21 results about "Fuzzy method" patented technology

The present invention discloses a fuzzy interval analysis method for assembly deviation of aerospace products based on Jacobian spinors, which includes: establishing an assembly connection relationship diagram of product assembly; combining the structural dimensions of the product and the position of the coordinate system to obtain the Jacobian matrix of each functional feature; characterizing the deviation of each functional feature of the product based on the spinor method, and expressing it in the form of an interval; using a fuzzy method to discretize the deviation interval into confidence intervals of deviation sources under different confidence levels, and jointly establishing a Jacobian matrix to predict the deviation interval of the assembly function requirements of the final product under different confidence levels; establishing a deviation contribution calculation model to calculate the contribution value of each deviation source to the deviation of the assembly function requirements. The method can predict the possible interval of the deviation of the assembly function requirements in the actual assembly process according to the calculation results, and at the same time reasonably select the deviation source combination under different confidence intervals according to the deviation of the assembly function requirements, so as to minimize the manufacturing cost while ensuring the assembly accuracy.

The invention provides a traffic special bottleneck monitoring method based on multi-source road data, and the method comprises the following steps: S1, collecting road data of a plurality of intelligent network connection data clients, and building a road information database of different road segments; s2, performing precision complementation and error ablation on the road information of the same road section of a plurality of intelligent network connection data clients, outputting multi-source road information, and calculating overall evaluation parameters of multi-dimensional deep road section ablation; s3, calculating a road data fuzzy matrix; s4, setting and calculating the critical entropy of the traffic event; calculating a fuzzy entropy in combination with the multi-source road information and the road data fuzzy matrix; and when the fuzzy entropy is greater than the critical entropy, constructing a special event list, and listing the special event list for continuous tracking. Through the multi-dimensional multi-source deep road data ablation algorithm, the deep road data fuzzy method and the road data fuzzy entropy fluctuation recognition algorithm, the accuracy of monitoring the special traffic events is improved from the way of processing the multi-source road data.

The invention relates to the technical field of wireless power transmission, in particular to a fuzzy PID wireless power transmission control method, system and device based on load estimation, and the method comprises the steps: measuring an output voltage and an output current, and estimating the load information of a wireless power transmission line; an equivalent circuit model is constructed based on the load information, and the relation between the output active power of the full-bridge inverter and the load is established; monitoring load information in real time, identifying system interference and load change according to a preset change rate threshold value, and judging whether to execute fuzzy PID self-tuning control or not; when fuzzy PID self-tuning control is executed, fuzzy control rules are established by fuzzifying the input quantity error and the error change rate; and performing fuzzy reasoning according to a fuzzy control rule to obtain a control quantity, and generating a corrected PID control parameter through a defuzzification method. According to the invention, the problem of limitation of a traditional PID control method in a wireless power transmission system when facing nonlinearity, dynamic change and interference is effectively solved.

The invention discloses a circular array interferometer ambiguity resolution method based on adaptive angle clustering, and the method comprises the steps: firstly constructing a two-dimensional uniform circular array interferometer model, and calculating the position of each antenna array element; secondly, two units are randomly selected from the uniform circular array to form base lines, the fuzzy phase difference and the maximum fuzzy number of each base line are calculated, two base lines are randomly selected to form double-base-line combinations, each double-base-line combination is traversed, the azimuth angle and the pitch angle are calculated, and an angle matrix is formed; then, a neighborhood radius parameter of a DBSCAN clustering algorithm is set according to the input frequency, clustering analysis is carried out on the angle matrix, and a cluster with the maximum density is selected; and finally, calculating the average value of the data in the maximum density cluster to obtain the azimuth angle and the pitch angle of the target. According to the method, the correct ambiguity resolution probability and the direction finding precision of the two-dimensional circular array interferometer can be effectively improved.

The present application relates to micro energy network multi-objective optimization scheduling model, including: for micro energy network, establish multi-objective optimization scheduling model;Improved weighted fuzzy method is constructed;Specifically, including: constructing membership function, each sub objective function is fuzzy;According to the actual operation of micro energy network, determine the weight coefficient of each sub objective function at different time;The multi-objective optimization scheduling model is converted into single objective optimization scheduling model;Solve through traditional nonlinear optimization theory.The present application, improved weighted fuzzy method, the membership function and the weight setting of multi-objective function are optimized, the comprehensive coordination between multi-objective is improved, and the robustness of the algorithm is also improved, and the optimization scheduling model achieves the purpose of optimizing the output of each device in the operation process of micro energy network.

