224 results about "Basic probability" patented technology

The invention discloses a psychological stress assessment method based on multi-physiological-parameter integration. The method includes: designing a reasonable stimulation program, acquiring four types of electrophysiological signals, namely electrocardiogram signals, electromyographic signals, pulse wave signals and electroencephalogram signals from people suffering psychological stress; extracting affective features of the four types of electrophysiological signals; subjecting the extracted features to feature selection by means of Relief algorithm, genetic algorithm optimization and the like; acquiring related integration functions on the basis of basic probability assignment mass. According to the method, multi-parameter signals are subjected to acquisition, preprocessed, feature selection and psychological stress affective recognition and are integrated; compared to single-parameter classified recognition or multi-parameter data-level or feature-level integration, the method allows data information to be more fully utilized and psychological stress emotions to be more accurately recognized.

A method includes steps: 1) obtaining monitoring information of different monitoring points in normal state of power equipment; 2) setting faults and obtaining monitoring information of different fault types, positions, monitoring points of the equipment; 3) taking the monitoring information obtained in steps 1) to 2) as training dataset, taking the fault types and positions as labels, inputting the training dataset and the labels to deep CNN for training; 4) collecting monitoring data, performing verification and classification using step 3), obtaining probability values corresponding to each of the labels; 5) taking classification results of different labels as basic probability assignment values, with respect to a monitoring system composed of multiple sensors, taking different sensors as different evidences for decision fusion, performing fusion processing using the DS evidence theory to obtain fault diagnosis result. The invention can intelligently realize fault detection, fault type determination, and fault positioning of the power equipment.

A multi-sensor data fusion early warning method for monitoring an electric transmission line tower comprises the following steps that 1) current electric transmission line parameters of detection sensors are obtained in real time; 2) first-class BP neural networks are fused; 3) second-class D-S evidence theories are fused, output of the BP neural networks is evaluated between 0 and 1 and processed to be elementary probabilities to serve as evidences of the D-S evidence theories, and danger classes are obtained. According to the second step, 2.1) fault monitoring is carried out on a single detection sensor: a BP network is adopted to construct a detection sensor output sequence predication model, and assuming n time output samples of the observed sensors as x(1), x(2), x(3),..., x (n), (n+1) time sensor output values are predicted; 2.2) the BP neural network of each detection sensor carries out time data fusion; 2.3) input signals are normalized; 2.4) fusion identification is carried out on characteristic layers. The multi-sensor data fusion early warning method is good in stability, high in reliability and good in real-time performance.

The invention discloses a hierarchical multi-source data fusion method for a pipeline linkage monitoring network, which comprises the following steps: carrying out data level preprocessing for various primary linkage detection signals acquired by a sensor at a common node of the monitoring network by using wavelet transformation, and extracting leakage-sensitive characteristic parameters; establishing a characteristic level data fusion model based on an ant colony neural network, processing the leakage characteristic parameters extracted by various sensors on the node, and constructing an elementary probability assignment function of evidence according to the output result of the ant colony neural network; and carrying out evidence synthesis at a cluster-head node according to an evidence combination rule, and making final decisions according to a maximum trust value method. The invention provides the hierarchical multi-source linkage detection data fusion method from the data level and characteristic level to decision level, and solves the multi-source data processing problem of the pipeline linkage monitoring network; and the method utilizes the linkage detection information acquired by various sensors in the network so as to effectively improve the accuracy rate of leakage identification.

The invention discloses a target identification method based on the data fusion of an airborne radar and an infrared imaging sensor, comprising the following steps: firstly, identifying a target and generating a corresponding elementary probability partition function M1 by the infrared imaging sensor; then identifying the target and generating a corresponding elementary probability partition function M2 by the airborne radar; fusing the identification results of the airborne radar and the infrared imaging sensor by a D-S evidence theory; finally, identifying the target, and making decisions. In the invention, the airborne radar adopts the target identification method based on fuzzy reasoning to identify the target, thereby overcoming the defect of the high nondeterminacy of data measured by a radar sensor and finally realizing the data fusion of the airborne radar and the infrared imaging sensor. A simulation result shows that the identification effect of an intelligent target algorithm based on the airborne radar and the infrared imaging sensor is much better than that of single radar or single infrared sensor.

