Fire operation violation recognition and judgment method based on machine vision

Abstract

The invention discloses a method for identifying and judging violation of fire operation based on machine vision, which belongs to the technical field of fire operation identification, and specifically comprises the following steps: acquiring infrared thermal imaging data and optical image data of a fire operation area, and obtaining surface temperature distribution and outline of a fire tool; for the infrared thermal imaging data, extracting temperature gradient change characteristics of a heating area of the fire tool, and generating a dynamic deformation track model according to the temperature gradient change characteristics; for the optical image data, through contour difference analysis between continuous frames, extracting the contour offset of the hot tool after thermal deformation, and establishing a corresponding relation on a time sequence with the dynamic deformation track model; when the corresponding relation between the outline offset of the fire operation tool and the temperature gradient change characteristics of the fire operation tool deviates from a preset correlation threshold range, judging that the operation is illegal operation; according to the invention, the capability of judging complex violation behaviors is enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of hot work identification, and in particular to a method for identifying and determining hot work violations based on machine vision. Background Art

[0002] Hot work (such as welding, cutting, and spraying) is a common high-risk operation in industrial production. Improper operation or tool malfunction can lead to fires, explosions, and other safety incidents. Traditional safety monitoring relies primarily on manual inspections or simple temperature monitoring, making it difficult to identify violations in real time, especially abnormal conditions caused by hot work tools deforming due to heat. With the advancement of machine vision technology, intelligent monitoring systems based on image analysis are gradually being applied to hot work scenarios. However, due to the deformation characteristics of hot work tools at high temperatures, conventional vision algorithms are prone to misjudgment due to changes in tool shape, necessitating more accurate identification methods.

[0003] Currently, machine vision monitoring for hot work primarily relies on optical cameras or infrared thermal imaging devices working independently. For example, some solutions analyze the contour changes of welding guns or welding rods through optical images, combining them with preset shape template matching to determine tool status. Others rely solely on infrared thermal imaging data, using temperature thresholds to determine whether there is an overheating risk. Furthermore, a few studies have attempted to integrate optical and infrared data for comprehensive monitoring of hot work.

[0004] However, existing visual monitoring of hot work ignores the interference of thermal deformation on visual recognition. When hot work tools (such as welding rods and spray guns) expand and bend under high temperatures, the contours in the optical image differ greatly from the standard template, and traditional shape matching algorithms are prone to failure. Summary of the Invention

[0005] The purpose of the present invention is to provide a method for identifying and judging violations of hot work based on machine vision to solve the following technical problems: When hot work tools are exposed to high temperatures, they will expand, bend, and undergo other deformations, causing the contour in the optical image to differ significantly from the standard template, making traditional shape matching algorithms prone to failure.

[0006] The purpose of the present invention can be achieved through the following technical solutions: A method for identifying and determining violations of hot work regulations based on machine vision includes the following steps: Synchronously collect infrared thermal imaging data and optical image data of the hot work area through infrared thermal imaging equipment and optical zoom equipment, where the infrared thermal imaging equipment is used to obtain the surface temperature distribution of the hot work tools, and the optical zoom equipment is used to obtain the outline of the hot work tools; For infrared thermal imaging data, the temperature gradient change characteristics of the hot tool's heated area are extracted, and a dynamic deformation trajectory model is generated based on the temperature gradient change characteristics; For the optical image data, the contour difference between consecutive frames is analyzed to extract the offset of the hot work tool after thermal deformation, and a corresponding relationship in time series is established with the dynamic deformation trajectory model; When the correspondence between the offset of the outer contour of the hot work tool and its temperature gradient change characteristics deviates from the preset correlation threshold range, it is determined to be an illegal operation.

[0007] As a further solution of the present invention: the generation process of the dynamic deformation trajectory model is: Based on the temperature change rate of different areas on the surface of the hot tool in the infrared thermal imaging data, the areas where the temperature rise rate exceeds the preset critical value are marked as highly active hot zones. Based on the temperature diffusion direction of the highly active hot zones, the extension path of the hot tool's thermal deformation is simulated to generate a three-dimensional trajectory model including the time dimension.

[0008] As a further solution of the present invention: the specific method of establishing the corresponding relationship is: The offset direction of the hot tool's contour in the optical image is vector-superimposed with the temperature diffusion direction of the highly active hot zone in the dynamic deformation trajectory model. When the angle between the two directions is less than a preset angle, it is determined to be normal thermal deformation; when the angle exceeds the preset angle or the offset direction is opposite to the temperature diffusion direction, it is determined to be abnormal deformation.

