36results about How to "Achieving Adaptive Optimization" patented technology

The invention relates to the technical field of data packet transmission, and discloses a data packet transmission control method and device for a low-power-consumption dual-mode Bluetooth chip, and the method comprises the steps: obtaining a signal strength parameter, a power consumption parameter, a transmission rate parameter and an environment parameter of the dual-mode Bluetooth chip, inputting the parameters into a deep time convolution network, and carrying out the time sequence feature extraction, obtaining a transmission mode switching judgment result; calculating transmission state evaluation data; the chip transmitting power is adjusted in a grading mode, standby power consumption is controlled through a nanoamp LDO circuit, and a dynamic power control parameter is obtained; performing compression coding on the data packet to obtain a dual-mode transmission protocol configuration parameter; executing time sequence sampling, and constructing a dual-mode state feature sequence; the data packet delivery success rate, the end-to-end transmission time delay and the total power consumption of the system are calculated, transmission control parameter optimization is carried out through double-layer deep reinforcement learning, target transmission control parameters are obtained, and the optimal balance of the transmission performance and the power consumption of the dual-mode Bluetooth chip is achieved.

The invention relates to the technical field of audio decoding, and discloses an audio decoding performance optimization method and device for a multimode SoC main control chip, and the method comprises the steps: carrying out the framing processing of input audio data through a DSP processing unit, and extracting audio feature data; performing period detection and multi-frame smoothing processing on the audio characteristic data to obtain an audio period characteristic vector; performing principal component transformation and feature dimension reduction based on the audio period feature vector to obtain decoding prediction data, and inputting the decoding prediction data into a task division model to perform decoding processing sequence analysis to obtain decoding task data; carrying out hidden Markov modeling on the decoding task data, and calculating to obtain decoding optimization data; and mapping the decoding optimization data to a hardware acceleration unit of the multi-mode SoC main control chip, and executing parallel decoding operation to obtain target decoding data. According to the invention, adaptive optimization of the decoding process is realized, and the decoding strategy can be flexibly adjusted according to different audio data characteristics and processing requirements.

This application provides a method and apparatus for autonomous obstacle avoidance of unmanned aerial vehicles (UAVs) based on lidar, relating to the field of UAV technology. By extracting the optical features of the surface material of the current area and matching the optimal band interval based on a pre-built feature fingerprint database, the emission wavelength of the lidar can adapt to the main constituent materials of the environment, significantly improving the signal-to-noise ratio and feature recognition of the echo signal. A programmable gain circuit is introduced at the receiving end to dynamically compensate for signal strength changes caused by band switching or different distances, improving the reliability and consistency of point cloud data generation. This ensures that the generated "optimized obstacle avoidance path" not only effectively avoids marked obstacle points but also better conforms to actual environmental constraints, significantly improving the perception reliability and obstacle recognition accuracy of the UAV lidar in complex environments containing various heterogeneous materials, thereby comprehensively enhancing the safety of autonomous obstacle avoidance and the environmental adaptability of the overall system.

The invention discloses a crystal growth synthesis furnace which comprises a composite furnace body, a heating and temperature control system, an optical observation window assembly and a growth monitoring and control system. A furnace chamber of the composite furnace body is of a multi-layer gradient composite lining structure composed of a pressure-bearing water-cooled jacket, a carbon fiber reinforced silicon carbide composite material layer, a foam silicon carbide ceramic heat insulation layer and high-purity graphite paper. The heating and temperature control system adopts a distributed design and comprises a main heater, an upper auxiliary heating ring, a lower auxiliary heating disc and a lateral compensation heater. The optical observation window assembly is fixed to the center of the upper furnace cover and matched with the high-speed imaging unit to achieve in-situ monitoring of the growth process. According to the crystal growth synthesis furnace provided by the invention, accurate regulation and control of a three-dimensional temperature field and real-time visual monitoring of a growth interface in a silicon carbide crystal growth process are realized, and the crystal quality, the growth success rate and the process repeatability are remarkably improved.

This invention relates to the field of bearing fault diagnosis technology, specifically to a bearing fault diagnosis method based on neural networks and multi-criteria preference consensus. The method includes: data acquisition and feature extraction, data preprocessing, matching a fault diagnosis model, preliminary diagnosis and probability generation, final diagnosis and probability generation, and bearing state decision-making. This invention provides a multivariate decision-making auxiliary model that integrates physical marginal value functions and neural network attention mechanisms, combined with a reinforcement learning-driven consensus-building process, to achieve adaptive optimization of multi-expert fault diagnosis results. This not only solves the problems of existing bearing fault diagnosis methods being unable to handle complex working conditions, lacking physical interpretability, relying heavily on single decision-making patterns, and using static weight allocation, but also improves the accuracy, robustness, and interpretability of bearing fault diagnosis, achieving high-precision, low-round group fault diagnosis.

