82 results about "Fuzzy logic inference" patented technology

The technology of the 4D-GIS system deploys a GIS-based algorithm used to determine the location of a moving target through registering the terrain image obtained from a Moving Target Indication (MTI) sensor or small Unmanned Aerial Vehicle (UAV) camera with the digital map from GIS. For motion prediction the target state is estimated using an Extended Kalman Filter (EKF). In order to enhance the prediction of the moving target's trajectory a fuzzy logic reasoning algorithm is used to estimate the destination of a moving target through synthesizing data from GIS, target statistics, tactics and other past experience derived information, such as, likely moving direction of targets in correlation with the nature of the terrain and surmised mission.

A system and method to detect and mitigate denial of service and distributed denial of service HTTP “page” flood attacks. Detection of attack/anomaly is made according to multiple traffic parameters including rate-based and rate-invariant parameters in both traffic directions. Prevention is done according to HTTP traffic parameters that are analyzed once a traffic anomaly is detected. This protection includes a differential adaptive mechanism that tunes the sensitivity of the anomaly detection engine. The decision engine is based on a combination between fuzzy logic inference systems and statistical thresholds. A “trap buffer” characterizes the attack to allow an accurate mitigation according to the source IP(s) and the HTTP request URL's that are used as part of the attack. Mitigation is controlled through a feedback mechanism that tunes the level of rate limit factors that are needed in order to mitigate the attack effectively while letting legitimate traffic to pass.

A system and method to detect and mitigate denial of service and distributed denial of service HTTP “page” flood attacks. Detection of attack/anomaly is made according to multiple traffic parameters including rate-based and rate-invariant parameters in both traffic directions. Prevention is done according to HTTP traffic parameters that are analyzed once a traffic anomaly is detected. This protection includes a differential adaptive mechanism that tunes the sensitivity of the anomaly detection engine. The decision engine is based on a combination between fuzzy logic inference systems and statistical thresholds. A “trap buffer” characterizes the attack to allow an accurate mitigation according to the source IP(s) and the HTTP request URL's that are used as part of the attack. Mitigation is controlled through a feedback mechanism that tunes the level of rate limit factors that are needed in order to mitigate the attack effectively while letting legitimate traffic to pass.

One or more embodiments of the invention provide a method, apparatus, and article of manufacture for refining an approximate location of a mobile device using fuzzy logic reasoning. An approximate location of a device is determined. A rule based that comprises an ordered collection of rules is then read read into memory, or loaded from a database. A set of imprecise inputs are captured for processing in the rules. However, prior to processing the inputs in the rules, the inputs are processed to determine a magnitude of participation of the input in the rules. The rules are then applied to the imprecise inputs based on the magnitude of participation to produce a logical product. A refined location is then computed based on the logical product.

An intelligent data management system and method are disclosed. The system includes a database of stored data, a middleware layer having access to the stored data, and at least one client device for remotely accessing a provided course of action. The middleware layer includes a fuzzy logic knowledge base for generating, updating, or firing fuzzy logic rules and a fuzzy logic inference engine for processing the stored data guided by the fuzzy logic rules to provide the course of action.

The invention discloses a novel fuzzy active disturbance rejection controller based five-phase fault-tolerant permanent magnet motor speed control method, and designs the novel fuzzy active disturbance rejection controller. A rotating speed differential value generated by a tracking differentiator and a system disturbance value observed by a linear expansion state observer are taken as the input of a fuzzy logic theory machine; and the output bandwidth value omega<c> of the fuzzy logic theory machine is taken as bandwidth input of a proportional controller. The fuzzy controller can change parameters of the controller according to the working conditions of the system in real time; the design difficulty of the controller is lowered, and the controller parameters can be adjusted in real time according to the running working conditions of the system; the novel tracking differentiator of the novel fuzzy active disturbance rejection controller ensures that the motor has no overshoot rapid response in the whole dynamic process; and compared with a conventional linear active disturbance rejection controller, the novel fuzzy active disturbance rejection controller designed in the invention has strong disturbance resisting capacity and adaptive capacity for complex working conditions, and the excellent dynamic performance.

