Mechanical automation control method and system based on environmental perception

Abstract

The present invention relates to the field of mechanical control technology, and in particular to a mechanical automation control method and system based on environmental perception. Collect environmental perception visual data and mechanical operation-affecting perception parameters; analyze industrial mechanical control parameters based on environmental perception visual data to obtain industrial mechanical control parameters; perform mechanical automation control operations based on industrial mechanical control parameters; analyze historical fluctuation signals of perception parameters based on mechanical operation-affecting perception parameters to generate historical fluctuation signals of perception parameters; analyze the safety ratio interval between the perception parameters and mechanical operation performance based on the historical fluctuation signals of perception parameters; and perform safety optimization performance adjustment and limitation on mechanical automation control operations based on the safety ratio interval between the perception parameters and mechanical operation performance to obtain safe optimization mechanical automation control operations. The present invention realizes precise automatic control of mechanical execution based on environmental perception.

Description

Technical Field

[0001] The present invention relates to the field of mechanical control technology, and in particular to a mechanical automation control method and system based on environment perception. Background Art

[0002] With the continuous improvement of the level of industrial automation, mechanical automation equipment has been widely used in many fields such as manufacturing, logistics, and agriculture. During the operation of these devices, they often need to rely on preset programs and simple perception methods to complete specific tasks. Mechanical equipment usually relies on preset parameters and fixed processes, and cannot flexibly respond to environmental changes, such as fluctuations in light, temperature, or the position of the task object, resulting in a decrease in production efficiency. Mechanical automation control based on environmental perception can adjust the working mode of mechanical equipment in time according to changes in environmental conditions, such as changes in light, temperature, or spatial position, to improve production efficiency and reduce operational errors. However, the existing mechanical automation control methods based on environmental perception are mostly used for the collection of single data, and cannot comprehensively analyze complex environmental information. It is difficult to effectively integrate visual data and mechanical operation parameters to accurately judge the state and position of the task object, which affects the execution efficiency and accuracy of the machine; and there is a lack of monitoring and analysis methods for the perception parameters that affect the operation process, which leads to the easy attenuation of mechanical performance after high-performance operation or the inefficiency of low-performance operation, making it difficult to cope with complex and changing operation scenarios and reduce production efficiency. Summary of the invention

[0003] Based on this, the present invention provides a mechanical automation control method and system based on environmental perception to solve at least one of the above technical problems.

[0004] To achieve the above purpose, a mechanical automation control method based on environment perception includes the following steps:

[0005] Step S1: collecting environmental perception data through environmental monitoring sensors configured inside industrial machinery and equipment to generate environmental perception data, wherein the environmental perception data includes environmental perception visual data and mechanical operation impact perception parameters;

[0006] Step S2: performing environmental perception task object detection processing according to the environmental perception visual data to generate environmental perception task object data;

[0007] Step S3: Acquire industrial machinery task demand data; perform industrial machinery control parameter analysis based on the industrial machinery task demand data and the environmental perception task object data to obtain industrial machinery control parameters;

[0008] Step S4: Execute a mechanical automation control operation based on the industrial machinery control parameters;

[0009] Step S5: analyzing historical fluctuation signals of the perception parameters influencing the operation of the machine, and generating historical fluctuation signals of the perception parameters influencing the operation; and analyzing the safety ratio interval of the perception parameters influencing the operation of the machine according to the historical fluctuation signals of the perception parameters influencing the operation;

[0010] Step S6: Based on the safety ratio interval affecting the perception parameters and the mechanical operating performance, the mechanical automation control operation is subjected to safety optimization performance adjustment and limitation processing to obtain a safe and optimized mechanical automation control operation.

[0011] The present invention realizes comprehensive perception of the operating environment, including visual data and mechanical operating parameters, through the configuration of multiple environmental sensors. It provides an accurate data basis for the subsequent task object identification and dynamic adjustment of control parameters, so that the equipment can better adapt to the changing industrial environment and improve the accuracy and stability of the operation. The task object is detected in real time based on visual data, which ensures that the equipment can accurately identify the shape, position and other characteristics of the object to be operated, effectively avoids errors in operation, improves the accuracy of mechanical operation and the success rate of tasks, and shows higher reliability in dynamic or complex environments. Combined with the analysis of industrial machinery task requirements and environmental perception data, control parameters are dynamically generated to ensure that mechanical operation can be intelligently adjusted according to different requirements of tasks and changes in the environment, improve the flexibility of automatic control and the efficiency of task execution, thereby improving the adaptability and accuracy of the entire operation process. By automatically executing control parameters, mechanical equipment can independently complete various complex tasks, reduce manual intervention, and improve work efficiency. At the same time, accurate control parameters ensure the efficiency and safety of equipment operation and reduce the risk of deviations or errors during operation. Analyze historical operation data, predict the operation trend of mechanical equipment, and evaluate the health status of equipment. Monitoring based on historical parameter fluctuation signals and safety ratio intervals can effectively identify possible equipment failures or anomalies, perform maintenance in advance, and ensure that mechanical equipment operates stably and safely for a long time. By monitoring and adjusting the safety ratio interval, the operating performance of the equipment can be optimized in real time, ensuring that the equipment remains within a safe working range while operating efficiently. This not only improves the accuracy of the operation, but also significantly reduces equipment damage, operating errors and potential safety hazards, and improves the reliability and safety of the entire mechanical operation.

[0012] This specification provides a mechanical automation control system based on environment perception, which is used to execute the mechanical automation control method based on environment perception as described above. The mechanical automation control system based on environment perception includes:

[0013] An environmental perception data acquisition module is used to collect environmental perception data through environmental monitoring sensors configured inside industrial machinery and equipment to generate environmental perception data, wherein the environmental perception data includes environmental perception visual data and perception parameters affecting mechanical operation;

[0014] An environment perception task object detection module is used to perform environment perception task object detection processing based on environment perception visual data to generate environment perception task object data;

[0015] An industrial machinery control parameter analysis module is used to obtain industrial machinery task demand data; based on the industrial machinery task demand data and the environmental perception task object data, the industrial machinery control parameter analysis is performed to obtain the industrial machinery control parameters;

[0016] A mechanical automation control operation execution module, used to execute mechanical automation control operations based on industrial machinery control parameters;

[0017] The mechanical operation performance safety ratio interval analysis module is used to analyze the historical impact perception parameter fluctuation signal based on the mechanical operation impact perception parameter, generate the historical impact perception parameter fluctuation signal; analyze the safety ratio interval between the impact perception parameter and the mechanical operation performance according to the historical impact perception parameter fluctuation signal;

[0018] The optimized performance adjustment and limitation module of mechanical control is used to perform safe optimized performance adjustment and limitation processing on mechanical automation control operations based on the safety ratio interval affecting the perception parameters and the mechanical operating performance, so as to obtain safe optimized mechanical automation control operations.

[0019] The beneficial effect of the present application is that the present invention can effectively integrate and analyze multi-dimensional information in a complex environment by integrating a variety of environmental perception data, including visual data and mechanical operation-affecting perception parameters. Compared with a single data acquisition method, the collaborative processing of visual data and mechanical operation parameters is realized, and the state, position and dynamic changes of the task object can be accurately judged, thereby improving the execution efficiency and operation accuracy of mechanical equipment in a complex environment. Through the deep integration and real-time analysis of multi-source data, mechanical equipment can better perceive the surrounding environment, optimize the operation strategy, and ensure a higher success rate of task execution, especially in a dynamically changing or uncertain environment. Improve the adaptability and accuracy of the equipment. Through task requirements and environmental perception data, industrial machinery control parameters adapted to specific operation tasks are generated, and the control parameters are dynamically adjusted according to actual conditions during operation, solving the problem that mechanical equipment relies on fixed parameters and cannot flexibly respond to environmental changes. The monitoring of the perception parameters affecting mechanical operation and the fluctuation analysis of historical data are introduced, which can identify signs of attenuation of equipment performance or abnormal operation. Through the analysis of the safe ratio interval of the influencing perception parameters and mechanical operation performance, the mechanical operation is adjusted in time to maintain the equipment in the best operating state. Through dynamic optimization of control parameters, the operational flexibility of automated machinery is improved, and operational deviations caused by environmental changes or object state changes are reduced, thereby improving overall production efficiency and accuracy, especially in scenarios with complex tasks or uncertain environments. Through real-time monitoring and automatic adjustment of the equipment's operating status, it is possible to effectively avoid performance degradation after high-intensity operation or low operating efficiency in a low-performance state, thereby improving the safety and efficiency of equipment operation, as well as the reliability and stability of mechanical automation operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 A schematic diagram of the steps of a mechanical automation control method based on environment perception of the present invention;

[0021] Figure 2 for Figure 1 Detailed implementation steps of step S3 in FIG.

[0022] Figure 3 for Figure 1 Detailed implementation steps of step S6 in the flowchart;

[0023] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0024] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0025] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0026] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0027] To achieve this, please refer to Figures 1 to 3 The present invention provides a mechanical automation control method based on environment perception, comprising the following steps:

[0028] Step S1: collecting environmental perception data through environmental monitoring sensors configured inside industrial machinery and equipment to generate environmental perception data, wherein the environmental perception data includes environmental perception visual data and mechanical operation impact perception parameters;

[0029] Step S2: performing environmental perception task object detection processing according to the environmental perception visual data to generate environmental perception task object data;

[0030] Step S3: Acquire industrial machinery task demand data; perform industrial machinery control parameter analysis based on the industrial machinery task demand data and the environmental perception task object data to obtain industrial machinery control parameters;

[0031] Step S4: Execute a mechanical automation control operation based on the industrial machinery control parameters;

[0032] Step S5: analyzing historical fluctuation signals of the perception parameters influencing the operation of the machine, and generating historical fluctuation signals of the perception parameters influencing the operation; and analyzing the safety ratio interval of the perception parameters influencing the operation of the machine according to the historical fluctuation signals of the perception parameters influencing the operation;

[0033] Step S6: Based on the safety ratio interval affecting the perception parameters and the mechanical operating performance, the mechanical automation control operation is subjected to safety optimization performance adjustment and limitation processing to obtain a safe and optimized mechanical automation control operation.

