67 results about "Adaptive planning" patented technology

The invention relates to the technical field of pipeline welding automation, and discloses a pipeline multi-layer and multi-pass welding track self-adaptive planning method. The method comprises the steps that weld joint track poses, welding electrical parameters and temperature information are collected in real time, and a sliding time window data sequence is constructed; establishing an interlayer constraint model and a trajectory prediction model based on the sequence, and generating a plurality of trajectory deviation predictions through short-term recursive prediction and long-term sequence prediction; a residual error reciprocal weighted fusion strategy is combined with a welding seam forming quality evaluation function, fusion track deviation is obtained, and uncertainty is evaluated; the fusion deviation is superposed to an original planned trajectory, and a self-adaptive correction trajectory is generated through a multi-objective optimization model; and the welding robot is controlled to execute track correction and real-time feedback updating. According to the method, through dual-time scale prediction and trajectory-process parameter collaborative optimization, the problem of insufficient welding seam forming precision caused by lack of dynamic correction in traditional static planning is effectively solved, and the welding quality and efficiency are remarkably improved.

The invention relates to an APP intelligent marketing service method based on intelligent routing and multi-agent cooperation. The method comprises the following steps: receiving input information, wherein the input information comprises user active inquiry information or trigger event information generated based on user behavior monitoring; semantic analysis and intention recognition are carried out on the input information, a task planning directed acyclic graph is generated based on a recognition result, and the task planning directed acyclic graph comprises a plurality of subtask nodes and dependency relationships among the nodes; based on the task planning directed acyclic graph, the state of each functional agent and the historical performance index, executing dynamic routing so as to dispatch the plurality of sub-tasks to the corresponding functional agents; and in the execution process of the plurality of subtasks, performing dependency scheduling and state consistency management on an external tool call chain which is initiated by the functional agent and comprises a plurality of steps, and updating the shared memory associated with the user based on an execution result. By adopting the method, self-adaptive planning, robust execution and continuous optimization of marketing tasks can be realized.

The invention discloses a spray combustion sub-model integrated development method and equipment based on a large language model, and belongs to the technical field of engines. The method is realized by relying on a retrieval enhancement generation system and a multi-agent collaborative framework, and comprises the following steps: S1, user instruction and thesis extraction: extracting core information from related technical literatures to form a structured file according to a sub-module extension requirement proposed by a user; s2, source code analysis and comparison data generation; s3, function and interface planning: performing adaptive planning of an original model-OpenFOAM platform; s4, code generation and packaging: code conversion, dependency processing, test example generation and compilation packaging; s5, layered testing and verification graph generation; and S6, debugging and repairing: executing a positioning-repairing-regression closed-loop process through a debugging agent. According to the method, the problems that the spray combustion sub-model is difficult to migrate to the OpenFOAM simulation platform under different frameworks and the development period is long can be solved.

The invention provides an underwater operation path adaptive planning method and system combined with machine learning, and the method comprises the steps: employing satellite remote sensing, underwater in-situ sensing and edge computing architecture, obtaining flow fields and terrain basic data of different scales through a multi-source sensing device and technology, achieving the fusion of multi-source data through combining with an intelligent weight distribution algorithm, and achieving the adaptive planning of an underwater operation path. A high-precision real-time sensing result is output, a physical constraint and data-driven hybrid modeling framework is constructed, a spatial-temporal feature capture model is adopted to process multi-scale data, an online self-adaptive updating mechanism containing forgetting factors is designed, dynamic adaptation of the model to time-varying ocean current characteristics is achieved, simulation pre-training, on-site fine tuning and online re-planning closed-loop algorithms are constructed, and real-time ocean current sensing is achieved. The model training efficiency is improved based on reinforcement learning and transfer learning, and an optimal correction path is generated in combination with a trigger mechanism and energy consumption optimization logic.