The invention discloses a dosage self-adaptive control method and device based on multi-modal recognition, and belongs to the technical field of mode recognition and flotation dosing, and the method comprises the steps: carrying out the real-time recognition of a feeding coal quality image through a trained coal quality recognition model, judging a multi-modal working condition according to a recognition result, and then combining with a preset rule, and calculating the corresponding initial dosage. Key characteristics such as the tailing ash content, the tailing white foam amount and the tailing rough running condition are collected in real time, interval division and weighted calculation are conducted through a triangular membership fuzzy method, and the agent compensation amount is dynamically optimized. And timely transmitting a dosing amount decision value calculated based on the initial dosing amount and the comprehensive medicament compensation amount to an intelligent dosing station to complete closed-loop operation of dosing control. According to the method, the feeding coal quality and the tailing condition are comprehensively considered, accurate calculation of the dosage and real-time feedback of the control decision under the complex working condition are achieved, and stable operation of the flotation technology is guaranteed.

The invention relates to a tubular reactor temperature control method under the perspective of a singular partial differential equation. The method comprises the following steps: establishing a tubular reactor temperature concentration reaction rate system model described by a singular partial differential equation system; simplifying the temperature concentration reaction rate system model of the tubular reactor into a singular partial differential equation system; carrying out approximate linearization on the singular partial differential equation system through a fuzzy method, and designing an integral sliding mode surface containing a singular matrix; designing a sliding mode controller; and respectively analyzing the sliding mode motion accessibility and the index tolerance of the singular partial differential equation system based on a Lyapunov method to obtain a sliding mode controller gain, and applying the sliding mode controller gain to the sliding mode controller to complete the control of the temperature of the tubular reactor. According to the method, the defect that a traditional bivariate model cannot explicitly represent dynamic coupling of the reaction rate can be thoroughly overcome, the inhibition capability on the temperature runaway phenomenon is improved from the source, and the safety accident risk is remarkably reduced.

The invention discloses a construction and control method of a land pollution abatement system, and belongs to the technical field of environmental pollution abatement, and the method comprises the steps: constructing a land pollution abatement model described by a singular partial differential equation; the model is converted into a control system with a movable sprayer as an original point through coordinate transformation; carrying out approximate linearization on a nonlinear term in the system by utilizing a T-S fuzzy method, and designing an interval observer and a controller capable of estimating upper and lower bounds of a system state based on the approximate linearization; the bounded tolerance of the system is analyzed based on the Lyapunov stability theory, the gain of an interval observer and the gain of a controller are obtained by solving a linear matrix inequality, and the gains are applied to the designed observer and the designed controller to complete closed-loop control. According to the method, unknown soil conditions and external interference can be effectively handled, the control robustness is ensured through interval estimation, the limitation that a traditional model only depends on a partial differential equation is avoided, and accurate and stable treatment on polluted land is achieved.

The invention provides a multi-vehicle collaborative operation-oriented traction type AGV hinge angle robust estimation method, and belongs to the technical field of intelligent transportation AGV state observation. Firstly, in order to improve the adaptive capacity of an observer when facing the uncertain parameters of the traction-type AGV, especially for the time-varying longitudinal speed of the traction-type AGV and the trailer mass, a T-S fuzzy model is constructed by adopting a T-S fuzzy method, so that all possible uncertain parameters can be covered; secondly, in order to save communication resources and reduce the calculation burden of an AGV controller, a DETM is provided between a sensor and an observer. Finally, on the basis, an H-infinity robust hinge angle observer is provided, the observer and DETM are designed in a collaborative mode in combination with a fuzzy Lyapunov functional method and an LMI technology, and therefore the robustness of the observer is remarkably improved. According to the method, the robustness problem in hinged angle estimation of the traction type AGV can be effectively solved, and the reliability and stability of multi-vehicle collaborative operation are further improved.

The present invention discloses a method and device for adaptive control of dosing amount based on multimodal recognition, which belongs to the field of pattern recognition and flotation dosing technology. The method includes using a trained coal quality recognition model to perform real-time recognition of the feed coal quality image, and after determining the multimodal working condition according to the recognition result, combining it with the preset rules to calculate the corresponding initial dosing amount. By collecting key features such as tailings ash content, tailings white foam volume, and tailings coarseness in real time, the triangle membership fuzzy method is used to perform interval division and weighted calculation to dynamically optimize the reagent compensation amount. The dosing decision value calculated based on the initial dosing amount and the comprehensive reagent compensation amount is transmitted to the intelligent dosing station in a timely manner to complete the closed-loop operation of dosing control. The present invention comprehensively considers the feed coal quality and tailings conditions, realizes the accurate calculation of dosing amount and real-time feedback of control decision under complex working conditions, and ensures the stable operation of the flotation process.