[0034] The present invention realizes comprehensive perception of the operating environment, including visual data and mechanical operating parameters, through the configuration of multiple environmental sensors. It provides an accurate data basis for subsequent task object identification and dynamic adjustment of control parameters, so that the equipment can better adapt to the changing industrial environment and improve the accuracy and stability of the operation. Based on the visual data, the task object is detected in real time, which ensures that the equipment can accurately identify the shape, position and other characteristics of the object to be operated, effectively avoids errors in operation, improves the accuracy of mechanical operation and the success rate of the task, and shows higher reliability in dynamic or complex environments. Combined with the analysis of industrial machinery task requirements and environmental perception data, control parameters are dynamically generated to ensure that the mechanical operation can be intelligently adjusted according to the different requirements of the task and the changes in the environment, improve the flexibility of automatic control and the efficiency of task execution, thereby improving the adaptability and accuracy of the entire operation process. Through the automatic execution of control parameters, mechanical equipment can independently complete various complex tasks, reduce manual intervention, and improve work efficiency. At the same time, accurate control parameters ensure the efficiency and safety of equipment operation and reduce the risk of deviation or error during operation. Analyze historical operation data, predict the operation trend of mechanical equipment, and evaluate the health status of equipment. Monitoring based on historical parameter fluctuation signals and safety ratio intervals can effectively identify possible equipment failures or anomalies, perform maintenance in advance, and ensure that mechanical equipment operates stably and safely for a long time. By monitoring and adjusting the safety ratio interval, the operating performance of the equipment can be optimized in real time, ensuring that the equipment remains within a safe working range while operating efficiently. This not only improves the accuracy of the operation, but also significantly reduces equipment damage, operating errors and potential safety hazards, and improves the reliability and safety of the entire mechanical operation.

[0035] As an embodiment of the present invention, refer to Figure 1 The above is a schematic flow chart of a mechanical automation control method based on environment perception of the present invention. In this embodiment, the mechanical automation control method based on environment perception includes the following steps:

[0036] Step S1: collecting environmental perception data through environmental monitoring sensors configured inside industrial machinery and equipment to generate environmental perception data, wherein the environmental perception data includes environmental perception visual data and mechanical operation impact perception parameters;

[0037] In an embodiment of the present invention, multiple environmental monitoring sensors are configured in industrial machinery and equipment, and the types of sensors may include: Visual sensor: used to collect environmental perception visual data. For example, a high-definition camera or a 3D visual sensor is used to collect the three-dimensional structure or surface feature data of the task object. The resolution of the camera can be 1920×1080 pixels and the frame rate can be 30fps to ensure accurate recognition of the task object. Temperature sensor: used to detect the ambient temperature of the equipment, such as a temperature range of -40°C to 85°C with an accuracy of ±0.5°C. Vibration sensor: used to detect the vibration of the equipment during operation, with a vibration frequency monitoring range of 0 to 1000Hz and an accuracy of ±0.1Hz. Humidity sensor: used to detect the ambient humidity, with a humidity monitoring range of 0% to 100% RH and an accuracy of ±2%. The collected data will be integrated into environmental perception data, which includes environmental perception visual data (such as image data of the target object) and perception parameters affecting mechanical operation (such as temperature, vibration, humidity, etc.).

[0038] Step S2: performing environmental perception task object detection processing according to the environmental perception visual data to generate environmental perception task object data;

[0039] In an embodiment of the present invention, image processing and object recognition are performed on the environment perception visual data obtained by the visual sensor. First, the collected image is preprocessed and feature extracted using a convolutional neural network (CNN), such as using the YOLO algorithm to detect the task object. The task objects that the algorithm can detect may include parts on an industrial production line, and metal parts with characteristic dimensions of 100mm×50mm×30mm. The accuracy of the task object detection algorithm is 95%, and the minimum size of the recognized object is 5mm. The detection algorithm has a processing time of 50ms per frame to ensure real-time performance. Environmental perception task object data is generated based on the detection results, including information such as the type, size, shape, and spatial position of the task object. For example, the three-dimensional coordinate (X, Y, Z) data of the task object is a workpiece, which can be (200, 150, 75) mm.

[0040] Step S3: Acquire industrial machinery task demand data; perform industrial machinery control parameter analysis based on the industrial machinery task demand data and the environmental perception task object data to obtain industrial machinery control parameters;

[0041] In an embodiment of the present invention, relevant data is obtained according to the requirements of industrial tasks, and the task requirements may include requirements such as the handling, assembly or processing of workpieces. Assuming that the mechanical task is an assembly task, the required task requirement data includes: Task requirements: Assemble task object A (such as a metal part) into task object B (such as a plastic shell), and the gap is required to be less than 0.1mm. Working cycle: 20 parts are required to be assembled per minute. Touch accuracy: The positioning accuracy of mechanical equipment when performing assembly tasks needs to reach ±0.05mm. By analyzing the task requirement data with the morphological characteristics and spatial position data of the task object, the control parameters of the mechanical touch operation and the control parameters of the movement of the task object are generated by the inverse kinematics algorithm to analyze the control parameters of the industrial machinery. For example, by calculation, the control parameters of the robot arm are obtained as follows: Joint angle: The angle of joint 1 is set to 30 degrees, joint 2 is set to 45 degrees, and joint 3 is set to 60 degrees. Torque control: The touch torque is set to 2Nm to ensure that the robot arm will not damage the workpiece during the assembly process. The control parameters of the task object movement are the displacement characteristics of the task object moving in space. When obstacles or nodes that need to be controlled are identified, the optimized displacement control analysis is performed to ensure the displacement of the task object in space. The analysis of industrial machinery control parameters is to link the control parameters of mechanical touch operation and the linkage priority in the control parameters of task object movement, and finally conduct linkage control analysis.

[0042] Step S4: Execute a mechanical automation control operation based on the industrial machinery control parameters;

[0043] In an embodiment of the present invention, industrial mechanical equipment (such as a robotic arm) starts to perform automated operations according to control parameters. The robotic arm performs the grabbing, positioning, and assembly operations of the workpiece based on the set joint angle, torque, and speed. The robotic arm first moves to the target position (X, Y, Z) = (200, 150, 75) mm, grabs metal part A, and analyzes the grabbing node of metal part A, and then moves to the position of task object B (X, Y, Z) = (250, 100, 50) mm for assembly. The whole process takes 3 seconds to complete. The equipment monitors the torque and vibration in real time to ensure that the set torque (2Nm) is not exceeded during the assembly process. If an abnormal torque is detected, the equipment will automatically adjust to ensure assembly accuracy.

[0044] Step S5: analyzing historical fluctuation signals of the perception parameters influencing the operation of the machine, and generating historical fluctuation signals of the perception parameters influencing the operation; and analyzing the safety ratio interval of the perception parameters influencing the operation of the machine according to the historical fluctuation signals of the perception parameters influencing the operation;

[0045] In the embodiment of the present invention, during the operation of the mechanical equipment, the parameters that affect perception include: vibration frequency (collection frequency is 100 times per second, monitoring range is 0 to 1000Hz), temperature (measurement range is -40℃ to 85℃, accuracy is ±0.5℃), current and voltage fluctuations (for example, current 0 to 50A, voltage 0 to 400V). By monitoring the operation of the equipment under different workloads, ambient temperatures, etc. for a long time, historical data such as vibration frequency fluctuations, temperature fluctuations, and voltage fluctuations in mechanical operation are collected. Assume that the operation data of the equipment is recorded as: historical vibration frequency data: 600Hz ± 50Hz, historical temperature fluctuation data: 70℃ ± 5℃, historical current fluctuation data: 30A ± 2A. Using data processing algorithms (such as fast Fourier transform, FFT), these parameters are analyzed for fluctuation signals, the signal characteristics of frequency, temperature, and current fluctuations during the operation of the equipment are extracted, and fluctuation signals of historical parameters that affect perception are generated. For example, the spectrum of the vibration frequency fluctuation signal shows that the main resonance frequency is 600Hz, and the fluctuation range is between ±50Hz. According to the historical impact perception parameter fluctuation signal, the safety ratio range of the perception parameter and the mechanical operation performance is analyzed. After generating the historical impact perception parameter fluctuation signal, the relationship between the fluctuation range of each perception parameter and the safe operation performance of the mechanical equipment is further analyzed. The mechanical operation performance (such as the production efficiency and failure rate of the equipment) and the perception parameter fluctuation in the historical data are used for regression analysis. The set safe vibration frequency range is: 500Hz to 650Hz, the safe temperature range is: 65℃ to 75℃, and the safe current fluctuation range is: 28A to 32A. The safety ratio range of the perception parameter and the mechanical operation performance obtained by analysis is: the safety ratio range of vibration frequency to mechanical operation performance is 0.8 to 1.0. The safety ratio range of temperature to operation performance is 0.9 to 1.1. The safety ratio range of current fluctuation to operation performance is 0.95 to 1.05. By analyzing the historical data, the operation performance and safety of the equipment can be guaranteed within the above safety ratio range. In the future operation of the equipment, these influencing perception parameters will be monitored in real time to ensure that they are maintained within these safety ratio ranges.

[0046] Step S6: Based on the safety ratio interval affecting the perception parameters and the mechanical operating performance, the mechanical automation control operation is subjected to safety optimization performance adjustment and limitation processing to obtain a safe and optimized mechanical automation control operation.