This invention relates to the field of multi-agent cooperative control technology, and in particular to a switching multi-agent cooperative tracking control method based on deep reinforcement learning. The method includes building a two-layer independent architecture for each independent agent, constructing a multi-level grouping architecture for the overall multi-agent cluster, proactively adjusting the internal structure of the multi-level grouping architecture based on prediction results, and using causal analysis technology to trace and determine the root causes of sudden changes and select an execution strategy. This invention adopts a two-layer independent architecture scheme, configuring a leader layer and an executor layer for each agent. Through an asynchronous decision-making mechanism with unidirectional instruction transmission, it achieves complete decoupling between global planning and local execution, ensuring the global optimality of the cooperative tracking task, meeting the real-time control requirements in dynamic environments, eliminating the single-point failure risk of centralized decision-making, and improving the cluster decision-making efficiency and operational stability.

The application relates to the field of battery life prediction, in particular to a multi-feature fuel cell life prediction method based on a long short-term memory network; the method comprises the following steps: collecting voltage attenuation data and collecting running state data to construct an original input data set; analyzing the running state data, calculating a correlation coefficient according to the voltage attenuation data and each running state data, analyzing the correlation coefficient, and obtaining an input feature set; processing the input feature set and the voltage attenuation data to construct a neural network training data structure; dividing the training data structure into a training set and a test set; constructing a network architecture solution space to be searched, analyzing the network architecture solution space, constructing a fitness function, and determining an optimal network architecture parameter combination based on the fitness function; and inputting the training set into the optimal network architecture parameter combination for training to generate a target detection prediction result. The application can improve the prediction accuracy of the voltage attenuation trend.

This invention discloses an online visual inspection and laser dressing closed-loop control system for grinding wheel allowance, comprising a multi-axis precision linkage platform, a laser ablation dressing unit, a dual-modal composite visual sensing component, a real-time data processing unit, and a closed-loop feedback control unit. The dual-modal composite visual sensing component consists of a structured light scanning module and an infrared thermal imaging module connected by a coaxial optical path, and uses the same trigger signal to achieve spatial alignment and temporal synchronous acquisition, obtaining registered geometric point cloud and temperature field data of the grinding wheel surface. The real-time data processing unit incorporates a real-time dynamic decoupling model for thermally induced deformation, calculates the thermal expansion displacement field based on the temperature field, and separates it from the comprehensive radial deviation of the geometric point cloud to obtain the true geometric allowance. The closed-loop feedback control unit generates adjustment commands based on the deviation between the true allowance and the target contour, achieving high-precision closed-loop dressing. This invention solves the technical challenge of detecting thermal expansion interference accuracy during laser dressing, improving dressing accuracy and consistency.

The present invention discloses a method for preparing a postoperative wound intelligent healing patch based on nanomaterials, comprising the following steps: S1, preparing a temperature response layer, using PNIPAM and surface-modified zinc oxide nanoparticles for compounding; S2, preparing a pH response layer, compounding chitosan with surface-modified titanium dioxide nanoparticles; S3, preparing a humidity response layer, using PEGDA and silver nanoparticle composite materials to optimize the release of silver ions; S4, assembling each layer layer by layer through electrospinning technology or lamination technology, and combining meta-learning and transfer learning to control process parameters to complete the overall structure preparation of the patch; S5, embedding temperature, pH and humidity sensors to construct a sensor data set; S6, dynamically adjusting the drug release rate and material phase change behavior to achieve accurate response; S7, after the patch is prepared, combining Bayesian and multi-objective evolutionary algorithms to optimize sterilization parameters. The present invention combines nanomaterials with intelligent algorithms to prepare intelligent healing patches and achieve real-time environmental response.

This invention provides a method for optimizing BUCK circuit control based on adaptive reward weighting (DQN), comprising the following steps: Step 1, constructing a reinforcement learning control environment for the BUCK circuit; Step 2, designing a reward function based on output voltage error; Step 3, optimizing the reward weight parameters in the reward function using a particle swarm optimization (PSO) algorithm to obtain the optimal reward weight parameters and applying them to the reward function; Step 4, introducing external disturbances into the BUCK circuit control environment and training the DQN agent using the optimized reward function. This invention does not require a precise mathematical model and can achieve adaptive optimization control of the BUCK circuit under different operating conditions, demonstrating significant engineering application value.

