Safety detection method, medium, equipment and safety detection system of press machine

Abstract

The invention relates to the technical field of press machines, in particular to a safety detection method, a medium, equipment and a safety detection system of a press machine. The safety detection system aims at solving the problem that safety measures of an existing safety detection system of the press machine are low in effectiveness. In order to achieve the purpose, the safety detection method comprises the steps that in response to a starting signal of the press machine, visual information and human body sensing information are obtained; based on the visual information and the human body sensing information, whether a human body exists in the working area of the press is judged; and based on the two judgment results, selectively controlling the press machine to keep still or carry out pressing operation. In this way, when the press machine is started, whether the human body exists in the working area of the press machine or not can be judged in advance, and therefore safety risks are avoided. Moreover, according to the method, the safety protection level of the press machine is improved from administrative control to engineering control, the effectiveness of safety measures is improved, and safety risks caused by management defects are eliminated.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of press machine, in particular to a safety detection method, medium, device and safety detection system of press machine. BACKGROUND

[0002] In the automatic production workshop of vehicles, the press machine can make the flat material into various complex-shaped vehicle body parts in the mold through a huge pressure. In this process, safety risks are prone to occur due to fatigue operation, accidental touch, improper management and other problems.

[0003] The safety measures of the existing press machine almost all rely on safety grating and manual padlock to prevent the press machine from pressing and injuring personnel. However, the grating can reset after the personnel pass through, so it cannot determine whether there is personnel inside when the press machine is running. When the manual padlock is used, there are risks such as forgetting to hang the padlock, missing detection, violating shielding, and others mistakenly operating the press machine.

[0004] Correspondingly, there is a need in the art for a new technical solution to solve the above problems. SUMMARY

[0005] In order to solve at least one of the above problems in the prior art, that is, to solve the problem of low effectiveness of the safety measures of the existing safety detection system of the press machine, the present application provides a safety detection method for the safety detection system of the press machine, the safety detection method comprising:

[0006] In response to a start signal of the press machine, acquiring visual information and human body sensing information;

[0007] Based on the visual information and the human body sensing information respectively, determining whether there is a human body in the working area of the press machine;

[0008] Based on the two determination results, selectively controlling the press machine to remain stationary or to perform a pressing operation.

[0009] In the case of adopting the above technical solution, when the press machine starts, it can be determined in advance whether there is a human body in the working area of the press machine, thereby avoiding safety risks. Moreover, this method improves the safety protection level of the press machine from administrative control to engineering control, improves the effectiveness of safety measures, and eliminates safety risks caused by management defects such as non-standard operation of employees.

[0010] In the preferred technical solution of the above safety detection method, the selectively controlling the press machine to remain stationary or to perform a pressing operation based on the two determination results further comprises:

[0011] When both judgment results are that no human body exists in the working area, the press is controlled to perform a pressing operation; otherwise, the press is controlled to remain stationary.

[0012] In the technical solution, the redundant safety measures combining visual detection and human body sensing can completely eliminate the safety risks caused by management defects such as non-standard operation of the press by employees.

[0013] In the preferred technical solution of the safety detection method, the visual information includes continuous video frames, and the judgment of whether a human body exists in the working area of the press based on the visual information and the human body sensing information respectively further includes:

[0014] judging whether a human body exists in the working area based on the continuous video frames and a region detection model.

[0015] In the preferred technical solution of the safety detection method, the judgment of whether a human body exists in the working area based on the continuous video frames and a region detection model further includes:

[0016] determining whether a human body exists in the working area based on the continuous video frames;

[0017] under the premise that a human body exists, framing the human body and calculating an overlap area ratio of a human body detection frame and the working area;

[0018] judging whether the overlap area ratio is greater than or equal to a preset threshold;

[0019] if yes, it is determined that a human body exists in the working area; otherwise, it is determined that no human body exists in the working area.

[0020] In the preferred technical solution of the safety detection method, the judgment of whether a human body exists in the working area based on the continuous video frames and a region detection model further includes:

[0021] judging whether a human body exists in the working area based on the continuous video frames, an illumination compensation algorithm and the region detection model.

[0022] In the preferred technical solution of the safety detection method, the judgment of whether a human body exists in the working area based on the continuous video frames and a region detection model further includes:

[0023] judging whether a human body exists in the working area based on the continuous video frames, a background model and the region detection model.

[0024] In the preferred technical solution of the safety detection method, the safety detection method further includes:

[0025] Based on the continuous video frames, the background model is updated once every first preset time length.

[0026] In the preferred technical scheme of the safety detection method, the human body sensing information comprises human body infrared information, and the step of judging whether there is a human body in the working area of the press based on the visual information and the human body sensing information respectively further comprises:

[0027] Based on the human body infrared information, it is judged whether there is a human body in the working area.

[0028] In the preferred technical scheme of the safety detection method, the press is provided with a hot infrared human body sensor array, and a detection area formed by the hot infrared human body sensor array can cover the working area, and the step of judging whether there is a human body in the working area based on the human body infrared information further comprises:

[0029] Based on a plurality of the human body infrared information and a topological analysis method, it is judged whether there is a human body in the working area.

[0030] In the preferred technical scheme of the safety detection method, the step of judging whether there is a human body in the working area based on a plurality of the human body infrared information and a topological analysis method further comprises:

[0031] Based on all the trigger signals, signal duration and the topological analysis method of the received hot infrared human body sensors, it is judged whether there is a human body in the working area.

