305 results about "Grey correlation analysis" patented technology

A transformer operating state comprehensive evaluation method based on on-line monitoring comprises the following steps that monitoring various state indexes of a transformer in an on-line mode and conducting quantitative processing; determining the weights of evaluation indexes by combining improved analytic hierarchy process and grey correlation analysis; evaluating the state of the transformer. According to the transformer operating state comprehensive evaluation method based on on-line monitoring, the state of the transformer is combined to evaluate correlation function operation and membership degree process of the indexes, a transformer state comprehensive evaluation model based on combination of combination weighting approach and a fuzzy grey element is established, various on-line detecting state information quantities can be synchronized, the operation state of the transformer can be effectively and accurately judged in a comprehensive mode, an evaluation result is intuitive, and the method is used for instructing practical overhaul arrangement work of the transformer.

The invention provides a KNN-based improved missing data filling algorithm, which comprises the steps of (1) improving a traditional multiple correlation coefficient inverse weighting method and calculating the importance of each attribute on a missing value-containing attribute by using an improved algorithm, deleting a few of attributes with relatively small correlation with a key attribute and carrying out streamlined operation on an attribute set to obtain a data sample set which only contains the streamlined attribute set; (2) comprehensively considering the advantages of the correlation between the attributes and the variability by using a mahalanobis distance, effectively predicting an uncertain factor-containing sample by combining a grey correlation analysis method and calculating K adjacent samples of a missing sample; and (3) giving entropy weight values to the attributes corresponding to the K samples according to the calculated K distance values and an entropy weight method and then calculating a final filling value by combining attribute values. According to the KNN-based improved missing data filling algorithm, the calculating complexity of the missing data algorithm can be reduced, the accuracy of the adjacent sample values is improved and the estimation accuracy of the data filing value is improved.

The invention provides a method for comprehensively evaluating electric energy quality based on a grey theory. The method comprises the following steps that the weight of an electric energy quality evaluation index is calculated through an objective weighting entropy evaluation method; the weight of the electric energy quality evaluation index is calculated through a subjective weighting AHP method; the weight vector of the electric energy quality evaluation index is determined; the electric energy quality is comprehensively evaluated based on grey correlation analysis in the grey theory. Through the adopted combination weighting method, the defects of the single weighting method that the subjectivity of people is relied on too much in a subjective weighting method and expert opinions cannot be reflected in an objective weighting method are overcome, the expert opinions can be reflected, the actual condition of the electric energy quality can be reflected, and all subitem index weight coefficients of the scientific electric energy quality are obtained. The grey correlation analysis method is adopted on this basis, a sample to be evaluated is compared with standard samples of all electric energy quality level grades, and the comprehensive evaluation result of the electric energy quality can be objective and simple.

The invention discloses a low-permeability clastic rock reservoir effectiveness evaluation method based on a development permeability lower limit, and belongs to the technical field of exploration and development of petroleum and natural gas. The method comprises the following steps: A, calculating an effective development permeability lower limit under the constraints of economic limit primary oil and a development thickness; B, performing evaluation parameter optimization and single scoring based on a permeability difference value; C, computing a weight coefficient and a comprehensive score based on grey correlation analysis; D, performing low-permeability reservoir effectiveness classified evaluation based on an economic primary liquid amount. By adopting the method disclosed by the invention, the key problems of inaccurate computation of a physical property lower limit, difficulty in determining a rational evaluation parameter, uncertainty in a practical classification standard and the like in low-permeability reservoir effectiveness classified evaluation are solved, and the accuracy and practicability of effectiveness classified evaluation of a low-permeability clastic rock reservoir are improved.

The invention discloses a comprehensive cigarette process quality evaluation system based on grey correlation analysis and a method thereof, aims at overcoming the disadvantage that the existing single process evaluation method can not comprehensively evaluate the overall process quality of the cigarette process, and changing the situation of fuzzy process capability evaluation of a whole line at present. The evaluation system and the method thereof help comprehensively evaluates the quality of a plurality of processes, and can effectively grasp comprehensive situation of the process quality so as to provide basis for the continuous improvement in the process quality, and provide assurance for quality improvement of cigarette products. The system and the method combine the single-process quality evaluation method and the grey correlation analysis method. The method comprises the following steps: firstly, computing process capability indexes of various process parameters; then, comprehensively evaluating a Cpk value by the grey correlation method; finally, obtaining a comprehensive evaluation result which is taken as a process quality rank of various evaluated objects. Production practice can be effectively directed by analyzing the Cpk and the process quality ranking result.

