39 results about "Fuzzy control algorithm" patented technology

This invention discloses a method for constant temperature and humidity control of a cigar cabinet based on a fuzzy control algorithm, comprising the following steps: setting a target temperature and humidity range; collecting environmental data of each layer through a distributed sensor array and comparing it with the target range to obtain the temperature and humidity deviation of each layer; inputting the deviation into a temperature and humidity decoupling control module and outputting a weight adjustment signal; inputting the weight adjustment signal into a fuzzy controller to construct a multi-objective fitness function, optimizing it with the WFPSO algorithm, and outputting hierarchical fuzzy controller parameters; inputting the hierarchical fuzzy controller parameters into a hierarchical temperature and humidity model to monitor the status of each layer in real time, and outputting a drive command when the limit is exceeded; inputting the drive command and hierarchical parameters into an actuator, adjusting it, and outputting new environmental data; and using a feedforward control module to adjust in advance when a door opening / closing disturbance warning is issued, dynamically adjusting the status of the affected space layer. This invention improves the temperature and humidity control accuracy and disturbance adaptability of the cigar cabinet through hierarchical optimization and feedforward intervention control mechanisms.

This invention relates to the field of intelligent commerce technology, and more particularly to an electromagnetic linkage-based vehicle cruise control system based on adaptive fuzzy control. The system includes: a control switch for receiving input commands from the driver, including commands to activate / deactivate cruise control, accelerate / decelerate, cancel, and resume cruise control; a central controller connected to both a vehicle speed sensor and the control switch, the central controller incorporating an adaptive fuzzy control algorithm to generate throttle control commands based on the deviation between the current vehicle speed and a set speed; a servo actuator electrically connected to the central controller; and a motor that receives commands from the central controller to drive a synchronous belt. This invention achieves automatic and precise throttle adjustment and stable cruise control in motor vehicles, solving the problems of driver fatigue and poor driving comfort caused by the need for continuous manual throttle control during long-distance driving.

The detection system of individual transcranial alternating current stimulation current amplitude threshold and frequency band range relates to the technical field of data identification, recording and processing in medical instrument and meter technology. It comprises: an upper computer which sends stimulation parameters to a stimulator, receives and stores detection information sent by the stimulator; a control keyboard which obtains stimulation sensitivity of an individual under current stimulation and transmits to the stimulator; and the stimulator which adjusts alternating stimulation current parameters, obtains a frequency band range supplement interval in a frequency adjustment stage, adjusts stimulation current amplitude value based on a fuzzy control algorithm according to a frequency band range proportion and stimulation sensitivity in an amplitude adjustment stage, and repeatedly and alternately carries out the frequency adjustment stage and the amplitude adjustment stage until the current amplitude threshold of the individual is detected or the upper limit of test time is reached. The present application is suitable for threshold detection under different frequency bands, and the current amplitude change is improved in two aspects of direction and size, which will improve the practicability and accuracy of the detection system.

The application belongs to the technical field of vacuum equipment maintenance, and specifically discloses a molecular pump automatic purging pre-cleaning system and method. The system comprises a detection module, a control module and an execution module. The detection module collects flow, pressure, temperature and vibration parameters in real time through various sensors, obtains a pollution index PI through normalization and weighted operation, and accurately determines the pollution grade. The control module combines PID and fuzzy control algorithms and dynamically generates cleaning instructions in combination with an adaptive learning strategy. The execution module uses high-purity inert gas to complete the purging operation. The application solves the problems of low efficiency, unstable effect, easy damage to equipment and poor universality of traditional manual cleaning, can automatically adjust the cleaning cycle according to the load of the molecular pump, and has good hardware and software compatibility. The scheme has high automation degree and good cleaning effect, can reduce operation and maintenance cost and prolong the service life of the equipment, and is suitable for high-vacuum scenes such as semiconductor manufacturing, vacuum coating and particle accelerators.

This invention discloses an intelligent control logic system for a side-discharge bucket, relating to the field of engineering machinery control technology. It includes a sensor module, an actuator, and a control module. The sensor module collects multi-dimensional data from the side-discharge bucket. The actuator drives the side-discharge bucket to rotate 0° to 90° around its axis, dumping material onto a conveying device, and simultaneously activates a stirring device to agitate the material and prevent clumping. The control module detects the initial states of the sensor module and the actuator, reads the multi-dimensional data to determine if the material weight is excessive, and then, based on the material's characteristics, introduces a fuzzy PID control algorithm to control the actuator. This invention is applicable to material handling equipment such as loaders, achieving efficient and precise side-discharge operations through automatic and manual dual-mode coordinated control.