[0032] In the preferred technical scheme of the safety detection method, the signal synchronization error between a plurality of infrared human body sensors in the hot infrared human body sensor array is set to be less than a second preset time length.

[0033] In the preferred technical scheme of the safety detection method, the hot infrared human body sensor is triggered based on the following way:

[0034] In the initial temperature signal sampling period, the temperature signal falling into the first temperature window is calibrated;

[0035] In the secondary temperature signal sampling period, it is judged whether the calibrated temperature signal falls into the second temperature window;

[0036] If yes, the hot infrared human body sensor is triggered.

[0037] In the preferred technical scheme of the safety detection method, the temperature signal is filtered in each temperature signal sampling period.

[0038] In the preferred technical scheme of the safety detection method, the first temperature window is set to 34 DEG C or above, and the second temperature window is set to 33 DEG C to 38 DEG C.

[0039] The application also provides a computer readable storage medium, which stores a plurality of program codes, the program codes being adapted to be loaded and run by a processor to perform the safety detection method according to any one of the preceding.

[0040] The application also provides an electronic device, which comprises a processor and a storage device, the storage device being adapted to store a plurality of program codes, the program codes being adapted to be loaded and run by the processor to perform the safety detection method according to any one of the preceding.

[0041] The application also provides a safety detection system of a press machine, which comprises:

[0042] a vision unit configured to acquire vision information, and a sensing unit configured to acquire sensing information and capable of determining whether a human body exists in a working area of the press machine based on the sensing information;

[0043] an analysis unit configured to receive the vision information output by the vision unit and determine whether a human body exists in the working area of the press machine based on the vision information;

[0044] a control unit configured to receive the determination result output by the analysis unit and the determination result output by the sensing unit and selectively control the press machine to remain stationary or perform a pressing operation based on the two determination results.

[0045] With the above technical scheme, the safety detection system of the press machine can first determine whether a human body exists in the working area of the press machine when the press machine is started, thereby avoiding safety risks. Moreover, the safety protection level of the press machine is improved from administrative control to engineering control, which improves the effectiveness of safety measures and eliminates safety risks caused by non-standard operation of the press machine by employees.

[0046] In the preferred technical scheme of the safety detection system of the press machine, the sensing unit comprises four thermal infrared human body sensors, the four thermal infrared human body sensors are respectively arranged at four corners of the press machine and form a thermal infrared human body sensor array, and a detection area of the thermal infrared human body sensor array can cover the working area of the press machine.

[0047] In the preferred technical scheme of the safety detection system of the press machine, two of the thermal infrared human body sensors are located at one side of the working area and are both at a first height, and the other two thermal infrared human body sensors are located at the other side of the working area and are both at a second height, the first height being greater than the second height.

[0048] The two thermal infrared human body sensors at the first height are vertically downwardly inclined, and the two thermal infrared human body sensors at the second height are vertically upwardly inclined.

[0049] In the preferred technical scheme of the safety detection system of the press machine, the visual unit is a camera, and the camera is arranged at one side of the working area, and the visual area of the camera can cover the working area.

[0050] Scheme 1. A safety detection method for a safety detection system of a press machine, comprising:

[0051] In response to a start signal of the press machine, acquiring visual information and human body sensing information;

[0052] Based on the visual information and the human body sensing information respectively, determining whether there is a human body in the working area of the press machine;

[0053] Based on the two determination results, selectively controlling the press machine to remain stationary or to perform a pressing operation.

[0054] Scheme 2. The safety detection method according to scheme 1, based on the two determination results, selectively controlling the press machine to remain stationary or to perform a pressing operation further comprises:

[0055] When both determination results are that there is no human body in the working area, controlling the press machine to perform a pressing operation; otherwise, controlling the press machine to remain stationary.

[0056] Scheme 3. The safety detection method according to scheme 1, the visual information comprises continuous video frames, and based on the visual information and the human body sensing information respectively, determining whether there is a human body in the working area of the press machine further comprises:

[0057] Based on the continuous video frames and a region detection model, determining whether there is a human body in the working area.

[0058] Scheme 4. The safety detection method according to scheme 3, based on the continuous video frames and a region detection model, determining whether there is a human body in the working area further comprises:

[0059] Based on the continuous video frames, determining whether there is a human body in the working area;

[0060] In the presence of a human body, the human body is framed and the overlap area ratio of the human body detection frame and the working area is calculated;

[0061] It is judged whether the overlap area ratio is greater than or equal to a preset threshold value;

[0062] If yes, it is determined that there is a human body in the working area; otherwise, it is determined that there is no human body in the working area.

[0063] Scheme 5. According to the safety detection method of scheme 3, the method of judging whether there is a human body in the working area based on the continuous video frame and the region detection model further comprises:

[0064] Based on the continuous video frame, the illumination compensation algorithm and the region detection model, it is judged whether there is a human body in the working area.

[0065] Scheme 6. According to the safety detection method of scheme 3, the method of judging whether there is a human body in the working area based on the continuous video frame and the region detection model further comprises:

[0066] Based on the continuous video frame, the background model and the region detection model, it is judged whether there is a human body in the working area.

[0067] Scheme 7. According to the safety detection method of scheme 6, the safety detection method further comprises:

[0068] Based on the continuous video frame, the background model is updated once every first preset time interval.