The invention provides a robot failure diagnosis method achieved by multi-mode fusion inference. According to the method, results obtained from inference of various inference engines (such as inference engines based on rules, neural networks, the Bayesian network and evidence theories) are fused with the evidence theory method to obtain an inference result with higher credibility. The method mainly comprises the steps of determining an identification frame, converting the inference results of the various inference engines into elementary probability assignments, assigning a weight to each inference method, fusing the elementary probability assignments with the Dempster combination rule, and making decisions by means of gamble probability conversion. According to existing fusing inference methods, either a result obtained from last inference is used by next inference or different kinds of inference are adopted in different stages of a system, and therefore inference of the same information is only conducted with one inference method and the certainty can not be guaranteed. According to the robot failure diagnosis method achieved by multi-mode fusion inference, parallel inference is adopted, and the inference results obtained from the four inference methods are fused to improve the certainty of the inference result. The robot failure diagnosis method achieved by multi-mode fusion inference can be applied to failure diagnosis of multiple fields such as robots and can determine failures of a failure equipment system with a large number of uncertain factors.

Aspects of the various embodiments of the invention relate generally to computing relative base value probabilities using discrete experimental base values to calculate distributions of relative base probabilities. This information can be used with associated experimental measurements to increase the accuracy of the data analysis.

The present invention provides a distributed fusion recognizing method of wireless sensor network. Firstly each node of the wireless sensor network is established with a respective elementary probability distribution model, a sensor reliability analysis model, an uncertainty analysis model and a consistency analysis model. Then these node enabled by the target is executed with estimation to the elementary probability distribution function and sensor reliability analysis. Each node is executed with a time fusion in order to realize result synchronization. A modality fusion should be executed to the node which is equipped with a plurality of types of sensors. Then through analyzing the uncertainty to the recognizing result, the on-line self-adopting selection is executed. When the fusion center receives the element probability distribution and sensor reliability parameter transmitted by the selected node, the consistency analysis is executed. The information fusion is executed combining the reliability of sensor, and the uncertainty and consistency of result, and in this way the distributed fusion recognizing is realized.

The invention discloses a power equipment fault detection and positioning method based on artificial intelligence reasoning fusion. The power equipment fault detection and positioning method comprisesthe steps: 1) acquiring monitoring information of different monitoring points of power equipment in a normal operation state; 2) setting faults, and acquiring monitoring information of different fault types, different fault positions and different monitoring points of the equipment; 3) taking the monitoring information obtained in the steps 1) to 2) as a training data set and the fault type and position as labels, and inputting the training data set, the fault type and the position into a deep convolutional neural network for training; 4) collecting monitoring data, performing verification classification by using the method in the step 3), and obtaining a probability value corresponding to each label; and 5) taking classification results of different labels as basic probability distribution values, taking different sensors as different evidences ek of decision fusion for a monitoring system consisting of a plurality of sensors, and performing fusion processing by utilizing a DS evidence theory to obtain a final fault diagnosis result. According to the invention, power equipment fault detection, fault type discrimination and fault positioning can be intelligently realized.

The invention discloses a real-time fusion type travel time predicting method with multi-source and isomorphic data adopted. The real-time fusion type travel time predicting method with the multi-source isomorphic data adopted comprises the steps that on the basis that multi-source isomorphic continuous travel time data sequences at equal time intervals are obtained, a multi-source travel time D-S evidence inference model recognition framework is constructed; the real-time prediction mean value and dynamic variance of each kind of single travel time data source are calculated respectively by means of a time sequence model which enables the prediction mean value and the dynamic variance to be learnt; with a dynamic variance prediction result serving as input data, an elementary probability distribution function and a basic trust distribution function of a D-S evidence inference model are obtained through calculation, and the dynamic fusion weight of the multi-source travel time data is calculated according to the evidence synthesis rule; a travel time fusion result is calculated through the prediction mean values of the single data sources and the weight sum of the dynamic fusion weights. According to the real-time fusion type travel time predicting method with the multi-source isomorphic data adopted, the road travel time description or prediction uncertainty caused when a single data source is used for describing or predicting the road travel time is lowered, the travel time prediction accuracy and the travel time prediction reliability are improved, and the operability is high.

