A potential collision detection and optimization method for machining path trajectory simulation

Abstract

The application provides a potential collision detection and optimization method for machining path trajectory simulation, generates a virtual boundary through an ultrasonic dynamic sound field, adjusts the shape of the boundary in real time to adapt to changes in the workpiece and the environment. By using multi-path signal fusion and adaptive filtering technology, the detection accuracy is improved and the interference is reduced. Through the design of double-layer virtual boundary, early warning and safety protection are realized; combined with heuristic search and fast path planning algorithm, the path is dynamically optimized, and the collision avoidance demand and machining efficiency are balanced. Deep learning and reinforcement learning models are introduced, and the boundary and path are adaptively optimized based on historical data and real-time feedback. The method is suitable for multi-axis linkage machining and complex curved surface machining, and has high precision, strong anti-interference ability and wide applicability.

Description

Technical Field

[0001] This invention belongs to the field of CNC machining technology, specifically relating to a method for potential collision detection and optimization in machining path trajectory simulation. Background Technology

[0002] In modern industrial machining, with the continuous increase in product complexity and precision, multi-axis machining and complex surface machining have gradually become mainstream. However, in such machining tasks, accurate simulation of machining paths and collision detection have always been important but challenging technical problems. Especially in multi-tool collaborative or dynamic machining scenarios, the potential collision risk between tools, workpieces, and fixtures increases significantly, and traditional path planning and collision avoidance methods are difficult to meet the requirements of real-time performance and accuracy.

[0003] 1. Traditional methods often use predefined virtual boundaries for collision detection. The boundary shape is usually based on the initial workpiece geometry model, which is difficult to adapt to workpiece deformation, fixture movement, and other environmental changes during processing. Since the virtual boundary is statically set, false alarms or detection blind spots are prone to occur in complex processing tasks, affecting processing efficiency and safety.

[0004] 2. Path planning is often based on fixed optimization algorithms (such as the shortest path algorithm), which cannot respond to dynamic changes in the machining environment in real time. In complex scenarios (such as multi-axis linkage machining or collaborative machining), path planning algorithms often ignore the balance between collision avoidance priority and machining efficiency, which may lead to decreased efficiency or collision avoidance failure.

[0005] 3. In complex processing environments, ultrasonic signals are easily affected by scattering, reflection, and environmental noise, leading to a decrease in the clarity of virtual boundaries. Current technologies mostly employ simple filtering or signal enhancement methods, which cannot effectively solve the problems of multipath signal fusion and noise reduction in complex environments.

[0006] 4. Existing technologies for virtual boundary adjustment and path planning are mostly based on rules or predefined parameters, lacking dynamic learning and optimization capabilities. They also have low utilization of historical data, making it difficult to form a system-wide adaptive optimization mechanism.

[0007] In summary, existing technologies have the following shortcomings in the fields of machining path simulation and collision detection:

[0008] The virtual boundary has weak dynamic adjustment capability: it is difficult to adapt to the dynamic changes of workpiece and environment in complex machining tasks.

[0009] Insufficient real-time path planning: It cannot balance collision avoidance requirements with processing efficiency, especially in highly dynamic multi-axis machining scenarios.

[0010] Limited anti-interference capability: The accuracy of virtual boundary detection is insufficient due to the influence of environmental noise and signal interference.

[0011] Insufficient intelligence and adaptability: Lacking a data-driven intelligent optimization mechanism, it is unable to cope with complex and ever-changing processing needs. Summary of the Invention

[0012] Therefore, the purpose of this invention is to provide a potential collision detection and optimization method for simulating machining path trajectories. Through dynamic virtual boundary adjustment, real-time path optimization, and artificial intelligence-assisted optimization, the accuracy, real-time performance, and intelligence level of the machining path are significantly improved. It is particularly suitable for highly dynamic task scenarios such as multi-axis linkage machining, complex surface machining, and collaborative machining.

[0013] To address the aforementioned technical problems, according to one aspect of the present invention, the present invention provides the following technical solution:

[0014] A method for potential collision detection and optimization in machining path trajectory simulation, which achieves collision detection and avoidance in the machining path through virtual boundary construction based on ultrasonic dynamic sound field, real-time feedback control, and path optimization algorithm; the method includes the following steps:

[0015] S1. A dynamic sound field is generated in the processing area using an ultrasonic array to define a virtual boundary;

[0016] S2. The tool sensing module receives ultrasonic signals in real time and calculates the relative distance between the tool and the virtual boundary;

[0017] S3. When the tool approaches or touches the virtual boundary, trigger path adjustment or pause the machining operation;

[0018] S4. Dynamically adjust the shape of the virtual boundary based on real-time feedback to adapt to changes in the workpiece, fixture, and machining path.

[0019] The dynamic sound field is generated by superimposing multi-frequency ultrasonic waves, and the clarity of the virtual boundary and its resistance to scattering interference are enhanced by adjusting the emission frequency, phase and intensity.

[0020] Among them, by analyzing the time delay, intensity attenuation and frequency characteristics of ultrasonic echo signals through multipath signal fusion technology, scattering and reflection interference are filtered out, thereby improving the detection accuracy of virtual boundaries.

[0021] Among them, an adaptive filtering algorithm is used to dynamically optimize real-time signal processing, which removes environmental noise signals and enhances the recognition ability of effective signals by adjusting filter parameters in real time.

[0022] Among them, sound-absorbing materials are placed in non-processing areas to reduce interference from multiple ultrasonic wave reflections and to reduce the impact of complex processing environments on virtual boundary detection.

[0023] The virtual boundary includes two layers of boundaries:

[0024] The first boundary layer is used to detect when the tool approaches a dangerous area and triggers path deceleration or adjustment.

[0025] The second boundary layer is used to detect when the tool touches the boundary, triggering a machining pause and issuing an alarm signal.

[0026] The algorithm employs a dynamic path optimization method to dynamically replan the toolpath based on the real-time distance between the tool and the virtual boundary, the motion trend, and the machining strategy. This path optimization includes:

[0027] When the tool approaches the first layer boundary, it decelerates and adjusts its path direction.

[0028] When the tool enters the collision zone, it triggers a machining pause and generates a safe path to bypass the collision zone.

[0029] The system generates a noise feature model before processing using an active environmental compensation algorithm, recording the scattering characteristics of the workpiece, fixture, and tool. During processing, the real-time signal is compared with the noise feature model, and interference signals are subtracted to improve detection accuracy.

[0030] Among them, artificial intelligence algorithms are used to learn and optimize historical processing data, including a virtual boundary accuracy optimization model based on deep learning and a dynamic path planning model based on reinforcement learning, to improve processing efficiency and collision avoidance capabilities.