The invention discloses a laser cutting path planning method based on reinforcement learning. The method comprises the steps that S1, a task scene model is established; s2, performing rasterization processing based on the spatial state matrix, and constructing a cutting state vector; s3, inputting the cutting state vector into a PathFormer network, extracting spatial topological features and path global semantic information, and generating high-dimensional path feature embedding; s4, constructing a multi-target reward function according to feature embedding and candidate path actions, and calculating an instant reward value; s5, training a strategy network by using an improved APPO algorithm, and updating Actor and Critic parameters to jointly optimize path length, energy consumption and hot area distribution; and S6, mapping the optimal path sequence back to the actual coordinate system to generate a control instruction, and driving the laser head to execute cutting according to the planned path. Self-adaptive planning and energy consumption balance control of the laser cutting path are achieved, and the cutting efficiency, precision and machining stability are improved.

The invention discloses an adaptive planning method and system for a rural power distribution network containing distributed photovoltaics, and relates to the technical field of adaptive planning, and the method comprises the steps: carrying out the fault simulation based on an optimal photovoltaic access scheme, collecting fault data corresponding to a fault event generated through simulation in a fault simulation process, and carrying out the fault simulation according to the fault data; the dynamic operation risk of the power distribution network is evaluated; and based on the characteristics of the rural power distribution network and the dynamic operation risk of the power distribution network, performing multi-objective optimization, and generating a distributed photovoltaic access planning scheme. According to the invention, multi-source data is collected and preprocessed to generate a high-quality data set, and photovoltaic output and rural power distribution network characteristics are obtained, so that full-process automatic processing from data collection to power grid characteristic extraction is realized.

The invention discloses a weld defect intelligent identification and path adaptive planning system based on deep learning, and relates to the technical field of ultrasonic nondestructive testing, and the system comprises an ultrasonic data acquisition module, a defect identification module, a path planning module, a parameter adaptive regulation and control module and a result output module. The defect identification module adopts a multi-scale feature extraction network to be combined with an atlas convolution processing unit to extract deep semantic information and a global topological relation of ultrasonic features, high-precision defect identification is realized through an attention enhancement classification network, and the path planning module is used for planning a path based on a defect distribution probability graph. The self-adaptive scanning path is dynamically generated by adopting the Bayesian optimization algorithm, the detection efficiency is remarkably improved on the premise that the detection quality is guaranteed, the problems that a traditional method is insufficient in recognition accuracy and fixed and inflexible in detection path are solved, the recognition accuracy reaches 93%-96%, and the detection time is shortened by about 35%-40%.

The invention discloses a machine room resource capacity intelligent planning system and method based on multi-source data fusion, and belongs to the technical field of data center management, and the system comprises a multi-source data collection module, a resource manifold modeling module, a geodesic optimization module, a self-adaptive planning module and a verification and inspection module. The method comprises the following steps: mapping multi-dimensional resource parameters such as space, power, heat dissipation and load bearing of a machine room into a Riemannian manifold mathematical model, and constructing a resource measurement tensor representing a resource distribution density and a constraint relationship; calculating a resource allocation optimal path on the resource manifold, constructing a multi-objective function including space utilization rate, energy efficiency, heat dissipation efficiency and cost effectiveness, and generating an optimal deployment scheme of the machine room equipment; in combination with topological characteristic analysis of resource manifolds, potential resource bottlenecks are predicted, and a resource allocation scheme is dynamically adjusted; and the security and compliance of the evaluation scheme are verified through digital twinborn simulation, so that the problem of unbalanced resource allocation caused by independent planning of each system in traditional machine room planning is solved.