The invention discloses a GIS partial discharging detection system which comprises a partial discharging ultrasonic subsystem and a partial discharging ultrahigh frequency subsystem. The partial discharging ultrasonic subsystem and the partial discharging ultrahigh frequency subsystem are connected with a computer. Further disclosed is a detection method. The detection method comprises the steps of (1) detecting a detected GIS, uploading the detection results to the computer, (2) allowing the computer to carry out data processing and identification on the results detected through the ultrasonic detection method, giving evidences according to the detection results to assign a function value to an elementary probability of a target, namely the assigned probability, (3) calculating evidence space of each GIS fault, and (4) confirming diagnosis results, namely diagnosis types according to diagnosis decisions. According to the GIS partial discharging detection system and method, the partial discharging faults of the GIS can be accurately found, accuracy for identifying the fault types can be improved, maintenance of the GIS is promoted to be developed from periodic maintenance and accident maintenance to state maintenance and reliability maintenance, and detection accuracy is improved.

The invention relates to a method for mechanical fault diagnosis based on information entropies and an evidence theory. The method comprises the following steps of step 1 adopting four typical mechanical fault types to construct a recognition framework; step 2 taking four information entropies of a vibration signal as fault characteristics; step 3 computing to obtain fault characteristic reference values of the four typical mechanical fault types through analogue simulation; step 4 obtaining a fault vibration signal received by a sensor, and computing to obtain fault characteristic values thereof through the information entropies; step 5 utilizing a fault characteristic extraction method based on weighted information entropies to obtain sensor vibration signals to be distributed to basic probability assignment functions of the four typical mechanical fault types; step 6 utilizing an improved evidence synthesizing method based on a conflict between revised evidences to carry out evidence synthesizing on the obtained basic probability assignment functions in order to obtain a synthesized result; and step 7 obtaining a final result for fault diagnosis according to a decision rule.

The invention discloses a complicated equipment acoustic fault recognition and location method. The method comprises steps of carrying out data pre?processing and fault feature extraction on vibration signals of a single sensor in a distributed equipment monitoring network, using a within-class between-class distance as an evaluation function of genetic algorithm and optimally selecting characteristic parameters sensitive to a fault, building single-value classifier?models based on support vector data description for initial fault recognition through training a normal class sample set, and constructing a basic probability?assignment?function of?an evidence according to output information of fault classifiers of different measurement points, adopting an evidence combination rule to combine an evidence set and making a decision result. The invention provides an equipment acoustic fault recognition and location method with vibration information hierarchically-converged, a recognition technology in a multi-feature comprehensive analysis mode is adopted, vibration information of different measurement points is made full use of, a strong generalization ability is provided, and the problem that precise mathematical?modeling is hard to be built for fault recognition and location due to complicated structure of the equipment can be solved.

The invention discloses a multi-source target fusion method based on track matching. The multi-source target fusion method includes the steps: acquiring target information by the aid of various sensors; performing time alignment and space alignment on the target information acquired by the sensors; matching image target tracks with target tracks acquired by the other sensors, and supplementing information of the target tracks in the other sensors through information of the image target tracks if the image target tracks can be successfully matched with the target tracks acquired by the other sensors; selecting a target track generating result of a single sensor, a target matching result among different sensors and a track matching result among different sensors as three evidences of targetexistence, calculating probability of the three evidences of the target existence, and taking the probability as basic probability assignment of a DS (dempster-shafer) evidence theory; performing target existence fusion and category fusion by the aid of the DS evidence theory; outputting a fusion result. The method can solve the problem that a global target track is frequently interrupted as an image target position is inaccurate, and accuracy and reliability can be improved.