[0031] The method is applicable to multi-axis linkage machining scenarios and complex surface machining. By reconstructing virtual boundaries and path adjustment strategies in real time, it ensures the accuracy and efficiency of machining paths and dynamically optimizes machining paths in multi-tool or multi-robot collaborative environments to avoid path interference.

[0032] Compared with the prior art, the beneficial effects of the present invention are:

[0033] 1. Achieve dynamic adjustment of virtual boundaries

[0034] By employing dynamic sound field generation technology, the virtual boundary is dynamically adjusted based on real-time feedback data to adapt to workpiece deformation, fixture movement, and environmental changes. This achieves precise fitting and real-time updating of the virtual boundary without manual intervention.

[0035] The first-layer boundary provides an early warning function, triggering path deceleration or adjustment in advance to improve the system's response speed. The second-layer boundary is used for collision area detection, ensuring safe stopping and alarm functions when the tool contacts the boundary. This improves the accuracy and stability of the virtual boundary, adapting to dynamic machining environments. A layered protection mechanism is provided, balancing machining efficiency and safety.

[0036] 2. Dynamic path optimization improves processing efficiency and safety.

[0037] By utilizing heuristic search and a fast random tree algorithm, optimal collision avoidance paths are rapidly generated in complex machining environments. This achieves high path dynamism, enabling real-time adjustment of tool travel direction and speed.

[0038] Through an innovative optimization formula, it comprehensively considers multiple factors such as modular design, material properties, path efficiency, and processing costs. The optimization target weights are adjusted based on real-time feedback to balance collision avoidance requirements and processing efficiency. This achieves intelligent optimization of the processing path, ensuring collision avoidance while maximizing processing efficiency. It demonstrates excellent adaptability in complex multi-axis linkage processing and dynamic collaborative scenarios.

[0039] 3. Intelligent virtual boundary and path planning optimization

[0040] By using deep learning models to predict virtual boundary adjustments, the accuracy of boundary definition in complex scenarios is improved. Boundary adjustment is made intelligent and automated, reducing the need for manual intervention.

[0041] The reinforcement learning model dynamically optimizes path planning strategies based on real-time processed data. It learns and iterates on collision avoidance experience during the processing to optimize the success rate and response speed of path planning.

[0042] Virtual boundary and path planning enable intelligent and adaptive capabilities, significantly reducing processing errors. They demonstrate higher reliability and flexibility in dynamic and complex processing scenarios.

[0043] 4. Enhanced anti-interference capability

[0044] Multipath signal fusion technology, combined with an adaptive filtering algorithm, is employed to effectively filter scattered signals and environmental noise. An active environmental compensation algorithm is used to subtract noise interference, improving the detection accuracy of virtual boundaries.

[0045] Sound-absorbing materials are placed in non-processing areas to reduce multiple reflections and optimize the sound field distribution. The emission frequency and phase are dynamically adjusted to further improve the stability of the sound field.

[0046] The clarity and anti-interference capability of the virtual boundary are significantly improved. The system can adapt to complex processing environments with high noise and high vibration, and its operation is more stable.

[0047] 5. Wide applicability

[0048] It supports machining complex curved surfaces, dynamically adjusting virtual boundaries to fit the workpiece shape. It enables high-precision multi-axis linkage machining path planning.

[0049] In collaborative machining involving multiple robots or multiple tools, dynamic path planning is used to avoid path conflicts and resource waste.

[0050] The system is suitable for various machining scenarios, including simple path machining, complex surface machining, and dynamic collaborative machining. It features high scalability and high compatibility across a wide range of applications.

[0051] 6. Improve processing safety

[0052] The first boundary layer provides safety warnings, triggering deceleration and path adjustments in advance to avoid potential collisions. The second boundary layer ensures precise protection of the collision area, stopping the machine promptly and issuing an alarm. When the tool enters the collision range, path replanning is triggered to quickly generate a safe path. This prevents equipment damage or workpiece scrap due to machining anomalies.

[0053] The processing is safer and more reliable, reducing the probability of accidents. It also reduces equipment wear and tear, lowers workpiece scrap rates, and improves processing quality.

[0054] 7. Efficient data utilization and system optimization

[0055] By using deep learning training to process historical data, collision avoidance and optimization experiences can be extracted to improve the efficiency and accuracy of future processing tasks.

[0056] The system dynamically adjusts virtual boundaries and path optimization strategies based on real-time feedback to achieve intelligent closed-loop control of the processing process.

[0057] Data-driven optimization mechanisms enhance the system's intelligence and efficiency. The system can continuously learn and self-optimize, maintaining a high-efficiency operating state for extended periods.

[0058] In summary, this invention achieves the following significant beneficial effects through techniques such as dynamic sound field generation, real-time virtual boundary adjustment, path optimization algorithms, and AI-assisted optimization:

[0059] It improves the accuracy and adaptability of virtual boundaries.

[0060] It achieves intelligent optimization of path planning, balancing collision avoidance requirements with processing efficiency.

[0061] It enhances anti-interference capabilities and environmental adaptability.

[0062] It provides a safe and efficient processing protection mechanism.

[0063] It has broad applicability and supports complex processing scenarios.

[0064] The system has achieved intelligence and self-adaptation capabilities, enabling continuous optimization of processing performance.

[0065] These effects make the present invention applicable to highly dynamic and complex processing tasks, giving it significant technical value and application prospects. Attached Figure Description

[0066] To more clearly illustrate the technical solutions of the embodiments of the present invention, the present invention will be described in detail below with reference to the accompanying drawings and detailed embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. Wherein:

[0067] Figure 1 This is a schematic diagram of the method flow of the present invention;

[0068] Figure 2 This is a schematic diagram of information flow in the method of the present invention. Detailed Implementation

[0069] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0070] See Figure 1 and 2 This paper presents a potential collision detection and optimization method for simulating machining path trajectories. It achieves collision detection and avoidance in the machining path through virtual boundary construction based on ultrasonic dynamic sound fields, real-time feedback control, and path optimization algorithms. This method is applicable to multi-axis linkage machining scenarios and complex surface machining. By reconstructing virtual boundaries and adjusting path strategies in real time, it ensures the accuracy and efficiency of the machining path and dynamically optimizes the machining path in multi-tool or multi-robot collaborative environments to avoid path interference.

[0071] Specific steps:

[0072] S1. Dynamic Sound Field Generation and Virtual Boundary Definition

[0073] Dynamic sound field construction: A dynamic sound field is generated in the processing area using an ultrasonic array to define the virtual boundary of the processing path. The dynamic sound field is generated by superimposing multi-frequency ultrasonic waves, and the clarity and anti-scattering interference capability of the virtual boundary are enhanced by adjusting the emission frequency, phase, and intensity.

