1350 results about "PID controller" patented technology

The invention relates to the technical field of marine monitoring, in particular to a marine target visual servo tracking method, which comprises the steps of multi-modal sensor fusion, a self-adaptive visual tracking algorithm, a servo control and visual collaboration mechanism and a shielding processing and target re-identification strategy. The problem that tracking is unstable under the conditions of illumination change, ship body shaking, target shielding and the like in a traditional method is solved. The IMU, the GNSS and the visual data are fused through extended Kalman filtering, ship body shaking is compensated, and the target state estimation precision is improved; the improved D-Fi ne target detection model is combined with an online feature updating mechanism to dynamically adapt to the appearance change of the target; the prediction and correction control strategy and the double-closed-loop PI D controller cooperate to adjust the camera holder, and the tracking delay is reduced; the multi-clue shielding detection and space-time joint feature matching technology ensures accurate re-identification of the target after shielding is removed. The real-time performance and robustness of the tracking system on an embedded platform are improved, and an efficient and stable target tracking solution is provided.

The invention discloses a constant-temperature and constant-humidity test box temperature control system based on a multistage PID algorithm and a control method thereof. The constant-temperature and constant-humidity test box temperature control system comprises an environmental parameter detection module, an in-box parameter detection module and a multistage PID controller, wherein the environmental parameter detection module is used for collecting temperature, humidity and air pressure data outside a test box in real time; the in-box parameter detection module is used for collecting multi-dimensional environmental parameters inside the test box; when the failure of any sensor is detected, starting a fault self-diagnosis module, replacing the data of the failure sensor with a data interpolation method of a side sensor, and recording the deviation compensation amount at the same time. A multi-stage PID control architecture is adopted, and feedforward compensation, parameter adaptive optimization and fault redundancy strategies are combined, so that high-precision and anti-interference control of the temperature and humidity of the test box is realized.

The invention discloses an electric heating cooker uniform temperature control method and system for gradient temperature difference regulation and control, and relates to the technical field of temperature control, the method comprises the following steps: dividing an internal heating area of a target electric heating cooker, arranging temperature sensors, and acquiring meal temperature data of N subareas in real time through a subarea temperature sensor array; constructing a gradient temperature difference model based on meal heat conduction information and food material characteristic information, and performing deviation calculation on the meal temperature data of the N sub-regions based on the gradient temperature difference model to obtain temperature deviation data of the N sub-regions; and a PID controller is adopted to perform heating power analysis on the temperature deviation data of the N sub-regions, and the heating power adjustment amount of the N sub-regions is determined to control the target electric heating cooker to perform uniform-temperature heating control. The technical effects of realizing uniform temperature control of the electric heating cooker, effectively solving the problem of local overheating or half-cooking caused by a traditional heating mode, ensuring uniform heating of meals and improving the heating quality are achieved.

The invention discloses a processing control method and system for a carbon fiber composite transmission shaft, and relates to the technical field of intelligent transmission shaft manufacturing, and the method comprises the steps: dynamically adjusting the control current of a magneto-rheological damper through a PID controller based on a process control parameter set, and recording tension fluctuation and temperature gradient data; inputting tension fluctuation and temperature gradient data into an ANSYS coupling simulation engine, establishing a three-dimensional temperature field model, calculating a resin flow compensation coefficient, generating a temperature-pressure cooperative control curve through an NSGA-III multi-objective optimization algorithm based on the resin flow compensation coefficient, and calculating the resin flow compensation coefficient and the temperature-pressure cooperative control curve according to the resin flow compensation coefficient and the temperature-pressure cooperative control curve. And integrating through a time sequence control engine to generate a solidification control instruction. According to the invention, a multi-source data fusion algorithm is combined with the industrial Internet of Things edge computing gateway, so that accurate monitoring and synchronous processing of the process control parameter set are realized, and the dynamic behavior of the carbon fiber composite material in the processing process is comprehensively reflected.

