52 results about "Evidence synthesis" patented technology

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 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 surface water quality evaluation method based on combined weight, which includes the following steps, firstly selecting water quality indexes to build a water quality evaluation system, then adopting the subjective weighting method, the analytical hierarchy process, the objective weighting method and the super-standard weighted method to obtain three groups of weight vectors of the water quality indexes, and adopting the weight synthesis method based on the ideal point method for weight synthesis, so as to confirm the combined weight of the water quality indexes; taking the water quality indexes as evidences, calculating the basic trust distribution of the evidences to various water quality types, and then performing evidence synthesis based on the evidence additive synthesis rule of the combined weight; and selecting the water quality type with the highest trust degree as the water quality evaluation type as per the evidence synthesis result, and analyzing the variation trend of water quality as per the variation of trust degree of various water quality types. The surface water quality evaluation method provided by the invention integrates the influence of various water quality indexes to determine the water quality type, is objective and reasonable in evaluation results, and can be used for analyzing variation trend of water quality at the same time.

The invention provides a method for monitoring an underway ship in real time based on AIS and VTS information integration. The method comprises the steps of collecting signals; acquiring AIS static information, AIS dynamic information, information related to the voyage number and information about the security of a target ship through an AIS; detecting VTS dynamic information of the target ship through a VTS, and reflecting information about the size and the shape of the target by using VTS radar target echoes; building a D-S evidence theory identification framework through analyzing the difference between the AIS dynamic information and the VTS dynamic information acquired by the AIS and the VTS radar respectively; and constructing a focal element confidence function based on a Kalman prediction algorithm, carrying out evidence synthesis within the D-S evidence theory identification framework, and judging monitoring results. The method provided by the invention is based on the two existing real-time monitoring modes for ships, utilizes the D-S evidence theory identification framework, and constructs the focal element confidence function based on the Kalman prediction algorithm so as to achieve more accurate monitoring results.

The present invention provides a multi-sensor information fusion method based on evidence similarity. The method comprises: firstly, representing multi-sensor decision layer data by using evidence; secondly, performing Pignistic probability conversion on each piece of evidence, calculating the similarity between each two pieces of evidence after the conversion, and determining the supporting degree and the reliability degree of each piece of evidence; and finally, correcting an evidence source, and performing evidence synthesis. According to the multi-sensor information fusion method based on evidence similarity, reasonable measurement and correction are performed on the conflict degree by using existing evidence information, so that the influence of conflict evidence is reduced, the generation of an unreasonable result is avoided, the speed of multi-sensor information fusion is increased, and the precision of multi-sensor information fusion is improved.

The invention relates to a method and a system for integrated risk calculation of a computer information system, comprising the following functional modules: an original factor initial risk reliability valuator forms original factor initial risk reliability vector and a comprehensive risk reliability calculator connected with the original factor initial risk reliability valuator for calculating and evaluating the comprehensive risk reliability of the object; the method comprises the following steps: building risk level standard, analyzing the object and building weight, evaluating the original factor initial risk reliability, building risk reliability matrix, calculating the comprehensive risk reliability and quantizing the comprehensive risk. Evaluation factors are used as evidence of the evaluation object, and the risk of the evaluation object is calculated with an evidence synthesis method; the result of the evaluation factors is synthesized from the angle of the evidence, so as to be capable of directly expressing the uncertain or unknown factors in the evaluating process, and the information is kept in the synthesis process of the evaluation factors, thus leading the evaluation result to be more objective and real.

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.

The invention discloses a multi-type evidence synthesis assessment method of the burst water disaster of tunnel and underground construction. A risk factor which influences the burst water disaster of the tunnel and underground construction is subjected to comprehensive and systematic analysis, main factors are selected to construct an index system of risk assessment, an entropy weight method is adopted to endow the weight of each evidence index, meanwhile, a qualitative index is subjected to quantitative processing, an expert consulting system is used for giving the basic confidence level of the qualitative index, the contribution of expert experiences to an assessment result is kept, and the influence of subjectivity on the assessment result is reduced to a certain degree; and an assessment index is a multi-type index, and different types of evidence indexes are used for assessing the risk of the burst water disaster of the tunnel and underground construction under the same frame of identification through the standardized processing of the multi-type index. Through the multi-type evidence synthesis assessment method, the assessment result is expressed by deterministic data, and the generation level of the burst water disaster of the tunnel and underground construction can be visually and specifically displayed.