[0074] Interference signal filtering and environmental optimization: Utilizing multipath signal fusion technology, the time delay, intensity attenuation, and frequency characteristics of ultrasonic echo signals are analyzed to filter scattering and reflection interference, thereby improving the detection accuracy of virtual boundaries. An adaptive filtering algorithm is employed to dynamically optimize real-time signal processing, removing environmental noise signals by adjusting filter parameters in real time and enhancing the recognition capability of effective signals. An active environmental compensation algorithm generates a noise feature model before processing, recording the scattering characteristics of the workpiece, fixture, and tool. During processing, the real-time signal is compared with the noise feature model, and interference signals are subtracted to improve detection accuracy.

[0075] Physical environment optimization: Sound-absorbing materials are placed in non-processing areas to reduce interference from multiple ultrasonic wave reflections and to reduce the impact of complex processing environments on virtual boundary detection.

[0076] Layered design of virtual boundaries:

[0077] First boundary layer: Triggers path deceleration or adjustment when the tool approaches a dangerous area;

[0078] Second boundary layer: When the tool touches the boundary, the machining is paused and an alarm signal is issued.

[0079] Furthermore, the specific implementation method of S1 is as follows:

[0080] S1.1 Generation of Dynamic Sound Field

[0081] ① Arrangement and control of ultrasonic array

[0082] Array Arrangement: Arrange ultrasonic transmitter and receiver arrays at key locations in the machining area (such as workpiece edges and around toolpaths). Depending on the complexity of the machining task, a two-dimensional or three-dimensional array layout can be selected.

[0083] Transmission parameter design: The ultrasonic wave is set to a working frequency (20-100kHz), and the appropriate frequency range is selected according to the workpiece material and processing environment.

[0084] Phase control: Using phase adjustment to form directional beams, improving the coverage and energy concentration of the sound field.

[0085] ②Multi-frequency ultrasonic waves superimposed to generate a sound field

[0086] A multi-frequency superposition technique is employed to create multiple independent sound fields in space from ultrasonic waves of different frequencies. Each frequency corresponds to a sub-sound field, which enhances signal redundancy and detection accuracy. Frequency separation technology is used to decouple the signals for subsequent processing.

[0087] ③ Dynamically adjust the sound field distribution

[0088] Based on the three-dimensional model of the workpiece and fixture, a digital signal processor (DSP) is used to adjust the emission frequency, phase, and intensity of the ultrasonic waves in real time to ensure precise matching between the sound field and the processing area.

[0089] Dynamically adjustable parameters include: emission angle, to cover complex curved surfaces or edges; and intensity gain, to adapt to the reflection characteristics of different materials.

[0090] S1.2 Definition and Layering of Virtual Boundaries

[0091] ① Initial construction of virtual boundaries

[0092] Define the scope of the virtual boundary based on the sound field distribution and processing task:

[0093] Inner boundary (first layer): A warning line that marks a dangerous area. When the tool approaches this boundary, it will trigger a deceleration or path adjustment.

[0094] Outer boundary (second layer): Identifies the collision area. When the tool touches this boundary, machining is paused.

[0095] ② Boundary layer optimization

[0096] The boundary layers are dynamically assigned based on processing complexity and precision requirements: the first boundary layer is suitable for rapid collision avoidance and early warning. The second boundary layer provides hard constraints to ensure the safety of equipment and workpieces.

[0097] Define boundary parameters: First-layer distance threshold: set according to machining speed and path complexity, usually 1-2 times the tool diameter. Second-layer distance threshold: slightly less than the virtual boundary trigger condition, 0.5-0.8 times the tool diameter.

[0098] S1.3 Interference signal filtering

[0099] ① Multipath signal fusion technology

[0100] Ultrasonic signals are received from multiple receivers, and path differences are analyzed. Effective echo signals are extracted by time delay calculation and intensity comparison, while scattered and multiple-reflection signals are filtered out.

[0101] ② Real-time filter optimization

[0102] An adaptive filtering algorithm is applied to adjust filter parameters based on the real-time acquired signal: in the initial stage, filter weights are set according to environmental noise and echo characteristics. In the dynamic stage, the filter parameters are updated in real time to eliminate new interference generated during processing.

[0103] S1.4 Active Environmental Compensation and Physical Optimization

[0104] ① Environmental Active Compensation Algorithm

[0105] Before machining, a noise learning mode is run to record the scattered signal characteristics of the workpiece, fixture, and machining environment. A noise feature model is generated, including the frequency and intensity distribution of the interference signal. During machining, the real-time acquired signal is compared with the noise feature model, and the interference component is automatically removed.

[0106] ② Arrangement of sound-absorbing materials

[0107] Sound-absorbing materials are placed on non-working surfaces in the machining area (such as the back of fixtures and machine tool walls) to absorb ultrasonic signals that have been reflected multiple times. The layout and thickness of the sound-absorbing materials are optimized to reduce the noise propagation path.

[0108] S1.5 sound field self-calibration and real-time optimization

[0109] ① Real-time self-correction mechanism

[0110] Based on ultrasonic sensing data, changes in the sound field are analyzed in real time. If uneven or disturbed areas of the sound field are detected, the power and direction of the transmitter are dynamically adjusted to keep the virtual boundary stable.

[0111] ② Virtual boundary reconstruction

[0112] During the machining process, the sound field distribution is reconstructed in real time based on the deformation of the workpiece or the movement of the fixture. The reconstruction steps are: rescanning the workpiece surface, updating the sound field distribution parameters, and adjusting the boundary shape in real time.

[0113] The implementation of step S1 combines dynamic sound field generation, signal processing, and virtual boundary construction to form a high-precision virtual boundary system that is adjusted in real time, providing reliable basic data input for subsequent tool monitoring and path optimization.

[0114] S2. Calculation of the distance between the tool and the virtual boundary

[0115] The tool sensing module receives ultrasonic signals in real time and calculates the relative distance between the tool and the virtual boundary. Based on the distance between the tool and the boundary, the risk level is dynamically determined, triggering different collision avoidance strategies.

[0116] Furthermore, the specific implementation method of S2 is as follows:

[0117] S2.1 Ultrasonic Signal Acquisition and Fusion

[0118] ① Operation of the ultrasonic array

[0119] An ultrasonic array (transmitter and receiver) is arranged in the machining area. By emitting ultrasonic signals and receiving echo signals, the position of the tool relative to the virtual boundary is determined.

[0120] Sensors on the cutting tool receive echo signals in real time to calculate its distance from the boundary.

[0121] The propagation time difference of ultrasonic signals (time delay method) is used for preliminary calculation of tool position. This part is based on the conventional formula for ultrasonic propagation (such as d=v·Δt, which is common knowledge and will not be elaborated).