The invention provides an intelligent control method and system based on electro-hydraulic linkage. The method comprises the steps that multi-mode environment parameters are collected, a digital twin environment model is constructed, and data are synchronized with an electro-hydraulic servo system in real time. And establishing a nonlinear model, identifying parameters by using a least square method and a recursive least square method, verifying the precision through a step response test, and updating. And constructing an adaptive LSTM neural network inverse model to output a control voltage signal. And the signal is subjected to weighted fusion with the output of a PID controller, and the PID controller dynamically adjusts a gain parameter according to an error integral term to generate a control instruction to drive the system. According to the invention, the LSTM inverse model provides feed-forward compensation, the PID controller realizes feedback correction, and the LSTM inverse model and the PID controller are complementary. Meanwhile, based on a related nonlinear model and a parameter self-adaptive updating mechanism, the influence of working condition change is accurately described, and high-precision control of the electro-hydraulic servo system under the complex working condition is achieved.

The invention relates to a deformation online measurement and control method for multi-robot collaborative assembly. The method comprises the steps that multi-view surface images of workpieces in the assembly process are collected in real time through distributed robots and cameras arranged at the tail ends of the distributed robots; each view angle surface image is input into a deep learning model trained based on a digital image related technology, the optimal pixel displacement corresponding to each view angle surface image is output, and the optimal pixel displacement corresponding to each view angle surface image is converted into a spatial displacement label; the deep learning model takes an encoder-decoder as a trunk network; fusing the spatial displacement labels corresponding to the view angle surface images to obtain a fused displacement field; based on the fusion displacement field and the nominal path planning point, the tail end pose of the distributed robot is determined; the assembly error is calculated based on the reference target positioning and the tail end pose, and the PID controller adjusts the joint space of the distributed robot based on the assembly error. According to the method, the calculation overhead is remarkably reduced, and the measurement precision and robustness are improved.

The invention belongs to the technical field of intelligent home control, and particularly relates to an electric blanket intelligent temperature control system, which analyzes the matching relationship between the heating power and the temperature response in the historical operation cycle of a plurality of independent subareas of an electric blanket, fuses the thermal coupling effect between the subareas, and independently quantifies the dynamic thermal inertia parameter of each subarea. Based on the independent temperature change trend and the real-time temperature deviation of each partition, a control state including a steady state, a transient state or a strong compensation state is decided and maintained for each partition, the dynamic thermal inertia parameter, the real-time temperature deviation and the current control state are integrated, differentiated feed-forward compensation amounts are generated and superposed to the output of a PID controller of the corresponding partition, and the control state of the corresponding partition is calculated. A final power control instruction is generated after amplitude limiting and smooth filtering, temperature response lag caused by thermal inertia is actively predicted and counteracted, precise control is achieved in combination with partition state recognition, and the system response speed and control stability are remarkably improved.

The invention relates to the technical field of industrial process automation control, and discloses an intelligent adjusting method for an industrial waste liquid low-temperature evaporation process, which comprises the following steps of: superposing pressure step test excitation to a vacuum adjusting valve, synchronously acquiring temperature response data flow, calculating absolute error integral and SIAE and reply time characteristics of a response curve, and calculating the temperature response data flow according to the absolute error integral and SIAE and reply time characteristics of the response curve; substituting into an inverse model to solve an equivalent process gain and a time constant of the controlled object; based on the internal model control principle, PID controller parameters are dynamically calculated and updated through the calculated gain and the time constant, a control law is reconstructed to generate an execution instruction, and the problem of control divergence of a non-linear time-varying object under model mismatch is solved through active energy feature identification and a pole assignment mechanism; decoupling control and self-adaptive adjustment of fluid viscosity sudden change and equipment scaling are achieved, and the stability and control precision of the system are improved.

The invention relates to a system and method for rapidly establishing steady state vacuum chamber pressure. According to the system, the set value of the vacuum valve is fixed, and the driving current of the MFC electromagnetic valve is used for adjusting the pressure of the cavity, so that the pressure is stabilized more quickly. The system can operate in a training mode and an inference mode. In the training mode, a PID controller is used for determining set values of an MFC and a vacuum valve; in an inference mode during substrate processing, these settings are quickly invoked and executed, thereby achieving efficient and stable pressure control.