The invention discloses a fuzzy set based intelligent evidence theory inspection information fusion method. The method includes the steps of 1), collecting sensor information acquired from a robot in intelligent inspection; 2), calculating mutual support degrees of multiple sensors by the aid of fuzzy correlation function; 3), calculating fuzzy membership degrees of the sensors according to measurement data of the sensors and representing credibility of information provided by the sensors with the membership degrees; 4), converting support degrees and credibility of the sensors into basic probability assignments namely mass functions; 5), performing fusion on the information of the sensors by the aid of a D-S theoretical synthesis rule. With the method, technical problems that data sources in fusion of the information of the sensors of the intelligent inspection system in the prior are subjective, credibility of the sensors and mutual relation among the sensors are not objectively reflected resulting in large error in information fusion, low accuracy and the like are solved.

The invention provides a software quality evaluation method and system based on secondary evaluation. The method includes the steps that a software quality evaluation index space is selected, and a software quality evaluation result identification framework is built; sample data and data of software to be evaluated are collected; the number and the topological structures of BP neural networks aredetermined; the BP neural networks are trained in parallel, and the credibility levels are calculated; the quality evaluation index data of the software to be evaluated is input into each trained BP neural network, and preliminary evaluation results are obtained according to output results of the BP neural networks; the preliminary evaluation results are corrected in combination with the credibility levels of the BP neural networks to generate basic probability assignment of each proposition in the identification framework, and all pieces of evidence are fused according to the DS evidence theory to obtain a fusion result; decision-making is conducted on the fusion result based on decision criteria to generate a final evaluation result. By means of the method, software quality evaluation can be effectively achieved.

The present invention provides a system and a method to keep track of conflicts resulting from combining basic probability assignments (BPAs) without actually performing the normalization operation at every step of combination. This approach can be applied recursively, allowing the system to keep track of the normalization and conflict of the belief combinations inside a large belief inference system without ever performing a normalization operation as long as the computing system precision allows. The present invention can be applied to monitor conflicts within most inference systems, including the Valuation Based System (VBS) framework for Dempster-Shafer (D-S) evidential reasoning.

The invention discloses a mine roof safety evaluation method based on multi-target monitoring data fusion, mainly characterized in that the mine roof safety state is defined into three grades according to the actual production condition of a coal mine, and a frame for identifying the roof safety condition is determined; a computer fuses the elementary probability of multi-target monitoring sensordata by utilizing a data fusion model based on the D-S evidence theory to obviously show a certain state of roof safety, thereby realizing the purpose of identifying the roof safety state; and the computer analyzes the assigned value of the fused elementary probability according to the classification decision rules of the roof safety state and outputs the identifying result of the roof safety state, thereby realizing the evaluation of the mine roof safety condition. The invention establishes a conceptual framework for mine roof safety evaluation and provides information processing steps of analysis, processing, allocation, fusion and the like of multi-source data based on the D-S evidence theory, thereby greatly improving the quality and the credibility of roof evaluation index information.

The present invention relates to a valuation-based learning system. The system is configured to receive a plurality of inputs, each input being input evidence corresponding to a variable in a Dempster-Shafer Reasoning System. The Dempster-Shafer Reasoning System is a network of interconnected nodes, with each node representing a variable that is representative of a characteristic of a problem domain. A discount weight is then optimized for assigning to each of the inputs. A basic probability assignment (bpa) is generated using the Dempster-Shafer Reasoning System, and where the bpa is an output for use in determining a solution of the problem domain. Finally, a solution to the problem domain is determined using the bpa.

The invention discloses a circuit breaker fault diagnosis method for identifying a circuit breaker fault diagnosis based on sound and vibration signal fusion processing. There are four states: stuck fault, base loose fault, and refusal to move fault. (2) Step 2, use the db3 wavelet base to decompose the acoustic and vibration signals into three layers, and reconstruct the signals on the eight nodes in the third layer; perform the Hilbert transform on the reconstructed signals of the eight nodes , to obtain the modulus envelope. (3) The envelope signal is divided into 3 sections according to the principle of before opening, during opening and after opening. According to the principle of equal energy, it is divided into 3 sections before opening, 9 sections during opening, and after opening It is divided into 3 sections, and the energy entropy of the wavelet packet square difference of each state of the circuit breaker is extracted. (4) Input the feature vector matrix of each signal into the support vector machine and use the "one vs one" voting strategy to obtain the basic probability distribution. (5) Using improved evidence theory to fuse multi-sensor information to identify circuit breaker fault types.