[0069] Scheme 8. According to the safety detection method of scheme 1, the human body sensing information includes human body infrared information, and the method of judging whether there is a human body in the working area of the press machine based on the visual information and the human body sensing information respectively further comprises:

[0070] Based on the human body infrared information, it is judged whether there is a human body in the working area.

[0071] Scheme 9. According to the safety detection method of scheme 8, the press machine is provided with a hot infrared human body sensor array, and the detection area formed by the hot infrared human body sensor array can cover the working area, and the method of judging whether there is a human body in the working area based on the human body infrared information further comprises:

[0072] Based on a plurality of human body infrared information and a topology analysis method, it is judged whether there is a human body in the working area.

[0073] Scheme 10. The safety detection method according to scheme 9, the judging whether there is a human body in the working area based on the plurality of human body infrared information and the topological analysis method further comprises:

[0074] judging whether there is a human body in the working area based on all the received trigger signals, signal duration of the thermal infrared human sensor and the topological analysis method.

[0075] Scheme 11. The safety detection method according to scheme 9, the signal synchronization error between the plurality of infrared human sensors in the thermal infrared human sensor array is set to be less than a second preset time length.

[0076] Scheme 12. The safety detection method according to scheme 9, the thermal infrared human sensor is triggered based on the following way:

[0077] in the first temperature signal sampling period, the temperature signal falling into the first temperature window is marked;

[0078] in the second temperature signal sampling period, it is judged whether the marked temperature signal falls into the second temperature window;

[0079] if yes, the thermal infrared human sensor is triggered.

[0080] Scheme 13. The safety detection method according to scheme 12, in each temperature signal sampling period, the temperature signal is filtered.

[0081] Scheme 14. The safety detection method according to scheme 12, the first temperature window is set to 34℃ and above, and the second temperature window is set to 33℃-38℃.

[0082] Scheme 15. A computer storage medium, wherein a plurality of program codes are stored, the program codes are suitable for being loaded and run by a processor to execute the safety detection method according to any one of schemes 1-14.

[0083] Scheme 16. An electronic device comprising a processor and a storage device, the storage device is suitable for storing a plurality of program codes, the program codes are suitable for being loaded and run by the processor to execute the safety detection method according to any one of schemes 1-14.

[0084] Scheme 17. A safety detection system of a press machine, comprising:

[0085] a visual unit configured to acquire visual information, and a sensing unit configured to acquire sensing information, and capable of judging whether there is a human body in the working area of the press machine based on the sensing information;

[0086] an analysis unit configured to receive the visual information output by the visual unit and determine whether a human body exists in a working area of the press based on the visual information;

[0087] a control unit configured to receive the determination result output by the analysis unit and the determination result output by the sensing unit and selectively control the press to remain stationary or perform a pressing operation based on the two determination results.

[0088] Scheme 18. The safety detection system of the press according to Scheme 17, the sensing unit comprises four thermal infrared human sensors, the four thermal infrared human sensors are respectively arranged at four corners of the press and form a thermal infrared human sensor array, a detection area of the thermal infrared human sensor array can cover the working area of the press.

[0089] Scheme 19. The safety detection system of the press according to Scheme 18, two of the thermal infrared human sensors are located at one side of the working area and are both at a first height, and the other two thermal infrared human sensors are located at the other side of the working area and are both at a second height, the first height is greater than the second height.

[0090] The two thermal infrared human sensors at the first height are vertically inclined downward, and the two thermal infrared human sensors at the second height are vertically inclined upward.

[0091] Scheme 20. The safety detection system of the press according to Scheme 17, the visual unit is arranged as a camera, the camera is arranged at one side of the working area, and a visual area of the camera can cover the working area. BRIEF DESCRIPTION OF DRAWINGS

[0092] The safety detection method of the present application will be described below with reference to the accompanying drawings. In the drawings:

[0093] Figure 1 The main step flowchart of the safety detection method of one embodiment of the present application;

[0094] Figure 2 The step flowchart of determining whether a human body exists in the working area based on continuous video frames and a region detection model for one embodiment of the present application;

[0095] Figure 3 The schematic diagram of the triggered mode of the thermal infrared human sensor for one embodiment of the present application;

[0096] Figure 4 The schematic diagram of the main structure of the electronic device for one embodiment of the present application;

[0097] Figure 5 Fig. 1 is a schematic view of a safety detection system of a press machine according to the present application;

[0098] Figure 6 Fig. 2 is a first installation schematic view of a vision unit and a human sensing unit according to the present application;

[0099] Figure 7 Fig. 3 is a second installation schematic view of a vision unit and a human sensing unit according to the present application.

[0100] List of reference signs

[0101] 401, processor; 402, storage device; 501, vision unit; 502, sensing unit; 503, analysis unit; 504, control unit. DETAILED DESCRIPTION

[0102] The preferred embodiments of the present application will be described below with reference to the accompanying drawings. It should be understood by those skilled in the art that the embodiments are only used to explain the technical principles of the present application, and are not intended to limit the protection scope of the present application. For example, although the thermal infrared human sensor in the drawings is arranged at the four corners of the press machine, the positional relationship is not fixed, and those skilled in the art can adjust it as needed to adapt to specific application occasions.