[0047] In an embodiment of the present invention, the safety optimization adjustment of the mechanical automation control operation is performed based on the safety ratio interval between the influencing perception parameter and the mechanical operating performance. When the following safety ratio intervals are identified: the safety ratio interval between the vibration frequency and the mechanical operating performance: 0.8 to 1.0, the safety ratio interval between the temperature and the operating performance: 0.9 to 1.1, and the safety ratio interval between the current fluctuation and the operating performance: 0.95 to 1.05. In the mechanical automation operation, these influencing perception parameters are monitored in real time and ensured to be within the above-mentioned safety ratio interval. If a parameter is detected to exceed the safety interval (such as the vibration frequency rises to above 650Hz), the system will automatically perform the optimization adjustment operation. For example, when the vibration frequency exceeds 650Hz, it is analyzed whether the ratio of the mechanical motor operating performance to the vibration frequency is within the safety interval: when it is not in the safety interval, the workload of the equipment motor is automatically reduced, and the motor speed is reduced to reduce vibration until the frequency returns to the safety interval. When it is in the safety interval, the influencing perception parameter of the vibration frequency is marked as being caused by the operation of the equipment, and no adjustment is required. This adjustment process is automatically executed according to the system's pre-set safety ratio range and adjustment strategy to ensure that the equipment always operates within a safe range, thereby achieving safe optimization of equipment operation. In the above-mentioned safety optimization performance adjustment and limitation process, the system adjusts the equipment operating parameters according to the real-time changes in vibration frequency and temperature, and generates a safety optimization mechanical automation control operation that has been limited by the safety optimization performance adjustment of the mechanical automation control operation. For example: the motor speed is reduced by 20%, the cooling system power remains normal, and the system records and executes the new mechanical control strategy to ensure that the mechanical equipment can operate efficiently within a safe range, reduce the risk of equipment failure, and improve long-term operation stability.

[0048] Preferably, step S2 comprises the following steps:

[0049] Performing environment perception entity visual analysis according to the environment perception visual data to generate environment perception entity visual data;

[0050] Perform environmental perception task object detection processing based on environmental perception entity visual data to generate environmental perception task object data.

[0051] The present invention conducts in-depth analysis of environmental perception visual data, extracts more detailed feature information, ensures that the features of the task object can be accurately captured, and the device can effectively identify and locate multiple entities in complex scenes, reducing the possibility of misidentification. By analyzing visual data, the mechanical equipment can not only identify the task object, but also understand the state of its surrounding environment, improve the intelligence level of the equipment, and provide more comprehensive background information for subsequent operations. Entity visual analysis performs effective classification and identification in a multi-task environment, thereby supporting the device to perform multiple tasks in complex scenes and improving its flexibility and adaptability. Using environmental perception entity visual data to detect and update the information of the task object in real time is crucial for operations in a dynamic environment. It can ensure that the mechanical equipment has the latest task object status when performing tasks. Accurate task object data can guide the mechanical equipment to plan and make decisions more efficiently, and improve the efficiency of the entire operation process. For example, in tasks such as grabbing and carrying, the equipment can accurately identify the target, improve the success rate of grabbing, and reduce repeated operations and waiting time. Through accurate task object detection, operational errors caused by recognition errors are reduced, the failure rate of the equipment during operation is reduced, and the overall operational safety and reliability are improved.

[0052] In an embodiment of the present invention, industrial machinery equipment is equipped with a high-definition camera and a laser radar sensor for collecting visual data for environmental perception. The mechanical equipment scans the environment in the working area through these sensors to obtain real-time visual data. The equipment uses a configured high-definition camera to collect visual information in the working area. The camera has a resolution of 1920x1080 and a frame rate of 30 frames per second. The laser radar sensor obtains depth information and generates three-dimensional point cloud data in the environment with an accuracy of 1mm. The image data collected by the camera is analyzed by a deep learning algorithm to identify objects in the working environment, such as tools, workpieces and obstacles. After processing, the three-dimensional point cloud data provided by the laser radar can extract the spatial position and shape information of the object, such as the height, width and outline of the object. Combine the visual data and point cloud data to generate complete environmental perception entity visual data. Including: object category: such as mechanical tools, workpieces or safety obstacles; spatial coordinates: three-dimensional position of the object (x, y, z); width, height and depth of the object; shape features: shape outline obtained by point cloud analysis. Preliminary object recognition and classification is performed using a convolutional neural network (CNN), such as YOLO v4 or Mask R-CNN. The identified objects are analyzed for their 3D position and morphology in conjunction with the point cloud data. The 2D image from the camera and the depth data from the LiDAR are combined to generate 3D information for each object. All objects are preliminarily screened based on the environment-aware entity visual data obtained from the visual analysis. Assume that there are multiple different types of objects in this scene, such as mechanical parts, workpieces, and tools. These objects are detected and classified using a deep learning algorithm (such as YOLO v4). Set the detection parameters: the input image size is 608x608 pixels, the detection accuracy is set to 95%, and the category classification threshold is set to 0.7 (i.e., objects with a classification confidence of more than 70% will be identified as belonging to this category). During the detection process, multiple objects are identified in the environment, including the entity visual data. According to the task requirements, objects (cylinders) that meet the size and category are screened and marked as task objects to generate task object data.

[0053] Preferably, step S3 comprises the following steps:

[0054] Step S31: Acquire industrial machinery task demand data;

[0055] Step S32: performing task object morphological feature analysis according to the environment perception task object data to generate task object morphological feature data;

[0056] Step S33: performing inverse kinematics analysis of the mechanical touch operation based on the industrial machinery task requirement data and the task object morphological feature data to generate inverse kinematics data of the mechanical touch operation;

[0057] Step S34: performing a first mechanical control parameter analysis according to the mechanical touch operation inverse kinematics data to generate a first mechanical control parameter;

[0058] Step S35: performing task object spatial position analysis processing according to the environment perception task object data to generate task object spatial position data;

[0059] Step S36: performing task object optimization spatial displacement analysis based on the industrial machinery task demand data and the task object spatial position data to generate task object optimization spatial displacement data;

[0060] Step S37: analyzing the second mechanical control parameters according to the task object spatial displacement optimization data to generate the second mechanical control parameters;

[0061] Step S38: setting the industrial machine control parameter based on the first machine control parameter and the second machine control parameter to obtain the industrial machine control parameter.

[0062] The present invention obtains task requirement data to provide a clear target for subsequent operations, ensuring that mechanical equipment can be effectively planned and executed for specific tasks. By understanding the task requirements, the equipment can flexibly adjust the operation strategy to adapt to different industrial tasks and improve the overall work efficiency. By analyzing the morphological characteristics of the task object, the geometric and physical characteristics of the object can be accurately obtained, providing more detailed data support for subsequent operations and reducing errors in the operation process. The morphological feature data can help the equipment design a more suitable operation plan, thereby improving the success rate and efficiency of operations such as grasping and handling. Through inverse kinematics analysis, the precise joint angle and motion trajectory required for the mechanical equipment to complete a specific operation can be calculated to achieve high-precision control of the mechanical equipment. The process of mechanical operation is simplified, the complexity of human-computer interaction is reduced, and the operation is more intuitive and efficient. Through the analysis of the first mechanical control parameter, the stability and effectiveness of the mechanical equipment when performing the task are effectively ensured, and the success rate of the mechanical operation is improved. The control parameters are flexibly adjusted according to different task requirements, so that the equipment can better adapt to a diverse working environment. Through spatial position analysis, it is ensured that the mechanical equipment can accurately identify the position of the task object in space and provide effective position information for subsequent operations. Accurate spatial position data optimizes mechanical path planning, reduces the time of equipment movement, and improves work efficiency. Through spatial displacement analysis, the equipment can optimize the displacement path of the task object, thereby reducing unnecessary movement and improving work efficiency. The optimized spatial displacement path reduces the energy consumption of mechanical equipment and improves the economy and sustainability of the overall system. By analyzing the optimized displacement data, more flexible control parameters are generated, so that the equipment can better adapt to complex environmental changes when performing tasks. The setting of the second mechanical control parameter will further improve the operating accuracy of the equipment and ensure that the mechanical action is highly consistent with the task requirements. Combining the settings of the first and second mechanical control parameters, the control performance of the mechanical equipment can be comprehensively optimized, making it more efficient and accurate when performing tasks. Through the perfect control parameter setting, the equipment can achieve more intelligent operation, reduce manual intervention, and improve the level of automation and work efficiency.

[0063] As an embodiment of the present invention, refer to Figure 2 As shown, Figure 1 FIG. 1 is a flow chart of detailed implementation steps of step S3 in FIG. 1 . In this embodiment, step S3 includes:

[0064] Step S31: Acquire industrial machinery task demand data;

[0065] In an embodiment of the present invention, the task demand data of the current industrial machinery is obtained to clarify the task objectives and requirements, such as moving a cylinder (size 1.0mx 0.5mx 0.05m) and placing it at a specified location of (2.0m, 1.5m, 0.5m). The task demand data will be recorded by the system as a structured data format including the following key information: task type (such as "moving"), target object category (such as "cylinder"), target object size (such as "1.0mx 0.5mx 0.05m"), target placement location (such as "(2.0m, 1.0m, 0.3m)"), and task priority and time limit.

[0066] Step S32: performing task object morphological feature analysis according to the environment perception task object data to generate task object morphological feature data;

[0067] In an embodiment of the present invention, the environmental perception task object data is used to perform morphological feature analysis on the identified task object. The process includes detailed extraction and analysis of the shape, size, contour and other features of the task object. Assuming that the target cylinder has been identified before, image processing and deep learning algorithms are used to extract the boundary and contour of the cylinder from the environmental perception data to generate a point cloud model of its shape features. Further analysis may involve calculating information such as the center position, surface area, center of gravity position and stability of the cylinder. Finally, this information is summarized as task object morphological feature data and recorded as a data structure, including key parameters such as: object type ("cylinder"), center of gravity coordinates ("(1.5m, 0.8m, 0.025m)"), surface area ("0.5m²"), and morphological features. These data will provide necessary input for subsequent inverse kinematics analysis.

[0068] Step S33: performing inverse kinematics analysis of the mechanical touch operation based on the industrial machinery task requirement data and the task object morphological feature data to generate inverse kinematics data of the mechanical touch operation;

[0069] In an embodiment of the present invention, the acquired industrial machinery task requirement data and task object morphological feature data are used to perform inverse kinematics analysis of mechanical touch operation. The analysis aims to determine the control strategy of the touch of the robotic arm to accurately grasp and move the target object. The target touch node, that is, the edge position of the cylinder, is confirmed as the grasping point. Using the morphological feature data, the system determines the center of gravity of the cylinder and its stability index to ensure balance during grasping. Next, the required angles and positions of each joint of the robotic arm are calculated through the inverse kinematics algorithm to ensure that the arm can effectively grasp the cylinder and move smoothly to the target position. Taking a six-degree-of-freedom robotic arm as an example, assuming that the target angle of the first joint is "45°", the target angle of the second joint is "30°", the target angle of the third joint is "60°", and the target nodes corresponding to each joint, finally, the inverse kinematics data of the mechanical touch operation is generated, and the target position of each joint is recorded.

