blocks are selected using irregular polygons within the camera's shooting area (including visible and infrared light). Depending on business needs, the same linear coal yard can be divided into several zones or not. Once the coal yard zoning identification results are manually labeled, they do not require frequent updates as long as the camera's viewing angle remains unchanged. Based on the infrared image, the thermal imaging grayscale values ​​are converted into corresponding temperature values ​​and transmitted in real-time as an array, returning the thermal imaging temperature data from each acquisition perspective. Based on the coal pile area identification results and the coal yard zoning identification results, Boolean operations are performed on the thermal imaging temperature data, coal pile area identification results, and coal yard zoning identification results for each linear coal yard to obtain the coal yard temperature array from each acquisition perspective. This coal yard temperature array is then combined with the corresponding coal yard zoning identification template, and the coal yard temperature array is divided into blocks to obtain the surface temperature of the coal pile in each zone from each acquisition perspective.

[0058] In one possible implementation, the fitting function for the internal and external temperature relationship of the coal pile is obtained as follows: historical surface temperature data, historical internal temperature data, and historical environmental data of the coal pile are acquired; based on the historical surface temperature data, historical internal temperature data, and historical environmental data of the coal pile, one or more of the following models are used: a regression model based on a recurrent neural network, a time series prediction model, and a segmented linear regression model to fit the relationship between the coal pile surface temperature and environmental data and the internal temperature of the coal pile, and the model with the best fitting result is used as the preset fitting function for the internal and external temperature relationship of the coal pile.

[0059] Specifically, numerous factors influence the temperature rise of a coal pile, and currently there is no mature empirical formula to calculate the temperature distribution within the coal pile. Therefore, this embodiment collects influencing factors and internal and external temperature data of the coal pile. By analyzing the collected data, the corresponding relationship between each influencing factor and the internal and external temperatures of the coal pile is fitted, thereby achieving the prediction of the internal temperature of the coal pile. Simultaneously, the acquisition of various influencing factors varies significantly, requiring the screening and retention of factors that have a significant impact on temperature prediction. In this embodiment, environmental data is used as the influencing factor; optionally, coal type, etc., may also be included.

[0060] The historical internal temperature data of the coal pile can be obtained by measuring temperature using a thermometer. When fitting the data, regression models based on recurrent neural networks, time series prediction algorithms, and segmented linear regression models are considered. The predictive performance of different models is tested, and the optimal model is selected as the final fitting result.

[0061] Optionally, before applying this method, internal temperature data of the coal pile can be collected using wireless temperature measuring rods to provide a data foundation for fitting the fitting function. Furthermore, in the early stages of this method's application, after detecting abnormally high temperatures in a certain area of ​​the coal pile, wireless temperature measuring rods are manually deployed to obtain real-time internal temperature data, which is then compared with the prediction results of the fitting function. This enriches historical internal temperature data and optimizes the fitting function. In the mature stage of this method's application, the wireless temperature measuring rods can be discarded, and internal temperature prediction can be achieved directly through the fitting function.

[0062] In one possible implementation, the internal temperature includes the highest internal temperature and the average internal temperature; obtaining and integrating the internal temperatures of each zone of the coal pile under each acquisition perspective to obtain the internal temperature of each zone of the coal pile includes: taking the highest internal temperature of each zone of the coal pile under each acquisition perspective as the highest internal temperature of each zone of the coal pile in the coal yard; and taking the area-weighted average of the average internal temperature of each zone of the coal pile under each acquisition perspective as the average internal temperature of each zone of the coal pile in the coal yard.

[0063] Specifically, the results obtained from different acquisition perspectives are fused, the highest temperature is taken as the maximum value, and the average temperature is taken as the area (length) weighted average. Optionally, it is determined whether there is any missing data after fusion. If the missing data is located inside the coal yard, it is filled by linear interpolation using the nearest data on both sides. If the missing data is located at both ends of the coal yard, it is filled by equal value using the nearest neighbor data.

[0064] In one possible implementation, the dual-spectrum-based intelligent monitoring method for coal pile temperature further includes: visually displaying environmental data of the coal yard and visible light and infrared images from several acquisition perspectives; visually displaying the coal pile area identification results from each acquisition perspective of the coal yard; and visually displaying the surface temperature of each zone of the coal pile, the internal temperature of each zone of the coal pile, and the internal temperature of each zone of the coal pile from each acquisition perspective of the coal yard.

[0065] Specifically, the internal temperature of each coal pile in each zone is displayed in real time on the 3D visualization page of the coal yard, showing users the internal temperature distribution of the coal pile and the relative locations of dangerous points. A cube can be used to abstractly represent the coal storage in the coal yard, with its height indicating the coal storage height and quantity in a specific zone of a strip coal yard. A scale axis is used to represent the internal temperature of the coal pile along the long side of the coal yard, and a high-temperature icon can be displayed when the internal temperature is abnormal.