The application discloses a household intelligent electric baking pan and a use method thereof, and belongs to the technical field of intelligent kitchen appliances. The household intelligent electric baking pan comprises the following steps: S1, an upper disc and a lower disc and a flexible hinge are arranged, and an annular waveguide type ultrasonic array is arranged on the edge of the lower disc; S2, food materials are placed, and the pre-tightening force of a spring is adjusted to make the upper disc flexibly contact the surface of the food materials; S3, heating is started, a heat field is modulated through an independent high-frequency duty cycle, and internal heat flow of the food materials is directionally guided; S4, ultrasonic assistance is started, and micro-vibration is conducted by using an annular array standing wave, thereby breaking a steam film effect and improving efficiency; and S5, an acoustic impedance feedback signal is acquired in real time, and doneness is determined according to signal mutation characteristics and cooking is stopped. The application realizes self-adaptive optimization of micro-environment pressure during cooking.

The application discloses a new modal fiber design method and system, and relates to the technical field of fiber communication. The fiber design variable is obtained, parameterized representation is performed on the fiber design variable, parameterized fiber design variable is obtained, the parameterized fiber design variable is input into a pre-established deep learning model, candidate structure parameters are output, transmission mode solving is performed on the candidate structure parameters, mode field distribution and effective refractive index are obtained, intermodal coupling integral is calculated based on the mode field distribution and the effective refractive index, a loss function is generated based on the intermodal coupling integral, the deep learning model is trained based on the loss function, and real-time candidate structure parameters are output. Iterative training is continuously performed. When the real-time candidate structure parameters meet preset conditions, the final candidate structure parameters are output as the optimized fiber structure parameters and the low crosstalk design result of the fiber.

This invention discloses a bit-loading-based HPLC signal processing method, belonging to the field of power line carrier communication technology. The bit-loading-based HPLC signal processing method includes: reading bit data from a channel interleaving module and sequentially writing it into a first bit buffer queue according to a preset number of bits to be read from the channel interleaving module; in bit-loading mode, determining the target number of bits to be filled for each subcarrier based on the modulation scheme corresponding to each subcarrier; different modulation schemes correspond to different target bit numbers; sequentially reading the target number of bits from the first bit buffer queue according to the writing order, and mapping the read-out bit data to the corresponding subcarrier for modulation and transmission. This invention achieves efficient rate matching for data processing in bit-loading mode and data transmission without subcarriers crossing physical blocks.

This invention discloses a high-precision positioning and welding device for semiconductor equipment. The device includes a first robot, a workpiece positioning stage, a second robot, a laser welding head, a sensing module integrating laser and infrared sensors, a thermal excitation module, and an intelligent monitoring unit. This invention achieves precise detection of micro-assembly gaps and accurate workpiece positioning by fusing laser visual geometric scanning and active thermal excitation infrared imaging before welding. Pre-welding predictive planning utilizes low-power preheating to calibrate the thermal deformation model and optimize the welding path. During welding, online thermal deformation prediction based on real-time infrared temperature field and weld laser tracking compensation dynamically offset thermal deformation interference. Post-welding, the entire process data is traceable, enabling model self-optimization. This invention solves the problems of difficult detection of micro-defects and difficulty in compensating for dynamic thermal deformation in precision welding, significantly improving the welding accuracy and process stability of semiconductor equipment.

The invention relates to a method and device for avoiding dependence on parameter updating of a large language model, and is applied to the technical field of artificial intelligence. The method comprises the steps that by adopting a class reinforcement learning mode, output distribution of the large language model can be effectively changed through experience injection, the model simulates a decision normal form with high-quality experience, and the large language model can be effectively improved. The problems of generation illusion, output distribution offset and the like are remarkably reduced, and the reaction ability of the model to the context change of a downstream task and the professional semantic understanding ability are improved; multi-dimensional optimization of an external experience injector ensures accuracy and diversity of experience screening, avoids narrow model reasoning view caused by experience homogenization, and realizes adaptive optimization of reasoning behaviors; meanwhile, according to the method, model parameters do not need to be modified, the disastrous forgetting risk is fundamentally avoided, and the universal capacity of the model is reserved.