The invention relates to a method for evaluating battery performance based on a Delphi method and the grey relation theory. The method comprises the steps of determining evaluation indexes of the battery performance, setting up an analytical sequence, utilizing the Delphi method for determining the weight of factors affecting the battery performance, conducting dimension removal processing on actual values and ideal values of indexes of a battery to be evaluated, determining a reference matrix, setting up a grey relation model of battery comprehensive performance evaluation, obtaining the relation coefficient Xi0i(k) between the kth evaluation index of the ith evaluation object and the reference value according to grey correlation analysis, calculating the relation coefficient, and obtaining the relation degree of the battery according to the grey relation model of the battery comprehensive performance and the weight determined by the Delphi method. According to the technical scheme, a multi-index comprehensive evaluation method is provided for the performance evaluation of the battery, the one-sidedness of serving the single index as the evaluation criterion is overcome, and the reliable evaluation method is provided for the performance evaluation, screening and matching of the battery.

The invention discloses a high-voltage circuit interrupter fault diagnosis method based on grey correlation fuzzy clustering. A fuzzy similarity relation matrix is gained by means of a correlation coefficient method, and then a transitive closure operation is conducted. On the basis, clustering analysis is conducted, so that a class which a fault to be diagnosed is in can be gained. By searching for a fault which is similar to the fault to be diagnosed in the class, the component which produces the fault can be gained. The grey correlation analysis method is a powerful tool for resolving a fault diagnosis with little data and weak conditions, and has the advantages of being simple in modeling, little in needed data, and capable of gaining an accurate fault diagnosis under the condition that a confidence level is not very good, thereby providing a basis for reasonable recondition arrangement and safe operation. Large amount of human resource is saved and unnecessary waste is reduced. By adopting the high-voltage circuit interrupter fault diagnosis method based on grey correlation fuzzy clustering in the fault diagnosis of a high-voltage circuit interrupter, the work volume is reduced greatly. The high-voltage circuit interrupter fault diagnosis method based on grey correlation fuzzy clustering has a good application prospect.

The invention provides a method for evaluating operational safety of an interconnected power grid. The method includes computing various indexes of the power grid and a new project in each power grid sub-area to be used as original sample data, and constructing a sampling space; adopting the proportion of load of each power grid sub-area to total load of the power grid as an expert weight, obtaining a composite value of each single index by means of weighted computation and using the composite values as sample data; computing the correlation degrees of the various indexes, and obtaining objective weight of the various indexes by means of normalization computing; carrying out normalization based on the objective weights of the various indexes after composite values of the single indexes are computed, and computing correlation coefficients; carrying out weighted computation for the objective weights of the single indexes and the obtained correlation coefficients and obtaining the quality sequence of the power grid and the new project; and obtaining an overall safety index of each power grid sub-area by means of weighted computation according to the objective weights of the indexes, using the overall safety indexes as sample data, computing correlation degrees of each power grid sub-area by the aid of grey correlation analysis, and obtaining the quality sequence of safety of the various power grid sub-areas.

The invention discloses a multi-level evaluation method of horizontal-well volume fracturing effect influence factors. The method sequentially includes the following steps: 1) establishing an evaluation index database, which includes a sample set, a fracturing effect influence factor set and an evaluation index main-factor set; 2) establishing a multi-level evaluation system according to the evaluation index database; 3) utilizing a grey correlation analysis method to calculate all influence factor weight coefficients in the multi-level evaluation system, sorting the same to clarify primary-secondary relationships, and evaluating a fracturing effect; and 4) calculating a comprehensive reservoir evaluation factor, classifying reservoirs where all fracturing wells are located, and evaluatingthe fracturing effect. According to the method, the factors of volume-fracturing horizontal-well reservoir physical-properties, fracturing construction and production dynamics and the like are comprehensively considered, a purpose of multi-level evaluation on the horizontal-well volume fracturing effect influence factors is achieved through calculating the weight coefficients of all the influencefactors of different levels and the comprehensive reservoir evaluation factor, and an important guiding role is played on horizontal-well volume fracturing optimization design and development of tight oil reservoirs.

A method for analyzing influence factors of production decline of an oil and gas field includes the following steps that A, an influence factor set is determined; B, an analysis sequence is determined according to historical data; C, non-quantity processing is conducted on analysis sequence data; D, by the adoption of an improved grey correlation analysis method, influence factor association degrees are obtained and ranked; E, by the adoption of a combined hierarchical analysis method, factor weights are calculated and ranked; F, comprehensive analysis is conducted on the sequence obtained in the step D and the sequence obtained in the step E, a final influence degree sequence is obtained, and comprehensive analysis of the influence factors of production decline of the oil and gas field is achieved. According to the method, the determining mode of an identification coefficient p of a conventional grey correlation analysis method is improved, and subjectivity brought by empirical selection is eliminated; by means of the combined hierarchical analysis method, the importance degrees of the influence factors are determined from the subjective aspect and combined with an objective result. Calculation results obtained through the subjective method and the objective method are combined, so that an analysis result is more scientific, accurate and reasonable.

