186 results about "Fuzzy inference system" patented technology

A Soft Computing (SC) optimizer for designing a Knowledge Base (KB) to be used in a control system for controlling a motorcycle is described. In one embodiment, a simulation model of the motorcycle and rider control is used. In one embodiment, the simulation model includes a feedforward rider model. The SC optimizer includes a fuzzy inference engine based on a Fuzzy Neural Network (FNN). The SC Optimizer provides Fuzzy Inference System (FIS) structure selection, FIS structure optimization method selection, and teaching signal selection and generation. The user selects a fuzzy model, including one or more of: the number of input and/or output variables; the type of fuzzy inference; and the preliminary type of membership functions. A Genetic Algorithm (GA) is used to optimize linguistic variable parameters and the input-output training patterns. A GA is also used to optimize the rule base, using the fuzzy model, optimal linguistic variable parameters, and a teaching signal. The GA produces a near-optimal FNN. The near-optimal FNN can be improved using classical derivative-based optimization procedures. The FIS structure found by the GA is optimized with a fitness function based on a response of the actual plant model of the controlled plant. The SC optimizer produces a robust KB that is typically smaller that the KB produced by prior art methods.

The invention discloses a self-adaptive tracking loop, which comprises an unscented Kalman filter (UKF), an observation noise variance matrix detection module, a fuzzy inference system, an unscented transformation (UT) scale factor regulation module, a state compensator, a carrier wave numerical controlled oscillator (NCO), scale factors, a code NCO, an integration and zero-clearing module, a code loop phase discriminator and a second order code loop filter, and additionally discloses an implementation method for the self-adaptive tracking loop. The implementation method comprises a step 1 ofsignal correlation, integration and zero clearing; a step 2 of code phase tracking; a step 3 of UKF modeling; a step 4 of observation noise variance matrix estimation; a step 5 of process noise variance matrix estimation; a step 6 of UT scale factor regulation; a step 7 of state estimation deviation compensation; and a step 8 of assistance of the carrier wave NCO in the code NCO. According to theself-adaptive tracking loop, the UKF, the observation noise variance matrix detection module and the fuzzy inference system are designed in the carrier tracking loop, so not only can a contradiction between thermal noise vibration in the tracking loop and a dynamic stress error be solved, but a process noise variance matrix and an observation noise variance matrix can be regulated in a self-adaptive manner according to changes of the external environment, and thereby the self-adaptive ability of the tracking loop under complex changeable environments of high dynamic, strong interference, and the like is effectively improved.

The invention relates to a power distribution network fault classification method based on the adaptive neuro-fuzzy inference system. The method is an improved method based on the adaptive neuro-fuzzy inference system. According to several frequently-occurring short circuit fault types of the power distribution network, a hierarchical based adaptive neuro-fuzzy inference system is constructed in the method, various short circuit faults are simulated based on a simulation software and the fault phase current is collected as the training sample data, and the blended learning algorithm is used for training the constructed hierarchical adaptive neuro-fuzzy inference system to determine the parameter in the system; the hierarchical adaptive neuro-fuzzy inference system with the determined parameter can be used for discriminating the fault types of the power distribution network. A lot of simulation data validations indicate that the classification method provided by the invention has a higher classification and identification accuracy, and has a better robustness on the variation of the fault points and a strong adaptability on the variation of the network topology.

A Soft Computing (SC) optimizer for designing a Knowledge Base (KB) to be used in a control system for controlling a suspension system is described. The SC optimizer includes a fuzzy inference engine based on a Fuzzy Neural Network (FNN). The SC Optimizer provides Fuzzy Inference System (FIS) structure selection, FIS structure optimization method selection, and teaching signal selection and generation. The user selects a fuzzy model, including one or more of: the number of input and/or output variables; the type of fuzzy inference model (e.g., Mamdani, Sugeno, Tsukamoto, etc.); and the preliminary type of membership functions. A Genetic Algorithm (GA) is used to optimize linguistic variable parameters and the input-output training patterns. A GA is also used to optimize the rule base, using the fuzzy model, optimal linguistic variable parameters, and a teaching signal. The GA produces a near-optimal FNN. The near-optimal FNN can be improved using classical derivative-based optimization procedures. The FIS structure found by the GA is optimized with a fitness function based on a response of the actual suspension system model of the controlled suspension system. The SC optimizer produces a robust KB that is typically smaller that the KB produced by prior art methods.

