Laser shock peening equipment with active safety protection device
By integrating image acquisition and thermal imaging components into the laser shock strengthening equipment for dual-feature fusion judgment, controlling the laser to stop emitting light and driving the light shield to block the light path, the problem of blind spots in the protection of the laser shock strengthening equipment is solved, achieving higher safety and accuracy.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- SHANGHAI INST OF LASER TECH
- Filing Date
- 2026-01-15
- Publication Date
- 2026-05-29
AI Technical Summary
Existing laser shock peening equipment cannot be completely sealed off when workpiece clamping and observation are required, creating a blind spot that poses a risk of personnel accidentally being exposed to laser radiation.
The system uses image acquisition and thermal imaging components to collect surrounding information in real time. The data processing component performs dual-feature fusion judgment to generate a control signal to control the laser to stop emitting light and drive the light shield to block the light path, thereby achieving active safety protection.
It improves the safety of laser shock peening equipment by preventing personnel from accidentally entering the light radiation area through real-time monitoring and intelligent judgment, thus making up for the blind spots of traditional protection and improving the overall safety and accuracy.
Smart Images

Figure CN122105099A_ABST
Abstract
Description
Technical Field
[0002] This invention relates to the field of laser processing technology, and in particular to a laser shock strengthening equipment equipped with an active safety protection device. Background Technology
[0004] Laser shock peening technology utilizes high-energy pulsed lasers to induce shock waves that modify the surface of workpieces, significantly improving the fatigue properties of materials. However, high-energy laser beams are extremely destructive to human tissue. To ensure operational safety, existing laser shock peening equipment generally employs a completely enclosed protective chamber as the primary protective measure, with safety interlock devices installed at the chamber door. The design principle is to ensure that the laser can only be emitted when the chamber door is completely locked. However, this passive protective design has inherent limitations: to facilitate workpiece clamping, alignment, and process observation, the worktable and workpiece clamping area at the laser beam's point of impact must maintain a certain degree of openness and cannot be completely covered by the protective chamber. This creates a risk that personnel may accidentally enter this open area and be exposed to laser radiation during equipment operation, thus forming a substantial safety blind spot at the end of the optical path between the laser and the workpiece. Summary of the Invention
[0006] Therefore, it is necessary to provide a laser shock strengthening equipment with active safety protection devices that can compensate for the blind spots in the protection that cannot be completely closed due to the needs of workpiece clamping and observation, in order to address the above-mentioned technical problems.
[0007] The present invention provides a laser shock strengthening equipment with an active safety protection device, including a laser and a worktable for placing workpieces, and also includes an image acquisition component, a thermal imaging component, a data processing component, a control component, and a light shield. The image acquisition component is used to acquire visual information around the workbench in real time; The thermal imaging component is used to collect thermal imaging information around the workbench in real time. The data processing component is signal-connected to the image acquisition component and the thermal imaging component, and is used to receive the visual information and the thermal imaging information, and perform dual-feature fusion judgment; wherein, the dual-feature fusion judgment includes: extracting the human body contour features of the target based on the visual information, and extracting the temperature features of the target based on the thermal imaging information; when the human body contour features conform to a preset human body feature model and the temperature features are within a preset human body temperature range, it is determined that a person is approaching, and a first control signal is generated. The control component is signal-connected to the data processing component; The light-shielding plate is disposed in the optical path of the laser and is drivenly connected to the control component; The control component is configured to: when receiving the first control signal, control the laser to stop emitting light and drive the light shield to move to the closed position to block the light path.
[0008] In one embodiment, the data processing component includes a first data processing module and a second data processing module; the first data processing module is signal-connected to the image acquisition component and is used to perform contour feature extraction and judgment based on the visual information; the second data processing module is signal-connected to the thermal imaging component and is used to perform temperature feature extraction and judgment based on the thermal imaging information; the first data processing module and the second data processing module are communicatively connected to collaboratively complete the dual-feature fusion judgment.
[0009] In one embodiment, multiple image acquisition components and thermal imaging components are arranged around the perimeter of the worktable to cover the surrounding area of the worktable without any blind spots.
[0010] In one embodiment, the light-shielding plate is driven to the control component via a drive mechanism; the drive mechanism is configured to drive the light-shielding plate to reciprocate or rotate between a closed position and an open position, wherein in the open position, the light-shielding plate completely avoids the optical path of the laser.