The invention discloses a target intention recognition method based on an improved D-S evidence theory, belongs to the field of radar technology and relates to a networking radar target intention recognition technology. The method solves the problems that evidence acquired by different radar needs to be comprehensively considered for networking radar target intention recognition, and when different evidence has a mutual conflict, a traditional D-S evidence theory cannot effectively recognize a target intention. The method is characterized in that first, data received by networking radar is preprocessed, then basic probability allocation of all evidence is acquired based on similarities between intentions and the evidence, and finally a similarity coefficient among the evidence is introduced into evidence conflict handling and D-S evidence synthesis considering relevancy among the evidence. Through the method, abnormal data in the data received by the networking radar can be removed, adverse influences of the abnormal data on target intention recognition are reduced, the problem of an evidence conflict in practical application is effectively solved, and target intention recognitionperformance is improved.

The invention discloses a fuzzy logic and evidence reasoning-based transformer insulation stress calculation and evaluation method. The method comprises the following steps of firstly normalizing field data, namely, converting input data for describing a normal value, a limit value and the like of a transformer into dimensionless variables of a [0,1] region; secondly fuzzifying the input data, namely, mapping the input data to a fuzzy membership function, wherein a trapezoidal membership function, a generalized bell-like membership function or a Gaussian membership function can be used; thirdly building a transformer stress evaluation tree model, namely, establishing nodes from the input data of the transformer to an insulation stress of the transformer, and a connection mode of the nodes, and correlating the nodes of upper and lower layers by using a fuzzy correlation matrix; fourthly determining a weight value between the nodes, namely, obtaining a synthesized weight value by using a subjective weight value of an analytic hierarchy process and an objective weight value of eigenvector analysis; and finally obtaining the insulation stress of the transformer, namely, determining a total stress level of the transformer by using a reasoning mechanism and an evidence synthesis rule. The method has the advantages in accuracy, flexibility and capability of processing measurement uncertainty.

The invention discloses a gas pipe network leakage grade judgment method based on an improved evidence fusion algorithm. The gas pipe network leakage grade judgment method comprises the steps that multiple evidence sources used for judging gas pipe network leakage are obtained through gas pipe network information measured by a sensor; and for weak decision evidences, the focal element weight of the focal element with the highest mass value is taken as 1, and the other focal elements are multiplied by the respective focal element weights respectively, so that the difference between the maximumtrust focal element and the other focal elements is effectively expanded, and the evidence fusion result is more reliable, and the convergence speed is high. For conflict evidences, average evidencesare adopted to replace the conflict evidences, and the conflict evidences are limited by the evidence distance weights, so that the influence of the conflict evidences on an evidence synthesis resultis reduced, and weak decision evidences can play a decision role. According to the invention, the accuracy of gas pipe network leakage level decision can be improved.

The invention provides a scheme selection decision-making method and device based on a qualified value adaptive regret theory, and the method comprises the steps: carrying out the matrix standardization of an original evaluation matrix, and obtaining a standardized evaluation matrix; taking intermediate values of all values under each attribute in the standardized evaluation matrix as qualified reference values of the attribute; obtaining a utility value of each attribute under each scheme according to the qualified reference value of each attribute, and forming an attribute interval utility value matrix; calculating a regret value of each scheme under each attribute, and obtaining a perception utility value matrix; obtaining a basic probability distribution matrix; obtaining a phase separation degree deviation matrix according to the standardized evaluation matrix, and obtaining the weight of each attribute; obtaining a weight-based basic probability distribution matrix; and performing evidence synthesis, and sorting all the schemes. Compared with the traditional regret theory, the method is higher in flexibility, and can better describe decision-making habits and risk chasing psychologies of people.

The invention discloses an evidence synthesis method and module, and a multiple Agent diagnosis system. The evidence synthesis method includes the steps: calculating the distance between every two evidences in an evidence set; according to the distance between every two evidences, calculating the similarity between every two evidences; according to the similarity between every two evidences, calculating the support degree of each evidence; according to the support degree of each evidence, calculating the credibility of each evidence; and taking the credibility of each evidence as weight, performing weighted average on the elementary probability assignment of the evidences in the evidence set, and synthesizing the evidences in the evidence set so as to solve the conflict problem of evidences and realize valid synthesis of multi-source evidences.

