A method for intelligent human recognition and active safety protection in a pulp sheet pressing machine

Abstract

This application provides an intelligent human-shaped recognition active safety protection method for a pulp sheet pressing machine, relating to the field of industrial heavy equipment safety protection technology. The method includes: acquiring detection signals of preset protection areas at the front and / or rear of the pulp sheet pressing machine, the preset protection areas including an emergency stop zone near the machine's working mechanism and a warning zone outside the emergency stop zone; responding to the detection of a target entering the preset protection area based on the detection signals, performing human-shaped recognition on the target to obtain a target recognition result characterizing whether the target is a human or non-human target; determining the area the target has fallen into based on its position within the preset protection area; and triggering corresponding actions based on the target recognition result and the area the target has fallen into. This reduces the probability of non-human targets mistakenly triggering a shutdown, improving the accuracy and reliability of the pressing machine's safety protection.

Description

Technical Field

[0001] This application belongs to the field of industrial heavy equipment safety protection technology, specifically relating to an intelligent human figure recognition active safety protection method for a pulp board pressing machine. Background Technology

[0002] Pulp sheet presses are crucial heavy-duty equipment in the pulp and paper production and packaging process. They are typically used in conjunction with front-end conveying mechanisms, rear-end conveying mechanisms, and pressing actuators to transport, position, and press pulp sheets. Because pulp sheet presses involve significant clamping force, numerous moving parts, and continuous conveying operations, personnel who accidentally enter the vicinity of the press's working mechanism are prone to mechanical injuries. Therefore, effectively protecting the hazardous areas of pulp sheet presses is a key technical issue that needs to be addressed during the operation of pulp and paper production equipment.

[0003] Current safety protection methods for pulp sheet pressing machines typically rely on passive protection structures such as mechanical safety doors, safety door interlock switches, and emergency stop buttons. These methods primarily stop the pulp sheet pressing machine when the safety door is opened, when a person actively presses the emergency stop button, or when the external protective structure of the equipment is triggered, thereby reducing the safety risks when personnel enter the equipment or its surrounding area.

[0004] However, in actual production settings, the front and rear ends of the pulp sheet pressing machine are usually connected to conveyor belts, feeding areas, or unloading areas. These areas serve as continuous conveying channels for the pulp sheets and are also easily accessible to operators during inspections, cleaning, and equipment adjustments. Since these areas are often not fully covered by the safety door interlocking system, existing methods relying on the opening and closing status of safety doors are insufficient to promptly detect personnel entering the dangerous areas at the front or rear of the pressing machine, easily creating blind spots in protection.

[0005] Furthermore, while some existing technologies can detect the entry of a target using ordinary infrared sensors, photoelectric sensors, or proximity switches, these detection methods typically only determine whether an object exists within the detection range. They struggle to distinguish between a human body and non-human objects such as pulp boards, cardboard boxes, tools, or pulp residue. When a non-human object enters the detection range, the sensor may still trigger a shutdown or alarm, leading to frequent erroneous stops of the pulp board pressing machine and disrupting production continuity. Summary of the Invention

[0006] This application provides an intelligent human figure recognition active safety protection method for a pulp board pressing machine to solve one of the above-mentioned technical problems.

[0007] The technical solution adopted in this application is as follows: This application provides an intelligent human figure recognition active safety protection method for a pulp board pressing machine, characterized in that it includes: Acquire detection signals of preset protection areas at the front and / or rear of the pulp pressing machine, wherein the preset protection areas include an emergency stop area near the working mechanism of the pulp pressing machine and a warning area located outside the emergency stop area; In response to detecting that a target has entered the preset protection area based on the detection signal, human figure recognition is performed on the target to obtain a target recognition result, which is used to characterize whether the target is a human target or a non-human target; Based on the location of the target within the preset protection area, determine the area in which the target falls. Based on the target recognition result and the defined region where the target falls, a corresponding action is triggered.

[0008] According to one embodiment of this application, triggering a corresponding action based on the target recognition result and the defined region in which the target falls includes: When the target recognition result indicates that the target is a non-human target, the detection signal is filtered, and the current operating state of the pulp pressing machine is maintained; When the target identification result indicates that the target is a human target and the human target falls into the warning zone, a first safety control action is triggered, the first safety control action includes outputting a warning prompt; When the target identification result indicates that the target is a human target and the human target falls into the emergency stop zone, a second safety control action is triggered. The second safety control action includes outputting an emergency stop alarm and controlling the pulp press machine to perform an emergency stop.

[0009] According to one embodiment of this application, before acquiring the detection signal of the preset protection area, the method further includes: The emergency stop zone and the early warning zone are determined based on the position of the working mechanism of the pulp press and the position of the conveyor belt connected to the working mechanism. Establish a regional mapping relationship between the sensing range of the human figure recognition sensor and the emergency stop zone and the early warning zone; The determination of the area into which the target falls, based on the target's position within the preset protection area, includes: determining whether the target falls into the emergency shutdown zone or the early warning zone based on the human figure recognition sensor that generates the detection signal, the sensing range corresponding to the detection signal, and the area mapping relationship.

[0010] According to one embodiment of this application, acquiring the detection signal of the preset protective area at the front and / or rear end of the pulp pressing machine includes: The detection signal is acquired by human figure recognition sensors located at the front and / or rear of the pulp pressing machine; The front and / or rear end of the pulp pressing machine are equipped with at least two human body recognition sensors. The at least two human body recognition sensors are arranged diagonally redundantly relative to the corresponding preset protection area, and the sensing range of the at least two human body recognition sensors overlaps and covers the emergency stop area and the early warning area.