[0011] In one embodiment, the control component is further configured to perform a tiered alarm response, including: If a potential risk target is identified based on either the visual information or the thermal imaging information, a second control signal is generated and an early warning is triggered. The first control signal is generated and the laser stop and optical path blocking are executed only when the dual-feature fusion judgment determines that a person is approaching.
[0012] In one embodiment, the laser shock enhancement equipment further includes an alarm connected to the control component via a signal; the control component is configured to: control the alarm to issue a warning when receiving the second control signal; and control the alarm to issue an emergency alarm when receiving the first control signal.
[0013] In one embodiment, the condition for generating the second control signal and triggering the warning is precisely determined by introducing quantified risk parameters; the control component is configured to execute: S1. When a potential risk target is identified based solely on either the visual information or the thermal imaging information, calculate the real-time risk coefficient R of the target; wherein the formula for calculating the real-time risk coefficient R is: ,in The real-time distance between the potential risk target and the edge of the workbench. The preset baseline safety distance, The moving speed of the potential risk target. The preset reference speed, and The weighting coefficients are preset, and ; S2. The real-time risk coefficient R is compared with a preset first early warning threshold. Second warning threshold Comparison, among which ; S3, only when When this occurs, the second control signal is generated and an early warning is triggered; if At the same time as the warning is issued, the control component generates and executes a preparatory command to put the laser shock enhancement process into a deceleration or pause standby state.
[0014] In one embodiment, the first warning threshold and / or the aforementioned reference safety distance Reference speed This is not a fixed value, but rather dynamically and adaptively adjusted by the control components based on the real-time monitored environmental disturbance level E; specific adjustment methods include: S11. Calculate the interference fluctuation value of the current environment using the background data from the image acquisition component and / or thermal imaging component. ; S12, Based on the interference fluctuation value The environmental interference level E is dynamically queried or calculated based on the preset range in which it is located, where E is related to... Positive correlation; S13. Based on the preset mapping relationship, use the environmental interference level E to adjust the first warning threshold. and / or the aforementioned reference safety distance Make corrections; the correction formula is: , and / or ;in, and As the baseline value, As the baseline environmental interference level, This is the preset sensitivity coefficient; 14. In the subsequent step S2, the corrected version is used. and / or used when calculating R Make a judgment.
[0015] In one embodiment, the weighting coefficients and and the sensitivity coefficient and It is configured to perform iterative optimization based on historical warning and false alarm data through the control component; the optimization method includes the following periodic execution: S21. Collect all event records that trigger early warnings and emergency alarms within a statistical period, as well as the real-time distance between the potential risk target and the edge of the workbench before the corresponding event occurs. Movement speed and environmental interference level E; S22. Classify and analyze events: If an alert is not escalated to an emergency alert after being issued, and is verified to be a valid non-threatening target, it is marked as a tolerable alert; if an alert is quickly escalated to an emergency alert after being issued, it is marked as an accurate alert; if an emergency alert is triggered directly without prior warning, it is marked as a missed alert. S23. With the optimization objective of minimizing the false negative rate and keeping the tolerable warning rate below a preset upper limit, use gradient descent or genetic algorithm to optimize the parameter set. Perform iterative adjustments; S24. Optimize the new parameter set. Update the decision logic of the control component for risk assessment in the next statistical period.
[0016] In one embodiment, the control component is also communicatively connected to the laser's state detection unit and is configured to verify whether the laser has actually stopped emitting light after driving the light shield to the closed position; if not, to maintain the light shield in the closed position and report fault information.
[0017] The aforementioned laser shock strengthening equipment, equipped with active safety protection devices, utilizes image acquisition and thermal imaging components strategically placed around the workbench. A data processing component performs dual-feature fusion analysis on the acquired visual and thermal information, confirming that a person is approaching only when the target simultaneously matches human contour features and a specific body temperature range. This improves the accuracy and anti-interference capability at the source. When personnel are detected entering the danger zone, the control component simultaneously executes two core safety commands: stopping laser emission and moving the light shield to a closed position to physically block the light path. This expands traditional, static enclosure protection into dynamic, active protection targeting the laser beam's end-effect area, directly compensating for blind spots that cannot be completely sealed due to workpiece clamping and observation requirements. Through real-time monitoring, intelligent judgment, and rapid execution of closed-loop control to block the light path, it prevents potential harm from light radiation caused by accidental personnel entering the area, thus enhancing the overall safety of the laser shock strengthening equipment. Attached Figure Description
[0018] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.