The utility model relates to a kind of dosing device for intelligent wastewater treatment, to the problem of existing single parameter detection, rigid control and insufficient execution accuracy, provide integrated scheme of multi-parameter collaborative sensing, intelligent decision and accurate execution. Device includes distributed gas concentration sensor array, liquid concentration sensor group and pressure sensing unit, cooperate with neural network anomaly recognition submodule and fuzzy control algorithm submodule of intelligent analysis unit, realize multi-parameter coupling analysis;Dynamic dosing control module accurately executes instruction through at least three independent dosing channels High-precision metering pump and electromagnetic regulating valve;Feedback adjustment module constructs feedforward-feedback compound closed-loop control system, real-time correction decision model weight parameter;Drug storage container adopts anti-crystallization design and is equipped with automatic medicine replenishing system, remote monitoring terminal integrates data visualization, abnormal alarm and manual intervention function.

The application discloses a kind of AGV autonomous mapping and path planning method and system based on multi-sensor fusion, and it is related to robot navigation technical field.The method includes: obtaining environmental information by laser radar and depth camera and carrying out coordinate conversion;Multi-sensor data fusion is carried out using extended Kalman filter algorithm, and environment grid map is constructed based on fusion data, and map update is optimized using dynamic key frame selection strategy;Real-time positioning of AGV is realized based on Monte Carlo localization algorithm combined with adaptive particle sampling strategy;Global path planning is carried out based on improved multi-step A-Star algorithm, and the kinematic constraint of Mecanum wheel AGV is integrated into heuristic function;Fuzzy PID control algorithm is used for path tracking, and dynamic obstacle detection and local obstacle avoidance are carried out simultaneously.The application improves environmental perception ability through multi-sensor fusion, improves path quality and execution efficiency through improved path planning algorithm, and is suitable for AGV autonomous navigation in complex industrial environment.

This application discloses an automatic mixing and intelligent control method for marine fuel refueling enhancers, belonging to the field of marine fuel refueling technology. Based on the relationship between the main fuel flow fluctuation amplitude and a preset threshold, a PID control algorithm or fuzzy control algorithm is adopted. The atomization pressure threshold is calibrated based on the enhancer viscosity and nozzle diameter. The air pressure of the pneumatic diaphragm pump is adjusted first to meet the threshold, and then the opening of the adjustable proportional pneumatic regulating valve is fine-tuned to match the fuel flow ratio. When the fuel flow fluctuation reaches the compensation threshold, a gradual proportional correction strategy is initiated. When any core parameter deviates from the set range, a linkage control is triggered based on linear interpolation. After accumulating multiple batches of data, a dedicated operating condition parameter library is generated through improved K-means clustering and multiple linear regression analysis, achieving automatic matching of optimal control parameters when starting a new operating condition. This method achieves precise adaptive control of the enhancer ratio, efficient mixing uniformity, comprehensive safety protection, and intelligent closed-loop iteration of data.

This invention relates to the field of photovoltaic power generation technology, specifically to a photovoltaic-storage integrated power supply system and control method for a data center based on MPPT tracking. It includes: an MPPT intelligent tracking unit that works collaboratively with an improved perturbation observation method and a fuzzy control algorithm, and adaptively corrects the photovoltaic maximum power point reference voltage by combining a degradation compensation model established based on sunshine duration and the aging characteristics of photovoltaic modules; an energy storage adaptive management unit; and a data center load dynamic allocation unit. This invention uses the MPPT intelligent tracking unit to collect data such as the cumulative operating years and cumulative actual power generation of photovoltaic modules to calculate the module aging coefficient. It then dynamically corrects the perturbation step size of the improved perturbation observation method by combining real-time power changes of the photovoltaic array. Finally, through dual-algorithm collaborative scheduling and degradation compensation quantification, it integrates multiple parameters to adaptively correct the standard maximum power point reference voltage, effectively addressing the performance degradation problem of photovoltaic modules after long-term operation.