This invention proposes a dynamic scene deblurring method and system based on 4D Gaussian representation and pseudo-ground value supervision. The method includes: obtaining a sharp image and a rendered depth map from a 4D Gaussian representation; predicting the motion velocity of dynamic pixels using a velocity MLP network based on the rendered depth map; constructing a fuzzy weight network and predicting the contribution weight of each sampling point on the sampling trajectory; fusing the pseudo-sharp image with the original blurred input using a dynamic region mask to obtain a hybrid pseudo-ground value image; synthesizing a physically blurred image through weighted integration; and constructing a dual-domain reconstruction loss and geometry-motion regularization constraints by combining hybrid pseudo-ground value supervision and gradient decoupling strategies to jointly optimize the scene representation, motion parameters, and fuzzy model, thereby obtaining a sharp dynamic scene representation. This invention achieves explicit modeling of the physical blurring process through 4D Gaussian representation and a fuzzy weight network, improving the realism and view consistency of motion blur synthesis.

The invention provides a time difference constraint-based multi-carrier frequency phase difference ambiguity resolution method, which belongs to the field of radar arrival phase difference positioning and comprises the following steps of: designing an A group of uniform carrier frequency sequences and a B group of uniform carrier frequency sequences; respectively recording phase difference observation and time difference observation between a receiving station i and a receiving station j of the distributed radar system under the A group of carrier frequency channels and the B group of carrier frequency channels; obtaining an actual distance difference between a target and a receiving station i and an actual distance difference between the target and a receiving station j according to time difference observation, and further obtaining an inter-station phase difference fuzzy number possible value set; respectively constructing a least square cost function related to phase difference observation and fuzzy number combination under the A group of carrier frequency channels and the B group of carrier frequency channels, and selecting the fuzzy number combination enabling the cost function to be minimum as a fuzzy number solving result; and fusing the fuzzy number solving results obtained in the A group of carrier frequency channels and the B group of carrier frequency channels to obtain a final ambiguity solving result. The method is high in solving precision, high in anti-noise performance and low in calculation complexity.

The invention provides a fuzzy risk assessment model for off-site construction, and relates to the technical field of off-site construction risk assessment. The method comprises the following steps: firstly, identifying potential risk factors related to off-site construction by adopting a Delphi method; then, an interval value intuitionistic fuzzy IVIF-DEMATEL method is used in combination with Choquet integration, the relation between adopted risk factors ARFs is analyzed, and the method comprises the steps of data collection, decision maker weight determination, matrix construction and the like; and finally, determining the individual weight of each decision maker by using an intuitionistic fuzzy TOPSIS method, carrying out aggregation evaluation to construct a matrix, calculating an ideal solution, a distance index and a proximity coefficient, and carrying out priority ranking on risk factors. According to the method, the defects of a traditional risk assessment model are effectively overcome, and the complexity and uncertainty of off-site construction risks are comprehensively considered. By integrating multiple methods, the key risk factors and the interrelation thereof can be identified more accurately, a scientific and comprehensive risk assessment basis is provided for decision makers, and making of a more effective risk coping strategy is facilitated.

The present invention discloses a multi-agent pursuit-evasion game method and device based on reinforcement learning, which relates to the field of artificial intelligence technology. The present invention realizes the generation of strategies for multi-agent pursuit-evasion games through self-play. Based on the game data of multi-agent pursuit-evasion, by using fuzzy learning and Q-learning for the exploration and exploitation of the environment, it can autonomously generate optimal game strategies. Moreover, the present invention reasonably partitions the state-action space by using a fuzzy method. The Nash equilibrium solution generated according to the rules has global optimality and robustness. The local Q-value table composed of the adjacent states of the current state avoids the curse of dimensionality problem caused by the continuous state space.

The invention provides a fuzzy method for determining an optimal evacuation strategy of a storm, and relates to the technical field of natural disaster assessment, and the method comprises the steps: obtaining an initial intuitionistic fuzzy set through normalization processing based on an alternative scheme and an evaluation standard of a storm emergency decision; based on the initial intuitionistic fuzzy set, obtaining a standard intuitionistic fuzzy weight through calculation; summarizing the initial intuitionistic fuzzy sets to obtain a collective intuitionistic fuzzy decision matrix; performing weighting processing on the collective intuitionistic fuzzy decision matrix by using the standard intuitionistic fuzzy weight to obtain an intuitionistic fuzzy evaluation result of the alternative scheme; and based on the intuitionistic fuzzy evaluation results of the alternative schemes, sorting the alternative schemes to obtain a storm emergency decision result, and completing fuzziness for determining the optimal evacuation strategy of the storm. According to the method, the problem that a feasible emergency decision is difficult to provide for an unconventional sudden storm event is solved.