The invention relates to a parking lot reverse car seeking management system based on fuzzy positioning and an implementation method thereof. The parking lot reverse car seeking management system comprises an image capture device arranged on a traffic lane of a parking lot, a parking lot central database server connected with the image capture device, and intelligent car seeking query system terminals arranged at pedestrian exits / entrances of the parking lot. The intelligent car seeking query system terminals are all in communication connection with the parking lot central database server. The image capture device comprises a camera and an image recognition module, wherein the camera is arranged above the traffic lane and connected with the image recognition module, and the image recognition module is connected with the parking lot central database server. The parking lot central database server comprises a fuzzy inference system used for storing parking information and conducting search for parking spaces. Each intelligent car seeking query system terminal comprises a fuzzy query module, a printing module and a touch display unit, wherein the fuzzy query module, the printing module and the touch display unit are all in communication with the parking lot central database server. The parking lot reverse car seeking management system based on fuzzy positioning and the implementation method reduce the number of image capture devices and lower operation and maintenance cost.

Te invention discloses a battery SOC estimation method applying multiple models parallelly. The method includes following steps: 1), acquiring battery state parameters; 2), normalizing the battery state parameters; 3), respectively substituting the battery state parameters after being normalized into a genetic algorithm optimized BP neural network estimation model, a self-adaptive neural-fuzzy reasoning system model and an OS-ELM neural network model to acquire three SOC estimation results; 4), according to a SOC-OCV relation, acquiring initial estimation voltage values respectively corresponding to the three SOC estimation results acquired in the step 3); 5), respectively calculating difference values between the initial estimation voltage values and voltage, and normalizing the difference values to acquire weighting coefficient of the initial estimation voltage values; 6), calculating a final estimated value of SOC according to the weighting coefficient. By utilizing three importantparameters of a battery, using the three models parallelly, using multiple linear system estimation results to describe a nonlinear system and then weighting, summing and estimating the battery SOC value, estimation accuracy is improved effectively.

The invention discloses a device and method for suppressing subsynchronous oscillation of a power system. The method comprises the following steps of: firstly, filtering the rotation speed signal of a generator to obtain the subsynchronous rotation speed signal of each mode; processing the subsynchronous rotation speed signal of each mode respectively to obtain a change rate; then, generating an additional control signal through a Sugeno type fuzzy reasoning system; and finally, performing amplification, overlapping and amplitude limiting on the obtained additional control signal, and generating an exciting voltage additional control signal so as to change the exciting current, generate a subsynchronous frequency damping torque and suppress the subsynchronous oscillation. In the method provided by the invention, a training sample of a fuzzy controller is established according to the phase compensation principle, and the parameters of the fuzzy system are optimized and trained by use of a learning algorithm of an error backpropagation neural network. The method solves the problem that the expert experience is difficult to obtain by the fuzzy controller, and the additional exciting damping controller can effectively suppress the subsynchronous oscillation of the power system.

The invention provides a multi-robot angle control surround method based on a fuzzy inference system. According to the method, a multi-robot surround strategy is realized by adopting two layers of fuzzy inference; the first layer of fuzzy inference system is a decision layer which is used for identifying the state of a surround task and selecting a corresponding multi-robot strategy; when surround persons are in the search state, the decision layer outputs Search through fuzzy inference, and the surround persons perform the search strategy; when the surround persons are in the approach state, the decision layer outputs Approach, i.e. the surround persons perform the approach strategy; and when the surround persons are in the surround state, the decision layer outputs Surround, and the surround persons perform the surround strategy. The experiment is performed by using the simulation programs, the environment of the simulation programs is proportionally reduced according to the parameters in the actual environment, and movement of robots meets the kinematic model constraint. Multiple times of the simulation experiment is performed under different initial conditions so that feasibility of the algorithm is verified and great effect is achieved.