[0066] In one possible implementation, the dual-spectrum-based intelligent monitoring method for coal pile temperature further includes: based on the internal temperature of each zone of the coal pile in the coal yard, when the internal temperature of the current zone of the coal pile exceeds a preset temperature warning threshold, generating a graded warning information for the current zone by combining preset graded warning judgment indicators.

[0067] In this embodiment, coal spontaneous combustion early warning is divided into five levels: green, blue, yellow, orange, and red. The criteria for a green warning are: the highest temperature inside the coal pile exceeding 70°C for three consecutive days; for a blue warning, exceeding 90°C for three consecutive days; for a yellow warning, exceeding 130°C for three consecutive days; for an orange warning, exceeding 170°C for three consecutive days; and for a red warning, exceeding 210°C and detecting open smoke and flames on site.

[0068] The following are embodiments of the apparatus of the present invention, which can be used to execute embodiments of the method of the present invention. For details not disclosed in the apparatus embodiments, please refer to the embodiments of the method of the present invention.

[0069] See Figure 2 In another embodiment of the present invention, a dual-spectrum intelligent monitoring system for coal pile temperature is provided, which can be used to implement the above-mentioned dual-spectrum intelligent monitoring method for coal pile temperature. Specifically, the dual-spectrum intelligent monitoring system for coal pile temperature includes a data acquisition module, an identification module, a surface temperature determination module, and an internal temperature determination module.

[0070] The data acquisition module is used to acquire environmental data, zoning information, and visible light and infrared images from several acquisition perspectives of the coal yard. The identification module is used to obtain the coal pile area identification results from each acquisition perspective of the coal yard based on the visible light and infrared images from each acquisition perspective of the coal yard, through a preset coal pile identification semantic segmentation model. The surface temperature determination module is used to obtain the surface temperature of each zone of the coal pile from each acquisition perspective of the coal yard based on the zoning information of the coal yard, the coal pile area identification results from each acquisition perspective, and the infrared images. The internal temperature determination module is used to obtain the internal temperature of each zone of the coal pile from each acquisition perspective of the coal yard based on the environmental data of the coal yard and the surface temperature of each zone of the coal pile from each acquisition perspective, through a preset internal and external temperature relationship fitting function of the coal pile, and integrate them to obtain the internal temperature of each zone of the coal pile in the coal yard.

[0071] In one possible implementation, the environmental data includes one or more of the following: ambient temperature, wind speed, and air humidity.

[0072] In one possible implementation, obtaining the surface temperature of each coal pile in each acquisition view from the coal yard based on the coal yard's zoning information, the coal pile area identification results from each acquisition view, and the infrared image includes: marking the coal yard zoning identification results on the visible light and infrared images from each acquisition view of the coal yard based on the coal yard's zoning information to obtain the coal yard zoning identification results from each acquisition view; obtaining the thermal imaging temperature data from each acquisition view of the coal yard based on the infrared images from each acquisition view; and performing Boolean operations based on the coal pile area identification results, coal yard zoning identification results, and thermal imaging temperature data from each acquisition view of the coal yard to obtain the surface temperature of each coal pile in each acquisition view of the coal yard.

[0073] In one possible implementation, the fitting function for the internal and external temperature relationship of the coal pile is obtained as follows: historical surface temperature data, historical internal temperature data, and historical environmental data of the coal pile are acquired; based on the historical surface temperature data, historical internal temperature data, and historical environmental data of the coal pile, one or more of the following models are used: a regression model based on a recurrent neural network, a time series prediction model, and a segmented linear regression model to fit the relationship between the coal pile surface temperature and environmental data and the internal temperature of the coal pile, and the model with the best fitting result is used as the preset fitting function for the internal and external temperature relationship of the coal pile.

[0074] In one possible implementation, the internal temperature includes the highest internal temperature and the average internal temperature; obtaining and integrating the internal temperatures of each zone of the coal pile under each acquisition perspective to obtain the internal temperature of each zone of the coal pile includes: taking the highest internal temperature of each zone of the coal pile under each acquisition perspective as the highest internal temperature of each zone of the coal pile in the coal yard; and taking the area-weighted average of the average internal temperature of each zone of the coal pile under each acquisition perspective as the average internal temperature of each zone of the coal pile in the coal yard.