[0122] ② Multipath signal fusion

[0123] Signals from multiple receivers are fused to eliminate interference caused by scattering or reflection: valid signals are filtered based on signal strength attenuation and path time difference. Multipath fusion technology is used to comprehensively calculate the signals from different receivers using a weighted averaging method, thereby improving tool positioning accuracy.

[0124] ③ Signal processing and real-time updates

[0125] A dynamic filter is used to adjust the filtering parameters in real time according to the noise environment and processing conditions: filtering out noise and invalid signals while retaining valid echo information.

[0126] By combining an active environmental compensation algorithm, a noise feature model is generated before processing; during processing, the echo signal and noise features are compared in real time to deduct interference.

[0127] S2.2 Distance Calculation and Risk Level Assessment

[0128] ① Calculation of the distance between the cutting tool and the virtual boundary

[0129] Once the tool position is determined, the distance between it and each point on the virtual boundary is calculated in real time, and the closest distance is selected:

[0130] d min =min{d1,d2,…,d n}; where d min The closest distance from the tool to the virtual boundary. d1, d2, ..., d n : Distance from the tool to each point on the virtual boundary.

[0131] ② Dynamic classification of risk levels

[0132] According to d min The layered design of virtual boundaries is divided into the following risk levels:

[0133] Safety range: when d min >D1, the tool moves away from the first layer boundary, and the system maintains normal machining.

[0134] Warning range: When D2 <d min ≤D1, the tool approaches the first layer boundary, triggering path deceleration or adjustment.

[0135] Collision range: when d min If the value is ≤D2, the tool enters the second-layer boundary area, the system pauses processing and issues an alarm.

[0136] ③ Dynamic updates to risk assessment: During the processing, the risk level is updated in real time, and boundary parameters (such as distance thresholds D1 and D2) are adjusted in combination with changes in the processing environment to ensure that the boundary always adapts to the current task requirements.

[0137] S2.3 Optimization Formula Q o Dynamic applications of pt

[0138] ① Introduction of the optimization formula

[0139] Based on real-time distance calculation, an optimization formula Q is introduced. optA comprehensive evaluation of the tool's operating status is conducted.

[0140] Wherein, M: Modular design coefficient, dimensionless, representing the contribution of modular design to machining path flexibility, calculated through machining parameters (such as the number and size of workpiece modules). α: Path sensitivity, dimensionless, representing the impact of path design on machining efficiency, usually related to path complexity and machining direction. β: Material property influence factor, dimensionless, representing the impact of material properties (such as strength and elasticity) on toolpath planning. E: Material elastic modulus, in Pascals (Pa), extracted from a material database, used to describe the material's resistance to deformation. n: Nonlinear loading adjustment coefficient, dimensionless, representing the correction of material properties under nonlinear stress loading conditions. V: Machining area volume, in cubic meters (m3), the three-dimensional volume of the machining area calculated in conjunction with the toolpath. γ: Path efficiency factor, dimensionless, representing the dynamic change in path planning efficiency. C: Unit machining cost, in monetary units (e.g., yuan / meter). Calculates the cost consumed by the toolpath in real time. τ: Remaining tool life, in hours (h), estimated based on the tool's cumulative running time and current load state. m: Life sensitivity index, dimensionless, representing the sensitivity of tool performance to changes in remaining tool life. η: Friction loss factor, dimensionless, representing energy loss during machining.

[0141] The purpose of the optimization formula is to dynamically evaluate tool performance, including comprehensive optimization of path planning, machining efficiency, and material properties.

[0142] ③ Dynamic application of optimization formulas

[0143] During the processing, real-time parameters are substituted into the formula to calculate Q. opt Combined with Q opt Path optimization is performed based on the calculation results:

[0144] If Q opt ≥Q target Maintain the current path.

[0145] If Q opt target Trigger path adjustment to optimize tool movement direction and speed.

[0146] S2.4 System Feedback and Path Adjustment

[0147] ① Feedback mechanism

[0148] Risk level and Q opt The calculation results are fed back to the path optimization module, triggering corresponding adjustments:

[0149] Safety range: No adjustment.

[0150] ​Warning zone: Slow down or adjust direction.

[0151] Collision range: Processing is paused, and the path is replanned.

[0152] ②Dynamic adjustment of virtual boundaries

[0153] Based on the relative position of the tool and the boundary and Q opt The shape of the virtual boundary is dynamically adjusted to adapt to changes in the workpiece, fixture, and machining path.

[0154] Step S2 is achieved through ultrasonic signal acquisition, distance calculation, and optimization formula Q. opt The dynamic application of this technology enables real-time assessment of tool operating status and path adjustment. This step, combined with risk level classification and system feedback mechanisms, provides accurate input data for subsequent path optimization.

[0155] S3. Dynamic Path Optimization and Collision Avoidance

[0156] Path adjustment mechanism: When the tool approaches the virtual boundary, path adjustment or pausing of machining operation is triggered.

[0157] Path optimization includes the following two cases:

[0158] As the tool approaches the first layer boundary: the system triggers path deceleration or adjusts the path direction;

[0159] When the tool enters the collision zone: this triggers a machining pause and generates a safe path to bypass the collision zone.

[0160] Dynamic path optimization algorithm: A lightweight dynamic path optimization algorithm is introduced, combining heuristic search algorithms and fast path planning to reduce computational complexity. Based on the real-time distance between the tool and the virtual boundary, movement trends, and machining strategies, the optimal path is dynamically generated in high-risk areas.

[0161] Furthermore, the specific implementation method of S3 is as follows:

[0162] S3.1 Triggering conditions for path adjustment

[0163] ① Real-time monitoring and judgment

[0164] Based on the closest distance d between the tool and the virtual boundary calculated in step S2 min Conditions for determining whether a path adjustment or collision avoidance operation is triggered:

[0165] Safety range: d min >D1, the tool is away from the boundary, no path adjustment is needed.

[0166] Alert area: D2 <d min ≤D1, the tool approaches the first layer boundary, triggering deceleration or path adjustment.

[0167] Collision range: d min ≤D2, the tool enters the second-layer boundary area, triggering a machining pause and replanning the path.

[0168] ② Dynamic risk assessment

[0169] In each monitoring cycle, the risk of the current path is assessed based on the relative relationship between the tool position and the virtual boundary, combined with path complexity, machining speed and environmental changes.

[0170] The priority of path optimization is dynamically adjusted based on the risk level.

[0171] S3.2 Dynamic Path Optimization Algorithm

[0172] ① Path optimization principle

[0173] Dynamic path optimization should take the following principles into account:

[0174] Collision avoidance priority: When the tool approaches the virtual boundary, the path is adjusted first to ensure safety.