The invention discloses a soft measurement method for sewage pumping station flow of an urban drainage converged network. The conventional drainage pipe network system has lots of uncertain factors and high measurement hardware cost. The method comprises the following steps of: analyzing main influencing factors of converged node pumping station flow by using mechanism analysis and priori information, and primarily determining influencing factors of a back-propagation (BP) neural network, namely determining input / output variables; determining lag time of different upstream pumping station flows by using a grey correlation analysis method; and establishing a grey neural network model on the basis of pumping station historical operating data, and predicting the converging node pumping station flow. By combining two methods of grey correlation analysis and grey neural network, the method solves the problem of difference of drainage time delay of different upstream pumping stations, well simulates the nonlinear pipe network drainage process, realizes soft measurement of converged node sewage pumping station flow, saves the hardware resources, and is low in cost and high in accuracy.

The present invention discloses a method and an apparatus of acquiring an inter-well communication relationship. The method comprises: acquiring a first production data set of a first oil well and a second production data set of a second oil well, wherein the first production data set and the second production data set are production data of the oil wells at different time points within the same time period; acquiring a grey correlation degree coefficient between the first production data set and the second production data based on a grey correlation analysis method; acquiring a dynamic time similarity value between the first production data set and the second production data set based on a dynamic time warping algorithm; and according to the grey correlation degree coefficient and the dynamic time similarity value, acquiring a communication coefficient for representing communication performance between the first oil well and the second oil well. The technical scheme solves a technical problem in the prior art that considering a delay causes determining of an inter-well communication relationship to be inaccurate, thereby improving accuracy of acquiring an inter-well communication relationship.

The invention discloses an evaluation method for a soft foundation treatment scheme. The method comprises the following multiple steps of: a. classifying whether soft soil is subjected to shallow, medium and deep treatment by applying a case-based reasoning technology; b. determining an evaluation index system with a Delphi method; c. obtaining an evaluation index weight with a combined weighting method combining an entropy weight method with an analytic hierarchy process; d. screening evaluation indexes by applying fuzzy cluster analysis; and e. calculating a grey evaluation weight by applying grey correlation analysis in a grey theory, establishing a fuzzy weight matrix and calculating a final evaluation result with a fuzzy comprehensive evaluation method. According to the method, different theories and methods are applied in links of evaluation work, so that the defect of excessive dependence on expert experience in a conventional evaluation method for a soft foundation treatment scheme is overcome, both expert opinions and actual situations can be reflected, and the reliability of a comprehensive evaluation result is high.

The invention relates to a method for a grey correlation analysis method to determine the number of hidden layer characteristic graphs of a convolutional neural network, comprising steps of taking a binary image of a traffic sign as an image database, using the convolutional neural network method to perform identification, introducing a gray correlation analysis method in a network training process in order to automatically choose a hidden layer characteristic image which has a greatest impact on the identification result so as to optimize a network structure, taking the traffic sign as an object to perform identification and performing optimization on the CNN network structure. The experiment shows that the number of the characteristic image can be adaptively determined by using the method and the optimization of the CNN network structure can be finished. Compared with the experiment method, the invention can improve and determine the efficiency of the network.

The invention discloses a method for recognizing reservoir fluid properties based on grey correlation analysis. The method includes the following steps of 1, collecting the six parameter values of gasometry, themolysis, quantitative fluorescence, porosity, permeability and interval transit time of a stratum to be analyzed and stratums with oil test conclusions, wherein the stratum to be analyzed and the stratums with oil test conclusions belong to the same oil and gas reservoir; 2, conducting dimensionless processing on the six parameters; 3, calculating the correlation degree; 4, calculating the weight coefficient of each parameter; 5, conducting weighted summation on three parameters of gasometry, themolysis and quantitative fluorescence of each stratum to obtain the oil and gas abundance index of the stratum, and conducting calculation on the other three parameters to obtain the physical property index; 6, drawing an interpretation chart with the two indexes, and marking areas; 7, calculating the oil and gas abundance index and the physical property index of the stratum to be analyzed, and drawing dots in the interpretation chart, wherein the areas corresponding to the dots represent reservoir fluid properties. According to the method, the reservoir fluid properties are comprehensively evaluated with multiple parameters, so that the limitation and multiplicity of solutions of a single-parameter evaluation method are avoided, and the logging oil-gas-water layer interpretation coincidence rate is increased.