[0075] In one possible implementation, it further includes: visually displaying environmental data of the coal yard and visible light and infrared images from several acquisition perspectives; visually displaying the coal pile area identification results from each acquisition perspective of the coal yard; visually displaying the surface temperature of each zone of the coal pile, the internal temperature of each zone of the coal pile, and the internal temperature of each zone of the coal pile from each acquisition perspective of the coal yard.

[0076] In one possible implementation, the method further includes: based on the internal temperature of the coal piles in each zone of the coal yard, when the internal temperature of the coal pile in the current zone is greater than a preset temperature warning threshold, generating a graded warning information for the current zone by combining preset graded warning judgment indicators.

[0077] All relevant content of each step involved in the aforementioned embodiments of the intelligent monitoring method for coal pile temperature based on dual spectrum can be referred to the functional description of the corresponding functional module of the intelligent monitoring system for coal pile temperature based on dual spectrum in the embodiments of the present invention, and will not be repeated here.

[0078] The module division in this embodiment of the invention is illustrative and represents only one logical functional division. In actual implementation, other division methods may be used. Furthermore, the functional modules in the various embodiments of the invention can be integrated into a single processor, exist as separate physical entities, or be integrated into a single module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0079] In another embodiment of the present invention, a computer device is provided, comprising a processor and a memory. The memory stores a computer program, which includes program instructions. The processor executes the program instructions stored in the computer storage medium. The processor may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing and control core of the terminal, suitable for implementing one or more instructions, specifically suitable for loading and executing one or more instructions in the computer storage medium to achieve a corresponding method flow or corresponding function. The processor described in this embodiment of the present invention can be used for the operation of a dual-spectrum intelligent monitoring method for coal pile temperature.

[0080] In another embodiment of the present invention, a storage medium is provided, specifically a computer-readable storage medium (Memory), which is a memory device in a computer device used to store programs and data. It is understood that the computer-readable storage medium here can include both the built-in storage medium in the computer device and extended storage media supported by the computer device. The computer-readable storage medium provides storage space that stores the terminal's operating system. Furthermore, the storage space also stores one or more instructions suitable for loading and execution by a processor. These instructions can be one or more computer programs (including program code). It should be noted that the computer-readable storage medium here can be a high-speed RAM memory or a non-volatile memory, such as at least one disk storage device. The processor can load and execute one or more instructions stored in the computer-readable storage medium to implement the corresponding steps of the dual-spectrum intelligent monitoring method for coal pile temperature in the above embodiments.

[0081] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0082] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0083] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0084] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0085] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for intelligent monitoring of coal pile temperature based on dual spectra, characterized in that, include: Acquire environmental data, zoning information, and visible light and infrared images from several acquisition angles of the coal yard; Based on visible light and infrared images from various acquisition perspectives in the coal yard, a pre-defined coal pile recognition semantic segmentation model is used to obtain the coal pile area recognition results from each acquisition perspective. Specifically, visible light and infrared images are received at a fixed frame rate. During the day, the visible light image is used as the basis, and at night, the infrared image is used as the basis to perform edge detection on the images, judging the similarity of the edges between the preceding and following images. When the similarity exceeds a threshold, the coal pile recognition semantic segmentation model is triggered. In constructing the coal pile recognition semantic segmentation model, the frame rate of the visible light image and the frame rate of the infrared image are adjusted to be an integer multiple, and visible light and infrared images from the same time period are extracted as samples. Based on the coal yard's zoning information, coal pile area identification results from each acquisition perspective, and infrared images, the surface temperature of the coal pile in each zone under each acquisition perspective is obtained. This includes: marking the coal yard zoning identification results on the visible light and infrared images of the coal yard from each acquisition perspective, thus obtaining the coal yard zoning identification results from each acquisition perspective; obtaining the thermal imaging temperature data of the coal yard from each acquisition perspective based on the infrared images of the coal yard from each acquisition perspective; and performing Boolean operations on the coal pile area identification results, coal yard zoning identification results, and thermal imaging temperature data from each acquisition perspective to obtain the surface temperature of the coal pile in each zone under each acquisition perspective. Based on the environmental data of the coal yard and the surface temperature of the coal piles in each zone from each collection perspective, the internal temperature of the coal piles in each zone from each collection perspective is obtained and integrated through a preset fitting function for the relationship between the internal and external temperatures of the coal piles, thus obtaining the internal temperature of the coal piles in each zone of the coal yard. The fitting function for the temperature relationship between the inside and outside of the coal pile was obtained in the following way: Acquire historical surface temperature data, historical internal temperature data, and historical environmental data of the coal pile; Based on historical surface temperature data, historical internal temperature data, and historical environmental data of the coal pile, one or more of the following models are used: a regression model based on a recurrent neural network, a time series prediction model, and a segmented linear regression model to fit the relationship between the surface temperature and environmental data of the coal pile and the internal temperature of the coal pile. The model with the best fitting result is used as the preset fitting function for the relationship between the internal and external temperatures of the coal pile.