[0103] It should be noted that in the description of the present application, the terms indicating the direction or positional relationship of "left", "right", "vertical", "horizontal" and the like are based on the direction or positional relationship shown in the drawings, which is only for the convenience of description, and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present application. In addition, the terms "first", "second" are only for the purpose of description, and cannot be understood as indicating or implying relative importance. In addition, in the description of the present application, "a plurality of" means at least two.

[0104] In addition, it should also be noted that in the description of the present application, unless otherwise explicitly specified and limited, the terms "mounting", "connecting", "connection" should be understood broadly, for example, it can be fixedly connected, or detachably connected, or integrally connected; it can be mechanically connected, or electrically connected; it can be directly connected, or indirectly connected through an intermediate medium, or the internal communication of two elements. Those skilled in the art can understand the specific meaning of the above terms in the present application according to the specific circumstances.

[0105] In the description of the present application, the "processor" can include hardware, software or a combination of both. The processor can be a central processor, microprocessor, digital signal processor or any other suitable processor. The processor has data and / or signal processing functions. The processor can be implemented in software, hardware or a combination of both. The computer readable storage medium includes any suitable medium that can store program code, such as magnetic disk, hard disk, optical disk, flash memory, read-only memory, random access memory, etc.

[0106] The following refers to Figure 1 The safety detection method of the present application is described. Among them, Figure 1 The main step flow chart of the safety detection method of an embodiment of the present application.

[0107] As Figure 1 shown, in order to solve the problem of low effectiveness of safety measures in the existing safety detection system of the press, the present application provides a safety detection method for the safety detection system of the press, the safety detection method comprising the following steps:

[0108] S101, in response to the start signal of the press, acquiring visual information and human body sensing information;

[0109] S102, respectively based on the visual information and the human body sensing information, judging whether there is a human body in the working area of the press;

[0110] S103, based on the two judgment results, selectively controlling the press to remain stationary or to perform the down operation.

[0111] In this embodiment, if the press is started, the visual information can be acquired according to the visual equipment such as camera, the human body sensing information can be acquired according to the sensing equipment such as thermal infrared human body sensor and ultrasonic sensor, then whether there is a human body in the working area of the press is judged through the visual information and the human body sensing information respectively, and the press is selectively controlled to remain stationary or to perform the down operation according to the two judgment results.

[0112] It should be explained that the working area of the press refers to the dangerous area where personnel cannot enter, and in the dangerous area the material will be stamped into the set shape. Through the above method, when the press is started, it can be judged in advance whether there is a human body in the working area of the press, so as to avoid safety risks. And this method improves the safety protection level of the press from administrative control to engineering control, improves the effectiveness of safety measures, and eliminates the safety risks caused by the management defects such as non-standard operation of the press by employees.

[0113] Further, the step S103 "selectively controlling the press to remain stationary or to perform the down operation based on the judgment result" comprises:​

[0114] When both results are that there is no human body in the working area, the press is controlled to perform a pressing operation, otherwise, the press is controlled to remain stationary.

[0115] In the embodiment, the press is only started normally when both detection methods indicate that there is no human body in the working area. The redundant safety measure combining visual detection and human sensing can completely eliminate the safety risks caused by management defects such as non-standard operation of the press by the staff.

[0116] It should be explained that the above embodiment is not necessary. In an alternative embodiment, if the visual camera relied on by the visual detection is damaged or blocked, the presence or absence of a human body in the working area can be determined temporarily only by sensing information, and then the press is controlled to perform a pressing operation or not.

[0117] In some embodiments, the visual information includes continuous video frames, and the step S102 of determining whether there is a human body in the working area of the press based on the visual information and the human sensing information respectively further includes:

[0118] Determining whether there is a human body in the working area based on the continuous video frames and the area detection model.

[0119] In the embodiment, the visual information can be obtained by a camera. For example, the camera can continuously collect a video stream of the working area at a rate of 30 fps (frames per second), and input the video stream, i.e., continuous video frames, to the area detection model to identify whether there is a human body in the video stream.

[0120] Reference is made below to Figure 2 , Figure 2 a step flowchart for determining whether there is a human body in the working area based on continuous video frames and an area detection model according to an embodiment of the present application.

[0121] As shown in Figure 2 , determining whether there is a human body in the working area based on continuous video frames and an area detection model further includes:

[0122] S201, determining whether there is a human body in the working area based on continuous video frames;

[0123] S202, under the premise that there is a human body, the human body is framed and the overlap area ratio of the human body detection frame and the working area is calculated;

[0124] S203, determining whether the overlap area ratio is greater than or equal to a preset threshold;

[0125] S204, if yes, it is determined that the human body exists in the working area; otherwise, it is determined that the human body does not exist in the working area.

[0126] In the embodiment, the region detection model can be set as a YOLOv5s (You Only Look Once version 5 small) model, and the confidence threshold can be set as 0.7, at which time the YOLOv5s model does not need to be retrained. After the video frame is scaled to 640x640, it can be input to the YOLOv5s model for human body detection. If the human body exists in the video frame, the YOLOv5s model will locate the human body through the detection frame. At this time, the proportion of the overlapping area of the detection frame and the working area to the area of the working area, i.e., the overlapping area ratio of the human body detection frame and the working area, can be calculated. When the overlapping area ratio is greater than or equal to a preset threshold, such as 30%, it is considered that the human body exists in the working area of the press machine.