This invention provides an adaptive planning system and method for UAV inspection paths based on transfer learning, belonging to the field of human-machine inspection path planning technology. The system includes: constructing a vertical airflow layer structure representation model of the inspection space for inspection areas with densely packed tall structures, and outputting a set of vertical airflow layer structures for the inspection space; performing airflow layer mapping processing on the inspection path based on the set of vertical airflow layer structures, and outputting a set of airflow-adapted paths; constructing a path cost model with airflow constraints based on the set of airflow-adapted paths, and outputting a set of path costs including the total cost of the inspection path and the comprehensive cost of path segments; and performing cross-airflow layer path reconstruction based on the set of path costs and the set of vertical airflow layer structures, outputting the optimal inspection path. This accurately identifies airflow separation layers in the inspection space, achieving airflow adaptation, risk quantification, and adaptive planning of the inspection path, effectively improving the flight stability and operational safety of UAVs during inspections in areas with densely packed tall structures.

The invention provides a lightweight satellite-borne satellite group adaptive planning method based on Transform-DRL, and belongs to the field of satellite autonomous planning. According to the method, firstly, environment input is carried out, target events and feasible satellites are screened, feature construction is carried out, then, generated hidden representations are projected into a unified potential space through a full connection layer, context sensing representations are obtained, and then, context sensing is carried out on the basis of the representations. The strategy network scores feasible event-satellite actions and generates probability distribution, actions are selected to be executed in combination with action masks, Transform and strategy parameters are updated end to end through an Actor-Critic mechanism according to rewards after execution, and satellite group autonomous task planning is achieved. The method has the characteristics of high efficiency of arranging different types of events and satellites, high autonomy and the like, and is suitable for flexible and autonomous satellite group task planning.

The application provides a UAV recovery path adaptive planning method and system based on air-ground cooperation, relates to the technical field of robot motion planning, and comprises the following steps: constructing a three-dimensional grid map of a task environment, acquiring the positions of a UAV and an unmanned vehicle and the maximum flight distance of the UAV; determining the responsibility distribution of the UAV and the unmanned vehicle in a recovery task based on the positions of the UAV and the unmanned vehicle and the maximum flight distance of the UAV, and obtaining an optimal UAV recovery scheme; selecting a corresponding path planning mode according to the optimal UAV recovery scheme, and determining the starting point, the ending point and the dimension of the search space of path planning based on the positions of the UAV and the unmanned vehicle; executing a path planning algorithm according to the selected path planning mode, and generating a final recovery path; and through air-ground cooperative decision and cross-dimension bidirectional joint path planning algorithm, the application realizes safe and efficient recovery of the UAV under the constraint of electric quantity, and significantly improves the task success rate and the system cooperation efficiency.

The invention discloses a policy sensitivity-driven multi-town industry deduction parameter adaptive planning system. The system comprises a data acquisition module, a deduction calculation module, a policy sensitivity analysis module, a multi-town industry linkage deduction module, a parameter adaptive correction module and a deduction result verification module. The policy sensitivity analysis module extracts policy indexes to generate influence weights, the multi-town industry linkage deduction module constructs an incidence matrix to calculate overflow effect coefficients, the parameter adaptive correction module dynamically adjusts deduction parameters, and the deduction result verification module outputs verification errors; the system solves the problems that existing deduction parameters are fixed and do not adapt to policy and industry linkage, and improves the accuracy and dynamic adaptability of multi-town industry deduction.

The application provides an unmanned aerial vehicle optimal track planning method and system fusing image recognition and M-RRT and APF algorithms. Wind power generator point cloud and visual data are acquired in real time through a multi-modal sensor, key components of blades are recognized based on deep learning, a geometric mapping model is constructed, tip point is corrected in combination with DBSCAN clustering, and a shutdown posture is predicted. A global path adopts an M-RRT algorithm improved by a direction heuristic factor, and a key area of the blade is guided to search; a local track is optimized through a dynamic weight APF algorithm, and a repulsive force field is adjusted in real time to cope with posture changes. An online replanning mechanism is introduced, NSGA-III multi-objective optimization is triggered when an environment mutates or a tracking error exceeds a threshold, and optimal tracks are generated by comprehensively considering energy consumption, time and safety. The system integrates high-precision perception, adaptive planning and dynamic optimization, and significantly improves inspection coverage and track safety under a complex shutdown posture.