[0070] Step S34: performing a first mechanical control parameter analysis according to the mechanical touch operation inverse kinematics data to generate a first mechanical control parameter;

[0071] In an embodiment of the present invention, the first mechanical control parameter is analyzed based on the generated inverse kinematics data of the mechanical touch operation. This process focuses on converting the inverse kinematics data into specific control instructions to ensure that the robotic arm can move according to the predetermined nodes. Assume that through the previous analysis, the first joint target angle is "45°", the second joint target angle is "30°", the third joint target angle is "60°", and the specific joint touch nodes are obtained, so as to analyze the control parameters of each joint, form an overall control instruction set, and generate the first mechanical control parameters.

[0072] Step S35: performing task object spatial position analysis processing according to the environment perception task object data to generate task object spatial position data;

[0073] In an embodiment of the present invention, the spatial position analysis of the task object is performed based on the generated environment perception task object data. Assume that the system has identified the boundary and outline of the cylinder and determined that its center of gravity is "(1.5m, 0.8m, 0.025m)". The geometric analysis method will be used to calculate the position relationship of the object in three-dimensional space, including the relative position with surrounding objects, spatial direction and its accessibility in the working space. By introducing the coordinate system transformation, the position of the cylinder is converted from the working coordinate system to the base coordinate system of the robot arm. For example, if the origin of the base coordinate system of the robot arm is "(0, 0, 0)" and there is a rotation angle, the system will apply the transformation matrix to calculate the new position. Finally, the generated task object spatial position data includes the absolute coordinates, relative coordinates, direction information and accessibility parameters (such as "accessibility: 100%) of the target position, and these data are stored in a structured form for subsequent use.

[0074] Step S36: performing task object optimization spatial displacement analysis based on the industrial machinery task demand data and the task object spatial position data to generate task object optimization spatial displacement data;

[0075] In the embodiment of the present invention, the previously acquired industrial machinery task requirement data and task object spatial position data are used to perform an optimization spatial displacement analysis of the task object. Assume that the current task requirement is to move a cylinder from position "(1.5m, 0.8m, 0.025m)" to "(2.0m, 1.0m, 0.3m)". Evaluate the shortest path between two points and use a path optimization algorithm (such as The algorithm (such as Dijkstra algorithm) is used to analyze the feasible movement routes and calculate the possible obstacle impact and its safe distance. For example, if the path passes through the obstacle of "(1.75m, 0.85m, 0.1m)", an optimal movement path to avoid collision is calculated, such as "(2.0m, 1.5m, 0.3m) → (2.5m, 1.7m, 0.4m) → (3.0m, 2.0m,0.5m)", as well as the rotation angle information of the object during the movement, etc., to generate the task object optimization space displacement data.

[0076] Step S37: analyzing the second mechanical control parameters according to the task object spatial displacement optimization data to generate the second mechanical control parameters;

[0077] In the embodiment of the present invention, the second mechanical control parameters are analyzed based on the spatial displacement optimization data of the task object. Assuming that the optimized moving path involves multiple key points, the control instructions for each point need to be calculated. The movement requirements from the current joint position to the target joint position are analyzed, and the interpolation algorithm (such as linear interpolation or cubic spline interpolation) is used to smooth the path. The second mechanical control parameters finally generated will include the target angle, moving distance, key point movement control and other control parameters of the robot arm.

[0078] Step S38: setting the industrial machine control parameter based on the first machine control parameter and the second machine control parameter to obtain the industrial machine control parameter.

[0079] In an embodiment of the present invention, a first mechanical control parameter (used to perform initial touch and grasping operations) and a second mechanical control parameter (used for moving operations) are comprehensively analyzed, and by coordinating the movements of each joint and the different stages of the task process, it is ensured that the mechanical equipment performs continuous and seamless movements when performing grasping, moving and placing tasks. The priorities of grasping, stabilizing and other actions are analyzed based on the perception of the current state of the robotic arm, and the control actions of the first mechanical control parameter and the second mechanical control parameter are set in sequence according to the priority. Finally, the set control parameters are integrated to obtain industrial machinery control parameters.

[0080] Preferably, step S33 includes the following steps:

[0081] Step S331: performing target touch node combination matching and recognition processing according to the industrial machinery task requirement data and the task object morphological feature data to generate target touch node combination data;

[0082] Step S332: when the target touch node combination data is less than the preset touch node combination requirement threshold, an abnormal target touch node combination identification is performed on the target touch node combination data, abnormal target touch node combination data is generated, and step S333 is executed; when the target touch node combination data is not less than the preset touch node combination requirement threshold, valid target touch node combination data analysis is performed on the target touch node combination data to generate valid target touch node combination data;

[0083] Step S333: when abnormal target touch node combination data is identified, a global optimized touch node combination analysis is performed according to the task object morphological feature data to generate global optimized touch node combination data;

[0084] Step S334: performing inverse kinematics analysis of the mechanical touch operation according to the valid target touch node combination data and the global optimized touch node combination data to generate inverse kinematics data of the mechanical touch operation.

[0085] The present invention matches the comprehensive task requirements with the object features, effectively identifies the touch nodes most relevant to the task, thereby improving the accuracy of the operation. Based on the generated target touch node combination data, the device can make intelligent decisions based on real-time data, thereby optimizing the subsequent mechanical operation process. By setting the touch node combination requirement threshold, the abnormal combination is timely identified and marked, the operation risk caused by recognition errors is reduced, and the overall safety is improved. The generation of effective target touch node combination data optimizes the operation path and strategy of the mechanical equipment, makes full use of equipment resources, and improves work efficiency. Flexible processing of touch node combinations is provided, whether it is abnormal data or effective data, it can provide corresponding data support for subsequent operations and improve adaptability. Through global optimization of touch node combination analysis, the device can make up for the deficiencies caused by abnormal combinations and ensure the overall quality and effectiveness of the touch node combination. Global optimization analysis provides the ability to re-combine and adjust touch nodes, so that the device can flexibly respond to different environments and conditions, ensuring the success rate of operations. By combining effective and optimized data for inverse kinematics analysis, the motion trajectory and posture of the mechanical equipment are ensured to be more accurate, and the success rate of executing tasks is improved. It enables the equipment to be intelligently controlled and operated under complex tasks, optimize mechanical movements, and further improve the efficiency and reliability of overall operations.

[0086] In an embodiment of the present invention, task requirement data of industrial machinery and morphological feature data of task objects are obtained, and potential touch node combinations on task objects are identified through computer vision and shape matching algorithms. For example, a feature matching algorithm (such as SIFT or SURF) in computer vision technology is used to analyze the morphological features and match nodes of task objects. It is defined whether the touch nodes detected by the system meet the preset standard, and the minimum spacing of touch nodes is set to 0.1m. The preset threshold of the number of touch nodes is 3 touch points to ensure uniform distribution of force and stability of operation. SIFT (scale invariant feature transform) is used for feature point detection and matching. The minimum response threshold of the feature point descriptor is set to 0.04 to ensure that only feature points with sufficiently high responses are selected for matching. For a cylinder with a diameter of 0.5 meters, the task requirement is to grasp and carry it. The system will analyze the feature points on the surface of the cylinder, and generate a number of touch node combination data through SIFT (scale invariant feature transform) analysis, that is, the graspable nodes whose response parameters meet the minimum response threshold, and generate target touch node combination data. The generated target touch node combination data is evaluated according to the preset touch node combination requirement threshold (such as the number of touch points, distance uniformity, mechanical balance, etc.). If the number of identified touch nodes is less than the set threshold (such as a minimum of 3 touch points, but the system only recognizes 2 points), the system will mark it as abnormal touch node combination data. Set the threshold according to the task requirements, such as the minimum number of touch nodes is 3 and the node spacing is not greater than 0.1 meters. If the number of identified nodes does not meet the requirements, the system will generate abnormal data, indicating that there is a problem with the node layout. On the contrary, if the preset requirements are met, the system will perform further analysis and generate valid touch node combination data for subsequent operations. When an abnormal touch node combination is detected, it will automatically enter the global optimization stage. Through the multi-dimensional angle analysis technology of morphological features, the target object is re-analyzed from different perspectives to try to generate an optimized touch node combination. For example, for an irregularly shaped task object (such as a cylinder), multi-view reconstruction technology will be used, such as horizontal 0°, 45°, 90°, 135°, 180° and other five view angles to reconstruct the object model, use 128-dimensional SIFT descriptors or 64-dimensional ORB descriptors to describe the morphological feature pixels, analyze the benefit score of the touch node based on the morphological feature pixel descriptor, and analyze the benefit score of the touch node based on the grasping stability, operating torque, etc., and identify more suitable grasping points. After optimization processing, generate global optimized touch node combination data, and ensure that these nodes can meet the distribution requirements of the grasping force to improve the stability of the mechanical equipment operation. Perform inverse kinematics analysis based on the effective target touch node combination data and the global optimized touch node combination data to generate control instructions for the mechanical equipment to perform touch operations.Using the inverse kinematics model and setting the final target position and current position of the robot arm joints, the required movement path and angle of each joint of the robot arm during operation are calculated. Through inverse kinematics calculation, the angles of each joint of the robot arm are generated to ensure that the robot arm can stably grasp the target object. The generated inverse kinematics data for mechanical touch operation includes control parameters such as the movement speed, angle, and displacement path of each joint.