[0019] Figure 1 This is a schematic diagram of a laser shock enhancement device with an active safety protection device, as one embodiment.
[0020] Figure label: 1. Control component; 2. Laser; 3. Worktable; 4. Sample; 5. First data processing component; 6. Image acquisition component; 7. Alarm; 8. Thermal imaging component; 9. Sunshade; 10. Second data processing component. Detailed Implementation
[0022] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0023] It should be noted that when a component is referred to as being "fixed to" or "set on" another component, it can be directly on the other component or there may be an intermediate component. When a component is considered to be "connected to" another component, it can be directly connected to the other component or there may be an intermediate component present. The terms "vertical," "horizontal," "upper," "lower," "left," "right," and similar expressions used in this specification are for illustrative purposes only and do not represent the only possible implementation.
[0024] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, the terms "first" and "second" are limited to this specific usage. The feature may explicitly or implicitly include at least one of the features. In the description of this invention, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified.
[0025] In this invention, unless otherwise explicitly specified and limited, "above" or "below" the second feature can mean that the first feature is in direct contact with the second feature, or that the first feature and the second feature are in indirect contact through an intermediate medium. Furthermore, "above," "over," and "on top" the second feature can mean that the first feature is directly above or diagonally above the second feature, or simply indicates that the first feature is at a higher horizontal level than the second feature. "Below," "below," and "under" the second feature can mean that the first feature is directly below or diagonally below the second feature, or simply indicates that the first feature is at a lower horizontal level than the second feature.
[0026] Unless otherwise defined, all technical and scientific terms used in this specification have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "and / or" as used in this specification includes any and all combinations of one or more of the associated listed items.
[0027] The following is combined with Figure 1 The present invention describes a laser shock enhancement equipment equipped with an active safety protection device.
[0028] like Figure 1 As shown, in one embodiment, a laser shock enhancement equipment with an active safety protection device includes a laser 2 and a worktable 3 for placing workpieces. It also includes an image acquisition component 6, a thermal imaging component 8, a data processing component, a control component 1, and a light-shielding plate 9. The image acquisition component 6 is used to acquire visual information around the worktable 3 in real time, and the thermal imaging component 8 is used to acquire thermal imaging information around the worktable 3 in real time. The data processing component is signal-connected to the image acquisition component 6 and the thermal imaging component 8, and is used to receive visual information and thermal imaging information, and perform dual-feature fusion judgment. The dual-feature fusion judgment includes: extracting the human contour features of the target based on visual information, and extracting the temperature features of the target based on thermal imaging information. When the human contour features conform to a preset human feature model and the temperature features are within a preset human body temperature range, it is determined that a person is approaching, and a first control signal is generated. The control component 1 is signal-connected to the data processing component. The light-shielding plate 9 is disposed on the optical path of the laser 2 and is drivenly connected to the control component 1. The control component 1 is configured to: when receiving the first control signal, control the laser 2 to stop emitting light and drive the light-shielding plate 9 to move to a closed position to block the optical path.
[0029] This embodiment integrates a dual sensing and fusion judgment mechanism of visual and thermal imaging, and links it with a physical shading device. Specifically, the image acquisition component 6 (such as an industrial camera) and the thermal imaging component 8 capture information about the surroundings of the workbench 3 from different dimensions. The data processing component performs parallel processing and feature extraction on these two information sources: by analyzing the shape, posture, and other information in the visual image, it determines whether the target conforms to a preset human contour model (for example, a detection algorithm based on a convolutional neural network can be used); at the same time, it analyzes the thermal imaging data to determine whether the surface temperature of the target falls within a preset human body temperature range (such as 32°C to 42°C). Only when both conditions are met simultaneously does the system confirm that a "person" is approaching, rather than other heat sources or objects, thereby generating a first control signal. Upon receiving this high-confidence signal, control component 1 immediately executes two safety actions: first, it sends a command to laser 2 to stop emitting laser light; second, it drives the light-shielding plate 9 (which may be a mechanical baffle driven by a motor, cylinder, etc.) to move rapidly (e.g., translate or rotate) into the laser beam path, forming a physical barrier. Even if laser 2 fails to stop immediately due to a malfunction, it ensures that the laser beam is blocked and cannot illuminate the workbench area. Thus, the dual-feature fusion judgment greatly reduces the false alarm rate (for example, it will not trigger a shutdown due to a hot object with a similar outline or a non-human heat source with a temperature close to that of a human body), improving the accuracy of personnel identification. Simultaneously, the light-shielding plate 9, as the last line of physical defense, forms redundant safety protection with the laser 2's stop-light command. Even if the electrical control command fails, it can provide reliable physical isolation, enhancing the active safety protection level of the equipment when personnel accidentally enter a dangerous area.