[0011] According to one embodiment of this application, the human figure recognition sensor is mounted above and / or to the side of the conveyor belt of the pulp pressing machine via an angle-adjustable mounting bracket; The establishment of a regional mapping relationship between the sensing range of the human figure recognition sensor and the emergency stop zone and the early warning zone includes: Based on the equipment structure at the front and / or rear of the pulp pressing machine, the position of the conveyor belt, and the range of the preset protection area, adjust the installation angle of the human figure recognition sensor so that the sensing range of the human figure recognition sensor covers the corresponding emergency stop area and early warning area, and associate the adjusted sensing range with the corresponding divided area.

[0012] According to one embodiment of this application, in response to detecting that a target has entered the preset protection area based on the detection signal, human figure recognition is performed on the target to obtain a target recognition result, including: The human figure recognition sensor acquires the detection features of the target based on the infrared signal reflected by the target, and the detection features include at least one of contour features, body shape features and motion features; The detected features are matched with preset human feature conditions; When the detected features meet the preset human feature conditions, the target recognition result is determined to represent the target as a human target; When the detected features do not meet the preset human feature conditions, the target recognition result is determined to indicate that the target is a non-human target.

[0013] According to one embodiment of this application, the process of acquiring the detection signal of the preset protection area further includes: Obtain the operating status of the at least two human figure recognition sensors; When the working status of one of the human figure recognition sensors indicates that it is malfunctioning or occluded, and the other human figure recognition sensors are in normal working condition, the detection signal of the preset protection area is continuously acquired based on the human figure recognition sensor in normal working condition, and the determination of the target recognition result, the determination of the divided area, and the triggering of the corresponding action are performed according to the continuously acquired detection signal. At the same time, it outputs abnormal prompts corresponding to the malfunction or occlusion of the human recognition sensor.

[0014] According to one embodiment of this application, before and / or during the triggering of a corresponding action based on the target recognition result and the defined region in which the target falls, the method further includes: Obtain the safety door interlock status of the pulp press machine; When the safety door interlock status indicates that the safety door is open, the pulp pressing machine is controlled to be in a stopped state, a prohibited start state, or a maintenance state, and the action triggering logic of the preset protection area is adjusted to avoid repeated emergency stop triggering during maintenance operations. When the target identification result indicates that the target is a human target and the human target falls into the emergency stop area, an interlock signal is output to the safety door interlocking system to keep the pulp press machine in a prohibited start state or a pending reset state until the human target leaves the emergency stop area and the reset operation is completed.

[0015] According to one embodiment of this application, the process of acquiring the detection signal through the human figure recognition sensor further includes: The human figure recognition sensor is subjected to fault self-detection, which includes detecting at least one of the infrared emission signal, infrared reception signal and communication signal of the human figure recognition sensor. When the infrared transmission signal, the infrared reception signal and / or the communication signal meet the preset fault conditions, a sensor fault result is generated. Based on the sensor malfunction result, a fault alarm is triggered, and the pulp press machine is controlled to switch to low-speed operation, automatic operation prohibited, or maintenance mode.

[0016] According to one embodiment of this application, the process of performing fault self-detection on the human figure recognition sensor further includes: Detect the occlusion status of the probe of the human figure recognition sensor; When the sensing signal of the human figure recognition sensor attenuates to a preset occlusion condition, or when the probe occlusion state indicates that the probe of the human figure recognition sensor is occluded, an occlusion detection result is generated. Based on the occlusion detection results, an occlusion alarm or cleaning prompt will be output; The human figure recognition sensor has a transparent protective cover on the outside of its probe. The transparent protective cover is used to prevent dust, oil and / or slurry from adhering to the probe. A detachable cleaning scraper is provided on the outside of the transparent protective cover. The detachable cleaning scraper is used to clean the adhering substances on the surface of the transparent protective cover.

[0017] Due to the adoption of the above technical solution, the beneficial effects achieved by this application are as follows: This application acquires detection signals from the preset protection areas at the front and / or rear of the pulp press machine, and divides the preset protection areas into an emergency stop zone near the working mechanism of the pulp press machine and a warning zone outside the emergency stop zone. This enables the establishment of an active detection range for the conveying connection area at the front and / or rear of the press machine, making up for the shortcomings of traditional safety door interlocking systems that cannot cover the front and rear working areas, and improving the ability to detect personnel accidentally entering dangerous blind spots.

[0018] This application performs human-shaped recognition on the target after detecting that it has entered a preset protection area, obtaining a target identification result to characterize whether the target is a human or a non-human target. Therefore, based on the detection of the target's entry, it can further determine the target's attributes. For non-human targets such as pulp boards, cardboard boxes, tools, and pulp residue, the corresponding detection signals can be filtered to avoid triggering a shutdown interlock, thereby reducing the probability of false alarms and false shutdowns caused by non-human objects and improving the continuity of equipment operation.

[0019] This application determines the zone a target falls into based on its location within a pre-defined protected area, and triggers corresponding actions based on the target identification results and the zone designation. Specifically, when a human target falls into the warning zone, a warning notification is triggered; when a human target falls into the emergency stop zone, an emergency stop alarm is triggered, and the pulp press machine is controlled to perform an emergency stop. This achieves a shift from "single-stop protection" to "zonal and graded protection," ensuring that safety control actions match the actual level of danger, reducing unnecessary production interruptions while protecting personnel safety.