The application relates to a hyper-redundant robot adaptive control method and system based on double-loop evolutionary reinforcement learning. The method comprises the following steps: acquiring robot data; constructing an outer loop evolutionary evaluation layer and an inner loop behavior execution layer; the outer loop evolutionary layer generates a plurality of candidate weight vectors of a reward function; the inner loop behavior execution layer trains according to the plurality of candidate weight vectors and the robot data and generates a plurality of fitness indexes; the candidate weight vector corresponding to the highest fitness index is retained, and the plurality of candidate weight vectors are dynamically optimized again to generate the plurality of candidate weight vectors for execution training until the training is completed, and the optimal weight ratio is obtained; and the adaptive control of the robot is realized. By introducing the double-loop evolutionary reinforcement learning mechanism, the dependence on the setting of the reward function weight of the artificial experience in the reinforcement learning control process is reduced, the automatic adjustment of the reward parameter and the adaptive optimization of the strategy performance are realized, and therefore the autonomous decision-making ability and the control robustness of the hyper-redundant robot in a limited complex environment are improved.

The application provides a wind power prediction method, device and equipment fusing multi-scale decomposition and state perception, and belongs to the technical field of wind power prediction. The method provided by the application comprises the following steps: decomposing historical wind power data to obtain a plurality of intrinsic mode function components and a residual component; calculating a zero-crossing rate of each intrinsic mode function component, and calculating an average period according to the zero-crossing rate; reconstructing each intrinsic mode function component in the same frequency band to obtain a high-frequency feature, a medium-frequency feature and a low-frequency feature, and determining a trend change feature according to the low-frequency feature and the residual component; generating a running state label according to the position of a structural mutation point in the trend change feature; establishing an input set, optimizing the hyperparameters of a model, inputting the input set into the optimized model, and outputting a wind power prediction value. The wind power prediction method, device and equipment fusing multi-scale decomposition and state perception are used to improve the prediction accuracy of long-time-series non-stationary wind power.

The invention relates to the technical field of karst treatment construction, in particular to a self-monitoring karst treatment construction method which comprises the following steps that S1, holes are formed in the ground; s2, a self-sensing FRP rib is put down along the open hole; s3, the self-sensing FRP rib is connected with a strain demodulator; s4, the karst cave and the open hole are subjected to filling treatment; and S5, processing effect detection: S6, carrying out self-monitoring, sensing a data basis provided by the FRP rib, extracting and mining information values through multi-scale features, diagnosing a global health state through graph convolution, carrying out reinforcement learning and optimizing an early warning decision, and capturing a mutation behavior through GRU. The system realizes a sensing-diagnosis-early warning-optimization closed loop through tight coupling of a data stream and an algorithm stream, constructs a self-sensing, self-learning and self-perfecting intelligent karst cave monitoring system, and lays a methodological foundation for intelligent geotechnical engineering.

This invention relates to the field of industrial control technology, specifically to an automated intelligent mortar mixer, which solves the technical problem in existing vertical mortar mixers where the fixed structure of the mixing blades makes it unable to adapt to different states of materials during mixing, resulting in poor mortar mixing performance. The automated intelligent mortar mixer includes: a mixing tank, a mixing shaft disposed within the mixing tank, a mixing assembly connected to the mixing shaft, a data acquisition unit, and an intelligent control unit; the mixing assembly includes retractable mixing blades and a drive device for driving the retractable mixing blades to extend and retract; the data acquisition unit is used to collect state data of the mortar during the mixing process; the intelligent control unit is used to determine the target size of the retractable mixing blades based on the state data and control the drive device to adjust the retractable mixing blades to the target size.

The invention discloses a method and a system for monitoring and classifying broken ends of yarns of a spinning frame in real time. The method comprises the following steps: acquiring a multi-view image and a synchronous electromechanical agent signal; distortion removal, cutting and normalization are carried out on the image, filtering and standardization are carried out on the electromechanical signal, and a sliding window is divided according to a unified time baseline; frame-level yarn segmentation and key point features are extracted, short time sequence coding is carried out, and visual and electromechanical time sequence embedding is generated; three-dimensional candidate broken end positions are obtained through multi-view key point matching and triangularization, and geometric consistency is calculated; inputting each modal feature into a fusion model, and outputting a broken end probability and a broken cause probability; and after probability calibration and uncertainty evaluation, a final broken end judgment result, a broken cause category result and a three-dimensional positioning result are generated, and a control instruction is output when a broken end is true. According to the invention, stable broken end detection, broken cause classification and accurate positioning are realized, and the automatic processing efficiency of the spinning frame is improved.