[0009] As a further solution of the present invention: the determination of abnormal deformation further includes: A time series analysis is performed on the offset of the hot tool's contour. If the offset shows a non-monotonic increase or a sudden change within a continuous time window, and is accompanied by a step-like fluctuation in the temperature diffusion rate of the highly active hot zone, it is determined to be an illegal operation.

[0010] As a further solution of the present invention: the processing of the optical image data includes: The three-dimensional contour of the hot work tool after heat deformation is reconstructed to generate a three-dimensional model that includes the curvature changes of the tool surface. The three-dimensional model is spatially compared with the standard model in the unheated state, and the local areas where the curvature difference exceeds the preset threshold are extracted as abnormal deformation areas.

[0011] As a further solution of the present invention: spatially project and match the curvature change trend of the abnormal deformation area with the temperature diffusion path in the dynamic deformation trajectory model. If the overlap between the area with the largest curvature change and the end position of the temperature diffusion path is lower than a preset ratio, it is determined to be an illegal operation.

[0012] As a further solution of the present invention: if an abnormal temperature rise is detected in the non-working area of ​​the hot work tool in the infrared thermal imaging data, and the temperature rise area simultaneously shows unexpected deformation in the optical image, and the deformation direction forms a spatial conflict with the force direction of the tool during normal operation, it is determined to be an illegal operation.

[0013] As a further solution of the present invention: for different types of hot work tools, a standard database of their heat deformation trajectories is pre-established, including the axial linear expansion trajectory model of the welding rod and the radial radial deformation trajectory model of the spray gun; in actual detection, the real-time generated dynamic deformation trajectory model is pattern matched with the standard database, and if the matching degree is lower than the preset threshold, a violation alarm is triggered.

[0014] Beneficial effects of the present invention: The present invention solves the problem in the prior art of failure of image recognition algorithms due to thermal deformation of hot work tools through synchronous data collection of infrared thermal imaging equipment and optical zoom equipment. The construction of the dynamic deformation trajectory model can accurately reflect the correlation between the temperature gradient change and the deformation trend of the tool after heating. By performing vector superposition analysis on the contour offset and the temperature diffusion direction, it can effectively distinguish between normal thermal deformation and abnormal deformation caused by illegal operation, overcoming the limitations of traditional static image matching algorithms. At the same time, a standard database pre-established for different hot work tools enables the system to adapt to differentiated characteristics such as the axial linear expansion of welding rods and the radial radial deformation of spray guns, greatly improving the recognition accuracy. By analyzing the spatial projection matching relationship between the abnormal deformation area and the temperature diffusion path through time series, the ability to judge complex illegal behaviors is further enhanced, and finally high-precision intelligent recognition of illegal behaviors in hot work operations is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The present invention will be further described below with reference to the accompanying drawings.

[0016] Figure 1 It is a schematic flow diagram of the present invention. DETAILED DESCRIPTION

[0017] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative efforts shall fall within the scope of protection of the present invention.

[0018] See also Figure 1 As shown, the present invention is a method for identifying and judging violations of hot work based on machine vision, comprising the following steps: Data collection Using infrared thermal imaging equipment and optical zoom equipment, data collection is performed simultaneously in hot work areas. The infrared thermal imaging equipment focuses on capturing the temperature distribution on the surface of hot work tools. For example, during normal welding, the temperature distribution of the soldering iron tip is uniform and maintained within a specific temperature range. However, if improper operations such as prolonged welding or excessive current are observed, the tip temperature rises sharply, and the temperature distribution becomes uneven. The optical zoom equipment is responsible for providing clear images and accurately capturing the contours of the hot work tools, providing the basic data for subsequent analysis of these contour changes. Infrared thermal imaging data processing The key to capturing infrared thermal imaging data is extracting the temperature gradient characteristics of the hot tool's heated area. These characteristics provide a visual representation of the rate of temperature change over time and space. During normal operation, the temperature gradient in the hot tool's heated area changes gently and follows specific patterns. For example, in a gas cutting torch, during normal gas cutting operation, the temperature near the flame nozzle rises rapidly. As the distance from the nozzle increases, the temperature gradually decreases, and the rate of cooling remains relatively stable. Based on the analysis of these temperature gradient characteristics, a dynamic deformation trajectory model is generated. This model, using time as a dimension, displays the temperature change trends and corresponding deformation trajectories of the hot tool's heated area at different times. Optical image data processing When processing optical image data, a contour difference analysis method between consecutive frames is used. During hot work, changes in tool heating and operating conditions will cause changes in the contour. By comparing consecutive frames of optical images, the contour offset of the hot work tool after heat deformation can be accurately extracted. For example, in the heating and bending operation of metal sheets, as the heating time increases, the contour of the metal sheet gradually changes. By analyzing the contour differences of the metal sheet in consecutive frame images, the contour offset can be obtained. Subsequently, a time series correspondence is established between the contour offset and the previously generated dynamic deformation trajectory model, thereby comprehensively and dynamically monitoring the operating status of the hot work tool from two dimensions: temperature change and contour change.

