32 results about "Fuzzy inference engine" patented technology

The invention provides an intelligent door and window control method and system, and the method comprises the steps: S1, obtaining multi-source environment data; s2, inputting the multi-source environment data into a fuzzification module, and converting the multi-source environment data into a fuzzy variable through a preset ambiguity function; s3, dynamically generating an environment parameter weight vector according to the real-time scene parameters; s4, inputting the fuzzy variable and the environmental parameter weight vector into a fuzzy inference engine, executing logical operation of a fuzzy rule base, and outputting comprehensive evaluation values of window opening suitability, window closing urgency and shading demand; and S5, generating a final control instruction through a defuzzification strategy, and executing the final control instruction. According to the method, the problem of frequent invalid operation caused by fluctuation of the environmental parameters near the boundary value is solved, the environmental parameter weight vector is dynamically generated based on the time parameters, the user preset mode and the meteorological data confidence factor, adaptation to seasons, time periods, user states and other scenes is achieved, and decision logic can be flexibly adjusted according to actual requirements; and a contradictory decision under a traditional fixed rule is avoided.

The invention relates to an intelligent control method, system, equipment and medium for automatic discharging mining tunneling cutting picks, and the method comprises the following steps: monitoring the flowing state of coal rock slag in a spiral discharging channel in real time, collecting a channel pressure difference signal and a cutting pick vibration signal, and generating discharging state characteristic parameters; blocking risk quantification is carried out on the characteristic parameters, and a real-time blocking index is generated through weighted fusion calculation; based on the index, a cutting head rotating speed optimization adjustment amount is generated through a fuzzy reasoning mechanism; and finally, generating a rotating speed control instruction through dynamic amplitude limiting processing and sending the rotating speed control instruction to a variable-frequency driving system. By means of the method, real-time sensing and dynamic self-adaptive adjustment of the blockage risk of the discharging channel are achieved, the problem that the discharging channel is blocked due to coal rock property changes is effectively solved, the discharging efficiency and the stability of tunneling operation are improved, and the service life of cutting teeth is prolonged.

The invention relates to a multi-motor cooperative control method, system and device based on position and speed double feedback and a self-adaptive sliding mode and a medium, and relates to the technical field of multi-motor cooperative control. The multi-motor cooperative control method comprises the following steps: acquiring an actual position signal and an actual speed signal of each motor, and converting and calculating a position synchronization error and a speed synchronization error between the motors; calculating a position tracking error and a speed tracking error of each motor according to a preset reference position signal and a reference speed signal; fusing the weighted operation position synchronization error, the speed synchronization error, the position tracking error and the speed tracking error to construct a sliding mode surface function; iteratively optimizing the sliding mode surface function according to a preset fuzzy reasoning mechanism, outputting a self-adaptive adjustment amount, updating the original switching gain, and calculating a new switching gain; and calculating the final control quantity of each motor according to the new switching gain, the sliding mode surface function and the saturation constraint function, and outputting the final control quantity to a corresponding motor driver to drive the motor to move.

The invention relates to the technical field of automatic control, and discloses a sliding mode control buffeting suppression method based on an interval type-2 fuzzy rule. Dynamic balance of buffeting suppression and robustness is realized through deep cooperation of an interval type-2 fuzzy logic system and sliding mode control: an interval membership function is utilized to accurately capture an uncertainty boundary of the system, a double-layer fuzzy reasoning mechanism is combined to cooperatively optimize switching gain and boundary layer thickness, and high-precision tracking is maintained under strong disturbance; the control signal high-frequency oscillation energy is monitored in real time to drive parameter reconstruction, and buffeting is eliminated from the source; the modular design can be directly embedded into an industrial control system, abrasion of an executing mechanism is remarkably reduced, the service life of equipment is prolonged, and the inherent contradiction between dynamic response and stability of a traditional method is solved.