The invention discloses a cloud configuration safety assessment method. The cloud configuration safety assessment method comprises the following steps: (1), performing qualitative and quantitative analyzing on security problems and security evidences in the hierarchical structure of each service configuration including an IaaS layer, a Paas layer and an Saas layer; (2), assessing the security of each service configuration of a cloud platform; and (3), assessing the overall security of the cloud platform, establishing a first-level cloud security assessment model by use of a Sugeno fuzzy inference system based on an adaptive neural network, and analyzing the overall security of the cloud platform. Compared to the prior art, the number of users accessed to a network end is dynamically and reasonably controlled, loads accessed to the network end are always maintained within a certain acceptable scope, the users can be dispersed when a large number of users are simultaneously accessed to a network at the same frequency, the users can be accessed to the network as soon as possible, and the system random access performance in case of network congestion is greatly improved.

The invention discloses a real-time prediction system and method for a boiler entering heat value of a circulating fluidized bed household garbage incineration boiler. By means of hidden knowledge in operation historical data and an operational mechanism of the circulating fluidized bed household garbage incineration boiler and through an integrated modeling method of a particle swarm optimization (PSO) algorithm, a subtractive clustering algorithm and an adaptive neuro-fuzzy inference system (ANFIS) algorithm, the system and the method which are fast and economical are established for real-time prediction of the heat value of boiler entering garbage, the complicated work of off-line measurement for garbage components is avoided, a new path is provided for boiler operation operators and relevant management staff of a power plant to judge the heat value of the boiler, and meanwhile, a heat value judgment signal can be provided for an automatic control system of the power plant.

A system, method, and article for profiling an applicant, an examiner, and agency or examination group for the purposes of examination of an application that undergoes a regulated or structured examination. One aspect of the invention can provide a greater degree of predicting success or potential success based on identifying a data factor that has a potential influence upon success of the application. Another aspect uses statistical methods or logic from a fuzzy inference system to analyze data factors. One example is directed towards the filing and prosecution of intellectual property documents such as patent and trademark applications.

The invention discloses a voltage sag source identification method based on Mamdani fuzzy reasoning, belonging to technical field of voltage quality monitoring of a power system. The method comprises the steps of calculating the membership degree of three-phase voltage to balance, the membership degree of the voltage at the end of voltage sag to mutation degree and the membership degree to harmonic content; inputting the membership degrees to an Mamdani fuzzy reasoning system and substituting into fuzzy rules to calculate a corresponding fuzzy result; and using the center of gravity defuzzification for defuzzifying the fuzzy result to obtain the type of a sag source. The method takes into account of inherent differences of four different sag causes and is started from amplitude, mutation and harmonic, thereby avoiding the impacts of a plurality of uncertain features on the analysis accuracy of different sag sources; in addition, the method fuzzifies the input and the output quantities of the reasoning system, thereby avoiding the practice that the prior art needs to determine thresholds of all the feature values and further reducing the identification errors caused by the fixation of the thresholds.

The invention discloses a robot path planning method based on an ANFIS fuzzy neural network, and mainly solves the problems of complex trap path reciprocating and path redundancy in conventional reactive navigation. The method comprises the following steps: to begin with, establishing a kinematic model for a mobile robot; providing a mobile robot navigation controller based on the fuzzy neural network by means of autonomous learning function of the neural network and fuzzy reasoning ability of the fuzzy theory; constructing a Takagi-Sugeno fuzzy inference system based on an adaptive fuzzy neural network structure and serving the Takagi-Sugeno fuzzy inference system as a reference model for local reaction control of the robot; the fuzzy neural network controller outputting offset angle and operation speed in real time, and adjusting the migration direction of the mobile robot online to enable the mobile robot to be able to adjust speed automatically and approach the goal collisionless; and through an improved virtual target method, selecting an optimal path capable of allowing the robot to escape a trapping state.