The invention discloses a self-adaption strong tracking unscented kalman filter (UKF) positioning filter algorithm based on fuzzy logic. The self-adaption strong tracking UKF positioning filter algorithm comprises the steps that: (1) a positioning filter model is built; (2) initial parameters of a filter are set; (3) the state quantity is subjected to filtering by adopting the UKF filter algorithm; (4) a fuzzy logic system is used for solving softening factors in the self-adaption tracking algorithm; (5) the self-adaption factors in the strong tracking self-adaption algorithm are solved; and (6) the epoch moment is increased by 1, the next moment observation is read, and the operation returns to the step (4) until the operation is completed. The strong tracking self-adaption algorithm in introduced on the basis of the UKF filter algorithm, in addition, a novel recursive algorithm is adopted in the strong tracking self-adaption algorithm for estimating the information covariance matrix, and the softening factors in the strong tracking algorithm are solved through a fuzzy logic reasoning system and are estimated in real time according to the work state of an epoch moment filter. The estimation is carried out in satellite navigation user receiver position estimation, and the positioning performance and the capability of carriers adapting to the dynamics can be greatly improved.

In order to solve the problem of local minimum of a virtual force-based route planning method and realize real-time adaptive planning parameter setting in the planning process, the invention provides a fuzzy virtual force (FVF)-based unmanned plane route planning method. In the method, the real-time adaptive planning parameter setting is performed by combining a Bayesian network and fuzzy logic inference, and the problem of local minimum of the virtual force method is solved by a threat combination method. The fuzzy virtual force-based unmanned plane route planning method comprises the following steps of: 1) setting initial conditions for unmanned plane route planning, including planning an initial point, a target point, and thread distribution and attributes; 2) setting an iterative step of the unmanned plane route planning; 3) setting planning parameters so as to determine a relationship between a virtual repulsion coefficient and a virtual attraction coefficient; 4) performing route planning; and 5) judging whether the local minimum appears, if so, performing thread combination, otherwise, continuously performing route planning until the target point is reached.

A vertical switching control system based fuzzy logic comprises obfuscation mobile, inference module of fuzzy logic, deobfuscating module, knowledge base and configuration managing module. It is featured as carrying out comprehensive evaluation on network link quality, bandwidth, price, battery capacity, mobile speed and user interest by utilizing said modules through fuzzy algorithm in order to select out optimum network for carrying out switching.

The invention proposes an old people's abnormal behavior detection method based on deep learning, which belongs to the deep learning field. According to the invention, a plurality of sensors are used to acquire the body characteristic information, the position information and the image information of an old person so as to determine the abnormal behaviors of the old person in a jointed detection way, reducing the mis-judgment probability. The method comprises: first, based on the data of the plurality of sensors, preprocessing the signal; inputting the processed data to a well-trained BP neural network to obtain the health condition of the old person; then, according to the original image, preprocessing the image and transmitting the image to a 3D convolution neural network to extract characteristic vectors; and through the Softmax classifier recognizing the multiple behaviors by the old person; and in combination of the position information of the old person as well as his or her duration there and according to the fuzzy logic inference, determining whether the behaviors of the old person are abnormal or not. According to the invention, a jointed detection method is utilized, and through the deep learning and the fuzzy logic inference, it is possible to realize jointed judgment about the abnormal behaviors of the old person, which reduces the mis-judgment rate and increases the detection accuracy.

The invention discloses an electric vehicle power battery safety monitoring device and method. The monitoring device comprises a data acquisition system, a data transmission system, a data saving system and a state monitoring system. The state monitoring system comprises a data processing subsystem, an execution module and a remote communication unit. The data acquisition system sends the collected battery state data to the data saving system for caching through the data transmission system, and injects into the data processing subsystem to detect the internal resistance of a battery cell through an online parameter identification module. A evaluation index system combines the multi-factor and multi-level fuzzy logic reasoning to comprehensively evaluate the battery safety status; according to the evaluation result in combination with a corresponding control strategy, a control signal is injected into the execution module to achieve the battery safety monitoring and control. The devicehas the advantages of being systematic and intelligent, and the monitoring and troubleshooting of faulty vehicles are achieved through a remote communication technology in combination with a monitoring platform.

The invention relates to a method for forecasting the running load of a hybrid electric vehicle, which comprises the steps: a speed sequence x0'(n) of the hybrid electric vehicle that runs a period of time is collected; a running period T of the hybrid electric vehicle is obtained according to the speed sequence x0'(n) and is used as the length of each sliding time window, the speed sequence x0'(n) is segmented at time by using sliding time windows, each sliding time window is divided into historical time T1 and forecasting time T2, data of the T1 time period is carried out dimension reduction by using DCT, a load level of the T2 time period is obtained by using fuzzy logic inference according to the data of the T2 time period, the data of the T1 time period after the dimension reduction and the load level of the T2 time period are used as training data to train a support vector machine, the speed of the running hybrid electric vehicle is collected, after the sliding time window is used for collecting the T1 time length, a speed sequence x0(n) is obtained, the x0 (n) is carried out dimension reduction by using the DCT to obtain x1(n), the x1(n) is classified by using the trained support vector machine, and load levels in the T2 time period is forecasted. The invention increases the forecasting precision and the generalization capability in the prior load forecasting method, reduces the computational complexity and realizes the dynamic forecast of the running load of hybrid electric vehicle.