This application relates to the field of robotic systems technology, and provides a robot-based adaptive planning method and apparatus for optical mirror assembly paths. After establishing a scenario model of the optical system mirror assembly, the method pre-defines a standardized assembly path and generates an initial trajectory using a Data Modeling (DMP) system, forming an initial assembly mechanism that couples the robot with the optical system's sub-mirror modules. This effectively ensures the rationality and feasibility of the initial assembly path. Through improved path integration strategies and model predictive control, internal and external collaborative optimization is achieved, enabling mirror assembly path generalization, obstacle avoidance safety, and high-precision traversal of designated positions, thus enhancing the robustness of the robotic arm. In dynamic and unstructured environments, adaptive iterative optimization can be performed, continuously outputting the optimal path for optical system mirror assembly, ensuring the safety and accuracy of the optical system mirror assembly, and providing reliable technical support for the on-orbit assembly of large-aperture optical detection systems.

The invention discloses an AI-based cultural activity adaptive planning method and system, and relates to the technical field of information intelligent processing and activity planning, and the method comprises the following steps: obtaining user behavior data from a plurality of campus digital platforms in real time, a dynamic short-term interest vector and a dynamic long-term preference vector are generated through processing of a time sequence model and a graph neural network, and a fusion user portrait set is formed through fusion of a learnable fusion mechanism; through multi-source data real-time acquisition and time sequence model and graph neural network processing, a learnable fusion mechanism is utilized to construct a fusion user portrait, so that a cultural activity planning scheme is established on the basis of continuously perceived real group preference, a traditional subjective mode depending on static experience is changed, and the user experience is improved. Objective and dynamic planning strategies are further realized; a planning scheme is structured into a planning element combination space with spatialization and dimensionalization, and multiple optimization targets are defined and model quantification processing is carried out.

The invention relates to an unmanned loader precise control system and method for a dynamic target and self-adaptive unloading, and belongs to the technical field of engineering machinery intelligent control. The system comprises a dynamic target identification and trajectory prediction module, a multi-sensor fusion sensing module, a self-adaptive alignment and tracking control module, an intelligent unloading planning and execution module, a dynamic safety evaluation and multistage protection module and a multi-machine collaborative operation management module. According to the method, accurate, self-adaptive, safe and collaborative unloading operation of the unmanned loader on a dynamic target in a complex environment is achieved through dynamic target sensing, track prediction, MPC tracking control, material characteristic self-adaptive unloading track planning, multi-stage safety protection and multi-machine collaborative scheduling. According to the invention, the automation level, the operation precision and the system safety of the unloading operation are obviously improved.

The invention relates to the technical field of semiconductor production and manufacturing, and provides a silicon crystal ingot laser cutting method which comprises the steps that a subsurface scanning path and a target depth are generated based on coordinate data of an operation station, the scanning path is subjected to self-adaptive planning according to subsurface curvature and crystal orientation, and the target depth is obtained; the target depth is determined as the initial priority area of the crack in the silicon crystal ingot; when the first light beam is used for scanning the target depth along the scanning path, a high-resolution detector integrated in an optical imaging system is used for capturing an image sequence formed by cracks in real time; crack width data are extracted from the image sequence, and continuous distribution of crack widths is obtained through filtering and normalization processing; executing a corresponding crack control strategy according to the crack width level; and starting a phase modulation system of the second light beam for the crack reaching the preset crack width level. According to the method, accurate control over cracks and self-adaptive planning of the cutting path are achieved, and the cutting efficiency and quality of the silicon crystal ingot are improved.