[0030] The data processing component includes a first data processing module 5 and a second data processing module 10. The first data processing module 5 is signal-connected to the image acquisition component 6 and is used to perform contour feature extraction and judgment based on visual information. The second data processing module 10 is signal-connected to the thermal imaging component 8 and is used to perform temperature feature extraction and judgment based on thermal imaging information. The first data processing module 5 and the second data processing module 10 are communicatively connected to collaboratively complete the dual-feature fusion judgment. The specific architecture of the data processing component is a distributed or modular design. The first data processing module 5 is specifically responsible for processing the visual information stream from the image acquisition component 6 and running the human contour recognition algorithm. The second data processing module 10 is specifically responsible for processing the thermal imaging information stream from the thermal imaging component 8 and running the temperature range judgment algorithm. The two modules are connected through a communication link (such as a bus or network) to exchange intermediate judgment results or raw feature data, and finally collaboratively make a fusion judgment (for example, after receiving the "target matching human contour found" information sent by the first data processing module 5, the second data processing module 10 checks whether the temperature of the target in the thermal imaging image meets the standard, and vice versa). This collaborative architecture separates computational tasks, allowing for the use of optimized processing hardware and algorithms for different sensor data types, thus improving the overall system processing speed and real-time performance. Simultaneously, the modular design facilitates system maintenance, upgrades, and fault diagnosis. Multiple image acquisition components 6 and thermal imaging components 8 are arranged around the perimeter of the workbench 3 to provide comprehensive coverage of its surrounding area. In practice, multiple industrial cameras and thermal imagers can be installed around, above, or at key entrances to the workbench 3, ensuring that approaching objects are detected from all angles. This eliminates blind spots that may exist with a single sensor, ensuring that at least one image acquisition component 6 and one thermal imaging component 8 can capture information regardless of the direction from which personnel approach the hazardous area of the workbench 3, thereby guaranteeing the continuous effectiveness of dual-feature fusion judgment and comprehensive protection.
[0031] The light-shielding plate 9 is driven and connected to the control component 1 via a drive mechanism. The drive mechanism is configured to drive the light-shielding plate 9 to reciprocate or rotate between a closed position and an open position. In the open position, the light-shielding plate 9 completely avoids the optical path of the laser 2. The drive mechanism can be a linear motor, a servo motor with a lead screw, a rotary cylinder, or an electromagnet, etc. Under normal operating conditions, the light-shielding plate 9 is in the "open position," that is, completely removed from the optical path, without affecting the normal transmission of the laser beam to the workpiece. Only upon receiving the first control signal does the control component 1 command the drive mechanism to act quickly, pushing the light-shielding plate 9 into or rotating it to the "closed position" to block the optical path. The light-shielding plate 9 is a dynamically controllable optical shutter, rather than a fixed obstruction, ensuring the smooth flow of the optical path during normal processing while responding quickly in emergencies, achieving a balance between safety and functionality. The laser shock peening equipment also includes a laser adapter plate for mounting the laser 2. The drive mechanism is mounted on the laser adapter plate and drives the light-shielding plate 9 to enter or exit the optical path by swinging or rotating. Specifically, the drive mechanism (such as a swing cylinder or a rotary servo motor) is directly fixed to the adapter plate or mounting base supporting the laser 2, so that the rotation axis or swing center of the light-shielding plate 9 is close to the optical path. This compact and integrated installation method reduces the transmission chain of the light-shielding plate 9, improves the response speed and positioning accuracy; at the same time, it closely links the safety components with the laser body structure, simplifies the overall mechanical layout, and enhances the rigidity and reliability of the system.