The present application relates to the technical fields of green mining and intelligent construction of mines, and discloses an underground intelligent material distribution and regulation system for coal gangue concrete, which comprises a three-stage warehouse structure of a storage warehouse, a preparation warehouse and a metering warehouse connected in sequence, and is matched with a high-precision weighing sensor, an online density detection device and a controllable precision gate. A central control unit acquires the material bulk density in real time according to the input target concrete proportioning, dynamically calculates and controls the volume through a fuzzy control algorithm, and adjusts the gate opening to realize the accurate proportioning of coal gangue aggregate and cementitious materials. The present application effectively solves the problems of inaccurate metering and out-of-control proportioning caused by the complex grading and large density fluctuation of underground gangue, improves the uniformity and strength stability of concrete preparation, supports the resource utilization of gangue in coal mines without ascending to the surface, and has the advantages of high automation, strong adaptability, high control precision and the like.

The application discloses an oil well variable domain fuzzy control separate production regulation method and device and a pipe column, and the method comprises the following steps: when producing fluid in a layer, opening a flow regulation valve, regulating the front course of the flow regulation valve to rapidly open to a basic opening degree, and the basic opening degree is smaller than a preset opening degree; comparing the actual fluid production flow of the layer at the basic opening degree with a target fluid production flow through a downhole flow meter, judging the difference between the actual fluid production flow and the target fluid production flow at the basic opening degree; obtaining an opening degree deviation value, obtaining a target flow regulation difference value and an opening degree adjustment value through a variable domain fuzzy control algorithm, and performing PID differential regulation; regulating the rear course opening degree of the flow regulation valve, repeating the regulation until the actual fluid production flow is the same as the target fluid production flow. The variable domain fuzzy control algorithm is adopted in combination with PID control, the opening degree of the flow regulation valve is continuously regulated, accurate regulation is realized, and stable oil production and yield increase are realized.

The application discloses a kind of investment casting water-soluble core sewage treatment method and device after core, belong to metal processing field, the method includes: collecting water-soluble core sewage;Through plate-and-frame filter press, remove suspended fiber and semi-solid impurities;Filter liquor is sent into low-temperature evaporation crystallization equipment, evaporates;Water vapor is condensed to obtain distilled water and is recycled;Concentrated liquid is collected as solid waste.The application also discloses a special device for realizing the method, including sewage collection tank, plate-and-frame filter press, intermediate storage tank, low-temperature evaporation crystallization unit and recycled water tank, and introduces intelligent control system, evaporates state is monitored in real time by liquid level, temperature, pressure sensor, controller uses fuzzy control algorithm to automatically adjust heater power and vacuum pump speed, maintains stable and efficient evaporation process.Significantly reduce hazardous waste treatment cost and fresh water consumption, with the advantages of energy saving and environmental protection, high degree of intelligence.

This invention aims to provide a smart battery control method for cold chain environments, comprising the following steps: A) Sensor data acquisition, real-time acquisition of ambient temperature T, ambient humidity H, condensate level W, battery voltage U, and battery temperature Tb; B) Data preprocessing; C) Setting preset thresholds, including temperature threshold, humidity threshold, SOC threshold, and insulation resistance threshold; D) Establishing a fuzzy rule base, inputting ambient temperature T, ambient humidity H, condensate level, alarm level, and BMS status into corresponding functions of the fuzzy rule base, outputting various control parameters for control by a controller, while simultaneously providing feedback on the status. An adaptive neural fuzzy control algorithm is used to correct and optimize the above functions in real time, achieving nonlinear dynamic regulation. The method of this invention can effectively solve the technical problems of battery range degradation, high short-circuit risk, and shortened lifespan in cold chain environments characterized by low temperature, high humidity, and easy condensation.

This invention belongs to the field of unmanned construction technology and discloses a collaborative intelligent unmanned control method and system for asphalt pavement paving equipment clusters. The method includes: integrating and outputting standardized sensing data streams; performing initial path planning based on the standardized sensing data streams and pre-set construction tasks; based on the initial path planning results and the standardized sensing data streams, invoking a multi-field coupling model, a load balancing strategy library, and a fuzzy PID control algorithm to calculate construction quality risk nodes, equipment collaborative status, and process parameter deviations in real time, generating a primary control instruction set; evaluating the collaborative relationship and optimizing the risk-benefit of the primary control instruction set, the standardized sensing data streams, and the material lifecycle traceability database to obtain an optimized control instruction set; and distributing the optimized control instruction set to the execution units of the paving equipment to perform collaborative operations. This invention significantly improves construction accuracy and effectively solves problems such as uneven accuracy in traditional construction methods.