The invention provides a fault diagnosis method of capacitive equipment. The fault diagnosis method comprises the following steps of: utilizing a grey correlation analysis method to obtain a grey correlation degree between a dielectric loss factor tandelta of the capacitive equipment and an environmental factor and taking the obtained grey correlation degree as characteristic quantity to establish a matter-element model of the capacitive equipment to be diagnosed; and then, gaining the grey correlation degree between the matter-element model of the capacitive equipment to be diagnosed and each pre-established typical fault matter-element model by applying an extension theory; and finally, comparing the grey correlation degrees to judge that the equipment has the type of fault if the grey correlation degree between the matter-element model of the capacitive equipment to be diagnosed and the type of fault matter-element model is the highest. According to the invention, influences on diagnosed results by the environmental factor are effectively eliminated, not only various probable faults can be accurately diagnosed, but also the condition that a plurality of the faults simultaneously happen can be diagnosed. The method provided by the invention has the advantages of definite physical meaning and easiness of realizing programming.

The invention belongs to the technical field of drilling safety, and discloses a reservoir gas drilling safety risk analysis system and method based on a BP neural network. A gray correlation analysisof reservoir gas drilling risk identification is carried out; fuzzy identification of the reservoir gas drilling risk identification is carried out; the invention aims at the engineering practical problem of risk control of a gas drilling reservoir, the method and software achievement for real-time observation and prediction of gas drilling accident identification are established through basic theory analysis, model establishment and computer simulation analysis by combining modern information acquisition, data processing, risk intelligent identification and management technologies to reducethe possibility of safety risk occurrence to the greatest extent. According to the invention, a drilling accident identification method based on gray correlation degree is provided by utilizing a graycorrelation analysis method. The identification example shows that the method of risk prediction with grey correlation degree is feasible and has the advantages of small calculation amount, simplicity and convenience, reliable result and the like.

The invention discloses a prediction method for establishing a multiple linear regression model on the basis of a grey correlation analysis method so as to predict a coal calorific value. The method carries out correlation analysis on the coal calorific value and five indexes including moisture, ash content, volatile components, gelatinous layer maximum thickness and an oxygen and carbon atomic ratio to find a main impact factor associated with the coal calorific value and establish the multiple linear regression model so as to predict the coal calorific value. The method adopts a correlation analysis method in a grey system theory to analyze five factors which affect the coal calorific value, a main factor which affects the coal calorific value is picked up from the five factors, and the multiple linear regression model between the coal calorific value and the main impact factor is established. The prediction method of the coal calorific value is simple and feasible and is high in prediction precision, and a relative prediction error does not exceed + / -8%.

The invention belongs to the technical field of planning of automatic collision prevention paths of ships, and mainly relates to a multi-ship encounter collision prevention method for bacterial foraging optimization. The multi-ship encounter collision prevention method comprises the following steps: establishing a required simulation interface of a ship simulation test, and determining parameters of a ship and each target chip in multi-ship encounter collision prevention; judging an encounter situation and analyzing collision risks; establishing a target function (an optimization algorithm target function) of the multi-ship encounter collision prevention method; determining a key ship which needs to prevent collision and risk based on a grey correlation analysis method: determining an ideal effect sequence: calling an improved bacterial foraging algorithm to optimize the multi-ship encounter collision prevention paths; completing the encounter collision prevention sailing, re-sailing and restoring original courses. According to the multi-ship encounter collision prevention method, the quality of the bacteria is integrally analyzed based on a mean value and variance of the bacteria, and a last-time trended target function value is combined for judging bacteria for copy operation, so that the convergence rate and the searching precision of the algorithm are improved, and the efficiency of generating a multi-ship encounter collision prevention strategy is improved.

The present invention discloses a wind speed prediction method of a wind farm. Problems are mainly considered that spatial correlation among wind farms, unscented Kalman Filter optimization, and the like are not well considered in an existing method. The method mainly comprises: calculating a rank correlation coefficient between a target wind farm and the other 21 wind farms if 22 wind farms are given; determining a wind farm for prediction according to the correlation coefficient; and selecting a wind farm with a Kendall rank correlation coefficient greater than 0.55 and a Spearman rank correlation coefficient greater than 0.75; then establishing a non-linear state space model by using support vector machine regression, and performing unscented Kalman filter prediction by using the established non-linear state space model; optimizing a scale parameter of the unscented Kalman filter according to a principle of prediction error minimization; and finally, selecting wind speed data of a wind farm of a same time in four years, and performing grey correlation analysis by using the wind speed data and wind speed data of a target wind power turbine, No.9 wind power turbine, of the same time in the first year.