The invention provides a bioreactor aeration self-adaptive control method and system based on machine learning, and the method comprises the steps: collecting the water inlet flow, ammonia nitrogen concentration, dissolved oxygen concentration, water temperature and chemical oxygen demand data of a bioreactor in real time through a sensor, and carrying out the water balance verification and the Kalman filtering pretreatment containing a water temperature compensation item; generating an aeration instruction by adopting multi-model collaboration; outputting a reference aeration rate by a deep reinforcement learning DRL model; the self-adaptive PID controller dynamically adjusts the proportionality coefficient according to the dissolved oxygen deviation and calculates the correction amount; and the LSTM network generates a fusion weight, and combines the seasonal compensation factor and the safety coefficient to synthesize the final aeration rate. The system passes mutation rate constraint and nitrification efficiency verification, an ASM1 model is triggered to recheck when the deviation exceeds the standard, and after passing, an air blower with the precision of + / -2% executes an instruction and performs closed-loop feedback in a period smaller than or equal to 10 seconds. After the method is implemented, the aeration energy consumption is reduced to 0.38 kWh / m, the effluent ammonia nitrogen standard reaching rate is improved to 98.5%, the dissolved oxygen fluctuation range is reduced to + / -0.3 mg / L, and the impact load response time is shortened to be within 15 minutes.

The invention relates to the technical field of environmental engineering water treatment automatic control, and discloses a landfill leachate treatment control method based on cooperative control. The method comprises the following steps: acquiring real-time monitored water quality parameter data streams including a pretreatment stage pH value, a main treatment stage COD concentration, a deep treatment stage membrane pressure difference and the like in a landfill leachate treatment system, inputting the data streams into a cooperative control framework, and dynamically correcting PID controller parameters through a nonlinear gain function to generate a primary adjustment instruction; evaluating and generating a strategy optimization instruction based on the reinforcement learning strategy network; inputting the two into a grey prediction model and outputting a cooperative control signal containing a feedforward compensation amount; and finally, dynamically adjusting the coagulant dosage, the aeration intensity and the working pressure of the membrane component according to the signal to form a closed-loop control loop. The method can master the water quality change in real time, accurately regulate and control the treatment process, improve the stability and reliability of the treatment system, and effectively improve the landfill leachate treatment effect.

The invention discloses a focusing control method and related equipment, and the method comprises the steps: synchronously collecting the data of a multi-modal sensor, extracting features and parameters, inputting a multi-modal fusion model subjected to joint optimization to generate a motor control instruction, and achieving the focusing through the hierarchical control of rough adjustment, fine adjustment and dynamic tracking. The dynamic weight fusion network deploys the weight of each modal data according to the environmental sensitivity coefficient, and combines the historical memory and trajectory pre-judgment of the alignment trajectory prediction network to reduce invalid calculation and repeated search and greatly improve the focusing speed; the multi-mode sensor works cooperatively to replace a special hardware function, so that the cost and the power consumption are reduced; the dynamic weight fusion network can adjust the modal confidence according to the environment and enhance the anti-interference capability in the complex light environment; the alignment trajectory prediction network and the fuzzy self-adaptive PID controller are in hierarchical cooperation, the problem of erroneous judgment of a complex scene is solved, and the micro-distance and dynamic tracking precision is improved; the model is subjected to pruning, distillation and quantitative optimization, light weight is achieved, and low-cost equipment is adapted.

The invention relates to the technical field of annealing furnace control, in particular to an annealing furnace pressure control method and system.The method comprises the steps that pressure data in all furnace sections of a continuous bright annealing furnace, temperature data of furnace walls at all the furnace sections and flow data at outlets of pressure regulating valves used at all the furnace sections are collected in real time; presetting an adjusting period of a proportion parameter in a PID controller used by a pressure adjusting valve used by each furnace section to obtain each adjusting moment of the proportion parameter; obtaining each synchronous change moment of each furnace section in a time period between each adjustment moment and an adjacent previous adjustment moment, and obtaining a pressure characteristic value of each furnace section at each adjustment moment; obtaining a trend similar characteristic value of each furnace section at each adjustment moment; and obtaining the value of the proportion parameter in the PID controller in the time interval between each adjustment moment and the next adjustment moment adjacent to the adjustment moment so as to control the furnace pressure in each furnace section. The invention aims to improve the control precision of the furnace pressure.