The invention discloses a ship group tail end welding method based on laser vision and reinforcement learning, which comprises the following steps: S1) simulating a real laser vision system, scanning group parts to generate three-dimensional point cloud data, and extracting the type characteristics, position parameters and direction parameters of the tail end of a welding seam; s2) constructing a three-dimensional reinforcement learning training scene, simulating a ship assembly welding environment, and dynamically setting assembly part position parameters and welding process parameters; s3) designing a state space, an action space and a reward function of the reinforcement learning model; s4, coordinate transformation, speed optimization and technological parameter adjustment are conducted on the action sequence output by the reinforcement learning model, and the welding robot is driven to execute welding work.The defects of an existing ship group robot welding technology can be overcome, and automatic and accurate recognition of the types of the tail ends of welding seams and self-adaptive planning of the welding technology are achieved.

This invention discloses a high-throughput experimental sequence adaptive planning method based on Bayesian optimization, relating to the field of chemical experiment automation technology. The method includes: digitally encoding multiple chemical variables involved in the experiment to construct a multi-dimensional chemical space to be searched; constructing a probabilistic prediction surrogate model based on known experimental samples; pre-setting the acquisition cost of each variable and establishing a cost function; combining the expected improvement amount and the cost function, calculating the next batch of candidate experimental points through a target optimization algorithm, prioritizing the experimental points with the largest unit cost gain; converting the candidate coordinates into instructions and sending them to the automated experimental platform, and updating the surrogate model with the returned experimental data in real time, repeating the process until convergence to the global optimum or reaching the cost ceiling. This invention, by introducing a cost-sensitive acquisition function and a heterogeneous molecular fingerprint fusion strategy, achieves synergistic optimization of experimental results and experimental costs, significantly improving the efficiency and resource utilization of high-throughput experiments.

The application is based on a new energy power system multi-stage stochastic programming method based on conditional value at risk, step S1, based on historical data, a scene library for representing multi-stage uncertainty such as load growth and new energy output in the planning period is constructed; step S2, a power system multi-stage stochastic programming model is established, which takes minimizing the total expected discounted cost in the planning period as the target, and the conditional value at risk constraint for quantifying the short-time power imbalance and long-term power shortage risk is embedded in the investment and operation constraints of the model; step S3, the model is solved by using the approximate dynamic programming algorithm; step S4, a multi-stage decision sequence is output, and an adaptive planning scheme of power generation, energy storage and power transmission equipment is formed. The application integrates the risk quantification of short time and long time scales into the planning framework, and realizes dynamic decision by using approximate dynamic programming, which can effectively cope with the uncertainty of new energy output and load demand, and develop a dynamic adaptive multi-stage power grid development planning scheme.

The invention relates to a curve path adaptive planning method and system, a three-coordinate measuring instrument and computer equipment, and the method comprises the steps: determining a curve measurement route, and carrying out the sampling based on a maximum sampling distance, and obtaining a plurality of measurement points; performing iterative detection based on the interval and the deflection angle between the adjacent measurement points, and inserting a newly added measurement point in the detection process so as to obtain a discrete measurement point sequence; a curve path is determined based on the sequence of measurement points. Therefore, the change of the geometric characteristics of the curve can be adaptively matched, so that measurement points are added in a key geometric characteristic region, and the measurement precision is ensured; and meanwhile, the deflection angle is used as an encryption criterion, so that the calculation complexity is effectively reduced, and the measurement efficiency is improved.

The unmanned aerial vehicle optimal path adaptive planning method based on particle swarm optimization relates to the field of unmanned aerial vehicle path planning, and comprises the following steps: constructing a spatial constraint model of an unmanned aerial vehicle flight task; initializing a particle swarm based on the spatial constraint model; combining path smoothness, path threat probability and voyage efficiency to establish a multi-objective fitness function, and calculating the fitness value of each particle based on the particle swarm; performing hierarchical particle swarm optimization iteration, in each iteration, adaptively adjusting the control parameters based on the current particle swarm distribution characteristics, and updating the path node position of the particles; when the convergence condition is met, outputting the global optimal path as the final flight trajectory of the unmanned aerial vehicle, and controlling the unmanned aerial vehicle to execute. The unmanned aerial vehicle optimal path adaptive planning method based on particle swarm optimization solves the problems that the unmanned aerial vehicle route path optimization target is single and difficult to coordinate, and the route planning path effect is poor.