[0020] This application involves installing at least two human figure recognition sensors at the front and / or rear of the pulp pressing machine, with these sensors arranged diagonally redundantly relative to a preset protection area. This allows multiple sensing ranges to collectively cover the warning zone and the emergency stop zone. Therefore, even if the detection capability of a single human figure recognition sensor decreases due to malfunction, obstruction, or limited detection angle, other normally functioning human figure recognition sensors can still continue to acquire detection signals, reducing the risk of protection gaps caused by single-point failures.

[0021] This application can determine whether a target has fallen into a warning zone or an emergency stop zone based on the installation location and sensing range of the human figure recognition sensor, as well as the regional mapping relationship between preset protection zones. By establishing a correspondence between the sensor's sensing range and the zone division, the core control unit can quickly determine the target's danger level based on the source of the detection signal and the target's location, improving the accuracy and response efficiency of graded safety control.

[0022] This application can obtain the safety door interlock status of the pulp sheet press machine and perform interlock control based on the safety door interlock status and the human detection protection status. When the safety door is open, the pulp sheet press machine is put into a stopped state, a prohibited start state, or a maintenance state, and the action triggering logic is adapted accordingly. When a human target falls into the emergency stop zone and triggers an emergency stop, an interlock signal is output to the safety door interlock system, keeping the pulp sheet press machine in a prohibited start state or a pending reset state. This allows the newly added human detection active protection system to form a collaborative control relationship with the existing safety door interlock system, avoiding the problems of independent safety systems or inconsistent control states.

[0023] This application enables self-detection of faults in the infrared emission, reception, and / or communication signals of a human figure recognition sensor during the acquisition of detection signals. When a sensor fault is detected, a fault alarm is triggered, and the pulp press machine is switched to a low-speed operation state, an automatic operation prohibited state, or a maintenance state. This allows for timely detection of sensor abnormalities and adjustment of the equipment's operating mode based on changes in the reliability of the protection system, reducing the safety risks associated with continued normal operation under sensor malfunction.

[0024] This application can detect the occlusion status of the probe of a human recognition sensor. When the sensing signal attenuation reaches a preset occlusion condition or the probe is blocked, an occlusion alarm or cleaning reminder is output. This allows for timely detection of decreased detection capability caused by dust, oil, or slurry buildup, facilitating timely maintenance and reducing the risk of missed detections due to probe occlusion.

[0025] This application allows for the installation of a transparent protective cover on the outside of the probe of a human figure recognition sensor, and a removable cleaning scraper on the outside of the transparent protective cover. The transparent protective cover prevents dust, oil, and / or pulp residue from directly adhering to the probe, while the removable cleaning scraper can clean the adhering substances from the surface of the transparent protective cover. Thus, cleaning and maintenance can be completed without frequent disassembly of the sensor, improving the adaptability and maintenance convenience of the device in complex working conditions such as dust and oil in pulp and paper workshops.

[0026] This application establishes a proactive safety protection closed loop for hazardous areas at the front and / or rear of a pulp sheet pressing machine through the coordination of target detection, human recognition, area judgment, graded action triggering, safety door interlocking, fault self-detection, obstruction detection, and redundant fault-tolerant control. This closed-loop protection method improves the accuracy of hazardous area detection, the reliability of equipment safety control, and the continuous protection capability under complex on-site working conditions, thereby providing a more suitable safety protection solution for pulp sheet pressing machines and similar heavy-duty pressing equipment. Attached Figure Description

[0027] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments of this application and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings: Figure 1 This is a schematic diagram of the redundant coverage installation structure of the human figure recognition sensor for the pulp pressing machine provided in this application embodiment; Figure 2 This is a schematic diagram of the preset protection area division and hierarchical sensing provided in the embodiments of this application; Figure 3 This is a schematic diagram of the anti-occlusion structure of the human figure recognition sensor provided in the embodiments of this application; Figure 4 This is a flowchart of the intelligent human figure recognition active safety protection method for the pulp pressing machine provided in the embodiments of this application. Detailed Implementation

[0028] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are merely some, not all, of the embodiments of the present application. All other embodiments obtained by those skilled in the art based on the embodiments of the present application without creative effort should fall within the scope of protection of the present application.

[0029] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising," "having," and any variations thereof are intended to cover non-exclusive inclusion.

[0030] The intelligent human-shaped recognition active safety protection method for pulp sheet pressing machines provided in this application embodiment can be applied to pulp sheet pressing machines in pulp and paper production lines, as well as to heavy-duty pressing equipment, stamping equipment, forging equipment, or other industrial equipment with front-end and / or rear-end conveying connection areas that have similar hazardous area structures to pulp sheet pressing machines. For ease of explanation, the following description uses a pulp sheet pressing machine as an example.

[0031] In this embodiment, the pulp sheet pressing machine may include a working mechanism, a front-end conveyor belt, a rear-end conveyor belt, a pressing machine actuator, an existing safety door interlocking system, and a newly added human recognition active safety protection system. The pressing machine actuator can perform actions such as pressing, conveying, positioning, or resetting pulp sheets; the existing safety door interlocking system can detect the opening and closing status of the safety door and, when the safety door is open, put the pulp sheet pressing machine in a stopped, prohibited-from-start, or maintenance state; the human recognition active safety protection system can perform target detection, human recognition, area judgment, and graded safety control on the preset protection areas at the front and / or rear of the pulp sheet pressing machine.

[0032] In one optional implementation, the human detection active safety protection system may include a human detection sensor, a core control unit, an alarm device, a fault detection module, an occlusion detection module, a safety door interlock interface, and a control interface for the pressing machine actuator. The human detection sensor can be a sensor with infrared detection and human detection functions; it is not limited to a specific product model, as long as it can output target detection results or human detection results based on target reflection signals or target detection characteristics. The core control unit can be a PLC controller, industrial controller, embedded controller, or other control device capable of performing logical judgments and interlocking controls.