The invention discloses a metal flat plate thickness and conductivity eddy current measurement method and system. According to the method, an electromagnetic detection platform is built, and a coaxial excitation-receiving eddy current probe structure is designed. Establishing a coaxial eddy current detection analysis model, and deducing a dynamic calculation result of mutual inductance parameters of the sensor in a frequency sweeping mode; setting two PID (Proportion Integration Differentiation) controllers and initial control variables thereof, and inputting the control variables serving as a thickness value and a conductivity value into the analytical theoretical model to obtain a corresponding mutual inductance change result; calculating an instantaneous error term and an accumulative error term of the current iteration period in real time, and when the error exceeds a preset convergence threshold value, inputting the error into a PID controller and updating the two control quantities until the maximum iteration frequency is reached; otherwise, outputting a control variable value, wherein the two control variables output by the controller are the thickness and the conductivity of the metal plate respectively. According to the invention, the thickness and conductivity of the metal plate can be accurately and simultaneously measured.

The invention discloses a drying oven temperature control system and method, the system is provided with a temperature distribution detection module, a neural network training prediction module and a control optimization feedback module, and the method comprises the steps: obtaining tunnel drying oven temperature distribution data and related influence parameters, and carrying out the preprocessing; training an LSTM (Long Short Term Memory) network by utilizing the preprocessed temperature distribution data and related influence parameters, and predicting PID (Proportion Integration Differentiation) parameters in a temperature dynamic control process; the LSTM neural network model is integrated into an edge calculation unit of the tunnel oven temperature control system, and real-time online PID parameter prediction feedback is carried out; carrying out parameter setting on the predicted and output PID parameters, optimizing the parameters of a PID controller by adopting a particle swarm algorithm, and outputting an optimal PID parameter combination; the optimal PID parameter combination is applied to an actual tunnel oven temperature control system, the temperature uniformity of dynamic change disturbance in the system is improved, the temperature control precision is improved, and the overall response time is shortened.

The invention discloses an intelligent optimization system based on big data predictive control for a granulating slag micro mill, and belongs to the technical field of mill production control, the intelligent optimization system is used for constructing a multi-level PID control structure, an outer ring PID controller generates an intermediate control quantity as a set value of an inner ring PID controller according to a deviation between an outer ring set value and an actual measurement value, and the inner ring PID controller generates an intermediate control quantity as a set value of the inner ring PID controller; the inner ring PID controller outputs a cascade control instruction according to the inner ring deviation; establishing a multivariable prediction model, predicting the change trend of the multivariable prediction model in a short period, and generating a feedforward compensation instruction before disturbance; obtaining a plurality of input variables and interference variables related to the operation state of the execution equipment, inputting the input variables and the interference variables into the trained neural network model, and outputting a neural network output instruction based on historical experience; and performing weighting processing on the cascade control instruction, the feed-forward compensation instruction and the neural network output instruction to generate a final control instruction so as to realize optimal control of the production process.

The invention relates to an intelligent control method and system for extrusion forming of an aluminum profile, and the method comprises the following steps: carrying out acoustic emission sensor array measurement and preprocessing on a mold inlet region of the aluminum profile in an extrusion process, and obtaining a preprocessed acoustic emission signal sequence; performing time-frequency domain energy distribution analysis on the acoustic emission spectrum to generate an acoustic emission energy spectrogram; carrying out material flow stability analysis based on the spectrogram to obtain a flow analysis result; if the flow instability degree exceeds the target stability range, multi-constraint optimization calculation is conducted on the main cylinder pressure and the extrusion speed based on the analysis result, and optimization control parameters are obtained; and finally, closed-loop feedback control is performed on the extruder through a distributed PID controller, so that the material flow stability is kept in a target range, intelligent high-precision forming control is realized, and the problem that in the traditional extrusion process, the material flow stability is often influenced by factors such as the extrusion speed, the main cylinder pressure and the mold design is solved. And a flow instability phenomenon is easy to occur.

The invention relates to the technical field of water pump intelligent control, and discloses a water pump controller parameter self-adaptive adjustment control method and system.The water pump controller parameter self-adaptive adjustment control method comprises the steps that meteorological early warning data, pressure pulsation signals of all pump stations and pipe network topology data are obtained; generating a time-space synchronous disaster monitoring data set through a data fusion algorithm; inputting the disaster monitoring data set into the deep space-time diagram neural network, and outputting a pipe network damage probability distribution diagram; generating a pulsation propagation prediction model containing propagation time delay and an attenuation coefficient based on a fluid dynamics equation and the pipe network damage probability distribution diagram; calculating a PID controller parameter coordinated regulation scheme of each pump station by minimizing an objective function including pressure deviation, flow fluctuation and parameter regulation quantity; and system response data is acquired in real time, and adaptive optimization of a control strategy is realized. According to the invention, stable operation of the water supply system under disaster conditions is realized.