[0127] It needs to be explained that the above-mentioned way of determining whether the human body exists in the working area is not fixed. In an alternative embodiment, a person skilled in the art can change the region detection model according to the needs, as long as it does not affect the normal realization of the functions of the present application. For example, a target detection model such as SSD (Single Shot MultiBox Detector), R-CNN (Region-based Convolutional Neural Networks) is used for detection, at which time the detection frame of the human body can also be drawn. However, considering the processing speed, cost, etc., the YOLOv5s model is a relatively optimal choice. In another alternative embodiment, a person skilled in the art can change the size of the specific preset threshold, such as 25%, according to the needs.

[0128] In some embodiments, determining whether the human body exists in the working area based on the continuous video frames and the region detection model further comprises:

[0129] Determining whether the human body exists in the working area based on the continuous video frames, the illumination compensation algorithm, and the region detection model.

[0130] In the embodiment, the illumination compensation algorithm is a CLAHE (Contrast Limited Adaptive Histogram Equalization) algorithm. Through the CLAHE algorithm, the collected video frame can be preprocessed. The main principle is to improve the local contrast of the image, so as to eliminate the interference caused by metal reflection or uneven illumination, dust shielding and other factors, and thus ensure the accuracy of the region detection model for human body detection.

[0131] It needs to be explained that the CLAHE algorithm is prior art, and its specific implementation process will not be repeated here. In addition, the setting of the illumination compensation algorithm is not fixed. In an alternative implementation, the setting of the illumination compensation algorithm can be omitted, but in view of the influence of environmental factors on the accuracy of human body detection, in order to eliminate safety risks, setting the illumination compensation algorithm is a relatively optimal choice. In another alternative implementation, a person skilled in the art can change the setting of the illumination compensation algorithm according to needs, as long as it does not affect the normal implementation of the functions of the present application. For example, a deep learning algorithm is used for illumination compensation, but considering the operation speed and hardware requirements, using the CLAHE algorithm for illumination compensation is a relatively optimal choice.

[0132] In some embodiments, determining whether a human body exists in the working area based on the continuous video frames and the region detection model further comprises:

[0133] Determining whether a human body exists in the working area based on the continuous video frames, the background model and the region detection model.

[0134] In the present embodiment, the video frame or the video frame after illumination compensation can be directly compared with the background model to determine whether a person has entered the working area of the press machine. That is, the background model can only determine the moving object, which provides a premise for the subsequent region detection model to more efficiently determine whether a human body exists in the working area, reduces the calculation amount of the region detection model, and improves the accuracy of subsequent detection.

[0135] It needs to be explained that the setting of the background model is not fixed. In an alternative implementation, the setting of the background model can be omitted, and at this time the region detection model can directly determine whether a human body exists in the working area, but in view of the calculation amount and calculation speed, setting the background model is a relatively optimal choice.

[0136] In some embodiments, the safety detection method further comprises:

[0137] Based on the continuous video frames, the background model is updated once every first preset time interval.

[0138] In the embodiment, the first preset time length is set to 5s, and the camera continues to collect the video stream of the working area at a rate of 30fps. In the initial stage, 1-2s of video of the empty background can be collected, and the average image of the scene can be obtained through the video, and the average image is taken as the initial background model. In the subsequent stage, the pixel points in the video stream input in every 5s, i.e., about 150 continuous video frames, are counted. If the region remains stable in most frames and no obvious change is found, it means that no human body is detected in the region, and the pixel value of the region can be updated to the background model. If obvious changes occur in the region, it means that a human body is detected in the region, and the region will not be updated. Through the above method, the global background model can be changed every 5s to adapt to the changes of the mold and the scene environment, thereby improving the accuracy of subsequent detection.

[0139] It should be explained that the above-mentioned updating method of the background model is not fixed, and those skilled in the art can change the specific settings according to the needs, as long as the normal implementation of the function of the present application is not affected. In an alternative embodiment, the first preset time length can be set to 3s, 10s, etc.

[0140] In some embodiments, the human body sensing information includes human body infrared information, and the step S102 of “judging whether a human body exists in the working area of the press machine based on the visual information and the human body sensing information respectively” further includes:

[0141] Based on the human body infrared information, it is judged whether a human body exists in the working area.

[0142] In the embodiment, a thermal infrared human body sensor pointing to the working area of the press machine can be used to detect whether a person passes through or stays in the working area of the press machine, but its setting is not necessary. In an alternative embodiment, other types of sensors such as ultrasonic sensors can be used or combined to jointly determine whether a human body exists in the working area.

[0143] In some embodiments, the press machine is provided with a thermal infrared human body sensor array, and the detection area formed by the thermal infrared human body sensor array can cover the working area. Based on the human body infrared information, it is judged whether a human body exists in the working area further includes:

[0144] Based on the multiple human body infrared information and the topological analysis method, it is judged whether a human body exists in the working area.

[0145] In the embodiment, the plurality of human infrared information obtained by the plurality of thermal infrared human sensors can be subjected to topological analysis, that is, whether a human body enters the working area can be determined by the triggering sequence and triggering time of the plurality of thermal infrared human sensors. For example, if the plurality of thermal infrared human sensors are triggered in sequence from the outside to the inside of the working area, and the triggering time is approximate, it can be explained that a human body enters the working area. In this way, the accuracy of determining whether a human body exists in the working area through human infrared information can be improved, so that even in the case that the visual unit relied on by the visual information is damaged or blocked, accurate determination can be made through the thermal infrared human sensor.