[0033] In one optional implementation, the preset protection zone may include an emergency stop zone near the working mechanism of the slab pressing machine and a warning zone located outside the emergency stop zone. The emergency stop zone refers to the area where personnel entering may directly approach the working mechanism of the pressing machine or the range of dangerous pressing actions; the warning zone refers to the area located outside the emergency stop zone, used to alert personnel to stay away from the dangerous area. By dividing the preset protection zone into an emergency stop zone and a warning zone, safety control actions can be matched to the degree of danger at the target location.

[0034] According to an embodiment of this application, an intelligent human figure recognition active safety protection method for a pulp sheet pressing machine is provided. It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system or industrial control system, such as a set of computer-executable instructions. Furthermore, although the flowcharts show a logical order, in some cases, the steps shown or described may be performed in a different order than that described herein.

[0035] like Figure 4 As shown, the intelligent human figure recognition active safety protection method of the pulp sheet pressing machine may include the following steps.

[0036] Step S100: Obtain detection signals of preset protection zones at the front and / or rear of the pulp press machine. The preset protection zones include an emergency stop zone near the working mechanism of the pulp press machine and a warning zone located outside the emergency stop zone.

[0037] Specifically, after the human figure recognition active safety protection system is activated, the core control unit can control the human figure recognition sensors located at the front and / or rear of the slab pressing machine to enter the detection state. The human figure recognition sensors face the connection area between the front conveyor belt and the working mechanism of the pressing machine, and / or face the connection area between the rear conveyor belt and the working mechanism of the pressing machine, to continuously detect the corresponding preset protection areas.

[0038] The detection signal may include at least one of the following: target entry signal, infrared reflection signal, sensor area signal, target position signal, and sensor recognition signal. The target entry signal indicates whether a target has entered the preset protection area; the infrared reflection signal indicates the target's reflection of the infrared detection signal; the sensor area signal indicates the humanoid recognition sensor or sensing channel that generates the detection signal; the target position signal indicates the target's position within the preset protection area; and the sensor recognition signal can be used to indicate the detection result output by the humanoid recognition sensor after preliminary target identification.

[0039] As an optional embodiment, before acquiring the detection signal of the preset protection area, the emergency stop zone and the warning zone can be determined based on the position of the working mechanism of the pulp pressing machine and the position of the conveyor belt connected to the working mechanism, and a regional mapping relationship can be established between the sensing range of the human figure recognition sensor and the emergency stop zone and the warning zone. Therefore, the core control unit can determine the area where the target has fallen based on the source of the detection signal, the sensing range corresponding to the detection signal, or the target location information.

[0040] For example, the area near the working mechanism of the pressing machine and corresponding to the pressing, conveying, or clamping actions can be designated as the emergency stop zone, and the area outside the emergency stop zone where safety warnings are required when personnel approach can be designated as the warning zone. The specific dimensions of the emergency stop zone and the warning zone can be determined based on the pressing machine model, conveyor belt width, equipment installation space, personnel operating paths, and safety distance requirements; this application does not impose any limitations on these.

[0041] As an alternative embodiment, such as Figure 1 and Figure 2 As shown, at least two human figure recognition sensors can be installed at the front and / or rear of the slurry pressing machine. These sensors are arranged diagonally redundantly relative to their corresponding preset protection areas, and their sensing ranges overlap to cover both the emergency stop zone and the warning zone. This reduces blind spots caused by a single detection direction and preserves the ability to detect critical protection areas even when a single human figure recognition sensor malfunctions.

[0042] As an optional embodiment, the human figure recognition sensor can be installed above and / or to the side of the conveyor belt of the pulp pressing machine using an angle-adjustable mounting bracket. During installation, the installation angle of the human figure recognition sensor can be adjusted according to the equipment structure at the front and / or rear of the pulp pressing machine, the position of the conveyor belt, and the range of the preset protection area, so that the sensing range of the human figure recognition sensor covers the corresponding emergency stop zone and warning zone, and the adjusted sensing range is associated with the corresponding divided area.

[0043] It should be noted that the installation angle, height, and position of the human figure recognition sensor can be adjusted according to the on-site conditions. As long as the detection range of the human figure recognition sensor covers the preset protection area and can output a detection signal for determining the target location or the area where the target is located, the technical effects of the embodiments of this application can be achieved.

[0044] Step S200: In response to detecting that a target has entered a preset protection area based on a detection signal, human-shaped recognition is performed on the target to obtain a target recognition result. The target recognition result is used to characterize whether the target is a human target or a non-human target.

[0045] Specifically, when the human recognition sensor detects a target entering a preset protection area, it can acquire the target's detection features based on the detection signal and perform human recognition on the target based on the detection features. The detection features may include at least one of the following: contour features, body shape features, motion features, target height features, target width features, target motion trajectory features, and infrared reflectance intensity features.

[0046] As an optional embodiment, the human recognition sensor can acquire the detection features of the target based on the infrared signal reflected by the target, and match the detection features with preset human feature conditions; when the detection features meet the preset human feature conditions, the target recognition result is determined to represent the target as a human target; when the detection features do not meet the preset human feature conditions, the target recognition result is determined to represent the target as a non-human target.