The present invention relates to the fields of PID control and Kalman filtering, and disclosed is an improved PID control method based on Kalman filtering. The present invention comprises: in the process of acquiring a target value of an expected signal, taking the difference between the target value and a current feedback quantity of a controlled object to obtain an error value, acquiring an output of PID from the error value, applying the output of PID to the controlled object to obtain a noisy output signal, then, after Kalman filtering, feeding the output back to PID, continuously iterating to make the feedback quantity approach the target value, and finally obtaining a stable output signal. Variable-speed integration and integral separation algorithms are added to an integral term of PID to change an integration speed on the basis of a system deviation, and an incomplete differential algorithm and a low-pass filter are added to a differential term of PID to prevent high-frequency interference. According to the present invention, the optimal estimation of a system state is obtained by means of prediction of a current state and updating of observation data, thereby reducing the influence of measurement errors and noise, and improving the performance and stability of a PID controller.

The invention relates to the technical field of attitude control, and discloses a method for realizing self-adaptive active leveling compensation, which comprises the following steps: acquiring real-time data of a vehicle, the data being provided by a plurality of sensors; processing the real-time data through a data fusion algorithm; according to the inclination state and the motion parameters of the vehicle, hydraulic supporting leg adjusting parameters are calculated through a multi-objective optimization algorithm; according to the calculated hydraulic supporting leg adjusting parameters, the action of the hydraulic supporting leg is adjusted through a PI D controller for vehicle balance recovery; the stability of the hydraulic supporting leg adjusting system is verified through the Lyapunov stability theory, and the hydraulic supporting leg adjusting system is used for enabling the adjusting process of the hydraulic supporting leg to be completed in all operation states; and the vehicle inclination state is fed back in real time. By fusing multi-sensor data and adopting a Kalman filtering or particle filtering algorithm, high-precision perception of the real-time inclination state and dynamic parameters of the vehicle is realized, and a more accurate and reliable vehicle attitude judgment effect is obtained.

The invention relates to the technical field of mechanical arm control, and discloses a multi-degree-of-freedom mechanical arm-based visual identification grabbing method, which comprises the following steps of: acquiring point cloud data of a target object by utilizing a depth camera, and screening the point cloud data to determine a target feature point; the target feature points are converted into mechanical arm base coordinate system pose data; solving an optimal joint angle; acquiring tail end pose data fed back by the depth camera in real time, and calculating a joint angle correction amount based on a preset formula and the tail end pose data; a control signal is output through the PID controller, and the seven-degree-of-freedom carbon fiber mechanical arm is controlled to grab a target object; and whether the seven-degree-of-freedom carbon fiber mechanical arm successfully grabs the target object or not is verified through point cloud collision detection. By implementing the method, the problems that mechanical arm visual grabbing has obvious defects in the aspects of flexibility of degree of freedom, visual perception robustness, control cooperation precision, grabbing verification reliability and the like, and high-precision and high-stability grabbing requirements in a complex environment are difficult to adapt are solved.

The invention relates to the technical field of tunnel and underground engineering construction, and discloses an intelligent closed-loop control system and method for a tunnel construction section contour, and the method comprises the steps: collecting geological-geometric data through the fusion of a three-dimensional laser scanner and a geological radar before blasting; dynamically generating a theoretical blasting contour line and adaptive blasting parameters through a convolutional neural network; iMU positioning and a PID controller are combined to realize millimeter-level accurate control of the drill boom; generating a three-dimensional deviation field by adopting an iterative point cloud registration algorithm after blasting; when the deviation exceeds a threshold value, triggering incremental learning to optimize model parameters; and finally, closed-loop iteration is formed. Through multi-source data fusion, contour and parameter intelligent generation, precise execution control, three-dimensional deviation field feedback and an incremental learning mechanism, a complete intelligent closed-loop control system is constructed, the limitation of traditional blasting design depending on experience is broken through, and the precision, efficiency and economic benefits of tunnel construction are remarkably improved.