[0019] Violation determination Based on the established correspondence, reasonable judgment rules are set. The preset correlation threshold range is derived from a large amount of experimental data and actual production experience. For example, multiple simulations of normal welding operations are conducted to statistically analyze the correspondence between the contour offset and temperature gradient change characteristics of the welding tool during normal operation, thereby setting a reasonable threshold range. If the actual operation monitoring data exceeds the threshold range, such as when the welding current is too high, causing the welding tool to overheat and deform beyond the normal range, it is judged as an illegal operation.

[0020] In a preferred embodiment of the present invention, the generation process of the dynamic deformation trajectory model is: First, an in-depth analysis of infrared thermal imaging data was conducted. During hot work, significant differences were observed in the temperature changes in different areas of the hot tool surface. Accurate calculation of the rate of temperature change allowed the thermal activity of each area to be clearly determined. Areas where the rate of temperature rise exceeded a pre-set critical value were marked as highly active hot zones. For example, during arc welding, the area where the electrode contacts the workpiece experiences an extremely rapid temperature rise rate due to the instantaneous generation of a large amount of heat, often far exceeding the pre-set critical value, and thus being identified as a highly active hot zone. After identifying the highly active hot zone, its temperature diffusion direction serves as a key benchmark. This temperature diffusion direction reflects the path of heat transfer across the hot tool surface, which is crucial for simulating the path of tool deformation caused by heat. Using specialized algorithms and data analysis methods, the potential deformation path of the tool is simulated along this temperature diffusion direction. Furthermore, the time dimension is incorporated to integrate the temperature diffusion of the highly active hot zone at different moments and the corresponding deformation extension path, ultimately generating a three-dimensional trajectory model that includes the time dimension. This model intuitively and dynamically displays the temperature diffusion and deformation extension of the highly active hot zone over time during the hot tool heating process, providing a key reference for subsequent analysis.

[0021] In another preferred embodiment of the present invention, the specific method of establishing the corresponding relationship is: In optical images, hot-fire tools exhibit deflection due to heat and operating conditions. Simultaneously, dynamic deformation trajectory models reveal specific temperature diffusion directions in highly active hot zones. Vectorial overlay analysis of these two features provides a deeper understanding of the tool's deformation state. During specific operations, a preset angle is used as a judgment benchmark. When the offset direction of the hot tool's contour in the optical image is vector-superimposed with the temperature diffusion direction of the highly active hot zone in the dynamic deformation trajectory model, if the angle between the two directions is less than the preset angle, it indicates that the tool deformation and temperature diffusion show a synergistic relationship that conforms to normal operating rules, and it can be determined to be normal thermal deformation. For example, in gas welding operations, the flame continuously heats the weldment, and the weldment's contour gradually shifts in the direction of the flame's temperature diffusion. The angle between the offset direction and the temperature diffusion direction is small. This situation is considered normal thermal deformation. Conversely, when the angle exceeds the preset value, or the deflection direction of the contour is completely opposite to the direction of temperature diffusion, it means that the tool deformation has deviated from the normal thermal deformation pattern and is considered abnormal deformation. For example, in the case of local overheating caused by improper operation, the contour of a part of the tool may suddenly deviate in the direction opposite to the temperature diffusion direction, which is considered abnormal deformation.

[0022] In a preferred embodiment of the present invention, the determination of abnormal deformation further includes: The determination of abnormal deformation has been further refined. In addition to considering the relationship between the direction of contour offset and the direction of temperature diffusion, a time series analysis of the hot work tool contour offset is also performed. By collecting and analyzing offset data within a continuous time window, its changing trends are observed. Under normal circumstances, within a continuous time window, if hot work is operating normally, the offset of the tool profile will exhibit relatively stable changes over time. For example, during the heating process of metal forging, the offset of the metal blank's profile will slowly and monotonically increase with increasing heating time. However, when irregular operation occurs, the situation is quite different. If the offset exhibits a non-monotonically increasing trend within a continuous time window, such as fluctuating, sometimes increasing and sometimes decreasing, or undergoes a sudden, large offset, and simultaneously experiences a step-like fluctuation in the temperature diffusion rate in the highly active hot zone—a sudden, rapid increase or decrease in the temperature diffusion rate—then this complex dynamics collectively indicate an abnormality in the hot work process, leading to a determination of irregular operation. For example, when using thermal cutting equipment, if the operator improperly adjusts the cutting parameters, this can cause a sharp temperature fluctuation in the cutting area and an abnormal change in the profile offset of the material being cut. In such cases, this comprehensive identification method can accurately identify irregular operation.