[0087] Preferably, the globally optimized touch node combination analysis according to the task object morphological feature data in step S333 includes the following steps:

[0088] A multi-dimensional angle visible pixel analysis of the morphological features is performed based on the morphological feature data of the task object to generate multi-dimensional angle visible pixel data of the morphological features; a morphological feature pixel descriptor analysis is performed based on the multi-dimensional angle visible pixel data of the morphological features to generate morphological feature pixel descriptor data; a touch node benefit analysis is performed based on the morphological feature pixel descriptor data to generate touch node benefit data; a global optimized touch node combination analysis is performed on the morphological feature data of the task object based on the touch node benefit data to generate global optimized touch node combination data.

[0089] The present invention obtains detailed information of the task object from different perspectives through multi-dimensional visual pixel point analysis, thereby improving the ability to understand and recognize the object's morphology. The generated multi-dimensional visual pixel point data provides more abundant basic data for subsequent analysis, thereby improving the accuracy and effectiveness of the overall analysis. According to the pixel point descriptor analysis, the morphological features are refined to more accurately represent the features of the object, thereby improving the efficiency of target recognition and matching. The refined feature data is helpful for accurate matching in practical applications, reducing the possibility of misidentification, and improving the safety and reliability of mechanical operation. According to the morphological feature pixel point descriptor data, the touch node benefit analysis is performed to quantify the operational benefits of different touch nodes, help select the optimal node for task operation, and improve work efficiency. According to the touch node benefit data, the task object morphological feature data is globally optimized for touch node combination analysis, the optimal touch node combination is identified, and the efficiency and speed of mechanical equipment when performing tasks are improved. The global optimization analysis enables the mechanical system to be flexibly adjusted according to different task requirements and environmental changes, thereby improving the overall adaptability and intelligence level.

[0090] In the embodiment of the present invention, the multi-dimensional angle visible pixel point analysis of the morphological feature is performed according to the morphological feature data of the task object, and the multi-view reconstruction technology is adopted, such as the horizontal 0°, 45°, 90°, 135°, 180° and other five angles for visual information, and the pixel points of the multi-dimensional angle visual information are extracted and superimposed to generate the multi-dimensional angle visible pixel point data of the morphological feature. The descriptor analysis is performed on these pixel point data, and the morphological feature pixel points are described using the 128-dimensional SIFT descriptor or the 64-dimensional ORB descriptor, and the features of each pixel point, such as texture, curvature and other visual information, are accurately described to generate the morphological feature pixel point descriptor data. The benefit analysis of the touch nodes on the surface of the task object is carried out, and the benefits of the touch nodes are calculated through the morphological feature pixel point descriptor data, such as the stability of the touch nodes through texture depth analysis. The benefits of the touch nodes are mainly comprehensively scored through factors such as stability, operability, and stress distribution. The touch node benefit score ranges from 0 to 1. The score is calculated by analyzing the stability of the grasping and the balance between the touch nodes. The benefit threshold of the effective touch node is set to 0.75, that is, only the touch nodes with a benefit score higher than 0.75 can be used as candidate nodes, and more suitable grasping points can be identified, and finally the touch node benefit data is generated. According to the distribution characteristics of the touch node benefit data and the accessible distribution characteristics of mechanical grasping touch, a global touch node combination analysis is carried out to generate global optimized touch node combination data, and ensure that these nodes can meet the distribution requirements of the grasping force to improve the stability of the mechanical equipment operation.

[0091] Preferably, step S36 includes the following steps:

[0092] Step S361: performing task object spatial displacement demand analysis according to the industrial machinery task demand data and the task object spatial position data to generate task object spatial displacement demand data;

[0093] Step S362: performing task object spatial displacement mutation point analysis according to the task object spatial displacement demand data, and generating task object spatial displacement mutation area data;

[0094] Step S363: performing spatial displacement mutation safety area difference analysis on the spatial displacement mutation area data of the task object according to a preset spatial displacement mutation safety area threshold, and generating spatial displacement mutation safety area difference data;

[0095] Step S364: performing spatial displacement adjustment route channel line filling processing according to the spatial displacement mutation safety area difference data to generate spatial displacement adjustment route channel line filling data;

[0096] Step S365: performing task object optimization spatial displacement analysis on the task object spatial displacement demand data according to the spatial displacement adjustment route channel supplementary line data, and generating task object optimization spatial displacement data.

[0097] The present invention performs task object spatial displacement demand analysis based on industrial machinery task demand data and task object spatial position data, accurately identifies the task object spatial displacement demand, and provides clear guidance for subsequent operations. Clear spatial displacement demand helps optimize the workflow of mechanical equipment, reduce unnecessary actions and time waste, and improve overall work efficiency. According to the task object spatial displacement demand data, the task object spatial displacement mutation point analysis is performed to timely identify the key points that cause risks or errors during task execution, providing a basis for subsequent adjustments. By accurately identifying the mutation area, the mechanical system can take preventive measures in advance, reduce operational risks, and improve overall safety. According to the preset spatial displacement mutation safety area threshold, the task object spatial displacement mutation area data is analyzed for spatial displacement mutation safety area difference, and by comparing with the safety area threshold, it is ensured that the mechanical operation is carried out within a safe range, further reducing potential accident risks. The result of the difference analysis can provide a basis for mechanical control, guide the adjustment and optimization of subsequent operations, and improve the accuracy of control. According to the spatial displacement mutation safety area difference data, the spatial displacement adjustment route channel is processed, and the mobile route of the machine is adjusted in real time to ensure the safety and effectiveness in the mutation area, thereby improving the smooth progress of the task. The optimized path reduces unnecessary movement and adjustment, and improves the response speed and work efficiency of the equipment. According to the spatial displacement adjustment route channel supplementary line data, the task object spatial displacement demand data is analyzed for task object optimization, ensuring that the mechanical equipment can achieve the predetermined goals more efficiently when performing tasks and improve overall performance. The optimization results enable the mechanical equipment to flexibly respond to the needs of different tasks, improving the adaptability and intelligence level of the system.

[0098] In an embodiment of the present invention, a spatial displacement demand analysis is performed based on the task requirements of the industrial machinery and in combination with the spatial position of the current task object. In specific implementation, assuming that the task requirement of the industrial machinery is to move a cylinder with a size of 1.0mx 0.5m from the current coordinates "(2.0m, 1.5m, 0.3m)" to "(4.0m, 2.0m, 0.5m)", the system will generate spatial displacement demand data for the task object according to the task requirements. The data includes the starting point, the target point, and the motion constraints of the mechanical equipment, such as the position accuracy requirements (for example: the target position accuracy is ±0.01m). Through the spatial displacement demand analysis, the spatial displacement demand data is generated, and the moving distance, speed and required spatial accuracy are clearly indicated. The spatial displacement mutation point analysis of the task object is performed based on the spatial displacement demand data of the task object to identify the discontinuous or sharply changing areas that may occur during the displacement process. In specific implementation, the system analyzes the key points on the path, such as turning points or locations where obstacles are encountered. For example, suppose that during the movement from the path "(2.0m, 1.5m, 0.3m)" to "(4.0m, 2.0m, 0.5m)", an obstacle pole with a height of 0.2m is detected, and the position of the obstacle pole "(3.0m, 1.8m, 0.2m)" is identified as the spatial displacement mutation point area. Generate the task object spatial displacement mutation area data, and mark the mutation area that needs special attention during the displacement process to avoid collision with obstacles. According to the preset safety area threshold, perform difference analysis on the mutation area data to determine whether there are safety hazards in the area. Set the threshold of the safety area to "0.1m", that is, the minimum safe distance between the task object and the mutation point is 0.1m. For example, near the obstacle pole position "(3.0m, 1.8m, 0.2m)" detected above, the system analyzes the actual distance between the object and the obstacle and the direction information of the relative movement of the task object. If the distance is 0.08m, the system will recognize that the area is not within the safety range and generate spatial displacement mutation safety area difference data, indicating that the actual distance is less than the preset safety threshold (the difference is -0.02m). This indicates that the current moving path needs to be adjusted in this mutation area. The route is adjusted according to the spatial displacement mutation safety area difference data, and the safety of the displacement process is ensured by line filling processing. The spatial displacement adjustment route channel line filling information is designed by the spatial spacing in each direction of the detour, so as to calculate a new path to bypass the mutation area or the area with insufficient safety distance. For example, for the aforementioned obstacle pole, the system replans the route so that the task object moves along the new path from "(2.0m, 1.5m, 0.3m)" to avoid the mutation area of ​​the obstacle pole. The new path after the patching may be adjusted to "(3.0m, 2.0m, 0.3m)" to bypass the obstacle and ensure that the spatial displacement safety distance near the obstacle pole meets the safety threshold of 0.1m.The generated spatial displacement adjustment route channel patching data includes the key point coordinates of the new path and the corresponding speed and acceleration parameters. The overall spatial displacement of the task object is optimized and analyzed according to the patching data to generate the final spatial displacement path and related control parameters. The new path after patching is compared with the original task requirements to ensure the feasibility and optimization of the path. Assuming that the task object needs to reach the target point in the shortest time, the system will recalculate the speed and acceleration of each segment in the path based on the optimization algorithm (such as the Dijkstra algorithm or the dynamic path planning algorithm) to ensure that the task object can still reach the target position efficiently while bypassing obstacles. For example, the speed is increased from the original "1.0m / s" to "1.2m / s" to compensate for the time delay caused by the patching path. The task object optimized spatial displacement data finally generated includes the adjusted moving path, speed, acceleration and other parameter information to ensure that the task object can complete the mobile task efficiently under safe conditions.

[0099] Preferably, step S5 comprises the following steps:

[0100] Step S51: analyzing historical impact perception parameter fluctuation signals based on the machine operation impact perception parameters to generate historical impact perception parameter fluctuation signals;

[0101] Step S52: performing historical impact perception parameter signal fluctuation base state interval analysis according to the historical impact perception parameter fluctuation signal to generate the historical impact perception parameter signal fluctuation base state interval;

[0102] Step S53: Collect historical mechanical operation performance data corresponding to the historical ground state interval of the fluctuation of the perception parameter signal; calculate the safety ratio interval of the influencing perception parameter and the mechanical operation performance according to the historical ground state interval of the fluctuation of the perception parameter signal and the corresponding historical mechanical operation performance data.