[0175] Efficiency balance: While avoiding collisions, maintain the efficiency of the path as much as possible (such as the shortest path and the lowest energy consumption).

[0176] Real-time performance: The optimization process must meet the requirements of real-time response to ensure that the system can quickly adapt to changes during processing.

[0177] ② Path optimization implementation methods

[0178] (1) Heuristic search algorithm

[0179] Using an optimized A*(A-star) algorithm, a new path that meets the collision avoidance conditions is quickly generated:

[0180] Define the path cost function f(n): f(n) = g(n) + h(n); where g(n): the cumulative cost of the current path, and h(n): the estimated cost (heuristic function) from the current node to the target node.

[0181] During the search process, collision avoidance priority weights are dynamically increased to ensure that the path stays away from high-risk areas of the virtual boundary.

[0182] (2) Rapid Path Planning (RRT)

[0183] In complex multi-axis machining scenarios, the Rapid Random Tree (RRT) algorithm is used to generate collision avoidance paths: randomly sample path points, expand the tree structure, and continue until a safe path from the starting point to the target point is found. The path smoothness is optimized to ensure that the path meets machining accuracy requirements.

[0184] (3) Dynamic constraint adjustment

[0185] The constraints of path optimization are dynamically adjusted based on real-time feedback, such as the safe range within the processing area and tool speed limits.

[0186] ③ Combining the optimization formula Q opt

[0187] During path optimization, the optimization formula Q will be used. opt Dynamically introduce and evaluate the overall performance of path adjustment;

[0188] Optimization goal: Select Q opt The optimal path selection ensures a balance between collision avoidance and efficiency.

[0189] S3.3 Path Adjustment Strategy

[0190] ① Route adjustment within the warning area

[0191] Deceleration: When the tool enters the warning range, the system dynamically adjusts the tool's feed rate to reduce the risk of collision during machining.

[0192] Fine-tuning direction: The path fine-tuning algorithm optimizes the tool's running direction, keeping it as far away from the virtual boundary as possible while maintaining the continuity of the machining path.

[0193] ② Path adjustment within the collision range

[0194] Pause Operation: When the tool enters the collision range, immediately pause processing to ensure the safety of the workpiece and equipment.

[0195] Path replanning: The system triggers the path replanning module to generate a completely new safe path based on the current tool position and machining target. Path replanning combines heuristic search algorithms (such as A*) and random sampling (such as RRT) to quickly find collision avoidance paths.

[0196] ③ Selection of multi-path schemes

[0197] During path adjustment or replanning, the system generates multiple candidate paths and, based on Q... opt The calculation results of the formula select the path with the best overall performance.

[0198] S3.4 System Feedback and Closed-Loop Adjustment

[0199] ① Real-time feedback mechanism

[0200] The tool position and running status information after path adjustment are fed back to the virtual boundary adjustment module in real time (step S4) to further optimize the shape and distribution of the boundary. If high-risk areas still exist after path adjustment, the next round of optimization is triggered.

[0201] ② Closed-loop adjustment mechanism

[0202] During the machining process, path optimization parameters (such as tool speed, path curvature constraints, etc.) are dynamically adjusted to improve the adaptability of collision avoidance operations. Key data during the adjustment process are recorded for subsequent training of the reinforcement learning model (see step S5).

[0203] Step S3 realizes closed-loop control of dynamic path optimization and collision avoidance operation. From trigger condition determination to path adjustment and replanning, and then to system feedback and closed-loop adjustment, it ensures safe and efficient tool operation and provides a highly real-time and highly adaptable solution for collision avoidance optimization in complex machining environments.

[0204] S4. Dynamic adjustment of real-time virtual boundaries

[0205] The virtual boundary shape is dynamically adjusted based on real-time feedback during the machining process to adapt to changes in the workpiece, fixture, and machining path. The intersection point between the tool path and the virtual boundary is predicted in advance, and the distribution of the virtual boundary in the machining area is dynamically optimized through a boundary reconstruction mechanism.

[0206] Furthermore, the specific implementation method of S4 is as follows:

[0207] S4.1 Real-time Feedback and Virtual Boundary Adjustment Trigger

[0208] ① Feedback Data Collection

[0209] The real-time data obtained from steps S2 and S3 includes:

[0210] The closest distance d between the tool and the virtual boundary min .

[0211] The offset of the tool travel path.

[0212] Environmental parameters (such as temperature, vibration, and processing speed).

[0213] Feedback data is used to determine whether the virtual boundary needs adjustment.

[0214] ② Triggering condition determination

[0215] Static error detection: When the tool deviates from the preset path, or the boundary shape does not match the actual position of the workpiece / fixture, adjustment is triggered.

[0216] Dynamic environmental changes: When workpiece deformation, fixture movement, or external environmental changes (such as increased noise) exceed a set threshold during the processing, dynamic boundary reconstruction is triggered.

[0217] S4.2 Virtual Boundary Adjustment Mechanism

[0218] ①Preliminary shape correction

[0219] Adjusting the shape of the virtual boundary based on real-time data:

[0220] Geometric correction: Redefine boundary positions based on the latest 3D model of the workpiece or fixture.

[0221] Layered optimization: The distance threshold between the first layer (safety boundary) and the second layer (collision boundary) is dynamically updated to adapt to the current processing environment.

[0222] ② Dynamic Reconstruction Algorithm

[0223] Boundary reconstruction formula:

[0224] The new virtual boundary shape is determined by the following formula: B new (x,y,z)=B init (x,y,z)+ΔB(x,y,z); where, B new (x,y,z): Adjusted boundary shape. B init (x,y,z): Initial boundary shape. ΔB(x,y,z): Adjustment amount, determined by real-time feedback data.

[0225] Calculation of adjustment amount ΔB: ΔB is calculated by combining the relative positional offset between the tool and the boundary and the environmental changes: ΔB=κ·d min +ψ·ΔE; where κ: the sensitivity coefficient for positional offset. d min ψ: Minimum distance between the tool and the boundary. ΔE: Weighting coefficient for environmental changes. ΔE: Amount of environmental change (e.g., vibration amplitude, temperature change).

[0226] ③ Multi-layer boundary adjustment

[0227] First-level boundary (safety boundary): Distance threshold D1 is dynamically adjusted according to processing speed to avoid too many false alarms.

[0228] The second boundary layer (collision boundary): the threshold D2 is updated in real time according to the workpiece deformation or fixture movement to ensure accurate triggering when the tool comes into contact.

[0229] S4.3 Reinforcement Learning Assisted Dynamic Adjustment

[0230] ① Introduction of reinforcement learning models

[0231] The virtual boundary adjustment is optimized using reinforcement learning algorithms (such as Deep Q-Network, DQN):

[0232] Input: Real-time feedback data (tool position, boundary offset, environmental changes).