[0047] For example, when the target entering the preset protection area is an operator, inspector, or maintenance personnel, the human figure recognition sensor can determine that it meets the human characteristic conditions based on the target's outline, body shape, or movement characteristics, and output the target recognition result corresponding to the human target; when the target entering the preset protection area is a pulp board, cardboard box, tool, pulp residue, or other non-human object, the human figure recognition sensor can determine that it does not meet the human characteristic conditions, and output the target recognition result corresponding to the non-human target.

[0048] Step S200 allows for further assessment of target attributes after a target enters a preset protection zone, preventing false alarms or accidental shutdowns caused by simply stopping the system based on the presence or absence of a target, thereby improving the accuracy of safety control.

[0049] Step S300: Determine the area in which the target will fall based on the target's position within the preset protection area.

[0050] Specifically, the core control unit can determine whether the target has fallen into the emergency stop zone or the warning zone based on at least one of the following: target location signal, human figure recognition sensor that generates detection signal, sensing channel corresponding to detection signal, and mapping relationship between sensing range and area.

[0051] As an optional embodiment, when a human figure recognition sensor has multiple detection sub-regions or multiple detection channels, each detection sub-region or detection channel can be associated with an emergency stop zone and a warning zone, respectively. When a detection signal comes from the detection sub-region corresponding to the warning zone, it is determined that the target has fallen into the warning zone; when a detection signal comes from the detection sub-region corresponding to the emergency stop zone, it is determined that the target has fallen into the emergency stop zone.

[0052] As another optional embodiment, when multiple human recognition sensors at different locations jointly cover a preset protection area, the area in which the target falls can be determined based on the position of the human recognition sensor that generates the detection signal, the intensity change of the detection signal, the direction of the target's movement, and the preset area mapping relationship.

[0053] Step S300 combines the target identification result with the area where the target is located, providing a basis for judgment to trigger different safety control actions in the future.

[0054] Step S400: Based on the target recognition result and the defined area where the target falls, trigger the corresponding action.

[0055] Specifically, the core control unit can trigger corresponding safety control actions based on whether the target identification result indicates that the target is a human target, and whether the area where the target falls is a warning zone or an emergency stop zone.

[0056] As an optional embodiment, when the target identification result indicates that the target is a non-human object, the core control unit filters the detection signal and maintains the current operating state of the pulp sheet press. In other words, when a non-human object enters the preset protection area, the shutdown interlock of the pulp sheet press is not triggered. This reduces the probability of accidental shutdowns caused by non-human objects such as pulp sheets, cartons, tools, and pulp residue.

[0057] As an optional embodiment, when the target identification result indicates that the target is a human body and the human body falls into the warning zone, the core control unit triggers a first safety control action. The first safety control action may include outputting a warning prompt, such as controlling the alarm device to output a low-level audible and visual alarm, voice prompt, or display prompt. At this time, since the human body has not yet entered the emergency stop zone near the pressing machine's working mechanism, the slab pressing machine can remain in a permissible operating state, or maintain its current operating state according to on-site safety requirements.

[0058] As an optional embodiment, when the target identification result indicates that the target is a human body and the human body falls into the emergency stop zone, the core control unit triggers a second safety control action. The second safety control action may include outputting an emergency stop alarm and controlling the slab pressing machine to perform an emergency stop. Further, the core control unit may send an emergency stop command to the pressing machine's actuator to stop the pressing action, conveying action, or other dangerous actions.

[0059] Step S400 enables graded safety control based on target attributes and area hazard levels. Compared to the "stop upon detection" control method of ordinary sensors, the embodiments of this application can ensure timely shutdown when personnel accidentally enter the core danger area, while reducing unnecessary shutdowns caused by personnel being in the outer warning area or non-human targets entering the detection range.

[0060] As an optional embodiment, before and / or during the corresponding action is triggered based on the target recognition result and the defined area into which the target falls, the safety door interlock status of the pulp press machine can also be obtained, and interlock control can be performed based on the safety door interlock status and the human figure recognition protection status.

[0061] Specifically, when the safety door interlock status indicates that the safety door is open, the core control unit can control the pulp press machine to be in a stopped, prohibited-from-start, or maintenance state, and adjust the action trigger logic of the preset protection zone to avoid repeated emergency stop triggers during maintenance operations. It should be noted that adjusting the action trigger logic when the safety door is open does not mean allowing the pulp press machine to operate normally when the safety door is open. Rather, it means adapting the alarm or emergency stop trigger logic of the human detection protection system based on the safety door interlock system already placing the pulp press machine in a stopped, prohibited-from-start, or maintenance state.

[0062] Specifically, when the target identification result indicates that the target is a human body and the human body falls into the emergency stop zone, the core control unit can output an interlock signal to the safety door interlock system, keeping the pulp press machine in a prohibited start state or a pending reset state until the human body leaves the emergency stop zone and completes the reset operation. This allows the newly added human recognition active protection system to form a collaborative control relationship with the existing safety door interlock system, avoiding inconsistencies in control states caused by the two safety systems operating independently.

[0063] As an optional embodiment, during the process of acquiring detection signals through human recognition sensors, the operating status of at least two human recognition sensors can also be acquired. When the operating status of one human recognition sensor indicates that it is faulty or has an occlusion abnormality, and the other human recognition sensors are in normal working condition, the core control unit can continue to acquire detection signals of the preset protection area based on the human recognition sensors in normal working condition, and perform target recognition result determination, area division determination, and corresponding action triggering according to the continuously acquired detection signals; at the same time, it outputs an abnormal prompt corresponding to the human recognition sensor with faulty or occlusion abnormality.