The invention provides a novel multistage fault diagnosis method for a power transformer. The method uses two primary algorithms including a posterior probability support vector machine (SVM) and an evidence theory, and realizes fault diagnosis on the transformer. For a to-be-detected sample, firstly, the to-be-detected sample is preprocessed with a codeless four-ratio method and a characteristic gas method, and two sets of characteristic vectors can be generated; secondly, basic probability assignment (BPA) is provided for the evidence theory by utilizing one-to-one posterior probability estimation of various SVMs; finally, a multistage comprehensive diagnosis system is created. The method can fully utilize redundant or complementary information of chromatographic data and solves a problem of uncertainty between a fault mode and fault characteristics; at the same time, the analyzability of the system can be improved, the identification capability of the fault mode is effectively improved, and the accuracy and reliability of a diagnosis result can be remarkably improved in comparison with those of a conventional diagnosis result.

The invention discloses a D-S evidence theory-based high-voltage circuit breaker mechanical fault diagnosis method.. The method comprises the steps of establishing a self-adaptive neural fuzzy inference system model; acquiring a sound signal and a vibration signal of the high-voltage circuit breaker; extracting characteristic quantities of the sound signal and the vibration signal; performing classification preprocessing on the characteristic quantity through the adaptive neural fuzzy inference system model to obtain a basic probability distribution function; enabling a D-S evidence theory modified by high conflict evidence to fuse a basic probability distribution function to obtain a mechanical fault diagnosis result.. According to the diagnosis method provided by the invention, the soundand the vibration signal are combined. The D-S evidence theory is used for information fusion to comprehensively diagnose the mechanical failure of the high-voltage circuit breaker, which improves the reliability and accuracy of the state assessment.

The invention, which belongs to the technical field of multi-sensor information fusion, discloses an evidence-synthesis-based information-fusion target recognition method. A plurality of sensors are used for carrying out attribute information collection on a to-be-identified target and a feature attribute is extracted from the collected attribute information; data having the feature attribute aredivided into training data and testing data, wherein the training data are used for constructing a neural network model and the testing data are used for obtaining a basic probability assignment value; and then evidences are synthesized based on an improved evidence synthesis method and the synthesized result is used as the target recognition basis. According to the invention, the basic probability assignment values of evidences are obtained accurately and a synthesis problem of high-conflict evidences is solved. The basic probability assignment values of evidences are obtained by using the neural network and the neural network has the high nonlinear mapping capability and is capable of mapping the intrinsic relationship between the target feature data, so that the accuracy of the basic probability assignment values is ensured, the conformance to the real scene is realized, and the practical significance is good.

This invention is method for multiple source monitoring data fusion, the details of which are the following: to select suitable datum of water environment monitoring according to chart one as fusion datum; to determine the identification frame in evidence theory with at most five kinds of basic values; to determine the basic confidence level and assign function values zero to one; to classify the process of the monitoring fusion data into two kinds of evidence and multiple kinds of evidence; to lay criterion rules for category; to distribute largest probability value to the determined water environment and the difference with other water environment more than threshold value 0.28; the basic uncertainty probability value m(theta) is less than threshold value 0.35 and the basic probability value of determined water environment m(A) is larger than uncertainty probability value m(theta).

The invention provides a seismic property combination method based on a Dempster / Shafe (D-S) evidence theory. According to the seismic property combination method based on the D-S evidence theory, source property data undergoes feature extraction and evidences are formed to obtain basic probability values. Under instruction of the D-S evidence theory, the basic probability values are combined to obtain a combined probability value. The combined probability value is used as a weighting coefficient and furthermore, all partial small blocks of attribute data are combined with a weight number to achieve combination of multiple seismic properties. Therefore, when single seismic property information is used to explain a complicated geology problem, a problem that multiple solutions are produced by the single seismic property information is solved.