This invention provides a central dynamic cooling system based on AI adaptive load prediction data, belonging to the field of dynamic cooling technology. It includes a load prediction module, a cooling decision module, a decision execution module, and a feedback optimization module. The load prediction module constructs a load prediction model based on a time-series attention mechanism, taking operating parameters and environmental parameters as input, and outputting load prediction results for a preset future time period. The cooling decision module constructs a cooling demand assessment system and generates adjustment schemes for dynamic cooling parameter combinations using a whale optimization algorithm. The decision execution module uses a fuzzy PID control algorithm to execute the dynamic cooling parameter adjustment schemes. The feedback optimization module corrects the parameters of the prediction model and decision algorithm through Bayesian inference. This invention achieves differentiated allocation of cooling resources through multi-dimensional perception and precise control, adapting to the differences in heat distribution in different areas of the data center, extending the service life of servers, and reducing the operation and maintenance costs of the data center.

This paper discloses a joint capacity estimation method based on the health status of energy storage batteries. The method first collects and preprocesses the operating and aging data of the energy storage batteries, and simultaneously divides the aging characteristic intervals of the battery health status. Then, a second-order Thevenin equivalent circuit model is constructed, and the model parameters are identified online using the recursive least squares method. Next, two-way capacity pre-estimation is completed by respectively using an improved adaptive extended Kalman filter algorithm and a trained and optimized gated recurrent unit (GRU) network. Finally, based on the aging characteristic intervals, the fusion weights of the two pre-estimation values ​​are dynamically adjusted using a fuzzy control algorithm, and the final usable capacity of the battery is output after weighted calculation. This invention combines the advantages of model-based and data-driven methods, solving the problems of large cumulative errors, unstable accuracy throughout the entire life cycle, and weak anti-interference ability of existing single methods. It can achieve online high-precision capacity estimation of energy storage batteries throughout their entire life cycle and under multiple operating conditions.

The present application relates to a kind of neural network-based denitration system prediction response control method and system, it is related to denitration control technical field, including NOx export concentration determination prediction model;According to the boiler load, flue gas flow and NOx inlet concentration determine normalization parameter and import prediction model, obtain ammonia nitrogen ratio optimal predicted value and NOx emission concentration predicted value and store in storage module;According to continuous time and the boiler load determination load change rate, according to NOx emission concentration predicted value and target emission limit value determine concentration prediction deviation value;By fuzzy control algorithm, obtain ammonia injection amount, hydrolysis reaction temperature adjustment amplitude and urea solution concentration adjustment amplitude;According to ammonia nitrogen ratio optimal predicted value and ammonia injection amount adjustment amplitude control ammonia injection unit, combine hydrolysis reaction temperature adjustment amplitude and urea solution concentration adjustment amplitude adjustment hydrolysis unit.The present application has the effect of reducing the probability that nitrogen oxide concentration is over standard.

The application discloses a multi-factor coordinated coal powder regulation system and method based on an external powder bin of a boiler, and relates to the technical field of thermal power generation. The system comprises a data acquisition module, an intelligent regulation module, a powder taking device and a powder feeding fan; the intelligent regulation module is connected with the data acquisition module, the powder taking device and the powder feeding fan; the data acquisition module is used for acquiring coal powder characteristic parameters, pipeline pressure parameters and conveying distance parameters; the intelligent regulation module is used for calculating the powder taking amount and the powder feeding speed through a fuzzy control algorithm or a neural network algorithm according to the coal powder characteristic parameters, the pipeline pressure parameters and the conveying distance parameters, controlling the powder taking device to take coal powder from the external powder bin of the boiler according to the powder taking amount, and controlling the powder feeding fan to convey the coal powder to the boiler according to the powder feeding speed. The system realizes accurate control over the powder taking and powder feeding processes.

This invention provides a speed identification method for a three-phase asynchronous motor based on sensorless vector control, comprising: establishing a mathematical model of the three-phase asynchronous motor; determining the parameter matrix to be identified; defining the observation length, neuron factor, and initializing the model reference adaptive covariance matrix P(N); generating the observation matrix and its transpose matrix; calculating the current-time model reference adaptive covariance matrix P(N); using a fuzzy control algorithm to calculate the gain matrix K(N-1) of the previous time step; updating the estimated values ​​of the parameters to be identified; and updating the objective function value J. t (θ). This invention effectively reduces torque ripple, enabling a three-phase asynchronous motor to smoothly transition from low speed to high speed operation. Current ripple is significantly reduced, improving the system control performance of the three-phase asynchronous motor under varying load conditions. The technical solution of this invention addresses the technical problems of high parameter sensitivity and poor disturbance rejection capability in traditional model reference adaptive methods, as well as the difficulty in adjusting the parameters of traditional PID controllers for the speed loop.