The invention discloses a flight control method and system for a vertical take-off and landing tilting quad-rotor unmanned aerial vehicle, and aims to solve the technical problem of poor time-varying adaptability of a control system in a nacelle tilting transition stage. According to the method, in a rotor wing flight mode and a nacelle tilting transition mode, attitude angle deviation, deviation change rate and flight speed of the unmanned aerial vehicle are obtained in real time, a fuzzy inference engine is adopted to dynamically output basic control quantity based on a predefined rule base, and a final control instruction is generated in combination with pneumatic feed-forward compensation quantity based on speed to drive a pneumatic control surface. According to the method, fuzzy intelligent decision making and feed-forward dynamic compensation are fused, the limitation that traditional control depends on an accurate model is broken through, the control precision and adaptability of a transition stage are remarkably improved, overshoot is effectively restrained, the adjusting time is shortened, the robustness of a system under model parameter changes and external interference is enhanced, and the system reliability is improved. And a reliable technical guarantee is provided for full-mode flight of the tilt-rotor unmanned aerial vehicle.

This invention relates to a cascaded fuzzy feedforward direct-drive speed control method and system based on LC filtering. The method includes: obtaining a speed error and error rate of change from a reference speed and a real-time measured speed; inputting the speed error and error rate of change into a Mamdani fuzzy inference engine to output a power setpoint coefficient; inputting the power setpoint coefficient and a normalized measured speed signal into a two-dimensional torque-current reference lookup table, performing bilinear interpolation calculation, and outputting an electromagnetic torque command; converting the electromagnetic torque command into a quadrature-axis command current, generating a PWM signal through current closed-loop regulation and SVPWM modulation, and driving a two-level voltage-type inverter; the output of the two-level voltage-type inverter drives a low-voltage permanent magnet synchronous motor through an LC sine wave filter with an RC damping branch. Compared with the prior art, this invention has advantages such as low computational load, improved dynamic response, and enhanced disturbance rejection.

The invention relates to the technical field of avionics, and discloses a friend behavior prediction and multi-platform autonomous decision-making method and system during communication interruption, and the method comprises the steps: constructing a multi-level fuzzy inference tree, and carrying out the fuzzy processing of multi-source heterogeneous input information, and forming a plurality of fuzzy sets; decomposing the complex input relation into a plurality of subsystems based on a hierarchical fuzzy reasoning mechanism, and obtaining a subtask response benefit value through layer-by-layer reasoning; input variables are fuzzified based on a triangular membership function, and a potential task allocation scheme of the friend formation is predicted in combination with a hierarchical rule reasoning mode. According to the method, centerless, low-dependence and high-robustness multi-platform autonomous task allocation can be realized, and the collaborative decision-making capability and task execution efficiency of formation members in a complex environment under an incomplete information condition are improved.

The invention provides a boundary flow control method and system based on a busy water area macroscopic basic diagram, electronic equipment and a storage medium, and the method comprises the steps: building a water area macroscopic basic diagram which can accurately reflect the macroscopic law of mixed traffic flows of different ship types through collecting and processing the data of a ship automatic recognition system; determining an optimal accumulated ship number target when the overall navigation efficiency of the system is highest; delimiting an easily-congested key area in the target water area as a core water area, and establishing a ship traffic flow dynamic balance model taking the optimal target as a balance point for the core water area as a control object; a fuzzy self-adaptive PID controller is designed and applied, the PID controller can sense the deviation between the actual number of ships in a core water area and a target value and the variation trend of the deviation in real time, control parameters are intelligently adjusted on line through a built-in fuzzy inference engine, the optimal boundary flow control rate is dynamically calculated and output, and therefore the flow of the ships entering the core water area is accurately adjusted. The number of the ships in the water area is actively and stably maintained in the optimal interval.