[0103] The present invention accurately records the operating state and changing trend of mechanical equipment by analyzing the fluctuation signal of the impact perception parameter when the machine is running, and provides important data support for subsequent performance adjustment. The historical fluctuation signal analysis can timely identify the unstable factors or abnormal conditions in the operation of the machine and prevent potential operation failures. According to the historical impact perception parameter fluctuation signal, the historical impact perception parameter signal fluctuation base state interval analysis is performed to establish a reference benchmark for the normal operation state of the mechanical equipment, which is convenient for identifying abnormalities in future operation. Based on the base state interval analysis, the subtle fluctuations or unstable factors in the operation of the machine are more sensitively captured, and the accuracy of equipment monitoring is enhanced. The historical mechanical operation performance data corresponding to the historical impact perception parameter signal fluctuation base state interval are collected; the safety ratio interval of the impact perception parameter and the mechanical operation performance is calculated according to the historical impact perception parameter signal fluctuation base state interval and the corresponding historical mechanical operation performance data, and the safety ratio interval of the mechanical operation is accurately calculated, so as to provide a safety range reference for the subsequent mechanical operation, that is, the ratio fluctuation interval of the operating efficiency and the impact perception parameter signal in the historical mechanical control operation. According to the safety ratio interval, the control parameters of the machine are used to adjust the performance to ensure that the automatic operation of the equipment is both efficient and safe, thereby avoiding overload or failure.

[0104] In an embodiment of the present invention, the sensor built into the industrial machinery equipment collects the sensor parameter fluctuation signal during the historical mechanical operation of the equipment. The industrial machinery equipment will monitor the changes in parameters such as temperature, vibration frequency, and pressure. For example, the temperature fluctuation range of the equipment during operation is 50°C to 80°C, and the vibration frequency is 20Hz to 40Hz. The system generates a fluctuation signal based on these historical impact sensor parameters, and performs periodic analysis on them to generate a historical fluctuation map of the mechanical operation. Assume that in a certain task, the vibration frequency fluctuates from 30Hz to 45Hz in a short period of time, and a historical impact sensor parameter fluctuation signal is generated. According to the historical impact sensor parameter fluctuation signal, the historical data is statistically analyzed to generate the base state interval during the mechanical operation. For example, suppose that the system finds that the temperature fluctuation range of the mechanical equipment is 55°C to 75°C and the vibration frequency is 25Hz to 35Hz during long-term monitoring, and the equipment can maintain stable operation within these parameter ranges. Therefore, these ranges can be defined as the "base state interval" of the historical impact sensor parameters. The base state intervals of different sensor parameters are obtained by using mathematical statistical methods, such as standard deviation analysis or quantile analysis. For example, the base range of temperature fluctuation can be set to 60±10℃, and the base range of vibration frequency can be set to 30±5Hz. The mechanical operation performance data within the base range is collected and analyzed. For example, the system found during multiple operation tasks that when the temperature of the equipment was at 60±10℃, the output power of the machine was 80kW±5%. By establishing a relationship model between the parameters, the safety ratio range that affects the perceived parameters and the mechanical operation performance is calculated. For example, based on the relationship between temperature and output power, the safety ratio range may be set to maintain the power at 80kW±10% for temperatures below 75℃. Exceeding this range indicates that the machine may be at risk of overload or failure. Similarly, for vibration frequency, the system sets the safety range to 30Hz±5%.

[0105] Preferably, step S6 comprises the following steps:

[0106] Step S61: performing a mechanical control performance adaptive adjustment process on the mechanical automation control operation according to a preset mechanical operation performance adjustment extreme value threshold, and generating a mechanical automation control operation with performance adjustment;

[0107] Step S62: performing real-time impact perception parameter signal monitoring and processing according to the mechanical operation impact perception parameters of the mechanical automation control operation of the performance adjustment, and generating a real-time impact perception parameter signal;

[0108] Step S63: performing outlier signal monitoring and processing on the real-time outlier signal of the influencing perception parameter according to the base state interval of the influencing perception parameter signal fluctuation, and generating an outlier signal of the influencing perception parameter;

[0109] Step S64: collecting outlier machine operation performance data corresponding to the outlier signal affecting the perception parameter; calculating the outlier ratio data affecting the perception parameter and the machine operation performance according to the outlier signal affecting the perception parameter and the corresponding outlier machine operation performance data;

[0110] Step S65: when it is identified that the outlier ratio data affecting the perception parameter and the mechanical operation performance is in the safe ratio interval affecting the perception parameter and the mechanical operation performance, the outlier mechanical operation performance data is marked as valid mechanical operation performance data;

[0111] Step S66: when it is identified that the outlier ratio data affecting the perception parameter and the mechanical operation performance is not in the safe ratio interval affecting the perception parameter and the mechanical operation performance, the outlier mechanical operation performance data is marked as abnormal mechanical operation performance data; the abnormal mechanical operation performance data is subjected to intelligent adjustment processing of the mechanical operation performance to obtain intelligently adjusted mechanical operation performance data;

[0112] Step S67: Feedback the effective mechanical operation performance data and the intelligently adjusted mechanical operation performance data to the mechanical automation control operation for performance adjustment, and perform safety optimization performance adjustment and limitation processing on the mechanical automation control operation to obtain a safe and optimized mechanical automation control operation.

[0113] The present invention performs adaptive adjustment processing of mechanical control performance on mechanical automation control operations according to preset mechanical operation performance adjustment extreme value thresholds, adjusts mechanical control performance to make it operate within the extreme value threshold range, and optimizes the working efficiency and precision of the machine to the greatest extent. According to the mechanical operation influence perception parameters of the mechanical automation control operation adjusted by performance, real-time influence perception parameter signal monitoring and processing are performed to timely discover potential problems and quickly respond to deviations occurring during operation. According to the fluctuation base state interval of the influence perception parameter signal, the influence perception parameter outlier signal monitoring and processing are performed on the real-time influence perception parameter signal, and abnormal conditions beyond the normal range are identified. Outlier monitoring can reduce the system instability caused by the failure to timely process abnormal signals. The outlier mechanical operation performance data corresponding to the outlier signal of the influence perception parameter is collected; the outlier ratio data of the influence perception parameter and the mechanical operation performance is calculated according to the outlier signal of the influence perception parameter and the corresponding outlier mechanical operation performance data, and the specific influence of the abnormal perception parameter on the mechanical operation performance is quantitatively evaluated, so as to facilitate the adoption of targeted adjustment measures, avoid misjudgment, and accurately distinguish the real abnormal operation conditions. When it is identified that the outlier ratio data affecting the perception parameters and the mechanical operation performance is in the safe ratio interval affecting the perception parameters and the mechanical operation performance, the outlier mechanical operation performance data is marked as valid mechanical operation performance data, which reflects the linear influence of the machine itself on the perception parameters due to the performance improvement in the mechanical control, and does not cause abnormal mechanical control. When it is identified that the outlier ratio data affecting the perception parameters and the mechanical operation performance is not in the safe ratio interval affecting the perception parameters and the mechanical operation performance, the outlier mechanical operation performance data is marked as abnormal mechanical operation performance data; the abnormal mechanical operation performance data is processed by intelligent mechanical operation performance adjustment to obtain intelligent adjustment mechanical operation performance data, automatically optimize the mechanical operation parameters, and ensure that the machine operates in the best state, which reflects the abnormal growth of the machine itself affecting the perception parameters due to the performance improvement in the mechanical control, and the performance in the mechanical control needs to be adjusted to prevent potential equipment failures and avoid downtime and production impact. Feedback the effective mechanical operation performance data and the intelligent adjustment mechanical operation performance data to the performance adjustment mechanical automation control operation to carry out the safe optimization performance adjustment limit processing of the mechanical automation control operation, so as to obtain the safe optimization of the mechanical automation control operation, continuously optimize itself during each operation process, improve the safety and operation efficiency of the control operation, maintain stability during long-term operation, reduce the failure rate of equipment, and extend the service life of the machinery.

[0114] As an embodiment of the present invention, refer to Figure 3 As shown, Figure 1 FIG. 5 is a flow chart of detailed implementation steps of step S6 in FIG. 5 . In this embodiment, step S6 includes:

[0115] Step S61: performing a mechanical control performance adaptive adjustment process on the mechanical automation control operation according to a preset mechanical operation performance adjustment extreme value threshold, and generating a mechanical automation control operation with performance adjustment;

[0116] In the embodiment of the present invention, the mechanical control performance adaptive adjustment process is performed on the mechanical automation control operation according to the preset mechanical operation performance adjustment extreme value threshold. For example, a certain industrial machine performs a mechanical automation control operation with a power output of 100kW to generate a mechanical automation control operation with performance adjustment.

[0117] Step S62: performing real-time impact perception parameter signal monitoring and processing according to the mechanical operation impact perception parameters of the mechanical automation control operation of the performance adjustment, and generating a real-time impact perception parameter signal;

[0118] In an embodiment of the present invention, the operating parameters in the mechanical automation control operation are monitored in real time. For example, the system collects data such as the operating temperature, vibration frequency, and pressure of the machine every second to generate real-time signals affecting the perceived parameters. Assuming that the temperature of the machine is 88°C-100°C after adaptive adjustment, the system transmits this information back to the control center through the sensor, records and generates a real-time temperature fluctuation curve. Similarly, other parameters such as a vibration frequency of 40Hz-50Hz will also be recorded by the system. Through these real-time signal monitoring, real-time signals affecting the perceived parameters are generated.

[0119] Step S63: performing outlier signal monitoring and processing on the real-time outlier signal of the influencing perception parameter according to the base state interval of the influencing perception parameter signal fluctuation, and generating an outlier signal of the influencing perception parameter;

[0120] In an embodiment of the present invention, the outlier signal of the influencing perception parameter is monitored and processed according to the ground state interval of the fluctuation of the influencing perception parameter signal, that is, the outlier signal of the influencing perception parameter is monitored when the real-time influencing perception parameter signal is not in the ground state interval of the fluctuation of the influencing perception parameter signal, and the outlier signal of the influencing perception parameter is output.