The invention provides a safe operation assessment method for a new energy power system, and the method comprises the steps: constructing an SWOT matrix based on an SWOT analysis method, and determining the advantages, disadvantages, opportunities and threat factors of the new energy power system; based on a fuzzy AHP method, constructing a hierarchical structure model, obtaining expert judgment, establishing a fuzzy pairwise comparison matrix, and calculating a weight value of each SWOT factor; based on a fuzzy MARCOS method, determining an evaluation standard, obtaining fuzzy judgment of experts on the improved strategies, calculating a weighted fuzzy matrix, and sorting the improved strategies through a utility function; and comprehensively considering the utility value of each improvement strategy, and evaluating the safe operation of the new energy power system. By combining SWOT analysis, fuzzy AHP and fuzzy MARCOS methods, the new energy power system can be comprehensively evaluated from multiple dimensions, not only are internal and external factors of the system considered, but also advantages and disadvantages of different improvement strategies are compared, and comprehensiveness and objectivity of an evaluation result are ensured.

The application discloses a state interval estimation method for activated sludge treatment process based on an interval observer. Considering a large amount of uncertainty existing in a sewage treatment process, the application studies state interval estimation of an activated sludge system composed of an aeration tank and a sedimentation tank. Firstly, a mathematical model is established for a dynamic process of activated sludge reaction. Secondly, a T-S (Takagi-Sugeno) fuzzy method is used to perform pseudo-linearization processing on the established nonlinear model, so that a T-S fuzzy system is obtained, and the complexity of the model is reduced. Finally, an interval observer is designed for the T-S fuzzy model, the interval observer has interference robustness, and through the interval observer, the upper limit and the lower limit of the state of the activated sludge treatment process can be estimated, thereby providing a new thought and method for state monitoring of the activated sludge treatment process.

This invention relates to the field of wireless power transfer technology, and more particularly to a fuzzy PID wireless power transfer control method, system, and apparatus based on load estimation. The method includes: measuring output voltage and output current to estimate load information of the wireless power transfer line; constructing an equivalent circuit model based on the load information to establish the relationship between the output active power of the full-bridge inverter and the load; monitoring load information in real time and identifying system interference and load changes according to a preset rate of change threshold to determine whether to execute fuzzy PID self-tuning control; when fuzzy PID self-tuning control is executed, establishing fuzzy control rules by fuzzifying the output error and error rate of change; obtaining the control quantity through fuzzy inference based on the fuzzy control rules, and generating corrected PID control parameters through a defuzzification method. This invention effectively solves the limitations of traditional PID control methods in wireless power transfer systems when facing nonlinearity, dynamic changes, and interference.

The invention relates to the technical field of dam safety, in particular to a dam site area seismic intensity calculation method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining seismic intensity data; presetting a membership function of each evaluation factor in the seismic intensity data to an evaluation target, and constructing a fuzzy relation matrix; based on the fuzzy relation matrix, obtaining an evaluation factor fuzzy vector; performing fuzzy discrimination based on the evaluation factor fuzzy vector to obtain a seismic intensity fuzzy reasoning relation; and performing multi-level evaluation on the fuzzy reasoning relationship to obtain the final seismic intensity. Based on the relationship between seismic oscillation parameters such as seismic oscillation frequency spectrum, amplitude and duration and seismic intensity, the high concrete dam intensity is quickly calculated, a fuzzy method is adopted to obtain the relationship between the intensity and each related physical quantity, judgment results of different factors are integrated to obtain a seismic intensity value, and the seismic intensity is calculated. Complete analysis of the relationship between the seismic oscillation parameter and the seismic intensity is realized, and the seismic intensity encountered by the dam is accurately reflected.

The invention relates to the technical field of passive positioning, and discloses a three-satellite time difference positioning method, system and device for a high-repetition-frequency target and a medium, and the method comprises the steps of information acquisition, time difference classification and preliminary positioning, ambiguity resolution positioning and result integration output. According to the method, time difference classification and preliminary positioning are carried out, the repeatability of pulse numbers is taken as a judgment basis, time delay difference data are clearly divided into a fuzzy pulse set and a non-fuzzy pulse set, a positioning result is directly generated for non-fuzzy pulses, and invalid processing is avoided; and for the fuzzy pulse, a pulse cluster of a real target is accurately focused through a flow of time difference window straight grid division-time difference number statistics-effective straight grid screening. By means of signal classification processing and multi-target sequential processing, the ambiguity resolution method for the high-repetition-frequency target in the satellite view field range can be achieved, and therefore multi-target high-reliability positioning is achieved.

This invention discloses an intelligent diagnosis method for subway fans based on multi-classification SVM information perception. The steps are as follows: vibration signals are collected via vibration sensors installed on fans within stations; the vibration signals are subjected to Fourier analysis to obtain a spectrum; fuzzy methods are used to further divide the signal frequencies and extract the frequency distribution based on expert knowledge; a support vector machine model is trained using the generated historical data; and the vibration frequency signals are monitored in real time using the support vector machine model. This method enables online monitoring of subway fans, quickly identifying fault types and providing alarms, providing maintenance personnel with maintenance and repair advice, and, to a certain extent, reducing unplanned downtime in rail transit, increasing the safety and cost-effectiveness of equipment operation, and improving equipment utilization.