The application relates to the technical field of ultrasonic riveting, and relates to a 224G high-speed wire harness assembly method and system based on ultrasonic riveting, which comprises the following steps: pretreating high-speed wire harness raw materials to obtain pre-riveting wire harness; aligning the pre-riveting wire harness with a pre-constructed target connector to obtain a wire harness to be riveted; riveting the wire harness to be riveted by using ultrasonic parameter values, environmental temperature values and riveting time, monitoring the wire harness to be riveted in real time based on a riveting monitoring instruction, obtaining a compression offset value and an energy absorption value; obtaining an updated ultrasonic frequency value by using a fuzzy control algorithm based on the compression offset value and the energy absorption value, obtaining a pre-confirmed high-speed wire harness by using the updated ultrasonic frequency value; performing quality detection on the pre-confirmed high-speed wire harness to obtain a target high-speed wire harness, and realizing the assembly of the high-speed wire harness based on the target high-speed wire harness. The application can realize high-precision assembly of high-speed wire harness by using ultrasonic riveting.

The application provides a slope automatic obstacle avoidance and speed control system and method of an electric wheelchair, and relates to the field of control systems.The control system comprises a driving module, an automatic obstacle avoidance module, a self-balancing controller module, a speed sensor module, a heart rate detection module, an alarm module, a speed reduction module and a central processing module.The driving module, the automatic obstacle avoidance module, the self-balancing controller module, the speed sensor module, the heart rate detection module, the alarm module and the speed reduction module are electrically connected with the central processing module.The application can remind the passenger to avoid the road section that the electric wheelchair cannot climb in advance, estimate the speed after 2s by measuring the acceleration and real-time speed, reduce the speed in advance before reaching the upper limit of the wheelchair climbing speed, measure the distance of the obstacle by ultrasonic sensors and infrared sensors, realize automatic obstacle avoidance by a fuzzy control algorithm, and realize the slope stability of the wheelchair by the self-balancing control module.

The application discloses a kind of control system and method of ecological discharge flow intelligent gate of hydropower station, it is related to the technical field of hydropower station intelligent control, including, real-time acquisition ecological hydraulic operation data, pre-processing is carried out, and using LSTM model predicts downstream ecological water demand prediction curve;Ecological water demand prediction curve and the ecological hydraulic operation data after pre-processing are combined, and the rule reasoning of fuzzy PD+I control algorithm is carried out to obtain the preliminary control parameter set of gate;By comparing the safety operation constraint condition of gate through numerical constraint analysis method, boundary mapping and smooth adjustment are carried out, and the constraint compliance gate control parameter set is obtained;Based on constraint compliance gate control parameter set and ecological water demand prediction curve, through digital twinborn model, rapid simulation verification is carried out, and the gate control parameter set that is verified is passed;The application is based on the fusion of prediction curve and real-time data by fuzzy PD+I control algorithm, realizes the efficient unity of ecological protection target and gate operation safety.

This invention relates to a pure hydrogen gas stove with precise control of the hydrogen-air premixing ratio. It includes an electronically controlled pressure regulating valve, a fan, an expansion bladder, a pressure chamber, a constant pressure valve, an electromagnetic flow valve, a check valve, a gas turbulence device, a gas mixer, a gas mixing layer, a flow stabilizing chamber, a backfire prevention support layer, a gas preheating layer, a pre-combustion layer, an ignition surface, and a combustion radiation layer. Through the combined action of the electronically controlled pressure regulating valve, the expansion bladder, and the constant pressure valve under controller monitoring, the gas is kept at a constant pressure and introduced into the pipeline in a predetermined ratio, thus precisely controlling the hydrogen-air mixing ratio. Air then enters the mixer via the gas turbulence device and undergoes preliminary mixing with hydrogen before entering the stove body in a turbulent flow. The gas mixture layer, with its gradual design, fully mixes the gas before reaching the combustion layer. A fuzzy control algorithm is used to achieve real-time and precise control of the adjustment range of the electronically controlled valve and the fan, avoiding imbalances in the gas premixing ratio caused by valve and fan speed adjustments.