2. The intelligent coal pile temperature monitoring method based on dual spectrum according to claim 1, characterized in that, The environmental data includes one or more of the following: ambient temperature, wind speed, and air humidity.

3. The intelligent coal pile temperature monitoring method based on dual spectrum according to claim 1, characterized in that, The internal temperature includes the highest internal temperature and the average internal temperature; The internal temperatures of each zone of the coal pile obtained from various acquisition perspectives in the coal yard are obtained and integrated to obtain the internal temperatures of each zone of the coal pile in the coal yard, including: The highest internal temperature of each zone of the coal pile under each collection angle in the coal yard is taken as the highest internal temperature of each zone of the coal pile in the coal yard. The average internal temperature of each zone of the coal pile under each collection perspective is taken as the area-weighted average and then used as the average internal temperature of each zone of the coal pile in the coal yard.

4. The intelligent monitoring method for coal pile temperature based on dual spectrum according to claim 1, characterized in that, Also includes: The system visualizes environmental data from the coal yard, as well as visible light and infrared images from several acquisition perspectives. Visualize the coal pile area identification results from various acquisition perspectives in the coal yard; The system visualizes the surface temperature of coal piles in each zone from various acquisition perspectives, the internal temperature of coal piles in each zone from various acquisition perspectives, and the internal temperature of coal piles in each zone of the coal yard.

5. The intelligent monitoring method for coal pile temperature based on dual spectrum according to claim 1, characterized in that, Also includes: Based on the internal temperature of the coal piles in each zone of the coal yard, when the internal temperature of the coal pile in the current zone exceeds the preset temperature warning threshold, the preset graded warning judgment indicators are combined to generate graded warning information for the current zone.

6. A dual-spectrum intelligent monitoring system for coal pile temperature, characterized in that, include: The data acquisition module is used to acquire environmental data, zoning information, and visible light and infrared images from several acquisition angles of the coal yard. The recognition module is used to obtain the coal pile area recognition results from various acquisition perspectives of the coal yard based on visible light and infrared images from different acquisition perspectives, using a preset coal pile recognition semantic segmentation model. Specifically, it receives visible light and infrared images at a fixed frame rate. During the day, it uses the visible light image as the basis, and at night, it uses the infrared image as the basis to perform edge detection on the images, judging the similarity of the edges between the previous and subsequent images. When the similarity exceeds a threshold, it triggers the coal pile recognition semantic segmentation model. In the process of constructing the coal pile recognition semantic segmentation model, the frame rate of the visible light image and the frame rate of the infrared image are adjusted to be an integer multiple, and visible light and infrared images from the same time are extracted as samples. The surface temperature determination module is used to obtain the surface temperature of each coal pile in each acquisition view from the coal yard based on the coal yard zoning information, the coal pile area identification results from each acquisition view, and infrared images. This includes: marking the coal yard zoning identification results on the visible light and infrared images from each acquisition view of the coal yard based on the coal yard zoning information, thus obtaining the coal yard zoning identification results from each acquisition view; obtaining the thermal imaging temperature data from each acquisition view of the coal yard based on the infrared images from each acquisition view; and performing Boolean operations based on the coal pile area identification results, coal yard zoning identification results, and thermal imaging temperature data from each acquisition view of the coal yard to obtain the surface temperature of each coal pile in each acquisition view. The internal temperature determination module is used to obtain the internal temperature of each zone of the coal pile under each acquisition perspective based on the environmental data of the coal yard and the surface temperature of each zone of the coal pile from each acquisition perspective. It uses a preset fitting function for the internal and external temperature relationship of the coal pile to obtain the internal temperature of each zone of the coal pile in the coal yard. The fitting function for the temperature relationship between the inside and outside of the coal pile was obtained in the following way: Acquire historical surface temperature data, historical internal temperature data, and historical environmental data of the coal pile; Based on historical surface temperature data, historical internal temperature data, and historical environmental data of the coal pile, one or more of the following models are used: a regression model based on a recurrent neural network, a time series prediction model, and a segmented linear regression model to fit the relationship between the surface temperature and environmental data of the coal pile and the internal temperature of the coal pile. The model with the best fitting result is used as the preset fitting function for the relationship between the internal and external temperatures of the coal pile.

7. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the intelligent monitoring method for coal pile temperature based on dual spectrum as described in any one of claims 1 to 5.

8. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the intelligent monitoring method for coal pile temperature based on dual spectrum as described in any one of claims 1 to 5.

Images