The application discloses an amphibious unmanned aerial vehicle flow measurement navigation self-adaptive planning adjustment system and method, relates to the technical field of amphibious unmanned aerial vehicles and hydrological monitoring, and comprises a river environment perception, initial flow measurement route planning, real-time drifting state detection, obstacle danger level evaluation, dynamic path adjustment execution and flow measurement path splicing verification module, and can be optionally provided with a calibration module. The system calibrates the global orthographic image of the river channel collected by a visual camera, identifies obstacles to generate a database for planning the initial flow measurement segmentation and path; the state of the floating boat and the flow parameters are detected in real time, the river channel is divided into grids, the grid danger level index is calculated, the floating boat drifting trajectory is predicted, and the high-risk area entry index is obtained; when the index reaches the threshold, emergency take-off and path re-planning are triggered, the final trajectory is spliced, and the data integrity is verified. The application realizes self-adaptive adjustment of the flow measurement path in a complex dynamic hydrological environment, guarantees operation safety and continuous and accurate data, and improves the flow measurement efficiency and automation level.

The invention belongs to the technical field of charging infrastructure planning, and discloses a charging station dynamic adaptive planning method based on model deduction, which comprises the following steps: dividing a target city into a plurality of planning areas, collecting multi-source heterogeneous data of each planning area, and constructing a data block containing time-space coupling information; establishing a simulation environment of the multi-agent game based on the data blocks; a reinforcement learning model comprising a spatial-temporal feature extraction module and a strategy evaluation module is constructed, an output game equilibrium result is used for training, and the long-term value of the station building action of each planning area is evaluated; deploying the trained reinforcement learning model in a virtual environment which can be dynamically updated, performing multi-step strategy deduction in combination with an optimization algorithm, and selecting an optimal construction scheme of the charging station; the problems that in the prior art, charging infrastructure layout and dynamic demand matching is insufficient, a multi-body game decision mechanism is lacked, and long-term adaptability optimization capacity is lacked are solved.

A multi-factor benefit analysis method and system for a power system resilience planning scheme. The method comprises: acquiring a novel power system planning scheme; assessing the capability of the novel power system planning scheme to respond to extreme events within a preset yearly timeframe, so as to obtain resilience indicators; using a carbon emission flow method to perform calculation and estimation on the obtained novel power system planning scheme, so as to obtain carbon emission benefit indicators; for the implementation costs of the obtained novel power system planning scheme, calculating power facility construction costs and substation and line reinforcement or retrofit costs, so as to obtain economic indicators; and comprehensively integrating the resilience indicators and the carbon emission and economic indicators and, under an evaluation and decision-making framework for novel power system planning schemes oriented toward resilience enhancement, evaluating and comparing different planning schemes to form a decision-making closed loop, and providing feedback and corrections for the planning schemes, thereby achieving novel power system construction and adaptive planning under climate change. The solution provides a scientific decision-making basis for improving investment decisions.

The invention provides an unmanned aerial vehicle recovery path self-adaptive planning method and system based on air-ground cooperation, and relates to the technical field of robot motion planning, and the method comprises the steps: constructing a three-dimensional grid map of a task environment, and obtaining the positions of an unmanned aerial vehicle and an unmanned vehicle, and the maximum flight distance of the unmanned aerial vehicle; based on the positions of the unmanned aerial vehicle and the unmanned vehicle and the maximum flight distance of the unmanned aerial vehicle, determining responsibility distribution of the unmanned aerial vehicle and the unmanned vehicle in the recovery task, and obtaining an optimal unmanned aerial vehicle recovery scheme; selecting a corresponding path planning mode according to the optimal unmanned aerial vehicle recovery scheme, and determining a starting point and an ending point of path planning and dimensions of a search space based on the positions of the unmanned aerial vehicle and the unmanned aerial vehicle; according to the selected path planning mode, executing a path planning algorithm to generate a final recovery path; through the air-ground collaborative decision and cross-dimension bidirectional joint path planning algorithm, safe and efficient recovery of the unmanned aerial vehicle under the electric quantity constraint is realized, and the task success rate and the system collaborative efficiency are remarkably improved.