This invention discloses a fuzzy logic energy-saving control method for a mechanical jigging screen, relating to the field of mineral sorting equipment control technology. The method includes real-time acquisition of raw multi-source state data from the equipment, preprocessing to generate a standardized state feature set containing normalized feed load characteristics, particle size distribution feature vectors, bed thickness variation trend characteristics, and motor power spectrum characteristics. This set is then input into a preset fuzzy inference engine, where fuzzy logic operations are performed using a predefined and tuned fuzzy rule base. The output is a fuzzy set of optimal driving parameters covering fuzzy suggestions for screen stroke, stroke frequency, and acceleration. This set is then defuzzified and converted into deterministic driving command parameters. This method enables precise adaptation of the equipment's multi-source operating states and driving parameters, enhances the collaborative adjustment capability of multi-dimensional driving parameters, optimizes equipment operating adaptability, and achieves the technical effects of dynamic matching of operating conditions and energy-saving regulation.

The invention discloses a power transmission and transformation project electronic file verification method based on a fuzzy reasoning mechanism. The method comprises the following steps: carrying out consistency verification on metadata of an electronic file through a Transform model, an LSTM network and Hash verification; on the basis of a conditional weight dynamic adjustment mechanism, screening out features most relevant to the target task in the electronic archive management system, and removing redundant data; according to an input condition, adaptively adjusting a scoring standard, and according to a fuzzy reasoning mechanism and the scoring standard, scoring the screened features to obtain a target feature score; and generating a final verification result of the electronic archive based on the target feature score. The design is suitable for integrated processing and accurate verification of large-scale and multi-modal data, and the accuracy and flexibility of electronic file verification can be effectively improved.

Implementations described and claimed herein provide systems and methods for developing a reservoir. In one implementation, a reservoir model is received. The reservoir model includes a static model and a dynamic model. The static model includes one or more clusters of a three-dimensional volume of the reservoir and an uncertainty quantification generated using a neural network. The dynamic model includes pressure values and fluid saturation values propagated across the three-dimensional volume through a nodal connectivity of neighboring clusters. A set of input features is generated from the static model and the dynamic model. The set of input features is related to a drilling attractiveness of a target region of the reservoir using a set of rules executed by a fuzzy inference engine. A quantification of the drilling attractiveness is generated. A recommendation for drilling in the reservoir is output based on the quantification of the drilling attractiveness.

The invention belongs to the technical field of oil and gas field development, and discloses a crude oil treatment inlet liquid steady flow control method based on fuzzy cascade PID, which comprises the following steps: determining fuzzy cascade PID regulation loop control logic of an inner loop control loop and an outer loop control loop, the input and output of the outer loop control loop are respectively a pressure buffer tank target liquid level and an inlet pressure buffer tank flow control valve opening; the input and the output of the inner ring control loop are respectively the opening degree of a flow control valve of an inlet pressure buffer tank and the opening degree of a gulp valve; determining initial domains of discourse of input and output parameters of a fuzzy inference engine, and performing fuzzification processing; determining fuzzy rule tables of the inner and outer ring fuzzy inference engines; the target liquid level of the pressure buffer tank serves as loop input, initial parameters of an inner ring PID controller and an outer ring PID controller are determined, the parameters are continuously optimized under the action of a fuzzy inference engine, and steady flow control is achieved. The stability of crude oil liquid inlet flow can be greatly improved, the processing capacity of a process rear-end device is met, and light-load operation of the pressure buffer tank is guaranteed.

The invention discloses an efficient full feeding system and method for a high-pressure roller mill, and belongs to the technical field of high-pressure roller mill feeding control. According to the system, multiple parameters such as the ore feeding amount, the material level and the pressure are collected in real time through the sensing module, the optimal pressure set value is dynamically calculated through a fuzzy inference engine of the control module, then an adjusting instruction is generated through the cascade control module, and finally the roller is driven by the execution module to change the speed. According to the invention, the problems that the high-pressure roller mill is easy to cause material blockage and production halt due to unstable material level of the feeding hopper and the working pressure and frequency are difficult to accurately adjust manually are solved. According to the invention, the full ore feeding state can be automatically maintained, and the working pressure and frequency are stabilized in a high-efficiency interval, so that material blockage accidents are effectively prevented, continuous and stable production is guaranteed, the rolling efficiency is improved, the product quality is stabilized, and the energy consumption is reduced.