The application discloses a folding mobile phone support and an opening and closing method thereof, and a manufacturing method of a double-shaft linkage hinge riveting part of the folding mobile phone support. Through the synergistic effect of the double-shaft linkage hinge and a dynamic fulcrum, the unfolding movement of the support is innovatively divided into two stages of rotation and lifting, thereby solving the core technical problem faced by the ultra-thin built-in support. On the one hand, the structure utilizes the dynamic fulcrum formed by the contact between the convex part and the bottom table, and automatically converts the rotating force into lifting force after reaching the preset angle, thereby realizing the adaptive optimization of the supporting angle, and more importantly, forming a reliable physical limit, which fundamentally avoids the interference between the upper hinge and the edge of the mobile phone shell groove due to excessive unfolding, and effectively prevents the plastic deformation and damage of the hinged structure. Meanwhile, since the structure adopts the double-shaft connection through the riveting part, the structural strength is greatly increased, and even if the support is opened to nearly 180 degrees, the hinge can still be ensured not to be damaged, and the support can be normally opened and closed.

This invention provides a method for multi-scale feature extraction and automatic identification of defects in weld X-ray inspection images, belonging to the field of non-destructive testing and image processing technology. The method includes: acquiring the original X-ray image of the weld and welding process parameters; constructing a process condition encoding vector and calculating an adaptive filtering kernel size for non-local mean filtering and noise reduction; calculating a histogram clipping and limiting coefficient based on material thickness parameters for block-based contrast-limited adaptive histogram equalization enhancement; extracting multi-scale feature maps through a backbone network and spatial pyramid pooling; fusing the process condition embedding vector with the multi-scale feature maps; employing a channel-space dual attention mechanism to enhance the feature response of the defect region; and outputting the defect location, type, and size through a detection head network, with feedback adjustment of enhancement parameters when the confidence level is below a threshold. This invention solves the problems of low sensitivity in detecting small-sized defects and poor generalization ability under different process conditions.

This invention relates to the field of network communication and collaborative control technology, and particularly to an information data processing method and system applied to high-concurrency scenarios. An information data processing method for high-concurrency scenarios includes the following steps: S1: Obtaining the initial and final information reception times of each cluster member in a robot cluster under high concurrency; and extracting the command and instruction sending times for the robot cluster; S2: Determining the leader device, candidate devices, and follower devices based on the initial information reception time, final information reception time, and command and instruction sending times. This invention constructs a dynamic scoring and clustering model based on time-series differences and multi-dimensional state data to achieve adaptive robot role partitioning; by monitoring role conversion rates and optimizing parameters, it overcomes the defects of static hierarchical classification, and improves the stability, fault tolerance, and response efficiency of cluster collaboration under high concurrency.

The application discloses a kind of multi-source data management method and device based on federal mechanism, belong to computer data processing technical field, it includes the local data of each data source node is collected and extracts semantic summary, is formed distributed data source register by consensus verification;Cross-source collaborative analysis request is received, and is parsed as non-cyclic directed task graph;According to task graph, query is executed locally in each node, and collaborative calculation is completed by encrypted shared intermediate result, generates final analysis result and task execution log;Analysis task execution log is generated for each node Dynamic credit score;According to credit score, update node weight to adaptively optimize the node selection of subsequent task.The application adopts the closed-loop management strategy that multi-source heterogeneous data is semantically abstracted, collaborative analysis request is parsed as execution task graph, dynamic credit score is generated in combination with task execution log and is adaptively optimized according to node selection, and cross-domain data collaborative analysis and management of safe, efficient and intelligent can be realized.

The application relates to a personalized federated learning method and system for non-independent and identically distributed data, and belongs to the technical field of federated learning. The method solves the problems of insufficient personalized adaptation and high privacy leakage risk in the existing non-independent and identically distributed data scene. The method comprises the following steps: a server sends global model parameters to each client; each client trains a local main model based on local data and the received global model parameters, obtains a local parameter increment, and uploads the local parameter increment to the server; time sequence data features are extracted from the local data, and the time sequence data features are transmitted into a trained personalized modulator together with task preference labels to generate local adaptation parameters; the local adaptation parameters are used to adjust the global model parameters to generate a local personalized model for local reasoning; the server receives the local parameter increments of each client, aggregates the local parameter increments to update the global model parameters, and enters the next round of iteration until the iteration end condition is met. The precision of the personalized model and the privacy protection degree are improved.