[0233] Output: Boundary adjustment amount ΔB.

[0234] Learning objective: Minimize the deviation between the virtual boundary and the actual processing area. Optimize the efficiency of boundary shape adjustment.

[0235] ② Learning mechanism

[0236] Training data: extracted from historical processing paths and adjustment records, including boundary adjustment data under different workpiece shapes and environmental conditions.

[0237] Real-time learning: Continuously optimize boundary adjustment strategies by combining feedback data from the current processing tasks.

[0238] S4.4 Adaptive Virtual Boundary Optimization

[0239] ① Parameter adaptive adjustment

[0240] Adaptive optimization is performed on the weight coefficients κ and ψ in the adjustment formula:

[0241] When the tool runs stably, reduce the weight of κ to reduce unnecessary adjustments.

[0242] When environmental changes are significant, increase the weight of ψ to prioritize responses to environmental disturbances.

[0243] ② Boundary dynamic update frequency

[0244] The update frequency is dynamically adjusted based on the complexity of the processing task.

[0245] Highly complex tasks: Increased frequency (e.g., updating 10 times per second).

[0246] Low-complexity tasks: Reduced frequency (e.g., updating twice per second).

[0247] S4.5 System Feedback and Closed-Loop Control

[0248] ① Feedback mechanism

[0249] After the adjustment is completed, the new virtual boundary shape is fed back to the path optimization module (step S3). The path optimization scheme is re-evaluated based on the updated boundary to ensure the matching between the boundary and the path.

[0250] ② Closed-loop control

[0251] A closed-loop control system for virtual boundary adjustment and path optimization is implemented: the results of virtual boundary adjustment directly affect the weight allocation in path optimization. Path optimization feedback data is used to further optimize the boundary shape.

[0252] Step S4 enables dynamic adjustment of the virtual boundary. By optimizing the boundary shape through real-time feedback, dynamic reconstruction formula, and reinforcement learning model, combined with adaptive parameter adjustment and closed-loop control mechanism, it provides high-precision and high-dynamic boundary definition and adjustment capabilities for complex processing scenarios, ensuring the safety and efficiency of the processing path.

[0253] S5. AI-assisted optimization

[0254] By using artificial intelligence algorithms to learn from and optimize historical data, the accuracy of virtual boundary detection and the efficiency of path planning can be further improved.

[0255] A deep learning-based virtual boundary accuracy optimization model is used for dynamic error compensation and noise filtering.

[0256] A dynamic path planning model based on reinforcement learning is used for real-time optimization of path collision avoidance strategies.

[0257] Establish a data acquisition and model iteration mechanism to dynamically update the artificial intelligence model during the processing.

[0258] Furthermore, the specific implementation method of step S5 is as follows:

[0259] S5.1 Data Acquisition and Preprocessing

[0260] ① Data collection

[0261] The following data will be collected during the machining process: the relative distance between the tool position and the virtual boundary; virtual boundary adjustment records, including the initial boundary shape and the dynamically adjusted shape; optimization records during path planning, including triggering conditions, optimized paths, and time consumption; dynamic changes in environmental parameters (such as vibration, temperature, and noise interference); and machining result evaluation indicators (such as collision avoidance success rate, machining efficiency, and energy consumption).

[0262] ② Data classification and labeling

[0263] The collected data is categorized according to the type of processing task, such as simple path processing, multi-axis complex surface processing, and collaborative robot processing.

[0264] Key events in the labeled data, such as:

[0265] Trigger collision avoidance adjustment: Record when the tool approaches the virtual boundary.

[0266] Path optimization complete: Recorded when the optimized path is successfully generated.

[0267] Boundary adjustment complete: Record of shape changes after virtual boundary reconstruction.

[0268] ③ Data preprocessing

[0269] Remove outlier data, such as unreasonable records caused by noise interference or sensor errors. Perform normalization processing to standardize different physical quantities (such as distance, time, and energy consumption) to fit the artificial intelligence model.

[0270] Training and Optimization of S5.2 Deep Learning Model

[0271] ① Deep learning model selection

[0272] Lightweight neural network structures are used for virtual boundary optimization.

[0273] Input: Machining history data, including tool position, boundary adjustment records, and environmental parameters.

[0274] Output: Boundary adjustment amount ΔB(x,y,z) or boundary reconstruction suggestion.

[0275] ② Model Training

[0276] Training objectives:

[0277] Minimize virtual boundary deviation:

[0278] Among them, B pred B: The boundary shape predicted by the model. true : Actual adjusted boundary shape. N: Number of training samples.

[0279] Training data: Boundary adjustment data recorded during processing is used as the training set. Simulated noise and random disturbances are added to enhance the robustness of the model.

[0280] Training method: Batch training is performed using GPU acceleration, and the Adam optimizer is used for optimization.

[0281] ③ Model optimization and validation

[0282] After optimizing the model on the training set, the model performance is tested using validation set data to ensure its adaptability in different processing scenarios.

[0283] Model optimization directions: Improve prediction accuracy in the processing of complex geometries. Reduce response time during boundary adjustment.

[0284] Design and Implementation of S5.3 Reinforcement Learning Model

[0285] ① Reinforcement Learning Framework

[0286] Use deep reinforcement learning (such as DDPG or PPO) to optimize path planning strategies.

[0287] State space: includes tool position, virtual boundary shape, current path direction, and environmental parameters.

[0288] Action space: including path direction adjustment, speed adjustment, or replanning the path.

[0289] Reward function:

[0290] Reward for successful collision avoidance: R success=+10;

[0291] Penalty Collision: R collision =-20;

[0292] Reward path efficiency: Where Δt represents the actual time for path planning. target :Target planning time.

[0293] ② Training and Updates

[0294] Simulation environment: Use virtual machining scenarios (such as complex surfaces and dynamic fixtures) to simulate path planning and collision avoidance processes under different conditions.

[0295] Training process: In the initial stage, the action space is explored using a random policy. During training, the policy is continuously updated to maximize the reward function.

[0296] ③ Real-time applications

[0297] After deployment, the reinforcement learning model receives tool position and boundary data in real time and predicts path adjustment actions. The model continuously updates its strategy based on actual machining data, enhancing its adaptability to dynamic environments.

[0298] S5.4 Adaptive Optimization Mechanism

[0299] ① Adaptive optimization of virtual boundaries

[0300] During processing, the input weights of the deep learning model are adjusted based on real-time feedback: boundary bias weights are increased to improve adaptability in complex environments; and the influence of irrelevant parameters (such as noise data in low-vibration environments) is reduced.