The application discloses a kind of intelligent high-voltage switch's circuit breaker body fault diagnosis method, device, equipment and storage medium, method includes: obtaining the historical fault data of circuit breaker in high-voltage switch, according to historical fault data determine suspected fault component set;Based on suspected fault component set, historical alarm information and fault reason are classified, determine the alarm information and fault reason corresponding to each fault component;Alarm timing information in historical fault data is checked with timing information constraint, and removes error fault information;The mapping relationship between the fault reason of each fault component and alarm information is analyzed using fault tree module;Based on the mapping relationship, the alarm information of target fault event is obtained by matrix form iteration operation by fuzzy inference mechanism, and the fault probability representation of high-voltage switch circuit breaker is obtained, and the fault diagnosis result is determined according to the fault probability representation of high-voltage switch circuit breaker.Effectively improve fault diagnosis efficiency.

This invention discloses an energy management method for hybrid energy storage systems based on fuzzy model predictive control. It constructs a linear variable parameter model predictive control architecture incorporating fuzzy decision-making for closed-loop optimization control. First, an LPV prediction model for the system is established, and the load power sequence is introduced as a measurable feedforward disturbance into the state equation. During the rolling optimization preparation stage, a fuzzy inference mechanism is used to analyze multi-dimensional operating conditions such as system power fluctuations, SOC, and SOV in real time, dynamically adjusting the weighting factors of energy tracking, battery loss, and current smoothing in the cost function to achieve an adaptive trade-off in the control strategy. Simultaneously, a hierarchical setpoint tracking strategy is adopted, intelligently switching the voltage state reference target based on the real-time energy level of the supercapacitor. Finally, based on the time-varying model, dynamic weights, and the reference target, a quadratic programming problem is solved, outputting the optimal control quantity applied to the power converter, thereby significantly improving the system's adaptive coordination capability and overall operating efficiency under complex and variable operating conditions.

The application provides a TBM jamming risk intelligent early warning method and system based on knowledge-data double driving, which comprises the following steps: acquiring multi-source parameter information collected in the TBM tunneling process of TBM tunneling cases under different stratum tunneling conditions, and constructing a multi-source parameter database; processing the data in the multi-source parameter database, and calculating data-driven jamming probability based on a robust time sequence anomaly detection model for abnormal changes; extracting expert experience knowledge based on TBM jamming literature research and experience knowledge in actual construction cases, and constructing a TBM tunneling jamming event knowledge base; determining the membership degree and the reliability of the fuzzy condition, constructing a TBM tunneling jamming event rule reasoning machine, and calculating knowledge-driven jamming probability based on a fuzzy reasoning machine model; multiplying the data-driven probability and the knowledge-driven probability by using a factor multiplication method, calculating the TBM tunneling jamming probability, and obtaining the TBM tunneling jamming risk prediction result based on the knowledge-data double driving.

Implementations described and claimed herein provide systems and methods for developing a reservoir. In one implementation, a reservoir model is received. The reservoir model includes a static model and a dynamic model. The static model includes one or more clusters of a three-dimensional volume of the reservoir and an uncertainty quantification generated using a neural network. The dynamic model includes pressure values and fluid saturation values propagated across the three-dimensional volume through a nodal connectivity of neighboring clusters. A set of input features is generated from the static model and the dynamic model. The set of input features is related to a drilling attractiveness of a target region of the reservoir using a set of rules executed by a fuzzy inference engine. A quantification of the drilling attractiveness is generated. A recommendation for drilling in the reservoir is output based on the quantification of the drilling attractiveness.