[0064] For example, when the pre-defined protected area is redundantly covered diagonally by two human detection sensors, if one sensor experiences a communication failure or its probe is blocked, the other sensor can still detect the emergency stop area and at least part of the warning area. In this case, the core control unit can continue human identification and safety control based on the detection signals from the normally functioning sensor, while simultaneously alerting staff to handle the malfunctioning sensor. This approach reduces the risk of a single point of failure causing a gap in protection.

[0065] As an optional embodiment, during the process of acquiring detection signals through the human figure recognition sensor, a fault self-detection of the human figure recognition sensor can also be performed. Fault self-detection may include detecting at least one of the human figure recognition sensor's infrared emitted signals, infrared received signals, and communication signals.

[0066] Specifically, when the infrared transmission signal, infrared reception signal, and / or communication signal meet preset fault conditions, the core control unit can generate a sensor fault result. The preset fault conditions may include at least one of the following: abnormal infrared transmission signal, infrared reception signal below a preset reception threshold, loss of communication heartbeat signal, communication interruption, abnormal sensor power supply, or continuous abnormal sensor output signal.

[0067] After generating sensor fault results, the core control unit can trigger a fault alarm based on the fault results and control the pulp press to switch to low-speed operation, automatic operation prohibited, or maintenance mode. The specific operating mode adopted can be determined based on the fault type, the number of faulty sensors, and the coverage capacity of the remaining normal sensors. For example, when a single human recognition sensor fails but redundant sensors can still cover the emergency stop area, the equipment can be allowed to enter a restricted operation mode and output a fault prompt; when multiple sensors fail simultaneously, causing the emergency stop area to be unable to be effectively covered, the pulp press can be controlled to enter an automatic operation prohibited mode or maintenance mode.

[0068] As an optional embodiment, during the self-detection of the human figure recognition sensor, the occlusion status of the sensor's probe can also be detected. When the sensor signal attenuation reaches a preset occlusion condition, or when the probe occlusion status indicates that the sensor's probe is blocked, an occlusion detection result is generated, and an occlusion alarm or cleaning prompt is output based on the occlusion detection result.

[0069] The preset occlusion conditions can be determined based on the reference signal of the human recognition sensor under normal unobstructed conditions, on-site dust and oil pollution conditions, historical signal change trends, or equipment maintenance requirements. For example, when the sensed signal continuously decreases relative to the reference signal and reaches a preset attenuation range, or when the occlusion detection module detects attachments on the outside of the probe, it can be determined that the preset occlusion conditions are met.

[0070] As an alternative embodiment, such as Figure 3 As shown, a transparent protective cover can be installed on the outside of the probe of the human recognition sensor. The transparent protective cover is used to prevent dust, oil, and / or slurry from adhering to the probe, thereby reducing direct contamination of the probe. The transparent protective cover can be made of acrylic, transparent engineering plastic, or other transparent materials that do not affect the sensor's detection performance.

[0071] Furthermore, a removable cleaning scraper can be provided on the outside of the transparent protective cover. The removable cleaning scraper is used to clean the surface of the transparent protective cover. The cleaning scraper can be installed on the outside of the transparent protective cover through a hinged, snap-fit, or detachable connection structure, and can rotate relative to the transparent protective cover to clean and maintain the surface of the transparent protective cover without removing the human recognition sensor.

[0072] By combining transparent protective covers, obstructed detection, and cleaning scrapers, human recognition sensors can adapt to the dusty, oily, and pulpy residue environments of pulp and paper workshops, reducing the risk of missed or false detections due to probe contamination.

[0073] The following describes the intelligent human figure recognition active safety protection method for the pulp pressing machine provided in this application embodiment, using a specific application scenario as an example.

[0074] In this application scenario, the front and rear ends of the slurry pressing machine are connected to the conveyor belt. The human detection active safety protection system has two human detection sensors at the front end and two at the rear end of the pressing machine. The two sensors at each end are arranged diagonally redundantly and are mounted above or to the side of the conveyor belt using angle-adjustable mounting brackets. The sensing range of each human detection sensor is adjusted to cover the warning zone and emergency stop zone at its corresponding end.

[0075] When the pulp press is running, the human detection sensor continuously acquires detection signals from the preset protection zone. If a pulp board, tool, or other non-human object enters the warning zone or emergency stop zone, the human detection sensor determines that the target is a non-human object based on its detection characteristics. The core control unit filters the corresponding detection signal and does not trigger the stop interlock.

[0076] If an operator enters the warning zone, the human detection sensor identifies the target as a human based on its detection characteristics. The core control unit determines that the human target has fallen into the warning zone based on the area mapping relationship and controls the alarm device to output a warning prompt to remind the operator to leave the corresponding area. At this time, if the human target has not entered the emergency stop zone, the slab press can remain in a permissible operating state.

[0077] If the operator continues to enter the emergency stop zone, the core control unit, based on the target identification result and the designated area where the target has fallen, triggers an emergency stop alarm and sends an emergency stop command to the pressing machine's actuator, causing the pulp pressing machine to cease its dangerous operation. Simultaneously, the core control unit outputs an interlock signal to the safety door interlock system, keeping the pulp pressing machine in a prohibited-start state or a pending reset state. Once the human target leaves the emergency stop zone, the alarm is deactivated, and a manual reset is completed, the pulp pressing machine can return to its normal operating readiness state.