[0301] ② Dynamic priority adjustment of path planning

[0302] The collision avoidance priority and path efficiency weights are dynamically adjusted using a reinforcement learning model: when the tool approaches the boundary, the collision avoidance priority is increased; when the tool moves away from the boundary, the path efficiency is optimized.

[0303] ③ Parameter update and model iteration

[0304] Based on historical processing data and current task performance, the deep learning and reinforcement learning models are updated regularly to optimize virtual boundary adjustment rules and improve path planning response speed and accuracy.

[0305] S5.5 System Feedback and Evaluation

[0306] ① Feedback mechanism

[0307] The optimization results are fed back to the virtual boundary adjustment module (step S4) and the path planning module (step S3) to ensure that the modules work together.

[0308] ②System performance evaluation

[0309] The following metrics are used to evaluate the effectiveness of AI optimization: deviation rate of virtual boundaries; success rate and efficiency of path planning; and overall system processing time and energy consumption.

[0310] The following is a summary of representative tests conducted using the scheme of this invention:

[0311] Case 1: Dynamic Collision Avoidance in Complex Surface Machining

[0312] An irregularly shaped metal workpiece with a complex curved surface requires multi-axis simultaneous machining. Traditional path planning methods often fail to detect potential collisions between the tool and the fixture in a timely manner, leading to workpiece scrap.

[0313] Implementing this invention:

[0314] Virtual boundaries are generated by dynamic ultrasonic sound fields, and the boundaries dynamically fit the curved surface shape, allowing for real-time monitoring of the distance between the tool and the workpiece surface.

[0315] When the tool approaches the first boundary layer, the system triggers path deceleration and adjusts its direction; when it enters the second boundary layer, the machining is paused and the path is replanned.

[0316] Utilize deep learning models to optimize virtual boundary adjustments and avoid false alarms and misoperations.

[0317] Results: Collision-free processing completed, 20% reduction in processing time, and 15% improvement in processing accuracy.

[0318] Case 2: Path Optimization in Multi-Tool Collaborative Machining

[0319] In a multi-tool collaborative machining task, two tools need to machine different areas simultaneously, and their paths intersect. Traditional path planning methods lack dynamic collision avoidance mechanisms, which leads to interference between the tools.

[0320] Implementing this invention:

[0321] Construct independent virtual boundaries for multiple tools and monitor the relative distance between tools in real time.

[0322] By dynamically optimizing the path using a reinforcement learning model, the order of tool tasks is redistributed, reducing path overlap.

[0323] The double-boundary design ensures that the cutting tools remain highly efficient while avoiding collisions during collaboration.

[0324] Results: Tool collaboration efficiency increased by 30%, and path conflicts were completely avoided.

[0325] Case 3: Complex Processing in High-Noise Environments

[0326] The machining workshop suffers from severe ultrasonic signal interference due to high-frequency vibration and environmental noise. Traditional virtual boundary methods cannot reliably detect tool positions, resulting in blurred virtual boundaries.

[0327] Implementing this invention:

[0328] Multipath signal fusion and adaptive filtering algorithms are used to remove noise interference and enhance signal effectiveness.

[0329] Sound-absorbing materials are placed in non-processing areas to further reduce reflection interference.

[0330] The boundary accuracy is dynamically adjusted using an active environmental compensation algorithm to ensure clear virtual boundaries.

[0331] Results: The virtual boundary is clear, the false alarm rate is reduced to 5%, and the processing efficiency is increased by 20%.

[0332] Case 4: Adaptive Machining in Dynamic Fixture Systems

[0333] During machining, the fixture is designed to be flexible and requires dynamic adjustment to fix the workpiece. Traditional virtual boundaries cannot adapt to changes in the fixture's position, which can easily lead to collisions.

[0334] Implementing this invention:

[0335] The virtual boundary tracks the position of the fixture in real time and predicts the movement trend of the fixture through a reinforcement learning model, adjusting the boundary shape in advance.

[0336] Add fixture motion parameters to the path planning to dynamically optimize the tool path and avoid fixture interference areas.

[0337] Results: No downtime during the entire processing, processing time reduced by 10%, and fixture adaptability significantly improved.

[0338] Case 5: Improving Path Efficiency in Complex Tasks

[0339] A complex processing task involving multiple steps needs to be completed efficiently, and traditional path planning methods cannot optimize path efficiency while avoiding collisions.

[0340] Implementing this invention:

[0341] By using optimization formulas to comprehensively evaluate path efficiency and collision avoidance priority, path length and time can be optimized while maintaining safety.

[0342] By combining reinforcement learning strategies to dynamically adjust the path direction and speed, the overall processing efficiency can be improved.

[0343] Results: Processing time was reduced to 4 hours, path optimization reduced redundant movement by 30%, and overall efficiency was improved by 25%.

[0344] The above examples demonstrate that this invention can be implemented in complex processing scenarios:

[0345] Efficient and precise dynamic adjustment of virtual boundaries.

[0346] Real-time path optimization and collision avoidance capabilities.

[0347] Excellent anti-interference performance and environmental adaptability.

[0348] Intelligent performance in multi-tool collaboration and dynamic machining environments.

[0349] These cases demonstrate that the present invention has significant technical advantages and application value.

[0350] Extended application scenarios of this invention:

[0351] Multi-axis linkage machining scenarios: The method can adapt to complex machining paths and ensure machining accuracy and efficiency by adjusting virtual boundaries and path optimization strategies in real time.

[0352] Complex surface processing: Dynamic sound field and multi-path signal fusion technology ensure that the virtual boundary can fit the complex surface, achieving high-precision collision avoidance.

[0353] Multi-tool or multi-robot collaborative machining: In a multi-robot or multi-tool collaborative environment, the toolpath is dynamically optimized to avoid path interference and ensure the safety and efficiency of collaborative machining.

[0354] Technical advantages of the present invention:

[0355] High-precision collision detection: The combination of dynamic sound field and multi-frequency ultrasonic superposition technology improves the detection accuracy of virtual boundaries. Multipath signal fusion and adaptive filtering algorithms effectively filter out interference signals.

[0356] Combining real-time performance with high efficiency: Lightweight path optimization algorithms reduce computational burden. Dynamic priority adjustment models balance collision avoidance requirements with processing efficiency.

[0357] Enhanced robustness and adaptability: Active environmental compensation algorithms and the application of sound-absorbing materials reduce interference from complex environments. Real-time boundary adjustment and path prediction ensure the system can adapt to changing processing environments.

[0358] Intelligent upgrade: Artificial intelligence models improve path optimization and boundary accuracy, and dynamically learn optimization strategies during the processing.