[0146] It should be explained that the setting of the above-mentioned topological analysis method is not necessarily required. In an alternative embodiment, only the plurality of thermal infrared human sensors can be provided, and at this time, if any one of the thermal infrared human sensors is triggered, it is determined whether a human body exists in the working area. However, since the triggering of a single thermal infrared human sensor can be caused by reasons such as reflection, heat source interference or blocking, this method is prone to misjudgment, thereby affecting the normal operation of the press, and therefore, the analysis of the plurality of human infrared information through the topological analysis method is a relatively optimal choice.

[0147] In some embodiments, determining whether a human body exists in the working area based on the plurality of human infrared information and the topological analysis method further comprises:

[0148] Determining whether a human body exists in the working area based on the triggering signals, signal duration and topological analysis method of all the thermal infrared human sensors received.

[0149] In the embodiment, in order to avoid misjudgment caused by short-time triggering of the thermal infrared human sensor due to reasons such as reflection and heat source interference, the signal duration can be introduced. For example, if a certain thermal infrared human sensor is triggered for 200 ms, for example, when a person steps into the working area, it can be determined as a valid input. If different thermal infrared human sensors are triggered in sequence within 200 ms, for example, when a person walks in the working area, it can also be determined as a valid input.

[0150] It should be explained that the setting of the above-mentioned signal duration is not necessarily fixed. In an alternative embodiment, a person skilled in the art can change the specific setting of the signal duration according to the needs. In another alternative embodiment, the setting of determining through the signal duration can be omitted, and at this time, the determination can be made only through the triggering sequence of the plurality of thermal infrared human sensors or a single triggering signal. However, in the case of considering reducing the false positive rate, the introduction of the signal duration is a relatively optimal choice.

[0151] In some embodiments, the signal synchronization error between the plurality of infrared human body sensors in the thermal infrared human body sensor array is set to be less than a second preset time length.

[0152] In the present embodiment, the second preset time length can be set to 10 ms. For example, the trigger delay can be calibrated using an oscilloscope to ensure that the synchronization error of the signals of the four infrared human body sensors is less than 10 ms. The specific implementation principle of the oscilloscope is prior art and will not be described here. Of course, the skilled person can also change the specific setting of the second preset time length according to the needs.

[0153] Reference will now be made to Figure 3 , Figure 3 Fig. 1 is a schematic diagram of the triggering mode of the thermal infrared human body sensor according to an embodiment of the present application. As shown in Fig. 1, in a preferred embodiment, the thermal infrared human body sensor is triggered based on the following mode: Figure 3

[0154] S301, in the initial temperature signal sampling period, the temperature signal falling into the first temperature window is marked;

[0155] S302, in the secondary temperature signal sampling period, it is judged whether the marked temperature signal falls into the second temperature window;

[0156] S303, if yes, the thermal infrared human body sensor is triggered.

[0157] In the present embodiment, the thermal infrared human body sensor is provided with a double threshold triggering mechanism, wherein the first temperature window is set to 34℃ and above, and the second temperature window is set to 33℃-38℃. Specifically, the implementation principle is as follows: in the initial temperature signal sampling period, first, all temperature signals greater than or equal to 34℃ are marked, and if in the next, i.e. the secondary temperature signal sampling period, the part of the marked temperature signals still falls into the range of 33℃-38℃, the thermal infrared human body sensor is triggered. Through the above setting, the false positives caused by high background temperature or reflection can be reduced, and the signal level can be screened, which is beneficial to provide a premise for subsequent judgment of whether there is a human body in the working area based on human body sensing information.

[0158] In some embodiments, the temperature signal can be filtered in each temperature signal sampling period by using a FIR digital filter.

[0159] ​It needs to be explained that, since the change of ambient temperature is usually slow, this change is a low-frequency component, while the heat radiation change of human body is obvious and fast, which is a high-frequency component. In the embodiment, the cutoff frequency of the FIR digital filter is set to 0.1 Hz, and in each temperature signal sampling period, the FIR digital filter can eliminate the interference caused by the slow change of ambient temperature by attenuating the low-frequency component below 0.1 Hz, and only keep the fast human heat source signal, so as to realize stable recognition.

[0160] The application also provides a safety detection system of a press machine, and the safety detection system of the press machine will be introduced below with reference to Figures 5-7 The safety detection system of the press machine provided by the application comprises a visual unit, a human sensing unit, an analysis unit and a control unit. Figure 5 FIG. 1 is a schematic diagram of the safety detection system of the press machine provided by the application, Figure 6 FIG. 2 is a first installation schematic diagram of the visual unit and the human sensing unit of the safety detection system of the press machine provided by the application; and Figure 7 FIG. 3 is a second installation schematic diagram of the visual unit and the human sensing unit of the safety detection system of the press machine provided by the application.

[0161] As shown in Figure 5 FIG. 1, the safety detection system comprises a visual unit 501, a sensing unit 502, an analysis unit 503 and a control unit 504. The visual unit 501 is configured to acquire visual information, the sensing unit 502 is configured to acquire sensing information, and the analysis unit 503 is configured to receive the visual information output by the visual unit 501 and determine whether there is a human body in the working area of the press machine based on the visual information. The control unit 504 is configured to receive the determination result output by the analysis unit 503 and the determination result output by the sensing unit 502, and selectively control the press machine to remain stationary or perform a pressing operation based on the two determination results.