[0023] In another preferred embodiment of the present invention, the processing of the optical image data includes: First, 3D reconstruction technology is used to reconstruct the contours of hot-work tools after they are deformed by heat. This process integrates and calculates multi-view optical image data to generate a three-dimensional model that accurately reflects the changes in the tool's surface curvature. For example, in the hot forging process of metalworking, the high temperature causes the shape of the metal workpiece to change, and the curvature of various parts of its surface also changes accordingly. 3D reconstruction technology can clearly show these changes. After the 3D model is generated, it is spatially compared with a standard model of the hot work tool in its unheated state. The standard model records the precise shape and surface features of the tool under normal, unheated conditions. Using a specialized spatial comparison algorithm, the corresponding parts of the two models are meticulously compared, focusing on extracting localized regions where the curvature difference exceeds a pre-set threshold. These regions are identified as areas of abnormal deformation. For example, a soldering iron tip maintains a relatively stable shape and surface curvature during normal use. However, if abnormal heating occurs, the curvature of certain areas of the tip may change significantly. By comparing the standard model, these abnormal regions can be quickly identified.

[0024] In a preferred embodiment of this embodiment, the curvature trend of the abnormally deformed area is spatially projected and matched with the temperature diffusion path in the dynamic deformation trajectory model. First, the curvature change of the abnormally deformed area is thoroughly analyzed to identify the area with the largest curvature change. This area is often where the tool is most significantly deformed due to heat. Simultaneously, the end of the temperature diffusion path is clearly defined in the dynamic deformation trajectory model. The end of the temperature diffusion path typically reflects the point at which heat transfer reaches the edge of the tool or the boundary of the affected area. Subsequently, a spatial projection matching operation is performed, projecting the area with the largest curvature change in the abnormal deformation region into the space constructed by the dynamic deformation trajectory model and comparing it with the position of the end of the temperature diffusion path. If the overlap between the two is less than a pre-set ratio, it means that there is a significant deviation between the location of the abnormal deformation region and the expected range of temperature diffusion. For example, during flame cutting, if the overlap between the abnormal deformation location in the cutting area and the end of the flame temperature diffusion path is low, it indicates that the cutting process may have been interfered with by abnormal factors, and the operation can be judged as illegal.

[0025] In another preferred embodiment of the present invention, during the analysis of infrared thermal imaging data, emphasis is placed on detecting abnormal temperature rises in the non-working area of ​​the hot tool. The non-working area generally refers to the portion of the hot tool that is not directly involved in heat generation or transfer, such as the outer casing of welding equipment. If an abnormal temperature rise is detected in the non-working area, further analysis is performed in conjunction with the optical image data. If unexpected deformation is observed in the optical image of the temperature-rising area, and the direction of this deformation conflicts with the direction of force applied during normal operation of the tool, it can be identified as an illegal operation. For example, when using an electric grinder, the grinding head generates heat during normal operation, and the force applied is clearly directed. If an abnormal temperature rise suddenly occurs in a certain area of ​​the grinder housing, and the optical image shows deformation in this area that is inconsistent with the normal force applied during normal operation, this is likely due to improper operation, such as excessive squeezing or collision, and the system will identify it as an illegal operation.

[0026] In another preferred embodiment of the present invention, a recognition strategy based on standard database matching is employed for different types of hot work tools. During the preliminary preparation phase, a standard database of heat deformation trajectories for various hot work tools was established through extensive experimentation and data collection. For example, a welding rod, a slender hot work tool, primarily exhibits axial linear expansion upon heating, and a model for its axial linear expansion trajectory was established based on this. Similarly, when a spray gun is in operation, heat is transferred radially from the nozzle, and a model for its radial deformation trajectory was constructed. During the actual inspection process, the system generates a dynamic deformation trajectory model of the hot work tool in real time and then matches it with the corresponding model in the standard database. Using a precise algorithm, the system calculates the degree of match between the two. If the match falls below a pre-set threshold, it indicates that the current hot work tool's thermal deformation trajectory differs significantly from the standard, suggesting a possible violation of regulations. The system will then trigger a violation alarm. For example, in actual welding operations, if the real-time deformation trajectory of the welding rod does not match the axial linear expansion trajectory model in the standard database, this may indicate improper settings of parameters such as welding current and voltage, resulting in abnormal heating of the welding rod. The system will then promptly issue an alarm to alert the operator.