[0359] In summary, this invention achieves closed-loop control from detection to collision avoidance, from the dynamic construction of virtual boundaries to path optimization strategies and the application of artificial intelligence learning. It meets the high-precision requirements of multi-axis linkage, complex surface machining, and collaborative machining environments, and has strong real-time performance and adaptability, making it suitable for high-end intelligent machining scenarios.

[0360] Although the present invention has been described above with reference to embodiments, various modifications can be made and components can be replaced with equivalents without departing from the scope of the invention. In particular, as long as there is no structural conflict, the features in the disclosed embodiments can be combined with each other in any manner. The lack of an exhaustive description of these combinations in this specification is merely for the sake of brevity and resource conservation. Therefore, the present invention is not limited to the specific embodiments disclosed herein, but includes all technical solutions falling within the scope of the claims.

Claims

1. A method for potential collision detection and optimization in processing path trajectory simulation, characterized in that, Collision detection and avoidance in the processing path are achieved through virtual boundary construction based on ultrasonic dynamic sound field, real-time feedback control, and path optimization algorithms; the method includes the following steps: S1. A dynamic sound field is generated in the processing area using an ultrasonic array to define a virtual boundary; S2. The tool sensing module receives ultrasonic signals in real time and calculates the relative distance between the tool and the virtual boundary; S3. When the tool approaches or touches the virtual boundary, trigger path adjustment or pause the machining operation; S4. Dynamically adjust the shape of the virtual boundary based on real-time feedback to adapt to changes in the workpiece, fixture, and machining path; The dynamic sound field is generated by superimposing multi-frequency ultrasonic waves, and the clarity of the virtual boundary and its anti-scattering interference capability are enhanced by adjusting the transmission frequency, phase and intensity. By analyzing the time delay, intensity attenuation, and frequency characteristics of ultrasonic echo signals using multipath signal fusion technology, scattering and reflection interference can be filtered out, thereby improving the detection accuracy of virtual boundaries. The virtual boundary comprises two layers of boundaries: The first boundary layer is used to detect when the tool approaches a dangerous area and triggers path deceleration or adjustment. The second boundary layer is used to detect when the tool touches the boundary, triggering a machining pause and issuing an alarm signal; The S2 step includes: distance calculation and risk level assessment steps and optimization formula. The dynamic application steps; the distance calculation and risk level assessment steps include: ① Calculation of the distance between the tool and the virtual boundary: Once the tool position is determined, the distance between it and each point on the virtual boundary is calculated in real time, and the closest distance is selected: ;in, The closest distance from the cutting tool to the virtual boundary; : Distance from the tool to each point on the virtual boundary; ② Dynamic classification of risk levels: according to The layered design of virtual boundaries is divided into the following risk levels: Safety range: when When the cutting tool is away from the first layer boundary, the system maintains normal machining. Warning range: When When the tool approaches the boundary of the first layer, it triggers path deceleration or adjustment. Collision range: when When the cutting tool enters the second boundary area, the system pauses processing and issues an alarm. ③ Risk assessment is dynamically updated: During processing, the risk level is updated in real time, and the boundary parameter distance threshold is adjusted according to changes in the processing environment. and Ensure that the boundaries always adapt to the needs of the current mission; The optimization formula The dynamic application steps include: Based on real-time distance calculation, an optimization formula is introduced. A comprehensive evaluation of the tool's operating status is conducted. ； in, Modular design coefficient, dimensionless, represents the contribution of modular design to the flexibility of the machining path, and is calculated by machining parameters: the number of workpiece modules and the module size. Path sensitivity, dimensionless, represents the impact of path design on processing efficiency and is related to path complexity and processing direction; Material property influence factor, dimensionless, represents the influence of material properties such as strength and elasticity on toolpath planning; The elastic modulus of a material, measured in Pascals (Pa), is extracted from a material database and is used to describe the material's resistance to deformation; n: nonlinear loading adjustment coefficient, dimensionless, representing the correction of material properties under nonlinear stress loading conditions; Processing area volume, unit cubic meters (m). 3 The three-dimensional volume of the machining area is calculated in conjunction with the toolpath. The path efficiency factor is dimensionless and represents the dynamic change in path planning efficiency. Unit processing cost, expressed in currency (yuan / meter), calculates the cost of toolpath consumption in real time; Remaining tool life, in hours (h), estimated based on the tool's cumulative running time and current load condition; The life sensitivity index, dimensionless, represents the degree to which tool performance is sensitive to changes in remaining tool life. Friction loss factor, dimensionless, represents the energy loss during the processing. During the processing, real-time parameters are substituted into the formula for calculation. , combined Path optimization is performed based on the calculation results: like Maintain the current path; like Trigger path adjustment to optimize tool movement direction and speed.

2. The method for potential collision detection and optimization of processing path trajectory simulation according to claim 1, characterized in that, An adaptive filtering algorithm is used to dynamically optimize real-time signal processing. By adjusting the filter parameters in real time, environmental noise signals are removed and the ability to identify effective signals is enhanced.

3. The potential collision detection and optimization method for processing path trajectory simulation according to claim 1, characterized in that, Sound-absorbing materials are placed in non-processing areas to reduce interference from multiple ultrasonic wave reflections and to mitigate the impact of complex processing environments on virtual boundary detection.

4. The method for potential collision detection and optimization of processing path trajectory simulation according to claim 1, characterized in that, A dynamic path optimization algorithm is employed to dynamically replan the toolpath based on the real-time distance between the tool and the virtual boundary, the motion trend, and the machining strategy; the path optimization includes: When the tool approaches the first layer boundary, it decelerates and adjusts its path direction. When the tool enters the collision zone, the machining process is paused and a safe path is generated to bypass the collision zone.

5. The method for potential collision detection and optimization of processing path trajectory simulation according to claim 1, characterized in that, A noise feature model is generated before processing using an active environmental compensation algorithm, recording the scattering characteristics of the workpiece, fixture, and tool. During processing, the real-time signal is compared with the noise feature model, and interference signals are subtracted to improve detection accuracy.

6. The method for potential collision detection and optimization of processing path trajectory simulation according to claim 1, characterized in that, Artificial intelligence algorithms are used to learn and optimize historical processing data, including a deep learning-based virtual boundary accuracy optimization model and a reinforcement learning-based dynamic path planning model, to improve processing efficiency and collision avoidance capabilities.

7. The method for potential collision detection and optimization of processing path trajectory simulation according to claim 1, characterized in that, The method is applicable to multi-axis linkage machining scenarios and complex surface machining. By reconstructing virtual boundaries and path adjustment strategies in real time, it ensures the accuracy and efficiency of machining paths and dynamically optimizes machining paths in multi-tool or multi-robot collaborative environments to avoid path interference.

Images