The health state assessment method for the spaceflight measurement and control data transmission integrated equipment is high in feasibility and high in assessment conclusion credibility. According to the technical scheme, in AHP software, an equipment-level and component-level health management module, a parameter-level health management module, a subsystem-level health management module and a system-level health management grading module are adopted to form a layered health management evaluation system architecture; the equipment-level and component-level health management module collects electric signals and characterization parameters of equipment circuit modules or components and devices; various parameter signals are fused to jointly predict health states of components and equipment, and the parameter-level health management module carries out state prediction and management on parameter changes; the subsystem-level health management module performs health assessment and prediction; and the system-level health management grading module analyzes and predicts a task execution form, constructs and forms a multi-level analysis evaluation model, calculates a weight coefficient, performs layer-by-layer weight fusion and performs evidence synthesis to obtain an evaluation result of a system comprehensive state.

The invention provides a blue-party model credibility evaluation method and system based on an evidence theory, and the method comprises the steps: M1, converting blue-party model output data Ysi intoevidence theory representation, and recording the evidence theory representation as simulation output; m2, evaluating an estimated value output by an actual system of the blue-party model according to expert experience, and recording the estimated value as reference output; m3, performing evidence synthesis on the simulation outputs and the reference outputs of all the blue-party models; M4, performing consistency measurement on the simulation outputs and the reference outputs by adopting an evidence distance; and M5, performing consistency measurement on the simulation output and the reference output according to the evidence distance, and calculating the final credibility. The blue-party model credibility evaluation method based on the evidence theory provided by the invention comprisesan evidence synthesis method considering the index weight, so that the existing credibility evaluation framework can be utilized to the greatest extent, and the integration of multiple credibility indexes of a complex model is realized.

The invention relates to a nuclear power plant main coolant system fault diagnosis method. A model building module, a BPA generator, an evidence fusion module and a decision-making diagnosis device are sequentially connected in sequence, the model constructed by the module is used as the input of the evidence fusion module through the data calculated by the BPA generator, the result is fused by the evidence fusion module and is transmitted to the decision-making diagnosis device, and finally the decision-making diagnosis device outputs a judgment result. The fault symptom is used as evidence for identifying a target, and a fusion result is obtained through an evidence synthesis method to judge the fault type, according to the method, the uncertainty of the fault diagnosis is analyzed and expressed from the evidence angle., and a hypothesis set is continuously reduced by means of accumulation of evidence, so that the diagnosis result is more objective and accurate. The fault symptom isused as the evidence for identifying a target, a fusion result is obtained through an evidence synthesis method to judge the fault type, according to the method, the uncertainty of the fault diagnosisis analyzed and expressed from the evidence angle, and a hypothesis set is continuously reduced by means of accumulation of evidence, and the 'unknown' and 'uncertain' can be distinguished, so that the diagnosis result is more objective and accurate. The BPA is generated by utilizing the triangular fuzzy number, the specific numerical value is obtained through quantitative calculation and is convenient to analyze, and the calculation is simple and convenient; secondly, the method has stronger flexibility and is beneficial to the analysis personnel to make a decision.

The invention discloses a testability index distribution method and a testability index distribution device based on an improved analytic hierarchy process. The testability index distribution method comprises the steps of: determining an evaluation index system and a hierarchical structure model of testability index distribution; determining a judgment matrix through expert scoring, solving a weight vector of each expert by using an improved AHP method, synthesizing weight values of multiple experts by using an optimized evidence synthesis formula, and respectively calculating to obtain a weight of a standard layer to a decision-making layer and a weight of an object layer to the standard layer; calculating a total hierarchical sorting result; and completing testability index distributionby using a weighting coefficient method. According to the testability index distribution method, an analytic hierarchy process is improved, consistency verification is avoided, and operation is simplified; and a more effective evidence synthesis formula is adopted, so that the reliability and reasonability of a synthesis result are improved.