The invention presents an method and system for information recommendation based on the fuzzy logic. The method includes: storing the user files with the fuzzy set, matching the user file with the received information by inference of the fuzzy logic, sieving out the information which conforms to the user's preference and recommending the information to the user after sequencing the information according to the preference thereof. The system includes means for carrying out above method. Said method and system for information recommendation can imitate the human thinking intelligently, hence increase greatly the efficiency and the satisfaction level of the information recommendation, so can be applied to the information recommendation of TV programs, shopping or the Internet and so on.

The invention discloses an automatic control system and method for coal slime flocculation settling, which belongs to the technical field of mechatronics and control of mechatronics and particularly relates to a control system and a fuzzy control technology for coal slime flocculation settling on the basis of turbidity gradient detection of a thickener supernate layer. The invention provides an automatic control system and method for coal slime flocculation settling, which can be used for controlling overflow water turbidity to be stable and reach the standard and have the advantage of reducing flocculant consumption. According to the system, a three-point turbidity distribution detection device is used for detecting the turbidity distribution of the thickener supernate layer along the depth direction. According to the turbidity distribution condition, the turbidity space change rate along the supernate layer depth direction can be obtained; the change tendency of flocculation settling is predicted in an early stage; then, by taking the change tendency as one of the inputs of the fuzzy controller, fuzzy logic reasoning and in-time reasonable control can be implemented; and the problem that control effect is unstable, even out of control, because an overflow water turbidity feedback signal is seriously lagged can be overcome, and circulating water turbidity can be prevented from deteriorating. The system and the method disclosed by the invention are suitable for the coal slime flocculation settling processing of various coal preparation plants.

The invention discloses a wireless network switching management method and system; the method uses software to define network inherent centralized control and programmability advantages, and fully considers influences on the network switching management strategy performance by multi factors such as the network, users and applications; the method selects a plurality of influence factors as the input parameters, such as user mobility, network states and user preferences, senses network demands in many aspects, and uses fuzzy logical reasoning to obtain the final network scoring result so as to provide a network switching final decision. The method considers objective factors on the network side and the user side, and considers user subjective customized demand preferences, thus providing differentiated network switching management services for different users.

The invention discloses a fuzzy-logic-based ice-covered power transmission line state estimation method, which comprises the following steps of: 1, determining and calculating a characteristic quantity of a specific estimated content in two aspects of the mechanical performance and the electric external insulation performance of a lead wire, a ground wire and a tower which serve as objects according to a monitoring parameter; 2, determining a fuzzy logic inference system and an input characteristic quantity and an output quantity thereof, and designing a membership function; 3, building the fuzzy logic inference system, designing a fuzzy rule, and inferring state fuzzy results of the mechanical performance and the electric performance; and 4, defuzzifying the fuzzy results obtained in the step 3 by a centroid anti-fuzzification method, and outputting a fuzzy subset with the maximum membership according to a maximum membership principle to obtain a state estimated result. The method has the advantages of comprehensive estimated content, scientific calculation mode, high accuracy and effectively prevented faults on a power transmission line.

The present invention discloses an island microgrid frequency control method based on a random acceleration particle swarm algorithm. The method concretely comprises: the frequency variation [delta]f of a microgrid is taken as input variable, and an optimal output membership function parameter is found through optimization of the random acceleration particle swarm algorithm; the obtained optimal parameter is configured to replace an output membership function parameter in an original fuzzy logic inferer; the fuzzy logic inferer employs a new output membership function parameter to perform fuzzification processing of the PI controller output quantity, the ambiguity resolution operation is performed, PI controller parameters Kp and Ki are obtained through scale transform, and the parameters in the current PI controller are replaced. The PI controller output controls the micro-gas turbonator to rotate to realize frequency regulation in the microgrid. Through combination of the particle swarm algorithm and the fuzzy logic algorithm, the island microgrid frequency control method based on the random acceleration particle swarm algorithm forms combination intelligent optimization, the optimization speed is obviously faster than that of the genetic algorithm, and the performances are improved.