[0121] Step S64: collecting outlier machine operation performance data corresponding to the outlier signal affecting the perception parameter; calculating the outlier ratio data affecting the perception parameter and the machine operation performance according to the outlier signal affecting the perception parameter and the corresponding outlier machine operation performance data;

[0122] In an embodiment of the present invention, outlier mechanical operating performance data corresponding to outlier signals of influencing perception parameters are collected, i.e., temperature of 88°C-100°C, vibration frequency of 40Hz-50Hz and other influencing perception parameters, and corresponding outlier mechanical operating performance data (operating power of 100KW) are collected. According to the outlier signals of influencing perception parameters and the corresponding outlier mechanical operating performance data, outlier ratio data of influencing perception parameters and mechanical operating performance are calculated, i.e., the ratio of temperature, vibration frequency and other influencing perception parameters to operating power.

[0123] Step S65: when it is identified that the outlier ratio data affecting the perception parameter and the mechanical operation performance is in the safe ratio interval affecting the perception parameter and the mechanical operation performance, the outlier mechanical operation performance data is marked as valid mechanical operation performance data;

[0124] In an embodiment of the present invention, when it is identified that the outlier ratio data affecting the perception parameters and the mechanical operating performance is in the safe ratio range of the perception parameters and the mechanical operating performance, that is, when the ratio of the temperature, vibration frequency and other perception parameters affecting the perception parameters to the operating power is in the safe ratio range of the perception parameters and the mechanical operating performance, the feedback affecting the perception parameters that is normally reflected due to the increase in the equipment operating power is marked as the outlier mechanical operating performance data.

[0125] Step S66: when it is identified that the outlier ratio data affecting the perception parameter and the mechanical operation performance is not in the safe ratio interval affecting the perception parameter and the mechanical operation performance, the outlier mechanical operation performance data is marked as abnormal mechanical operation performance data; the abnormal mechanical operation performance data is subjected to intelligent adjustment processing of the mechanical operation performance to obtain intelligently adjusted mechanical operation performance data;

[0126] In the embodiment of the present invention, when it is identified that the outlier ratio data affecting the perception parameters and the mechanical operation performance is not in the safe ratio interval affecting the perception parameters and the mechanical operation performance, that is, when the ratio of the perception parameters such as temperature and vibration frequency to the operating power is not in the safe ratio interval affecting the perception parameters and the mechanical operation performance, that is, when the operating power is 120KW, the temperature of the mechanical equipment reaches 160°C, then the outlier mechanical operation performance data is marked as abnormal mechanical operation performance data. The abnormal mechanical operation performance data is subjected to intelligent mechanical operation performance adjustment processing, that is, the operating power is reduced so that the ratio of the perception parameters such as temperature and vibration frequency to the operating power is in the safe ratio interval affecting the perception parameters and the mechanical operation performance, so as to obtain intelligently adjusted mechanical operation performance data.

[0127] Step S67: Feedback the effective mechanical operation performance data and the intelligently adjusted mechanical operation performance data to the mechanical automation control operation for performance adjustment, and perform safety optimization performance adjustment and limitation processing on the mechanical automation control operation to obtain a safe and optimized mechanical automation control operation.

[0128] In the embodiment of the present invention, the effective mechanical operation performance data and the intelligent adjustment mechanical operation performance data are fed back to the mechanical automation control operation for performance adjustment, and the mechanical automation control operation is subjected to safety optimization performance adjustment and limitation processing, so that the mechanical automation control operation can maintain the maximum operating power under normal conditions, and dynamically adjust the operating power, and re-optimize the operating state of the machine according to these feedback data, ensuring that the machine always remains within a safe performance range, reducing potential failure or loss risks. Ultimately, these optimization data will generate safe and optimized mechanical automation control operations, such as reducing the power output to 110kW, to ensure that the machine continues to operate in a safe and efficient state.

[0129] Preferably, the intelligent adjustment of the abnormal mechanical operation performance data in step S66 includes the following steps:

[0130] Design the mechanical operation performance constraint characteristics according to the safety ratio range of the influencing perception parameters and mechanical operation performance, and generate mechanical operation performance constraint characteristic data;

[0131] Intelligent adjustment of the abnormal mechanical operation performance is performed according to the mechanical operation performance constraint characteristic data to obtain intelligently adjusted mechanical operation performance data.

[0132] The present invention designs mechanical operation performance constraint features based on the safety ratio interval that affects the perceived parameters and mechanical operation performance. By designing constraint features based on the safety ratio interval, it is possible to ensure that the mechanical operation parameters are always within a safe performance range, prevent equipment damage or performance degradation due to excessively high or low parameters, and further improve the precise control of mechanical operation performance, so that it can achieve efficient and safe operation under constraint conditions. Intelligent mechanical operation performance adjustment processing is performed on abnormal mechanical operation performance based on the mechanical operation performance constraint feature data, and mechanical performance is dynamically adjusted according to different operating environments or task requirements to ensure that the machine can still operate stably in complex environments. Intelligent adjustment can effectively reduce abnormal conditions in equipment operation, avoid potential failure risks, and extend the service life of mechanical equipment, while optimizing energy consumption and improving overall efficiency.

[0133] In an embodiment of the present invention, based on the safe ratio range of the influencing perception parameters (such as temperature, pressure, vibration, etc.) and the mechanical operation performance (such as power, speed, load), the corresponding operation constraint characteristics are designed. For example, during the operation of the equipment, the constraint characteristics will be designed to ensure that the ratio of the influencing perception parameters such as temperature and vibration frequency to the operating power is within the safe ratio range of the influencing perception parameters and the mechanical operation performance. The constraint characteristic data is used to perform intelligent adjustment processing on the abnormal mechanical operation performance. For example, if the operation of the equipment exceeds the limit of the constraint characteristics, the following intelligent adjustment measures are taken: Adjust the power output: reduce the heat generation by reducing the power output of the equipment. For example, the power of the equipment is reduced from 120kW to 100kW. Slow down the operation speed: reduce the heat caused by friction or pressure by reducing the operating speed of the equipment, and the operating speed of the equipment is reduced from 1500RPM to 1300RPM to obtain intelligent adjustment of the mechanical operation performance data.

[0134] This specification provides a mechanical automation control system based on environment perception, which is used to execute the mechanical automation control method based on environment perception as described above. The mechanical automation control system based on environment perception includes:

[0135] An environmental perception data acquisition module is used to collect environmental perception data through environmental monitoring sensors configured inside industrial machinery and equipment to generate environmental perception data, wherein the environmental perception data includes environmental perception visual data and perception parameters affecting mechanical operation;

[0136] An environment perception task object detection module is used to perform environment perception task object detection processing based on environment perception visual data to generate environment perception task object data;

[0137] An industrial machinery control parameter analysis module is used to obtain industrial machinery task demand data; based on the industrial machinery task demand data and the environmental perception task object data, the industrial machinery control parameter analysis is performed to obtain the industrial machinery control parameters;

[0138] A mechanical automation control operation execution module, used to execute mechanical automation control operations based on industrial machinery control parameters;

[0139] The mechanical operation performance safety ratio interval analysis module is used to analyze the historical impact perception parameter fluctuation signal based on the mechanical operation impact perception parameter, generate the historical impact perception parameter fluctuation signal; analyze the safety ratio interval between the impact perception parameter and the mechanical operation performance according to the historical impact perception parameter fluctuation signal;

[0140] The optimized performance adjustment and limitation module of mechanical control is used to perform safe optimized performance adjustment and limitation processing on mechanical automation control operations based on the safety ratio interval affecting the perception parameters and the mechanical operating performance, so as to obtain safe optimized mechanical automation control operations.

[0141] The beneficial effect of the present application is that the present invention can effectively integrate and analyze multi-dimensional information in a complex environment by integrating a variety of environmental perception data, including visual data and mechanical operation-affecting perception parameters. Compared with a single data acquisition method, the collaborative processing of visual data and mechanical operation parameters is realized, and the state, position and dynamic changes of the task object can be accurately judged, thereby improving the execution efficiency and operation accuracy of mechanical equipment in a complex environment. Through the deep integration and real-time analysis of multi-source data, mechanical equipment can better perceive the surrounding environment, optimize the operation strategy, and ensure a higher success rate of task execution, especially in a dynamically changing or uncertain environment. Improve the adaptability and accuracy of the equipment. Through task requirements and environmental perception data, industrial machinery control parameters adapted to specific operation tasks are generated, and the control parameters are dynamically adjusted according to actual conditions during operation, solving the problem that mechanical equipment relies on fixed parameters and cannot flexibly respond to environmental changes. The monitoring of the perception parameters affecting mechanical operation and the fluctuation analysis of historical data are introduced, which can identify signs of attenuation of equipment performance or abnormal operation. Through the analysis of the safe ratio interval of the influencing perception parameters and mechanical operation performance, the mechanical operation is adjusted in time to maintain the equipment in the best operating state. Through dynamic optimization of control parameters, the operational flexibility of automated machinery is improved, and operational deviations caused by environmental changes or object state changes are reduced, thereby improving overall production efficiency and accuracy, especially in scenarios with complex tasks or uncertain environments. Through real-time monitoring and automatic adjustment of the equipment's operating status, it is possible to effectively avoid performance degradation after high-intensity operation or low operating efficiency in a low-performance state, thereby improving the safety and efficiency of equipment operation, as well as the reliability and stability of mechanical automation operations.