The invention provides a method based on fuzzy preference relation and D-S evidence theory. The first step is to obtain the basic probability distribution function of multi-sensor information in mechanical equipment monitoring; In the second step, the credibility of the evidence is obtained by the cosine angle function, that is, the credibility matrix. In the third step, we construct the uncertainty matrix based on Deng entropy variance, measure the uncertainty of evidence, and obtain the preference relationship between the evidence. In the fourth step, the fuzzy preference relation matrix isconstructed by using the preference relation obtained in the previous step, and the ranking value instead of BPA is generated. In the fifth step, the weighted average evidence is obtained by modifyingthe weight vector through the confidence matrix and the ranking value. In the step 6 Fusion of weighted average evidences by Dempster combination rule for n-1 times, decisions are made once the results of the fusion are obtained. The present invention proposes a novel conflict evidence correction technique for obtaining modified weighted average evidence.

The invention relates to a fault diagnosis method based on multi-feature information weighted fusion under spectral clustering analysis. The method comprises the steps of firstly, carrying out spectral clustering analysis on fault equipment; secondly, obtaining the reliability of a local diagnosis evidence of each SVM to each fault mode; thirdly, constructing basic probability distribution througha local diagnosis hard output judgment matrix of each SVM; fourthly, performing weighted processing on the basic probability distribution; fifthly, obtaining the credibility and the uncertainty; andfinally, through a set diagnosis rule, and in combination with the credibility and the uncertainty, performing diagnosis. Compared with the prior art, the method has the advantages that the situationthat evidences of different sources have different reliability for identification of propositions in an identification framework is considered, the conflict between the local diagnosis of the SVMs isreduced, effective combination of the SVMs and an improved evidence theory is realized, and the shortcoming that a synthetic result cannot reflect an objective fact due to the unreliability of identification is overcome.

The invention provides a fault fusion diagnosis method for a rolling bearing based on an improved D-S evidence theory. The method comprises the steps of: carrying out classification identification ondata of different fault states by adopting a plurality of fault diagnosis methods, and reflecting different fault characteristics of the rolling bearing from multiple angles to obtain a plurality of primary diagnosis results; constructing a correlation matrix between each evidence by utilizing a conflict factor in the D-S evidence theory, and calculating reliability of each evidence; according tothe reliability of each evidence, classifying similar evidences and conflict evidences by adopting a nearest neighbor rule; retaining probability distribution of similar evidences while modifying basic probability distribution of conflicting evidences; and fusing similar evidences and modified conflict evidences by adopting a D-S combinational rule to obtain a final diagnosis result. According tothe fault fusion diagnosis method for the rolling bearing based on the improved D-S evidence theory, fault diagnosis is performed from multiple angles, then multiple decisions are fused, advantages ofeach diagnostic method can be fully preserved, at the same time one-sidedness caused by single diagnostic method is preserved substantially, so that fault diagnosis rate and diagnosis reliability areimproved.

The invention belongs to the technical field of information processing and particularly relates to a marine environment safety assessment method based on the D-S evidence theory. According to the marine environment safety assessment method, according to the D-S evidence theory, multiple marine environment element data are fused, so that marine environment safety assessment is achieved. The marine environment safety assessment method comprises the steps that (1) a computer obtains marine environment element values, and the basic probability assignment of each marine environment element is output through calculation; (2) the computer conducts fusion on the basic probability assignment obtained in the step (1) according to the D-S evidence theory fusion rule, and the fused basic probability assignment is output; (3) the computer judges the fused basic probability assignment according to the decision rule, and then the marine environment safety elevation result is output. By the adoption of the marine environment safety assessment method based on the D-S evidence theory, marine environment safety assessment is effectively achieved, reasonable decision support can be provided for a decider, and the safety of a ship sailing on the sea and the economical efficiency of the ship are improved.