An adaptive, fuzzy logic-based system (100) for controlling rainwater quality for the intelligent detection of first runoff, comprising: a roof water inlet connection (102) designed to receive rainwater runoff from the roof; a removable dirt filter assembly (104) arranged downstream of the roof water inlet connection (102) to remove coarse contaminants from the incoming runoff; a sealed sensor chamber (106) hydraulically connected to the dirt filter assembly (104); a plurality of sensor units (108) arranged within or connected to the sensor chamber (106), the sensor units comprising at least a turbidity sensor, a conductivity or total dissolved solids sensor, a flow sensor, a storage tank level sensor, and optionally a pH sensor;a programmable controller (110) comprising a processor, memory, and a fuzzy inference engine (112) configured to receive sensor readings, normalize the received readings, generate fuzzy membership values, execute a stored fuzzy rule base, and continuously calculate a rainwater suitability value corresponding to the quality of the collected runoff water; an electronically actuated three-way valve (114) functionally coupled to the programmable controller (110) and designed to selectively direct the collected rainwater, according to the continuously updated rainwater suitability value, to a discharge outlet (116), a secondary use outlet (118), and a primary storage outlet (120);wherein the programmable controller (110) continuously adjusts the diversion decision during a rainfall event in response to changing runoff quality and the availability of storage tanks, thereby maximizing the amount of recoverable rainwater while preventing contaminated runoff from entering a primary storage tank.

The invention relates to the technical field of photoelectric pods, and discloses a fuzzy PID control method and servo system for a photoelectric pod, and the method comprises the steps: 1, obtaining the speed error e, the speed error change rate ec and the speed gain Kv of a brushless motor in real time; 2, e, ec and Kv serve as three-dimensional input variables to be sent into a fuzzy inference engine, and proportional gain correction delta Kp, integral gain correction delta Ki and differential gain correction delta Kd are output; 3, performing gravity center method ambiguity resolution on the delta Kp, the delta Ki and the delta Kd to obtain real-time PID (Proportion Integration Differentiation) parameters Kp, Ki and Kd; and 4, calculating a PWM duty ratio through real-time PID parameters, and driving the brushless motor to drive the photoelectric pod frame to rotate. According to the method, the speed gain serves as fuzzy input, so that the control algorithm can output more reliable control quantity, and the requirements for high precision and rapidity when the photoelectric pod is controlled by using a brushless motor can be met.

The present disclosure provides an aluminum electrolytic alumina concentration online identification method and system based on fuzzy reasoning, which comprises: obtaining apparent alumina concentration and comprehensive discharging period through a time sequence knowledge graph, calculating the PDHC value of the current comprehensive discharging period and the previous comprehensive discharging period; inputting the PDHC value of the current comprehensive discharging period and the previous comprehensive discharging period into a preset fuzzy reasoning machine to obtain the fuzzy reasoning output variable of the alumina concentration state and the alumina concentration change trend of the current comprehensive discharging period; and performing anti-fuzzification processing on the fuzzy reasoning output variable of the alumina concentration state and the alumina concentration change trend of the current comprehensive discharging period to obtain the identification evaluation value of the alumina concentration state and the alumina concentration change trend of the current comprehensive discharging period.

This invention discloses a method, system, equipment, and medium for real-time quality assessment in workshop production processes, specifically relating to the fields of intelligent manufacturing and industrial automation control technology. The method includes: S1 collecting multi-source heterogeneous data and forming a fused feature vector through spatiotemporal matching; S2 constructing a digital twin benchmark model based on historical good product data to generate a dynamic time-varying tolerance band; S3 dynamically adjusting thresholds based on equipment health status and calculating a multi-dimensional comprehensive deviation index; S4 matching rules using a fuzzy inference engine to output normal, warning, and out-of-control status labels and potential root cause hints; and S5 storing data and incrementally updating the model using newly added good product data. This invention solves the problems of poor real-time performance, high false alarm rate, and difficulty in root cause localization in traditional assessment methods through multi-source data fusion, dynamic threshold adaptation, equipment status perception, and model iterative optimization. It improves the accuracy, adaptability, and intelligence level of quality assessment, making it suitable for real-time quality control in workshop production processes.