[0142] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0143] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A mechanical automation control method based on environmental perception, characterized in that: The following steps are involved: Step S1: collecting environmental perception data through environmental monitoring sensors configured inside industrial machinery and equipment to generate environmental perception data, wherein the environmental perception data includes environmental perception visual data and mechanical operation impact perception parameters; Step S2: performing environmental perception task object detection processing according to the environmental perception visual data to generate environmental perception task object data; Step S3: Acquire industrial machinery task demand data; perform industrial machinery control parameter analysis based on the industrial machinery task demand data and the environmental perception task object data to obtain industrial machinery control parameters; wherein step S3 includes: Step S31: Acquire industrial machinery task demand data; Step S32: performing task object morphological feature analysis according to the environment perception task object data to generate task object morphological feature data; Step S33: performing inverse kinematics analysis of mechanical touch operation based on the industrial machinery task requirement data and the task object morphological feature data to generate inverse kinematics data of mechanical touch operation; wherein step S33 includes: Step S331: performing target touch node combination matching and recognition processing according to the industrial machinery task requirement data and the task object morphological feature data to generate target touch node combination data; Step S332: when the target touch node combination data is less than the preset touch node combination requirement threshold, an abnormal target touch node combination identification is performed on the target touch node combination data, abnormal target touch node combination data is generated, and step S333 is executed; when the target touch node combination data is not less than the preset touch node combination requirement threshold, valid target touch node combination data analysis is performed on the target touch node combination data to generate valid target touch node combination data; Step S333: when abnormal target touch node combination data is identified, a morphological feature multi-dimensional angle visible pixel analysis is performed according to the task object morphological feature data to generate morphological feature multi-dimensional angle visible pixel data; a morphological feature pixel descriptor analysis is performed according to the morphological feature multi-dimensional angle visible pixel data to generate morphological feature pixel descriptor data; a touch node benefit analysis is performed according to the morphological feature pixel descriptor data to generate touch node benefit data; a global optimized touch node combination analysis is performed on the task object morphological feature data according to the touch node benefit data to generate global optimized touch node combination data; Step S334: performing inverse kinematics analysis of the mechanical touch operation according to the effective target touch node combination data or the global optimized touch node combination data to generate inverse kinematics data of the mechanical touch operation; Step S34: performing a first mechanical control parameter analysis according to the mechanical touch operation inverse kinematics data to generate a first mechanical control parameter; Step S35: performing task object spatial position analysis processing according to the environment perception task object data to generate task object spatial position data; Step S36: performing task object optimization spatial displacement analysis based on the industrial machinery task demand data and the task object spatial position data to generate task object optimization spatial displacement data; Step S37: Analyze the second mechanical control parameters according to the optimized spatial displacement data of the task object to generate the second mechanical control parameters; Step S38: setting the industrial machinery control parameter based on the first machinery control parameter and the second machinery control parameter to obtain the industrial machinery control parameter; Step S4: Execute a mechanical automation control operation based on the industrial machinery control parameters; Step S5: analyzing historical fluctuation signals of the perception parameters influencing the operation of the machine, and generating historical fluctuation signals of the perception parameters influencing the operation; and analyzing the safety ratio interval of the perception parameters influencing the operation of the machine according to the historical fluctuation signals of the perception parameters influencing the operation; Step S6: Based on the safety ratio interval affecting the perception parameters and the mechanical operating performance, the mechanical automation control operation is subjected to safety optimization performance adjustment and limitation processing to obtain a safe and optimized mechanical automation control operation.

2. The mechanical automation control method based on environment perception according to claim 1 is characterized in that: Step S2 includes the following steps: Performing environment perception entity visual analysis according to the environment perception visual data to generate environment perception entity visual data; Perform environmental perception task object detection processing based on environmental perception entity visual data to generate environmental perception task object data.

3. The mechanical automation control method based on environment perception according to claim 1, characterized in that: Step S36 includes the following steps: Step S361: performing task object spatial displacement demand analysis according to the industrial machinery task demand data and the task object spatial position data to generate task object spatial displacement demand data; Step S362: performing task object spatial displacement mutation point analysis according to the task object spatial displacement demand data, and generating task object spatial displacement mutation area data; Step S363: performing spatial displacement mutation safety area difference analysis on the spatial displacement mutation area data of the task object according to a preset spatial displacement mutation safety area threshold, and generating spatial displacement mutation safety area difference data; Step S364: performing spatial displacement adjustment route channel line filling processing according to the spatial displacement mutation safety area difference data to generate spatial displacement adjustment route channel line filling data; Step S365: performing task object optimization spatial displacement analysis on the task object spatial displacement demand data according to the spatial displacement adjustment route channel supplementary line data, and generating task object optimization spatial displacement data.

4. The mechanical automation control method based on environment perception according to claim 1, characterized in that: Step S5 includes the following steps: Step S51: analyzing historical impact perception parameter fluctuation signals based on the machine operation impact perception parameters to generate historical impact perception parameter fluctuation signals; Step S52: performing historical impact perception parameter signal fluctuation base state interval analysis according to the historical impact perception parameter fluctuation signal to generate the historical impact perception parameter signal fluctuation base state interval; Step S53: Collect historical mechanical operation performance data corresponding to the historical ground state interval of the fluctuation of the perception parameter signal; calculate the safety ratio interval of the influencing perception parameter and the mechanical operation performance according to the historical ground state interval of the fluctuation of the perception parameter signal and the corresponding historical mechanical operation performance data.

5. The mechanical automation control method based on environment perception according to claim 4 is characterized in that: Step S6 includes the following steps: Step S61: performing a mechanical control performance adaptive adjustment process on the mechanical automation control operation according to a preset mechanical operation performance adjustment extreme value threshold, and generating a mechanical automation control operation with performance adjustment; Step S62: performing real-time impact perception parameter signal monitoring and processing according to the mechanical operation impact perception parameters of the mechanical automation control operation of the performance adjustment, and generating a real-time impact perception parameter signal; Step S63: performing outlier signal monitoring and processing on the real-time influencing perception parameter signal according to the historical influencing perception parameter signal fluctuation base state interval to generate an influencing perception parameter outlier signal; Step S64: collecting outlier machine operation performance data corresponding to the outlier signal affecting the perception parameter; calculating the outlier ratio data affecting the perception parameter and the machine operation performance according to the outlier signal affecting the perception parameter and the corresponding outlier machine operation performance data; Step S65: when it is identified that the outlier ratio data affecting the perception parameter and the mechanical operation performance is in the safe ratio interval affecting the perception parameter and the mechanical operation performance, the outlier mechanical operation performance data is marked as valid mechanical operation performance data; Step S66: when it is identified that the outlier ratio data affecting the perception parameter and the mechanical operation performance is not in the safe ratio interval affecting the perception parameter and the mechanical operation performance, the outlier mechanical operation performance data is marked as abnormal mechanical operation performance data; the abnormal mechanical operation performance data is subjected to intelligent adjustment processing of the mechanical operation performance to obtain intelligently adjusted mechanical operation performance data; Step S67: Feedback the effective mechanical operation performance data and the intelligently adjusted mechanical operation performance data to the mechanical automation control operation for performance adjustment, and perform safety optimization performance adjustment and limitation processing on the mechanical automation control operation to obtain a safe and optimized mechanical automation control operation.

6. The mechanical automation control method based on environment perception according to claim 5, characterized in that: The step S66 of performing intelligent adjustment on the abnormal mechanical operation performance data includes the following steps: Design the mechanical operation performance constraint characteristics according to the safety ratio range of the influencing perception parameters and mechanical operation performance, and generate mechanical operation performance constraint characteristic data; Intelligent adjustment of the abnormal mechanical operation performance is performed according to the mechanical operation performance constraint characteristic data to obtain intelligently adjusted mechanical operation performance data.

7. A mechanical automation control system based on environmental perception, characterized in that: The method for controlling a mechanical automation system based on environment perception according to claim 1 comprises: An environmental perception data acquisition module is used to collect environmental perception data through environmental monitoring sensors configured inside industrial machinery and equipment to generate environmental perception data, wherein the environmental perception data includes environmental perception visual data and perception parameters affecting mechanical operation; An environment perception task object detection module is used to perform environment perception task object detection processing based on environment perception visual data to generate environment perception task object data; The industrial machinery control parameter analysis module is used to obtain industrial machinery task demand data; perform task object morphological feature analysis based on environmental perception task object data to generate task object morphological feature data; perform target touch node combination matching and identification processing based on industrial machinery task demand data and task object morphological feature data to generate target touch node combination data; when the target touch node combination data is less than a preset touch node combination demand threshold, perform abnormal target touch node combination identification on the target touch node combination data to generate abnormal target touch node combination data; when the abnormal target touch node combination data is identified, perform morphological feature multi-dimensional angle visible pixel point analysis based on the task object morphological feature data to generate morphological feature multi-dimensional angle visible pixel point data; perform morphological feature pixel point descriptor analysis based on the morphological feature multi-dimensional angle visible pixel point data to generate morphological feature pixel point descriptor data; perform touch node benefit analysis based on the morphological feature pixel point descriptor data to generate touch node benefit data; perform global optimization of the task object morphological feature data based on the touch node benefit data Node combination analysis to generate globally optimized touch node combination data; when the target touch node combination data is not less than the preset touch node combination requirement threshold, perform effective target touch node combination data analysis on the target touch node combination data to generate effective target touch node combination data; perform inverse kinematics analysis of mechanical touch operation based on the effective target touch node combination data or the globally optimized touch node combination data to generate inverse kinematics data of mechanical touch operation; perform first mechanical control parameter analysis based on the inverse kinematics data of mechanical touch operation to generate first mechanical control parameters; perform spatial position analysis and processing of task objects based on environmental perception task object data to generate spatial position data of task objects; perform optimized spatial displacement analysis of task objects based on industrial machinery task requirement data and spatial position data of task objects to generate optimized spatial displacement data of task objects; perform second mechanical control parameter analysis based on the optimized spatial displacement data of task objects to generate second mechanical control parameters; set industrial machinery control parameters based on the first mechanical control parameters and the second mechanical control parameters to obtain industrial machinery control parameters; A mechanical automation control operation execution module, used to execute mechanical automation control operations based on industrial machinery control parameters; The mechanical operation performance safety ratio interval analysis module is used to analyze the historical impact perception parameter fluctuation signal based on the mechanical operation impact perception parameter, generate the historical impact perception parameter fluctuation signal; analyze the safety ratio interval between the impact perception parameter and the mechanical operation performance according to the historical impact perception parameter fluctuation signal; The optimized performance adjustment and limitation module of mechanical control is used to perform safe optimized performance adjustment and limitation processing on mechanical automation control operations based on the safety ratio interval affecting the perception parameters and the mechanical operating performance, so as to obtain safe optimized mechanical automation control operations.

Images