[0162] In a possible implementation, the visual unit 501 is set as a camera, the sensing unit 502 comprises four thermal infrared human sensors, the analysis unit 503 is set as an industrial computer, and the control unit 504 is set as a PLC controller. The camera transmits the collected continuous video frames to the industrial computer, the industrial computer scales the video frames to 640x640 and inputs the video frames into a YOLOv5s model for detection. If a human body appears in the video frames, the human body will be framed, at this time, whether there is a human body in the working area can be determined by calculating the overlap area ratio of the frame and the working area, and the determination result is sent to the PLC controller. The human infrared information collected by the four thermal infrared human sensors is directly transmitted to the PLC controller, which performs filtering processing, and determines whether there is a human body in the working area through the triggered thermal infrared human sensors and a topological analysis method. When the two determination results are both that there is no human body in the working area, the PLC controller controls the press machine to perform a pressing operation.

[0163] In the technical solution, the safety detection system of the press can first determine whether there is a human body in the working area of the press when the press is started, thereby avoiding safety risks. The safety protection level of the press is improved from administrative control to engineering control, the effectiveness of safety measures is improved, and safety risks caused by non-standard operation of the press by employees and other management defects are eliminated.

[0164] It should be explained that, in the selective control of the press to remain stationary or to perform the pressing operation based on the two determination results, the two determination results only refer to the determination result obtained from the visual information and the determination result obtained from the sensing information, which is not limited to the number of the visual unit 501 and the sensing unit 502. For example, a plurality of visual units 501 or a plurality of sensing units 502 can be provided. Taking the sensing unit 502 as an example, in one possible implementation, one determination result can be obtained from the sensing information of all the sensing units 502, and the sensing unit 502 directly sends the determination result to the control unit 504. For example, if any one of the thermal infrared human body sensors is triggered, it is determined that there is a human body in the working area, and the result is sent to the PLC controller. In another possible implementation, a preliminary determination result can be obtained from the sensing information of each sensing unit 502, and a final determination result is obtained from all the preliminary determination results. For example, if each thermal infrared human body sensor is triggered, it is temporarily determined that there is a human body in the working area, and the preliminary determination result is sent to the PLC controller. However, the final determination result needs to be determined by the PLC controller based on the sequence and duration of triggering of all the thermal infrared human body sensors. Then, the final determination result and the final determination result obtained based on the visual information are used to selectively control the press to remain stationary or to perform the pressing operation.

[0165] As shown in FIGS. 1, 2 and 3, in the embodiment, the sensing unit 502 includes four thermal infrared human body sensors, which are arranged at four corners of the press and form a thermal infrared human body sensor array. The detection area of the thermal infrared human body sensor array can cover the working area of the press. Figure 6 As shown in FIG. 4, the four thermal infrared human body sensors are arranged in the direction shown in FIG. 4. Two thermal infrared human body sensors are located on the right side of the working area and are at a first height, and the other two thermal infrared human body sensors are located on the left side of the working area and are at a second height. The first height is greater than the second height, and the two thermal infrared human body sensors at the first height are vertically inclined downward, and the two thermal infrared human body sensors at the second height are vertically inclined upward. Figure 7 Figure 6 As shown in FIG. 4, the four thermal infrared human body sensors are arranged in the direction shown in FIG. 4. Two thermal infrared human body sensors are located on the right side of the working area and are at a first height, and the other two thermal infrared human body sensors are located on the left side of the working area and are at a second height. The first height is greater than the second height, and the two thermal infrared human body sensors at the first height are vertically inclined downward, and the two thermal infrared human body sensors at the second height are vertically inclined upward.

[0166] ​The visual unit is arranged as a camera, which is arranged at one side of the working area and can cover the working area. During installation, the center point of the working area of the press machine can be determined by using a laser range finder first, and then the camera is fixed to the press machine through the shockproof support and the support, and the camera is adjusted to ensure that the field of view covers the whole mold moving area.

[0167] In the embodiment, the detection area formed by the four thermal infrared human sensors with different heights and orientations can realize complete coverage of the working area of the press machine, but the specific arrangement is not necessarily mandatory, and those skilled in the art can change the number, position, height, and inclination angle of the thermal infrared human sensor array according to the needs, as long as the function of the thermal infrared human sensor array is not hindered. In addition, the installation method and position of the visual unit are not fixed, and those skilled in the art can change them according to the needs, as long as the visual area of the visual unit can cover the working area and does not affect the normal function of the press machine.

[0168] Those skilled in the art can understand that all or part of the processes in the method of the above-mentioned embodiment can also be completed by a computer program instructing related hardware. The above-mentioned computer program can be stored in a computer readable storage medium, and when the processor executes the computer program, the steps of the above-mentioned various method embodiments can be realized. The above-mentioned computer program includes computer program code, which can be in the form of source code, object code, executable files, or some intermediate forms. The above-mentioned computer readable storage medium can include any entity or device, medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory, random access memory, electrical carrier signal, telecommunication signal, and software distribution medium, etc. that can carry the above-mentioned computer program code.

[0169] Further, the present application also provides an electronic device. Referring to the accompanying Figure 4 , Figure 4 is a schematic diagram of the main structure of an electronic device according to an embodiment of the present application. As shown in Figure 4 , the electronic device in the embodiment of the present application mainly includes a processor 401 and a storage device 402. The storage device 402 can be configured to store a program for executing the safety detection method of the above-mentioned method embodiment, and the processor 401 can be configured to execute the program in the storage device 402, which includes but is not limited to the program for executing the safety detection method of the above-mentioned method embodiment. For the convenience of description, only the parts related to the embodiment of the present application are shown, and the specific technical details not disclosed are referred to the method part of the embodiment of the present application.