[0032] Control component 1 is also configured to execute a tiered alarm response, including: if a potential risk target is identified based on either visual information or thermal imaging information, a second control signal is generated and an early warning is triggered; only when a person is determined to be approaching based on the dual-feature fusion judgment is a first control signal generated and laser shutdown and optical path blocking executed. The program logic of control component 1 includes two levels of judgment: primary judgment (single-feature recognition) and advanced judgment (dual-feature fusion). When either the image acquisition component 6 or the thermal imaging component 8 detects a suspicious target (e.g., a human-like outline is identified in the image, or a heat source close to human body temperature is detected in the thermal imaging), but the dual-feature conditions are not simultaneously met, the system considers there to be a "potential risk," and at this time, a second control signal is generated to trigger an early warning (e.g., an audible and visual prompt "Caution: Safety First"). Only when the dual-feature fusion judgment confirms that a "person" is approaching is the highest-level first control signal generated, executing ultimate protective actions such as machine shutdown and light shielding. Thus, a refined safety response is achieved, avoiding frequent production interruptions caused by non-personnel targets, and optimizing human-machine collaboration experience and production efficiency while ensuring absolute safety. The laser shock peening equipment also includes an alarm 7 connected to the control component 1. The control component 1 is configured to: issue a warning alert when a second control signal is received; and issue an emergency alarm when a first control signal is received. The alarm 7 can be a buzzer, a warning light, or a voice broadcast device. The control component 1 drives the alarm 7 to issue alarms of different modes and intensities according to the received signal level. For example, a warning alert might be an intermittent flashing yellow light or a low-volume warning sound; while an emergency alarm would be a continuous flashing red light and a high-decibel alarm sound. Through differentiated alarm signals, the current safety status level is clearly conveyed to on-site operators. The warning alert serves to draw attention, while the emergency alarm clearly indicates that a danger has occurred and equipment protection has been triggered, facilitating personnel's quick understanding of the situation and appropriate action. The control component 1 is also communicatively connected to the status detection unit of the laser 2 and is configured to verify whether the laser 2 has actually stopped emitting light after driving the light shield 9 to the closed position; if not, it maintains the light shield 9 in the closed position and reports fault information, thereby adding closed-loop verification and fault diagnosis functions to the safety link. After issuing the light-stop command and driving the light shield 9 to close, the control component 1 does not immediately end the safety process, but instead reads the information from the internal status detection unit (such as the optical power monitor and the light emission status feedback signal) of the laser 2 through the communication interface (such as digital I / O or fieldbus) to confirm whether the laser has indeed been extinguished.If the feedback indicates that the laser is still emitting light, control component 1 determines it to be a laser control failure. It will keep the light shield 9 closed to ensure safety, and simultaneously report specific fault information (such as "no response to laser stop command") through the human-machine interface, network, or log records. This achieves proactive verification of the safety command execution result, forming a closed-loop control for safety protection. It can promptly detect and lock down faults in the safety subsystem (laser control), improving the fault safety level and maintainability of the entire equipment. The human body temperature range is set to 32℃ to 42℃. The temperature threshold range used for personnel identification is quantified. Setting the temperature range to 32℃ to 42℃, rather than the more precise 36-37.5℃ core body temperature range, takes into account that human body surface temperature in actual industrial environments can fluctuate significantly due to factors such as clothing, ambient temperature, and activity level. This wider range covers more practical situations; for example, body surface temperature may be lower when wearing thick clothing, while it may be higher when approaching someone after strenuous exercise. While ensuring that most non-human heat sources (such as machine heating parts that are usually at higher or lower temperatures) are excluded, the recall rate of personnel identification is improved, the false negatives caused by slight fluctuations in body surface temperature are reduced, and the adaptability of the protection system under different working conditions is enhanced.