The invention provides a composite control method and system based on a fuzzy control algorithm and PID, and the method comprises the steps: obtaining an output error and an error change rate of a system in real time, and obtaining a state variable of the system; taking the output error, the error change rate and the state variable as input, and outputting a proportionality coefficient, an integral coefficient and a differential coefficient at the same time through a fuzzy inference engine; forming a parameter self-tuning PID (Proportion Integration Differentiation) controller by utilizing a proportionality coefficient, an integral coefficient and a differential coefficient, and calculating a control signal; and the control signal is output to a servo driver of the servo load simulator system to control an execution mechanism to act. All working conditions and nonlinear self-adaption of controller parameters are achieved through the fuzzy-PID fusion controller, and compared with a traditional PID controller, response can be made stably through self-adaption adjustment of the parameters in the face of load sudden change and other complex working conditions, overshoot is effectively reduced, the adjustment time is shortened, and the inherent high precision of the PID controller can be kept.

The embodiment of the invention discloses a self-adaptive fuzzy control method and system based on an air conditioner load, and the method comprises the steps: collecting historical operation characteristic data of a to-be-controlled air conditioner in different operation periods and environment influence characteristic data of a corresponding time period, and constructing a load prediction logic model through association mode mining, the air conditioner load state is deduced according to environment characteristics; when an air conditioner to be controlled is started, current environment characteristic data are obtained in real time and input into the model to obtain a load state inference result, and a target fuzzy control strategy set is selected from a preset control strategy set according to the load state inference result. In combination with deviation information of indoor environment feedback characteristics and a set target, a dynamic adjustment instruction of air conditioner operation parameters is generated through a fuzzy reasoning mechanism, self-adaptive control over the air conditioner load is achieved, and the air conditioner is made to respond quickly, operate with high precision and are low in energy consumption under various working conditions.

The invention discloses a design method of a fuzzy system with a center average defuzzifier, and the method comprises the steps: firstly determining a fuzzy rule number to obtain a fuzzy rule base, then defining an input fuzzy set membership function in a fuzzy rule, and determining the center and width of the membership function, and finally, determining the center of an output fuzzy set in the fuzzy rule to obtain a fuzzy system composed of a fuzzifier, a fuzzy rule base, a fuzzy inference engine and a defuzzifier. The method has the advantages that the fuzzy system principle is simple, the algorithm is easy to implement, and the universal approximation characteristic is achieved.

The application relates to an interpretable traffic cognition method based on fuzzy theory and belongs to the technical field of artificial intelligence. Real-time traffic data of a traffic scene is organized into an external attribute feature matrix, a traffic cognition feature matrix and an adjacency matrix. The preprocessed external attribute feature matrix is sent into a fuzzy reasoning mechanism, and an attribute influence feature matrix is output after feature calculation. The matrix, the traffic cognition feature matrix and the adjacency matrix are input into a graph convolutional neural network, and then input into a time characteristic capturing network based on a gated recurrent unit. Finally, a prediction result is output and used for attribute influence fuzzy classification and traffic cognition. The application can efficiently extract time and space dependence characteristics between multiple roads in a traffic scene, has higher traffic data cognition performance and interpretability, and solves the problems of low transparency, poor interpretability of a deep neural network and insufficient consideration of external attribute features of a traffic scene in a traffic cognition process.