The present invention involves a Soft Computing Optimizer (SCOptimizer) for designing a Knowledge Base (KB) to be used in a control system for controlling a plant. The SC Optimizer provides Fuzzy Inference System (FIS) structure selection, FIS structure optimization method selection, and training signal selection and generation. The user selects a fuzzy model, including one or more of: the number of input and/or output variables; the type of fuzzy inference model (e.g., Mamdani, Sugeno, etc.); and the preliminary type of membership functions. A Genetic Algorithm (GA) is used to optimize linguistic variable parameters and the input-output training patterns. A GA is also used to optimize the rule base, using the fuzzy model, optimal linguistic variable parameters, and a teaching signal.

The invention discloses a mixing scheduling method suitable for real-time system periodic tasks. The method comprises the following steps: searching a ready real-time system task set T and sorting the tasks in an ascending order according to deadlines; finding the task with the shortest deadline, wherein the execution time C and the deadline D of the task with the shortest deadline are taken as input data of a fuzzy reasoning system; processing the input data by a CPU (central processing unit), i.e. mapping a threshold value delta output by the fuzzy reasoning system onto a membership function of the threshold value, and determining the property of the threshold value delta according to the membership function. The mixing scheduling method uses a fuzzy system theory to organically combine an RM (rate monotonic) algorithm and an EDF (earliest deadline first) algorithm for scheduling the execution tasks, so the deadlines of the tasks cannot be missed, and system resources are fully utilized.

The invention discloses an early warning method for a bridge structure strain response exception. The method comprises the following steps that: utilizing a wavelet packet decomposition method to separate a bridge structure strain response; (2) utilizing a principal component analysis method to extract the principal component of a bridge ambient temperature field; (3) on the basis of an adaptive neural network fuzzy inference system, establishing a complex nonlinear relationship between an actual measurement load factor and corresponding strain data; (4) identifying the position information ofa vehicle on a bridge; (5) identifying the geometric parameter and the axle load of the vehicle; (6) on the basis of the adaptive neural network fuzzy inference system, establishing a complex nonlinear relationship between an actual measurement vehicle load parameter and corresponding strain data; (7) solving a bridge structure strain response theoretical value; and (8) comparing a theoretical solving result of the bridge structure strain response and the actual measurement result of the theoretical solving result, and updating the adaptive neural network fuzzy inference system. By use of themethod, effectively according to the actual measurement load parameter, the bridge structure strain response can be accurately predicted.

The invention discloses a lithium-ion battery SOC estimation method. According to analysis on experimental data of the lithium-ion battery rebound voltage at high or low temperature, a lithium-ion battery residual capacity prediction model of a self-adaption nerve fuzzy inference system is built. The rebound voltage and environment temperature are determined as input of the lithium-ion battery residual capacity prediction model while the lithium-ion battery residual capacity is determined as output. In the platform of MATLAB, according to the experimental data, the lithium-ion battery residual capacity prediction model of the self-adaption nerve fuzzy inference system is trained and verified. The obtained model is applied to predication and verification of the residual capacity of different battery packs. According to the method, the model is adaptable to being embedded into the existing battery management systems at present to realize accurately estimating the residual capacity of the battery so as to prevent overcharge and overdischarge of the battery; and thus, service life of the battery is prolonged, cost of users is lowered and the method has great economic benefit and social benefit.

The invention discloses an integrated navigation method based on satellite navigation and inertial navigation. The method can maintain higher navigation precision under the conditions of lower signal-noise ratio of satellite signals and greater noise change, and has two main characteristics that firstly, a bandwidth self-adaption satellite signal receiver based on a fuzzy inference system is adopted, and secondly, an integrated navigation algorithm for noise model self-adaption measurement on the basis of the fuzzy inference system is adopted. After the functions are added to the original integrated navigation system structure basis, the integrated navigation method has the advantages that higher navigation precision is maintained under the conditions of lower signal-noise ratio of the satellite signals and greater noise change, and the anti-noise-jamming capability is obviously enhanced.