[0033] The conditions for generating a second control signal and triggering an early warning are accurately determined by introducing quantified risk parameters; control component 1 is configured to execute: S1, when a potential risk target is identified based solely on either visual information or thermal imaging information, calculate the real-time risk coefficient R of the target; wherein, the formula for calculating the real-time risk coefficient R is: in, This represents the real-time distance between the potential risk target and the edge of the workbench 3. The preset baseline safety distance, For the movement speed of potential risk targets, The preset reference speed, and The weighting coefficients are preset, and S2. Compare the real-time risk coefficient R with the preset first warning threshold. Second warning threshold Comparison, among which S3, only when At that time, a second control signal is generated and an early warning is triggered; if Simultaneously with the warning, control component 1 generates and executes a preparatory command to decelerate or pause the laser shock enhancement process. This upgrades the primary warning mechanism from a simple "presence / absence" judgment to a continuous risk assessment model based on the target's dynamic behavior (distance D and velocity V). The system uses image tracking or thermal imaging tracking technology to calculate in real-time the distance D between the potential risk target and the edge of the worktable, as well as its moving velocity V. The formula for calculating the risk coefficient R is... It combines these two key factors: The closer the target is (the smaller D is), the greater the risk contribution. The term indicates that the faster the target speed (the larger V), the greater the risk contribution. Weighting coefficient. and This is used to adjust the relative importance of distance and speed factors. The system then compares the calculated R value with two incremental thresholds. and Comparison. Only when the risk reaches the minimum threshold. This only triggered a general warning. If the risk escalates further... Based on the early warning system, the system will issue preparatory instructions in advance, such as slowing down the laser processing head or putting it into a pause standby mode, to prepare for a smooth transition in case of a possible emergency shutdown. This solves the problems of traditional early warning mechanisms being either too sensitive (alarming at the slightest approach) or too insensitive (alarming only when very close). Through a quantified risk coefficient R, the system can more accurately assess the threat level, achieving a refined, tiered response: "long-distance slow approach → low risk, possibly no warning," "medium-distance medium-speed approach → medium risk, triggering a warning," and "close-range rapid approach → high risk, warning and preparation for shutdown." This significantly reduces production interruptions caused by non-threatening proximity, while providing early warnings and preparations when real threats occur, optimizing the balance between safety and efficiency.
[0034] First warning threshold and / or the aforementioned reference safety distance Reference speed It is not a fixed value, but is dynamically and adaptively adjusted by control component 1 based on the real-time monitored environmental interference level E. The specific adjustment method includes: S11, calculating the current environmental interference fluctuation value using background data from image acquisition component 6 and / or thermal imaging component 8. S12. Based on the interference fluctuation value The environmental interference level E is dynamically queried or calculated based on the preset range in which it is located, where E is related to... Positive correlation; S13. Based on the preset mapping relationship, use the environmental interference level E to set the first warning threshold. and / or baseline safety distance Make corrections; the correction formula is: and / or ;in, and As the baseline value, As the baseline environmental interference level, The preset sensitivity coefficient is used; S14. In the subsequent step S2, the corrected sensitivity coefficient is used. and / or used when calculating R The system makes a judgment, thereby enabling the risk assessment model to adapt to the environment. It analyzes background information collected by sensors in real time (such as brightness changes in visual images and background temperature uniformity in thermal imaging) and calculates a fluctuation value characterizing the intensity of environmental noise or interference. (For example, image pixel grayscale variance, thermal image temperature standard deviation). The magnitude of δ is mapped to the environmental interference level E. High environmental interference (high E) means a decrease in the sensor's signal-to-noise ratio and an increased likelihood of false alarms. To suppress false alarms, the system uses the formula... Raise the warning threshold This makes triggering an early warning require a higher risk factor; at the same time, through the formula Narrowing the baseline safety distance used for risk calculation This reduces the risk contribution value at the same actual distance. Conversely, in clear environments with minimal interference, a more sensitive benchmark value is used. This overcomes the shortcomings of fixed-threshold models, which are prone to false alarms or missed alarms in complex industrial environments (such as sudden changes in lighting, background heat sources, and thermal imaging drift caused by air disturbances). By dynamically adjusting key parameters, the sensitivity of the early warning system can be inversely linked to the environmental noise level. It is "passivated" in high-interference environments to reduce false alarms and "sharpened" in low-interference environments to improve detection sensitivity, thus enhancing the robustness and reliability of the entire hierarchical alarm system under different operating conditions. Weighting coefficients and and sensitivity coefficient and It is configured to perform iterative optimization based on historical warning and false alarm data through control component 1; the optimization method