[0078] During equipment operation, if a human figure recognition sensor experiences a communication interruption, abnormal infrared transmission, or abnormal infrared reception, the core control unit generates a sensor fault result, outputs a fault alarm, and controls the pulp sheet pressing machine to enter a low-speed operation state, an automatic operation prohibited state, or a maintenance state based on the coverage capacity of the remaining normal human figure recognition sensors. If the transparent protective cover on the outside of a human figure recognition sensor probe is blocked by dust, oil, or pulp residue, the obstruction detection module generates an obstruction detection result, and the core control unit outputs an obstruction alarm or cleaning prompt. Workers can clean the adhering substances on the surface of the transparent protective cover using a removable cleaning scraper.

[0079] Through the above-described embodiments, the present application can achieve active detection, human recognition, area classification judgment, graded safety control, safety door interlocking, fault self-detection, obstruction detection, and redundant fault-tolerant control of the dangerous areas at the front and / or rear of the pulp pressing machine, thereby improving the accuracy, reliability, and field applicability of the safety protection of the dangerous areas of the pulp pressing machine.

[0080] According to another aspect of the embodiments of this application, an intelligent human figure recognition active safety protection device for a pulp board pressing machine is also provided. This device may include a detection signal acquisition unit, a target recognition unit, an area determination unit, and a safety control unit.

[0081] The detection signal acquisition unit is used to acquire detection signals of the preset protection areas at the front and / or rear of the pulp pressing machine. The preset protection areas include the emergency stop area near the working mechanism of the pulp pressing machine and the warning area located outside the emergency stop area.

[0082] The target recognition unit, connected to the detection signal acquisition unit, is used to perform human-shaped recognition on the target in response to the detection signal that the target has entered the preset protection area, and to obtain the target recognition result. The target recognition result is used to characterize the target as a human target or a non-human target.

[0083] The area determination unit, connected to the target identification unit, is used to determine the area into which the target falls based on the target's position within the preset protection area.

[0084] The safety control unit, connected to the area determination unit, is used to trigger corresponding actions based on the target identification results and the defined area where the target falls.

[0085] As an optional embodiment, the safety control unit can be used to filter the detection signal and maintain the current operating state of the pulp press machine when the target identification result indicates that the target is a non-human target; to trigger a first safety control action when the target identification result indicates that the target is a human target and the human target falls into the warning zone; and to trigger a second safety control action when the target identification result indicates that the target is a human target and the human target falls into the emergency stop zone.

[0086] As an optional embodiment, the detection signal acquisition unit may include at least two human figure recognition sensors, which are arranged diagonally redundantly relative to the corresponding preset protection area, and the sensing range of the at least two human figure recognition sensors overlaps to cover the emergency stop area and the early warning area.

[0087] As an optional embodiment, the device may further include a region mapping establishment unit, which is used to determine the emergency stop zone and the early warning zone based on the position of the working mechanism of the pulp pressing machine and the position of the conveyor belt connected to the working mechanism, and to establish a region mapping relationship between the sensing range of the human figure recognition sensor and the emergency stop zone and the early warning zone.

[0088] As an optional embodiment, the device may further include a safety door interlock unit, which is used to acquire the safety door interlock status of the pulp pressing machine and perform interlock control based on the safety door interlock status and the human recognition protection status.

[0089] As an optional embodiment, the device may further include a fault self-detection unit, which is used to detect at least one of the infrared emission signal, infrared reception signal and communication signal of the human figure recognition sensor, and generate a sensor fault result when a preset fault condition is met.

[0090] As an optional embodiment, the device may further include an occlusion detection unit, which is used to detect the occlusion state of the probe of the human figure recognition sensor and generate an occlusion detection result when a preset occlusion condition is met.

[0091] As an optional embodiment, the device may further include a working condition adaptation structure, which includes a transparent protective cover disposed outside the human recognition sensor probe and a removable cleaning scraper disposed outside the transparent protective cover. The transparent protective cover is used to prevent dust, oil, and / or slurry from adhering to the probe, and the removable cleaning scraper is used to clean the adhering substances on the surface of the transparent protective cover.

[0092] The aforementioned intelligent human-shaped recognition active safety protection device for the pulp sheet pressing machine may also include a processor and a memory. The aforementioned detection signal acquisition unit, target recognition unit, area determination unit, safety control unit, area mapping establishment unit, safety door interlock unit, fault self-detection unit, and obstruction detection unit can all be stored as program units in the memory, and the processor executes these program units to achieve the corresponding functions. Each of the above units can also be implemented through hardware circuits, programmable logic controllers, or a combination of hardware and software.

[0093] According to another aspect of the embodiments of this application, an electronic device is also provided, which may include a processor, a memory, and a program stored in the memory and capable of running on the processor. When the processor executes the program, it implements any of the above-described intelligent human figure recognition active safety protection methods for pulp sheet pressing machines.

[0094] According to another aspect of the embodiments of this application, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored program, wherein when the program is executed by a processor, it implements any of the above-described intelligent human figure recognition active safety protection methods for pulp sheet pressing machines.

[0095] It should be noted that the steps performed by each unit in the above device embodiments can be found in the relevant descriptions in the above method embodiments, and will not be repeated here. In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods; multiple units or components can be combined or integrated into another system; some features can be ignored or not executed.

[0096] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units or control modules. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0097] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0098] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

[0099] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

[0100] The above description is merely an embodiment of this application and is not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for intelligent human recognition and active safety protection in a pulp board pressing machine, characterized in that, include: Acquire detection signals of preset protection areas at the front and / or rear of the pulp pressing machine, wherein the preset protection areas include an emergency stop area near the working mechanism of the pulp pressing machine and a warning area located outside the emergency stop area; In response to detecting that a target has entered the preset protection area based on the detection signal, human figure recognition is performed on the target to obtain a target recognition result, which is used to characterize whether the target is a human target or a non-human target; Based on the location of the target within the preset protection area, determine the area in which the target falls. Based on the target recognition result and the defined region where the target falls, a corresponding action is triggered.