Disclosed is a multi-factor benefit analysis method and system for resilience-oriented power system planning schemes, including acquiring new power system planning schemes; evaluating the abilities of the acquired schemes to withstand extreme events within a set period of years, to obtain resilience indicators; estimating the acquired schemes by using the carbon emission flow method, to obtain carbon emission indicators; calculating the cost of constructing power facilities and the cost of reinforcing or renovating substations and lines, to obtain economic indicators; and evaluating and comparing the planning schemes under the evaluation and decision-making framework of new power system planning schemes for resilience enhancement by comprehensively considering the resilience indicators, carbon emission indicators, and economic indicators, to form a closed loop of decision-making, and give feedback to and correct the planning schemes, thereby achieving adaptive planning for the construction of new power systems under climate changes.

The invention belongs to the technical field of artificial intelligence, and particularly relates to a personalized learning path planning method and system based on online education, and the method comprises the steps: firstly, precisely perceiving the state of a learner through constructing a multi-dimensional meta-cognitive state model; secondly, based on the state and the long-term target, the reinforcement learning agent carries out sequence decision making by taking maximization of the long-term income as a target, and a macroscopic learning path is generated; then, according to the path instruction, fairly and accurately matching specific learning resources from a resource library by combining content features with a UCB algorithm; and finally, updating the state model in real time according to learning feedback, optimizing a planning strategy and calibrating resource evaluation. The method achieves the global and adaptive planning of a learning path, remarkably improves the learning continuity and long-term efficiency, effectively solves a resource cold start problem, and drives the continuous optimization of teaching resource ecology.

The present application proposes a wafer epitaxial film thickness measurement method and system based on trajectory adaptation, belonging to the field of measurement and testing and semiconductor manufacturing technology. The measurement method includes wafer feeding and preliminary transfer steps, wafer positioning and correction compensation steps, measurement path planning steps, film thickness data acquisition and processing steps, data comparison and trend report generation steps, and abnormal alarm triggering steps. The measurement system includes feeding and transferring units, positioning and compensation units, measurement path planning units, film thickness data acquisition and processing units, data comparison and trend report generation units, and abnormal alarm triggering units. The positioning and compensation unit includes a correction mechanism and a compensation mechanism. The present application improves the precision and efficiency of wafer epitaxial film thickness measurement through trajectory adaptive planning and edge enhancement algorithm; combined with cloud collaborative analysis, it realizes real-time abnormal alarm and trend prediction, which helps to improve the yield and intelligent level of semiconductor manufacturing.

This invention discloses a UAV contouring flight system and method based on multi-sensor fusion and adaptive planning. The system includes a multi-sensor module for simultaneously acquiring 3D point cloud data, image data, and UAV inertial measurement data of the environment; a localization and mapping module for processing the acquired data through a tightly coupled fusion algorithm to output the UAV's real-time pose and a 3D map of the environment; an adaptive path planning module for identifying target objects based on the 3D environmental map and adaptively selecting and executing a matching path generation strategy to generate a contouring flight path that conforms to the target object's surface; and a flight control module for controlling the UAV according to the contouring flight path. This invention solves the problems of low positioning accuracy, inaccurate environmental modeling, and inability to generate high-precision 3D contouring paths for UAVs in environments lacking GPS signals, achieving efficient contouring for regular targets and high-precision contouring flight for complex targets.