The invention provides a distributed Internet of Things video data real-time analysis system and method, and the method comprises the steps: deploying video analysis units at a plurality of edge nodes, extracting the load index of each node, and achieving the quantification of the operation pressure of the nodes; an edge computing alliance is constructed based on the network topology distance between the nodes, the resource type and the historical cooperation efficiency, and periodic interaction between node loads and task metadata is achieved; when the node load exceeds a preset threshold value, migrating a part of video analysis tasks to low-load nodes for execution in the alliance in combination with task calculation feature similarity and node available computing power; in the migration process, node load changes are monitored, a collaboration degree score is calculated based on a fuzzy reasoning mechanism, and the collaboration degree score is used for dynamically adjusting weight parameters of a migration decision function so as to optimize task migration distribution and a node collaboration sequence. According to the technical scheme, dynamic collaborative scheduling of the video analysis tasks between the edge nodes can be realized, so that the overall operation robustness of the distributed Internet of Things video data analysis process is improved.

The invention discloses a monofilament production line tension cooperative control system and method based on neural network fuzzy adaptive PID. The system is composed of a distributed sensing layer, an execution driving layer and an intelligent control layer. The intelligent control layer adopts a neural network fuzzy adaptive PID control algorithm, optimizes a membership function and a rule weight of a fuzzy inference device on line through a neural network, dynamically sets parameters of a corresponding PID controller according to tension real-time deviation and a deviation change rate of each key process point, and executes an embedded multi-transmission-point coordination rule, so as to realize the optimal control of the tension of each key process point. And intelligent cooperative control of each transmission point is realized. According to the method, the self-learning ability of the neural network and the interpretability of fuzzy logic are fused, the problems that a traditional PID is poor in adaptability, a fuzzy controller depends on fixed expert experience, and multi-transmission-point collaboration is insufficient are solved, and the tension stability and uniformity and product consistency in the monofilament production process are remarkably improved.

The present application relates to the technical field of urban rail transit energy storage, and discloses a vehicle-mounted hybrid energy storage system energy control method and system, which calculates the output power of a train traction motor, establishes the relationship between the state of charge and the terminal voltage of a super capacitor group and the state of charge and the current of a storage battery group, constructs a fuzzy quantizer, a fuzzy inference engine and a fuzzy rule updater of the super capacitor group and the storage battery group, constructs a voltage outer loop PI controller and a current inner loop PI controller with a dead zone for the super capacitor group and the storage battery group, and obtains a control signal of a bidirectional DC / DC converter to maintain the stability of a DC bus voltage and improve the energy saving rate.

The invention relates to the technical field of centrifugal machines, and particularly provides a self-adaptive fuzzy PID control disc type centrifugal machine rotating speed adjusting method and system, and the method comprises the steps: obtaining a rotating speed error, an error change rate, a load torque change rate and a friction coefficient variable quantity; a fuzzy inference engine is constructed based on a preset parameter self-adjustment rule base, and PID parameter adjustment amount is obtained with the rotating speed error, the error change rate, the load torque change rate and the friction coefficient change amount as input variables of the fuzzy inference engine; and the PID control parameters are corrected according to the PID parameter adjustment amount, and the rotating speed of the disc type centrifugal machine is adjusted in real time according to the PID control parameters. According to the method, the load torque change rate and the friction coefficient change quantity are introduced to serve as input of the fuzzy inference engine, the load torque change rate serves as a disturbance feed-forward item, the working condition adaptability can be enhanced, and the defects that PID parameters are fixed, variable working conditions are difficult to adapt, and overshoot or slow response is likely to be caused in traditional PID control are overcome.

The application relates to the field of avionics, and discloses a method and system for friendly behavior prediction and multi-platform autonomous decision-making in communication interruption, which comprises the following steps: constructing a multi-level fuzzy reasoning tree, fuzzy processing multi-source heterogeneous input information to form multiple fuzzy sets; decomposing complex input relations into several subsystems based on a hierarchical fuzzy reasoning mechanism, and obtaining a subtask response benefit value through layer-by-layer reasoning; and fuzzy processing input variables based on a triangular membership function, and predicting a potential task allocation scheme of a friendly formation in combination with a hierarchical rule reasoning mode. The application can realize multi-platform autonomous task allocation without a center, with low dependence and high robustness, and can improve the cooperative decision-making ability and task execution efficiency of formation members under non-perfect information conditions in a complex environment.