includes the following periodic execution: S21, collecting all event records that trigger warnings and emergency alarms within a statistical period, as well as the real-time distance D, movement speed V, and environmental interference level E between the potential risk target and the edge of workbench 3 before the corresponding event occurs; S22, classifying and analyzing the events: if the warning does not escalate to an emergency alarm after being issued and is verified as a valid non-threat target, it is marked as a tolerable warning; if the warning quickly escalates to an emergency alarm after being issued, it is marked as an accurate warning; if an emergency alarm is triggered directly without a warning, it is marked as a missed alarm; S23, with the optimization objective of minimizing the missed alarm rate and keeping the tolerable warning rate below a preset upper limit, using gradient descent or genetic algorithm to optimize the parameter set. Perform iterative adjustments; S24, optimize the new parameter set. The decision logic of the control component (1) is updated for risk determination in the next statistical cycle. This gives the entire active safety protection system the ability to learn and continuously optimize itself. The system periodically (e.g., weekly or monthly) runs an offline or online optimization process. It first collects historical running data, including the target state (D, V, E) before and after each alarm event and the final result of the event. Then, it classifies the alarm quality according to the event result: "accurate warning" is the ideal situation; "tolerable warning" is a warning that is not a real threat but does not cause downtime interference, which is acceptable but should be minimized; "missed warning" is an emergency shutdown without warning, which is a safety mistake and must be avoided as much as possible. The optimization algorithm (such as gradient descent or genetic algorithm) uses these classified data as the "training set", takes "minimizing the missed warning rate" as the primary goal, and constrains the "tolerable warning rate" to not exceed a certain acceptable level, and automatically searches and adjusts the parameter set. The optimal value is obtained. The optimized new parameters will be applied to real-time judgments in subsequent cycles. This solves the deep-seated problems of initial system parameters relying on engineering experience, difficulty in perfectly adapting to specific installation environments, and the long-term operational needs of specific workflows. By constructing this closed-loop iterative optimization mechanism based on historical data feedback, the system can autonomously learn the risk patterns in the actual operating scenarios of the equipment, continuously fine-tune the weights and sensitivity of its risk assessment model, thereby dynamically improving the accuracy of early warnings, reducing unnecessary production interference, and maintaining a high level of protection and security in long-term operation. This achieves systematic and intelligent collaborative optimization of safety protection effectiveness and production process smoothness.
[0035] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0036] The above-described embodiments are merely illustrative of several implementations of the present invention, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these modifications and improvements all fall within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the appended claims.
Claims
1. A laser shock strengthening equipment with an active safety protection device, comprising a laser and a worktable for placing workpieces, characterized in that, It also includes image acquisition components, thermal imaging components, data processing components, control components, and a light shield; The image acquisition component is used to acquire visual information around the workbench in real time; The thermal imaging component is used to collect thermal imaging information around the workbench in real time. The data processing component is signal-connected to the image acquisition component and the thermal imaging component, and is used to receive the visual information and the thermal imaging information, and perform dual-feature fusion judgment; wherein, the dual-feature fusion judgment includes: extracting the human body contour features of the target based on the visual information, and extracting the temperature features of the target based on the thermal imaging information; when the human body contour features conform to a preset human body feature model and the temperature features are within a preset human body temperature range, it is determined that a person is approaching, and a first control signal is generated. The control component is signal-connected to the data processing component; The light-shielding plate is disposed in the optical path of the laser and is drivenly connected to the control component; The control component is configured to: when receiving the first control signal, control the laser to stop emitting light and drive the light shield to move to the closed position to block the light path.
2. The laser shock enhancement equipment with active safety protection device according to claim 1, characterized in that, The data processing component includes a first data processing module and a second data processing module; the first data processing module is signal-connected to the image acquisition component and is used to perform contour feature extraction and judgment based on the visual information; the second data processing module is signal-connected to the thermal imaging component and is used to perform temperature feature extraction and judgment based on the thermal imaging information. The first data processing module and the second data processing module are connected in communication to collaboratively complete the dual-feature fusion judgment.
3. The laser shock enhancement equipment with active safety protection device according to claim 1, characterized in that, Multiple image acquisition components and multiple thermal imaging components are arranged around the perimeter of the workbench to cover the surrounding area of the workbench without any blind spots.