The invention relates to the technical field of fuel cells, in particular to a method and system for accurately controlling the hydrogen stoichiometric ratio of a fuel cell, and the method comprises the steps: firstly, obtaining a quantitative anode health state value through a fusion calculation model by collecting load current, anode inlet and outlet pressure, temperature, high-frequency resistance and other multi-source signals in real time; a feed-forward model based on a load current change rate predicts sudden change of hydrogen demand, and an optimal hydrogen flow instruction is jointly generated in combination with output of a PID controller which adaptively adjusts parameters according to a health state value. According to the method, the integrated diagnosis parameter, namely the anode health state value, is created, so that the internal state of the fuel cell can be accurately perceived and prospectively judged. Through deep fusion of multi-source heterogeneous information such as high-frequency resistance, anode pressure difference, current and temperature, a comprehensive index capable of comprehensively and quantitatively reflecting anode water content, gas concentration and runner smoothness is generated.

The invention discloses a spiral anchor foundation grouting pressure-flow-deformation intelligent coupling control method, and relates to the technical field of foundation grouting technologies, and the spiral anchor foundation grouting pressure-flow-deformation intelligent coupling control method comprises the steps that according to specification parameters of a spiral anchor and the type of a soil body where the spiral anchor is located, a preset engineering parameter set is matched; collecting grouting data of each grouting channel, and calculating grouting deviation data in combination with the engineering parameter set; performing fuzzification processing on the grouting deviation data, and converting the grouting deviation data into fuzzy linguistic variables; inputting the fuzzy language variable into a preset fuzzy rule base for reasoning, and outputting a PID parameter correction amount; parameters of a PID controller are dynamically adjusted according to the correction amount, and a pump speed adjusting instruction is generated; executing the pump speed adjusting instruction, and collecting grouting data after execution; a soil body permeability coefficient is obtained through inversion by constructing a digital twinborn model, and the fuzzy rule base is optimized and updated by combining the executed grouting data. The method is used for solving the problem that a traditional spiral anchor foundation grouting technology is poor in adaptability to complex geology.

The invention relates to the technical field of pressure control, in particular to a butterfly valve pressure self-adaptive adjusting method, device and equipment and a storage medium. According to the method, a pre-constructed neural network model is introduced, and user set pressure, actual measurement pressure, current control signals and error parameters serve as input variables; dynamic generation and real-time self-adaptive adjustment of PID control parameters are realized, the technical bottlenecks that parameter setting of a traditional PID controller is complex and adaptability to non-linear and time-varying systems is insufficient are effectively solved, and the parameter adjustment period is shortened; the weight parameter of the neural network is continuously optimized through a back propagation algorithm, so that the inhibition capability of the system on external disturbance is remarkably enhanced, the overshoot is reduced, and the long-term stability and control precision of pressure control are improved; the target step number is calculated in combination with butterfly valve hardware parameters, the accuracy and rapidity of stepping motor driving are ensured, and the problem of response delay of traditional PID control is effectively solved.

The intelligent cargo transportation system for the stereoscopic warehouse comprises a super high-rise stacking machine module, the super high-rise stacking machine module comprises a stacking machine body, a horizontal shaft walking mechanism and a lifting shaft lifting mechanism, the horizontal shaft walking mechanism and the lifting shaft lifting mechanism are arranged on the stacking machine body, and the height of a stand column of the stacking machine body exceeds 30 m; the dynamic anti-swing control module comprises a synchronous and isochronous mode switching unit, an S-shaped curve compensation unit and a motion time sequence decoupling unit; the S-shaped curve compensation unit is used for generating an S-shaped speed regulation curve of the horizontal shaft walking mechanism and the lifting shaft lifting mechanism; the motion time sequence decoupling unit is used for calculating the delay starting time of the horizontal shaft walking mechanism relative to the lifting shaft lifting mechanism, and time sequence coordination of motion of the two shafts is achieved; and the self-adaptive PID controller is used for dynamically adjusting control parameters based on the real-time data of the multi-mode sensing module and compensating the running posture of the stacking machine in real time so as to restrain swinging. The method has the effect of effectively improving the super high-rise transportation stability of the stereoscopic warehouse.