This invention discloses a method for identifying ozone pollution layers in the low-altitude atmosphere and a method for rapid ozone deposition in the low-altitude atmosphere. The ozone pollution layer identification method achieves precise spatial positioning of the pollution layer through the synergy of a localized ozone exceedance risk threshold and lidar three-dimensional scanning. By combining precursor concentration data, ozone photochemical process correlation parameters, and observation-driven models to quantify regional transport contributions, it effectively identifies ozone pollution accumulation areas in the upper boundary layer, overcoming the limitations of ground monitoring stations and satellite remote sensing in terms of vertical resolution. The rapid ozone deposition method in the low-altitude atmosphere addresses the problems of difficult photochemical reaction control, insufficient intervention in the upper-altitude pollution layer, and weak suppression of cross-regional transport faced by existing ozone control technologies. Through the synergistic effect of physical disturbance and deposition, it accelerates turbulent diffusion, achieving large-scale, strongly disturbed ozone pollution control and reducing the height of the pollution layer and the impact of cross-regional transport.

The invention relates to the technical field of audio processing, and discloses a method for optimizing echo double talks in a reflection environment, a mobile terminal and a storage medium, the method comprises the following steps: in a hand-free call process, controlling a motor to vibrate for a preset duration; collecting a vibration signal generated by vibration of the motor; comparing the collected vibration signal with a preset reflection environment characteristic signal; and selecting an audio parameter according to a comparison result. By acquiring amplitude characteristics and / or spectrum characteristics of the vibration signals for comparison, a hard reflecting surface and a soft reflecting surface can be distinguished, and corresponding optimized audio parameters are selected. According to the method, the motor and the microphone of the mobile terminal are utilized, hardware cost does not need to be increased, whether the mobile terminal is in the reflection environment or not can be detected, the audio parameters are dynamically adjusted according to the detection result, the echo double-talk effect in the reflection environment is equivalent to that in a handheld scene, and the hand-free call quality is remarkably improved.

The invention relates to the technical field of power system frequency modulation control, and discloses a boiler master control optimal advance control method and system. Extra coal quantity correction composed of the optimal advanced coal quantity increment and the compensation quantity is applied at a time during first change or trend direction switching; wherein the value of the compensation quantity is equal to the optimal advance coal quantity increment of the previous adjustment stage and is only started during direction switching; the system acquires instantaneous deviation after responding, and updates the optimal advance coal quantity increment according to the deviation only when the operation data comprises a continuous lifting and single lifting load conversion stage; according to the method, quick response, adaptive optimization and stable control are realized, and the AGC frequency modulation performance of the thermal power generating unit is remarkably improved.

The application provides a patent retrieval system and method based on dynamic weight adjustment and multi-modal semantics. The system includes an input layer for receiving a natural language query of a user, an initial technical dimension weight adjustment instruction, and a display mode selection; a semantic retrieval layer for retrieving and sorting related patents from a patent document library based on the natural language query and the technical dimension weight to form a preliminary retrieval result; a processing layer for standardizing the preliminary retrieval result; a display layer for visualizing and rendering the standardized retrieval result in a corresponding multi-modal form according to the display mode selection, receiving a real-time weight adjustment instruction of the user, and obtaining an interactive feedback of the user; and a dynamic weight adjustment module for generating an initial technical dimension weight according to the initial technical dimension weight adjustment instruction or a preset retrieval strategy corresponding to the display mode selection, and dynamically optimizing the initial technical dimension weight based on the interactive feedback.

This application provides a hybrid truck platooning control method based on multi-factor compensation, applicable to scenarios such as ports, logistics, and mines. The method first obtains the powertrain types and real-time loads of the leading and following trucks in the platoon. The leading truck continuously broadcasts information including its target acceleration, real-time acceleration, and load status via a vehicle-to-everything (V2X) network. Upon receiving this information, the following truck dynamically calculates a cooperative safe distance that fully considers both emergency braking risk and normal following oscillation risk, taking into account its own load and the powertrain types of both trucks. Then, based on the leading truck's target acceleration and considering powertrain differences and its own load, the system generates a target acceleration command for the following truck using a multi-factor compensation strategy. This application's method suppresses platooning oscillations and ensures a safe following distance by compensating for the response differences of different powertrains.