4. The laser shock enhancement equipment with active safety protection device according to claim 1, characterized in that, The light-shielding plate is driven to the control component via a driving mechanism; the driving mechanism is configured to drive the light-shielding plate to reciprocate or rotate between the closed position and an open position, wherein in the open position, the light-shielding plate completely avoids the optical path of the laser.
5. The laser shock enhancement equipment with active safety protection device according to claim 1, characterized in that, The control component is also configured to execute tiered alarm responses, including: If a potential risk target is identified based on either the visual information or the thermal imaging information, a second control signal is generated and an early warning is triggered. The first control signal is generated and the laser stop and optical path blocking are executed only when the dual-feature fusion judgment determines that a person is approaching.
6. The laser shock enhancement equipment with active safety protection device according to claim 5, characterized in that, The laser shock enhancement equipment also includes an alarm connected to the control component via a signal; the control component is configured to: when receiving the second control signal, control the alarm to issue a warning prompt; and when receiving the first control signal, control the alarm to issue an emergency alarm.
7. The laser shock enhancement equipment with active safety protection device according to claim 5, characterized in that, The conditions for generating the second control signal and triggering the early warning are precisely determined by introducing quantitative risk parameters; the control component is configured to execute: S1. When a potential risk target is identified based solely on either the visual information or the thermal imaging information, calculate the real-time risk coefficient R of the target; wherein the formula for calculating the real-time risk coefficient R is: ,in, The real-time distance between the potential risk target and the edge of the workbench. The preset baseline safety distance, The moving speed of the potential risk target. The preset reference speed, and The weighting coefficients are preset, and ; S2. The real-time risk coefficient R is compared with a preset first early warning threshold. Second warning threshold Comparison, among which S3, only when When this occurs, the second control signal is generated and an early warning is triggered; if At the same time as the warning is issued, the control component generates and executes a preparatory command to put the laser shock enhancement process into a deceleration or pause standby state.
8. The laser shock enhancement equipment with active safety protection device according to claim 7, characterized in that, The first warning threshold and / or the aforementioned reference safety distance Reference speed This is not a fixed value, but rather dynamically and adaptively adjusted by the control components based on the real-time monitored environmental disturbance level E; specific adjustment methods include: S11. Calculate the interference fluctuation value of the current environment using the background data from the image acquisition component and / or thermal imaging component. ; S12, Based on the interference fluctuation value The environmental interference level E is dynamically queried or calculated based on the preset range in which it is located, where E is related to... Positive correlation; S13. Based on the preset mapping relationship, use the environmental interference level E to adjust the first warning threshold. and / or the aforementioned reference safety distance Make corrections; the correction formula is: , and / or in, and As the baseline value, As the baseline environmental interference level, This is the preset sensitivity coefficient; S14. In the subsequent step S2, the modified version is used. and / or used when calculating R Make a judgment.
9. The laser shock enhancement equipment with active safety protection device according to claim 8, characterized in that, The weighting coefficients and and the sensitivity coefficient and It is configured to perform iterative optimization based on historical warning and false alarm data through the control component; the optimization method includes the following periodic execution: S21. Collect all event records that trigger early warnings and emergency alarms within a statistical period, as well as the real-time distance between the potential risk target and the edge of the workbench before the corresponding event occurs. Movement speed and environmental interference level E; S22. Classify and analyze events: If an alert is not escalated to an emergency alert after being issued, and is verified to be a valid non-threatening target, it is marked as a tolerable alert; if an alert is quickly escalated to an emergency alert after being issued, it is marked as an accurate alert; if an emergency alert is triggered directly without prior warning, it is marked as a missed alert. S23. With the optimization objective of minimizing the false negative rate and keeping the tolerable warning rate below a preset upper limit, use gradient descent or genetic algorithm to optimize the parameter set. Perform iterative adjustments; S24. Optimize the new parameter set. Update the decision logic of the control component for risk assessment in the next statistical period.
10. The laser shock enhancement equipment with active safety protection device according to any one of claims 1 to 9, characterized in that, The control component is also communicatively connected to the laser's status detection unit and is configured to verify whether the laser has actually stopped emitting light after driving the light shield to the closed position; if not, maintain the light shield in the closed position and report fault information.