[0170] In some possible implementation of the present application, the electronic device can include a plurality of processors 401 and a plurality of storage devices 402. The program of the control method initiated by the program of the method embodiments described above can be divided into a plurality of sub-programs, each of which can be loaded and run by the processor 401 to perform different steps of the control method initiated by the program of the method embodiments described above. Specifically, each sub-program can be stored in a different storage device 402, and each processor 401 can be configured to execute the program in one or more storage devices 402 to jointly implement the security detection method of the method embodiments described above, i.e., each processor 401 respectively performs different steps of the control method initiated by the program of the method embodiments described above to jointly implement the security detection method of the method embodiments described above.

[0171] The plurality of processors 401 described above can be processors deployed on the same device, for example, the electronic device described above can be a high-performance device composed of a plurality of processors, and the plurality of processors 401 described above can be processors configured on the high-performance device. In addition, the plurality of processors 401 described above can also be processors deployed on different devices, for example, the electronic device described above can be a server cluster, and the plurality of processors 401 described above can be processors on different servers in the server cluster.

[0172] Further, the present application also provides a computer readable storage medium. In an embodiment of the computer readable storage medium according to the present application, the computer readable storage medium can be configured to store the program of the security detection method of the method embodiments described above, which can be loaded and run by the processor to implement the security detection method described above. For ease of illustration, only the parts related to the embodiments of the present application are shown, and the specific technical details not disclosed are referred to the method part of the embodiments of the present application. The computer readable storage medium can be a storage device formed by various electronic devices, and optionally, the computer readable storage medium in the embodiments of the present application is a non-transitory computer readable storage medium.

[0173] Those skilled in the art can understand that although some embodiments described herein include certain features included in other embodiments rather than other features, the combination of features of different embodiments means within the scope of the present application and forms different embodiments. For example, in the claims of the present application, any one of the claimed embodiments can be used in any combination.

[0174] So far, the technical solution of the present application has been described in combination with the preferred embodiments shown in the drawings, but it is easy for those skilled in the art to understand that the protection scope of the present application is obviously not limited to these specific embodiments. Those skilled in the art can make equivalent changes or replacements to the related technical features without departing from the principles of the present application, and the technical solutions after the changes or replacements will all fall within the protection scope of the present application.

Claims

1. A safety detection method for a safety detection system of a press, characterized in that, include: In response to the start signal of the press, it acquires visual information and human body sensing information; Based on the visual information and the human body sensing information, it is determined whether a human body exists within the working area of ​​the press. Based on the two judgment results, the press is selectively controlled to remain stationary or to perform a pressing operation.

2. The security detection method according to claim 1, characterized in that, The selective control of the press to remain stationary or perform a pressing operation based on two judgment results further includes: If both judgment results indicate that there is no human body in the working area, the press is controlled to perform a downward pressing operation; otherwise, the press is controlled to remain stationary.

3. The security detection method according to claim 1, characterized in that, The visual information includes consecutive video frames, and the determination of whether a human body exists within the working area of ​​the press based on the visual information and the human body sensing information further includes: Based on the continuous video frames and the region detection model, it is determined whether a human body exists within the working area.

4. The security detection method according to claim 3, characterized in that, The determination of whether a human body exists within the working area based on the continuous video frames and the region detection model further includes: Based on the continuous video frames, determine whether a human body is present in the working area; Given the presence of a human body, select the human body and calculate the ratio of the overlap area between the human body detection box and the working area; Determine whether the overlap area ratio is greater than or equal to a preset threshold; If yes, then it is determined that a human body exists in the work area; otherwise, it is determined that no human body exists in the work area.

5. The security detection method according to claim 3, characterized in that, The determination of whether a human body exists within the working area based on the continuous video frames and the region detection model further includes: Based on the continuous video frames, the illumination compensation algorithm, and the region detection model, it is determined whether a human body exists within the working area.

6. The security detection method according to claim 3, characterized in that, The determination of whether a human body exists within the working area based on the continuous video frames and the region detection model further includes: The presence of a human body within the working area is determined based on the continuous video frames, the background model, and the region detection model.

7. The security detection method according to claim 6, characterized in that, The security detection method also includes: Based on the continuous video frames, the background model is updated once every first preset time interval.

8. The security detection method according to claim 1, characterized in that, The human body sensing information includes human infrared information, and the determination of whether a human body exists within the working area of ​​the press based on the visual information and the human body sensing information further includes: Based on the human infrared information, it is determined whether a human body exists in the working area.

9. The security detection method according to claim 8, characterized in that, The press is equipped with a thermal infrared human body sensor array, and the detection area formed by the thermal infrared human body sensor array can cover the working area. The determination of whether a human body is present in the working area based on the human infrared information further includes: Based on multiple human infrared information and topology analysis methods, it is determined whether a human body exists within the working area.

10. The security detection method according to claim 9, characterized in that, The method for determining whether a human body exists within the working area based on multiple human infrared information and topology analysis further includes: Based on the received trigger signals from all thermal infrared human body sensors, the signal duration, and the topology analysis method, it is determined whether a human body exists within the working area.

Images