The invention relates to the technical field of remote monitoring, and discloses a high-precision holder control method and system. Comprising the steps of collecting a target scene image, performing denoising, distortion correction and resolution adjustment, obtaining a target pixel coordinate and confidence through a lightweight target detection model, and calling a corresponding image enhancement model to perform preprocessing when an abnormal environment is detected; transmitting a part of detection results as key frames to an edge end based on a frame extraction strategy, caching the rest of the detection results locally, and switching to a local tracking mode and reducing control frequency when network delay exceeds a threshold value; fusing visual detection data and inertial measurement data, and predicting a target position through extended Kalman filtering; carrying out sub-pixel-level refinement on the target position, and calculating a three-dimensional orientation in combination with a participated holder attitude in a camera; and adjusting the attitude of the holder in real time based on a prediction result and an anti-saturation integral separation PID controller.

The invention provides a path planning and energy management cooperative regulation and control method for a multi-agent unmanned aerial vehicle, and the method comprises the following steps: building a kinetic model based on a six-degree-of-freedom motion equation of a four-rotor unmanned aerial vehicle, and building an energy consumption model through combining the power of a motor and the discharge characteristics of a battery; sensing the state of the unmanned aerial vehicle in real time, defining a state space and an action space of a deep reinforcement learning algorithm, and generating navigation points by using the deep reinforcement learning algorithm; receiving a delivery request, and dynamically allocating tasks according to the state of the unmanned aerial vehicle by adopting a deep reinforcement learning algorithm; performing path planning on the unmanned aerial vehicle for task allocation by adopting an A * algorithm according to the navigation points in combination with the multi-dimensional cost, and obtaining an optimal path; dispersing the optimal path into a speed instruction, and dynamically adjusting the course angle and the flight speed of the unmanned aerial vehicle through a PID controller; through combination of deep reinforcement learning and an A * algorithm, the problems of path planning and energy management of the multi-agent quad-rotor unmanned aerial vehicle logistics distribution system in complex terrains are effectively solved.

The invention provides a satellite weak and small target on-orbit observation system and method based on intelligent closed-loop feedback, and the system comprises a detection module which carries out the image enhancement and time sequence consistency enhancement of an infrared image, obtains an enhancement feature, and obtains a candidate target set based on the enhancement feature; the tracking module is used for carrying out target matching in the search area; when the matching succeeds, the candidate position is used as an observation value, and the observation value is input into a Kalman filter to obtain a target state vector; when the matching fails, taking a prediction state of the Kalman filter as a target state vector, expanding a search window by taking a prediction position as a center, and executing re-identification; the control module is used for mapping the target state vector into an attitude error and generating a control instruction by adopting a single-neuron self-adaptive PID (Proportion Integration Differentiation) controller; and the closed-loop scheduling module is used for dynamically adjusting operation parameters of at least one module according to the execution error and the detection confidence coefficient. According to the invention, the continuous tracking precision and attitude control stability of the weak and small target are improved.

The invention discloses an efficient heat dissipation system of a new energy automobile circuit board, and the system comprises a composite heat dissipation substrate which is formed by compounding a ceramic substrate layer, a graphene heat conduction layer and a copper alloy supporting layer through vacuum hot pressing, and the surface of the graphene heat conduction layer is provided with a micron-sized groove array; the dynamic heat dissipation assembly comprises a thermoelectric refrigeration module and a temperature sensor which are embedded in the composite heat dissipation substrate, the thermoelectric refrigeration module is linked with the temperature sensor through a PID controller, and active refrigeration based on temperature rise of the circuit board is achieved; the multi-layer heat dissipation channel comprises a micro-channel and a bionic fin structure, the micro-channel vertically penetrates through the composite heat dissipation substrate, the bionic fin structure covers the surface of the substrate, and the micro-channel is filled with a phase change material and is communicated with an external liquid cooling circulation system; the airflow adjusting module comprises a rotatable flow guide plate and a piezoelectric fan array, the flow guide plate dynamically adjusts the heat dissipation airflow direction according to the vehicle speed, and the frequency response range of piezoelectric fans is larger than or equal to 100 Hz.