This invention discloses a method for controlling the stability of rear-wheel steering vehicles, comprising: 1. establishing a three-degree-of-freedom dynamic model and a magic tire model to construct a basic vehicle model; 2. designing a hierarchical coordinated control architecture for active rear-wheel steering and direct yaw moment; 3. constructing a normalized stability index S by dividing the upper layer into stable, unstable, and coordinated control regions based on phase plane theory. index The invention employs a fuzzy control algorithm to dynamically allocate control weights. The lower layer optimizes the rear wheel steering angle through model predictive control, combining sliding mode control and quadratic programming algorithms to achieve precise decision-making and allocation of yaw moment. Simulations under dual lane change, serpentine, and sinusoidal conditions have verified that this invention can accurately track the ideal yaw rate, effectively suppress the center of gravity sideslip angle, and reduce longitudinal speed fluctuations, thereby significantly improving vehicle handling stability under extreme conditions such as low-adhesion surfaces and high-speed, large-turn maneuvers.

The application discloses a GIS mixed gas supplementing self-adaptive control method, system, equipment and medium, relates to the GIS supplementing control technical field, and realizes the deep perception and early warning of the gas state through the multi-source data fusion trend prediction, and changes the passive supplementing to the active prevention. The self-adaptive control method adopts the fuzzy PID control algorithm, finely adjusts the controller parameters according to the deviation, the deviation change rate and the equipment load current, utilizes the predicted gas leakage rate as a feedforward signal to compensate the leakage amount, finally makes the pressure stable at the dynamic pressure set point, and the gas proportion is always kept constant. The whole process is smooth and impact-free, can adapt to different leakage rates, environmental conditions and equipment load changes, and has high robustness. In addition, the self-adaptive control method also adopts the matching strategy based on the mass flow control, ensures that the pressure and proportion of the supplemented gas reach the optimal set values.

The present application belongs to the technical field of organic fertilizer production, and discloses a rapid fermentation system for organic fertilizer, which comprises a closed fermentation tank, a central screw stirring device for vertically lifting materials and a multi-layer tangential aeration device for forming horizontal rotating airflow are arranged in the closed fermentation tank, and the two devices work together to make the materials in a three-dimensional spiral fluidized state; an intelligent control unit which is based on the parameters collected by sensors and their change rates, and uses a fuzzy control algorithm to predictively and adaptively regulate the fermentation process; and an integrated circulation system which re-mixes the collected percolate into the aeration airflow through atomizing injection devices, and preheats fresh intake air through a heat exchanger using the discharged high-temperature waste gas. Through the collaborative innovation of structure and control, the present application realizes efficient and uniform fermentation of the materials, and completes the closed-loop circulation of energy and nutrients, and has the advantages of fast fermentation speed, low energy consumption and no secondary pollution.

The application relates to an adhesive tape conveying and curing optimization method for an oven in the field of intelligent manufacturing, which comprises the following steps: acquiring real-time position data, material parameter and adhesive tape surface temperature distribution data in the adhesive tape conveying process to obtain initial temperature field data; detecting temperature abnormal area and classifying abnormal types according to the initial temperature field data to obtain abnormal category labels and real-time position prediction sequences of the abnormal area; determining regional hot air control instructions according to the initial temperature field data to obtain heat distribution states by adopting a partitioned hot air control algorithm; dynamically adjusting oven heat source power according to the updated heat distribution states to obtain optimized temperature gradients by adopting a fuzzy control algorithm; real-time updating flow velocity and flow direction parameters of a hot air circulation system according to the optimized temperature gradients to obtain a stable adhesive tape curing temperature field; and adjusting the running state of the hot air circulation system according to the final curing parameters and real-time monitoring adhesive tape surface bonding strength to obtain consistent curing quality data.

The application discloses a kind of cross-belt sorting machine's upper package control method and system, the method includes the following steps: package is placed in upper package table, and the weighing device of upper package table is weighed to package;Package is transported to acceleration section;Wait for upper package instruction;Fuzzy control algorithm is used to transport package from acceleration section to uniform speed section;Package is transported from uniform speed section to sorting tray.The fuzzy control algorithm is used, according to the package of different weights, dynamically adjust the speed, acceleration and deceleration of upper package table transport, ensure that sorting tray can reliably, accurately transport the package of different weights to corresponding sorting tray under the condition that guide rail is at high speed, improve the reliability of upper package, upper package precision and efficiency.