The invention relates to an image denoising method based on an evidence theory. The image denoising method based on the evidence theory comprises the steps that (1) a frame image is read, and a first pixel serves as a current pixel; (2) whether the current pixel is a noise point is judged; (3) with the noise point as the center, an n*n square template is constructed on the image for a target pixel; (4) the standard gray value of the current pixel in the n*n square template is calculated by utilizing an evidence synthesis formula; (5) the absolute value of the difference value between the gray level of the current pixel and the standard gray value of the current pixel is calculated according to the formula in the step (4); (6) the threshold value of the gray value is preset; (7) noise is removed, and when the current pixel is defined as the noise, correction is carried out by using the standard gray value of the current pixel to replace the gray level of the current pixel. According to the denoising method, based on gray evidences of the pixel calculated through the evidence theory, gray evidence synthesis is carried out by utilizing the evidence synthesis formula, calculation complexity can be effectively reduced, and a more accurate denoising result is obtained.

The invention provides an account-based service implementation method comprising the steps that all the correlated accounts in an account set and the correlation coefficient between the correlated accounts are acquired; any account in the account set and another account are mutually correlated accounts; the account set includes at least one white seed account and at least one black seed account; the account whiteness value and the account blackness value of non-seed accounts are determined according to the account whiteness value and the account blackness value of at least one correlated account of the non-seed accounts and the correlation coefficient between the correlated accounts; the account grayscale value of the non-seed accounts is generated by using the evidence synthesis rules based on the account whiteness value and the account blackness value of the non-seed accounts; and the service strategy of the non-seed accounts is determined according to the account grayscale value. When the technical scheme is applied to the service system involving the user fund account, the verification operation of the user of high credit rating and good behavior can be reduced without reducing the system security.

The invention relates to a weighted average evidence synthesis method based on similarity analysis, and belongs to the technical field of information fusion. The method comprises the following steps:step 1) obtaining basic probability distribution mi (A) of each evidence body Hi under an identification framework; 2) calculating a similarity coefficient sij between every two evidence bodies, and constructing a similarity coefficient matrix S of the evidence; 3) calculating a weight coefficient ki of each evidence body Hi according to the similarity coefficient matrix S of the evidence; and 4)synthesizing the evidence body according to the weighted average evidence combination rule to obtain the probability distribution m (A) after evidence synthesis. Compared with the prior art, the method has the advantages of being less influenced by evidence conflicts, simple in algorithm, good in stability, more reasonable in synthesis result and the like, and has important theoretical significance and application value.

The invention discloses a personnel violation behavior identification model training method, a personnel violation behavior identification method and computer equipment. The model training method mainly comprises the following steps: carrying out global semantic expression of video clips on local spatial-temporal features and human body posture features of training set samples; based on global semantic expression training of the video clips, obtaining first multi-classifiers of which the number is equal to that of the feature types; sending the verification set sample into multiple classifiersto obtain corresponding three-dimensional probability score matrixes, generating an evidence source of a DS evidence theory of each behavior category according to each three-dimensional probability score matrix, and calculating an identification sensitivity weight vector of each feature belonging to each behavior category in combination with a preset evidence synthesis strategy; performing globalsemantic expression of the video clips on the local spatial-temporal features and the human body posture features of all the video samples, and performing training based on the global semantic expression of the video clips to obtain a second multi-classifier; and constructing a personnel violation behavior identification model according to the identification sensitivity weight vector and the second multi-classifier.

The invention relates to an information fusion algorithm based on OPD-S, which is an algorithm for carrying out data fusion on disaster information, belongs to the field of data processing and machine learning, and is characterized by comprising the following steps: (1) determining a trust function of a set; (2) determining a basic probability distribution function under an open recognition framework; (3) determining credibility between evidences; (4) determining the comprehensive credibility of the evidence; (5) determining weighted average evidence; (6) carrying out information fusion on the D-S combination rule. According to the method, the problems that in the traditional disaster information fusion process, due to the fact that the background environment is complex, the noise proportion of collected information is too large, and information fusion is affected are solved, noise interference is effectively filtered out, the information fusion accuracy is greatly improved, meanwhile, the system capacity for processing uncertain information is greatly improved, the fuzzy information proportion is reasonably corrected, and the fusion efficiency is improved. And a method with relatively high fusion accuracy is provided for the field of disaster information fusion.