[0027] The above is a detailed description of an embodiment of the present invention. However, the content described is only a preferred embodiment of the present invention and should not be considered to limit the scope of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A method for identifying and judging violations of hot work based on machine vision, characterized in that: The following steps are involved: Synchronously collect infrared thermal imaging data and optical image data of the hot work area through infrared thermal imaging equipment and optical zoom equipment, where the infrared thermal imaging equipment is used to obtain the surface temperature distribution of the hot work tools, and the optical zoom equipment is used to obtain the outline of the hot work tools; For infrared thermal imaging data, the temperature gradient change characteristics of the hot tool's heated area are extracted, and a dynamic deformation trajectory model is generated based on the temperature gradient change characteristics; For the optical image data, the contour difference between consecutive frames is analyzed to extract the offset of the hot work tool after thermal deformation, and a corresponding relationship in time series is established with the dynamic deformation trajectory model; When the correspondence between the offset of the outer contour of the hot work tool and its temperature gradient change characteristics deviates from the preset correlation threshold range, it is determined to be an illegal operation.

2. The method for identifying and determining violations of hot work based on machine vision according to claim 1 is characterized in that: The generation process of the dynamic deformation trajectory model is as follows: Based on the temperature change rate of different areas on the surface of the hot tool in the infrared thermal imaging data, the areas where the temperature rise rate exceeds the preset critical value are marked as highly active hot zones. Based on the temperature diffusion direction of the highly active hot zones, the extension path of the hot tool's thermal deformation is simulated to generate a three-dimensional trajectory model including the time dimension.

3. The method for identifying and determining violations of hot work based on machine vision according to claim 1, characterized in that: The specific method of establishing the corresponding relationship is: The offset direction of the hot tool's contour in the optical image is vector-superimposed with the temperature diffusion direction of the highly active hot zone in the dynamic deformation trajectory model. When the angle between the two directions is less than a preset angle, it is determined to be normal thermal deformation. When the direction angle exceeds the preset angle or the offset direction is opposite to the temperature diffusion direction, it is determined to be abnormal deformation.

4. The method for identifying and determining violations of hot work based on machine vision according to claim 3 is characterized in that: The determination of abnormal deformation further includes: A time series analysis is performed on the offset of the hot tool's contour. If the offset shows a non-monotonic increase or a sudden change within a continuous time window, and is accompanied by a step-like fluctuation in the temperature diffusion rate of the highly active hot zone, it is determined to be an illegal operation.

5. The method for identifying and judging violations of hot work based on machine vision according to claim 1 is characterized in that: The processing of the optical image data includes: The three-dimensional contour of the hot work tool after heat deformation is reconstructed to generate a three-dimensional model that includes the curvature changes of the tool surface. The three-dimensional model is spatially compared with the standard model in the unheated state, and the local areas where the curvature difference exceeds the preset threshold are extracted as abnormal deformation areas.

6. The method for identifying and determining violations of hot work based on machine vision according to claim 5 is characterized in that: The curvature change trend of the abnormal deformation area is spatially projected and matched with the temperature diffusion path in the dynamic deformation trajectory model. If the overlap between the area with the largest curvature change and the end position of the temperature diffusion path is lower than the preset ratio, it is judged as an illegal operation.

7. The method for identifying and determining violations of hot work based on machine vision according to claim 1, characterized in that: If an abnormal temperature rise is detected in the non-working area of ​​the hot work tool in the infrared thermal imaging data, and the temperature rise area simultaneously shows unexpected deformation in the optical image, and the deformation direction forms a spatial conflict with the force direction of the tool during normal operation, it is judged as an illegal operation.

8. The method for identifying and judging violations of hot work based on machine vision according to claim 1, characterized in that: For different types of hot work tools, a standard database of their heat deformation trajectories is pre-established, including the axial linear expansion trajectory model of the welding rod and the radial deformation trajectory model of the spray gun. In actual testing, the real-time generated dynamic deformation trajectory model is matched with the standard database. If the matching degree is lower than the preset threshold, a violation alarm is triggered.

Images