2. The method according to claim 1, characterized in that, The step of triggering a corresponding action based on the target recognition result and the defined region in which the target falls includes: When the target recognition result indicates that the target is a non-human target, the detection signal is filtered, and the current operating state of the pulp pressing machine is maintained; When the target identification result indicates that the target is a human target and the human target falls into the warning zone, a first safety control action is triggered, the first safety control action includes outputting a warning prompt; When the target identification result indicates that the target is a human target and the human target falls into the emergency stop zone, a second safety control action is triggered. The second safety control action includes outputting an emergency stop alarm and controlling the pulp press machine to perform an emergency stop.

3. The method according to claim 1, characterized in that, Before acquiring the detection signal of the preset protection area, the process also includes: The emergency stop zone and the early warning zone are determined based on the position of the working mechanism of the pulp press and the position of the conveyor belt connected to the working mechanism. Establish a regional mapping relationship between the sensing range of the human figure recognition sensor and the emergency stop zone and the early warning zone; The determination of the area into which the target falls, based on the target's position within the preset protection area, includes: determining whether the target falls into the emergency shutdown zone or the early warning zone based on the human figure recognition sensor that generates the detection signal, the sensing range corresponding to the detection signal, and the area mapping relationship.

4. The method according to claim 3, characterized in that, The acquisition of detection signals from the preset protective areas at the front and / or rear of the pulp pressing machine includes: The detection signal is acquired by at least two human-shaped recognition sensors located at the front and / or rear of the pulp press machine; The at least two human figure recognition sensors are arranged in a redundant coverage manner with preset protection areas corresponding to different detection directions, and the sensing ranges of the at least two human figure recognition sensors overlap and / or complement each other to superimpose coverage of the emergency shutdown area and the early warning area.

5. The method according to claim 4, characterized in that, The human figure recognition sensor is mounted above and / or to the side of the conveyor belt of the pulp pressing machine via an angle-adjustable mounting bracket; The establishment of a regional mapping relationship between the sensing range of the human figure recognition sensor and the emergency stop zone and the early warning zone includes: Based on the equipment structure at the front and / or rear of the pulp pressing machine, the position of the conveyor belt, and the range of the preset protection area, adjust the installation angle of the human figure recognition sensor so that the sensing range of the human figure recognition sensor covers the corresponding emergency stop area and early warning area, and associate the adjusted sensing range with the corresponding divided area.

6. The method according to claim 4, characterized in that, In response to detecting a target entering the preset protection area based on the detection signal, human figure recognition is performed on the target to obtain a target recognition result, including: The human figure recognition sensor acquires the detection features of the target based on the infrared signal reflected by the target, and the detection features include at least one of contour features, body shape features and motion features; The detected features are matched with preset human feature conditions; When the detected features meet the preset human feature conditions, the target recognition result is determined to represent the target as a human target; When the detected features do not meet the preset human feature conditions, the target recognition result is determined to indicate that the target is a non-human target.

7. The method according to claim 4, characterized in that, The process of acquiring the detection signal of the preset protection area also includes: Obtain the operating status of the at least two human figure recognition sensors; When the working status of one of the human figure recognition sensors indicates that it is malfunctioning or occluded, and the other human figure recognition sensors are in normal working condition, the detection signal of the preset protection area is continuously acquired based on the human figure recognition sensor in normal working condition, and the determination of the target recognition result, the determination of the divided area, and the triggering of the corresponding action are performed according to the continuously acquired detection signal. At the same time, it outputs abnormal prompts corresponding to the malfunction or occlusion of the human recognition sensor.

8. The method according to claim 1, characterized in that, Before and / or during the triggering of the corresponding action based on the target recognition result and the defined region in which the target falls, the method further includes: Obtain the safety door interlock status of the pulp press machine; When the safety door interlock status indicates that the safety door is open, the pulp pressing machine is controlled to be in a stopped state, a prohibited start state, or a maintenance state, and the action triggering logic of the preset protection area is adjusted to avoid repeated emergency stop triggering during maintenance operations. When the target identification result indicates that the target is a human target and the human target falls into the emergency stop area, an interlock signal is output to the safety door interlocking system to keep the pulp press machine in a prohibited start state or a pending reset state until the human target leaves the emergency stop area and the reset operation is completed.

9. The method according to claim 4, characterized in that, The process of acquiring the detection signal through the human figure recognition sensor also includes: The human figure recognition sensor is subjected to fault self-detection, which includes detecting at least one of the infrared emission signal, infrared reception signal and communication signal of the human figure recognition sensor. When the infrared transmission signal, the infrared reception signal and / or the communication signal meet the preset fault conditions, a sensor fault result is generated. Based on the sensor malfunction result, a fault alarm is triggered, and the pulp press machine is controlled to switch to low-speed operation, automatic operation prohibited, or maintenance mode.

10. The method according to claim 9, characterized in that, The process of self-detecting faults in the human figure recognition sensor also includes: Detect the occlusion status of the detection window of the human figure recognition sensor; When the sensing signal of the human figure recognition sensor attenuates to a preset occlusion condition, or when the occlusion state of the detection window indicates that the detection window is occluded, an occlusion detection result is generated. An occlusion alarm is output based on the occlusion detection result, and a cleaning instruction is generated. The cleaning instruction is used to instruct the detection window of the human figure recognition sensor or the protective component located outside the detection window to be cleaned.

Images