The invention relates to a short-term power load forecasting method which is characterized by comprising the steps of: selecting a similar day set; constructing a RBF (Radial Basis Function) neural network forecasting model optimized by a bat algorithm; forecasting a power load on a forecasting day by utilizing the RBF neural network forecasting model optimized by the bat algorithm; and the like.According to the invention, on the basis of conventional gray correlation analysis, a similar day with a higher similarity is selected by adopting a distance similarity and shape proximity correlatedcomprehensive gray correlation degree, the defect that a conventional gray correlation analysis method only considers a geometric similarity degree among data sequences, but ignores a number proximitydegree when selecting the similar day is made up, and forecasting accuracy is improved; a weight of a RBF neural network is optimized by utilizing the bat algorithm, so that the defect that the RBF neural network is easy to fall into local optimization can be overcome, a convergence rate of the integral network is improved and computation efficiency of the integral network is improved; and the short-term power load forecasting method has the advantages of scientificity, reasonability, high applicability, good effect and the like.

The invention provides a voltage stabilization fault screening and ranking method based on a grey correlation analysis method, which comprises the steps of determining indexes for the severity of voltage stabilization faults in an electric power system; calculating to acquire values of the indexes; forming an initialization decision-making matrix according to the indexes; standardizing the initialization decision-making matrix to acquire a standardization decision-making matrix; calculating a correlation coefficient and a grey correlation degree according to the grey correlation analysis method; and screening to acquire a fault screening comprehensive index, and acquiring a fault severity ranking result according to the fault screening comprehensive index. The method provided by the invention reflects fault severity conditions more comprehensively and more effectively, thereby being convenient for the operating and scheduling personnel to take correspondingly prevention and correction measures timely, reducing influences imposed on power grid voltage stabilization by accident disturbance, and having important significance for guiding reliable running of an actual power grid.

The invention relates to a grey weighting method for sewage treatment process comprehensive evaluation, and belongs to the field of sewage treatment technology optimization. The grey weighting method comprises the following steps that 1, combined weights of evaluation indexes are determined, i.e., an entropy weight method and an order relation analytical method are respectively adopted for determining objective and subjective weights of evaluation indexes, and then, game theory thoughts are applied to determining the combined weights of the evaluation indexes; 2, the grey correlation analysis theory is applied to determining the optimum process. The grey weighting method has the advantages that the grey weighting method is used as an evaluation process of a sewage treatment process, the whole evaluation process adopts an objective and subjective weighting method, ranging results are enabled to show subjective information and objective information, the evaluation decision method is simple and intuitive, and the computer programming is easy.

The invention discloses a rail transit key node and a key road section identification method. The method includes: based on a complex network theory and a PageRank algorithm, calculating a topologicalindex value of the rail network as a node importance evaluation system value; carrying out evaluation value calculation on a node importance evaluation matrix by adopting three evaluation methods ofa grey correlation analysis method, a TOPSIS method and a principal component analysis method, determining weights of evaluation results by utilizing an entropy weight method, and finally obtaining importance values of the nodes and the road sections so as to identify the key nodes and the key road sections. According to the invention, identification of the key nodes of the rail transit network isobjectively and comprehensively considered; the key node importance degree calculation method is designed by using relevant theories such as a complex network and comprehensive evaluation, stations needing important maintenance in rail transit operation can be judged, the importance degrees of all the stations are ranked, and a choice is further provided for robustness analysis of the key nodes of the rail transit network.

The invention provides an integrated supply chain performance indicator evaluation method, which is characterized in that the method comprises the following steps: step a, determining quantification indicators of supply chain performance; step b, determining quantification indicators of customer satisfaction evaluation; step c, calculating the two kinds of quantification indicators based on an analytic hierarchy process; and step d, determining performance indicator results according to calculation results. The invention additionally provides an integrated supply chain overall performance evaluation system, which is characterized in that the system comprises a customer satisfaction evaluation indicator system and a supply chain value evaluation indicator system, and the two systems are combined together to establish the integrated supply chain overall performance evaluation system. The invention aims at obtaining integrated supply chain overall performance evaluation indicator values through customer satisfaction indicator evaluation and supply chain performance indicator evaluation, and providing helps for industries such as the manufacturing industry, the retail industry and the like in making operating decisions according to performance evaluation results.

The invention discloses a transformer fault diagnosis method based on an entropy weight method and grey correlation analysis, belonging to the technical field of transformer fault diagnosis. The transformer fault diagnosis method comprises the steps of: carrying out standardization processing on transformer fault sample data; adopting the entropy weight method to determine weight of a transformer fault diagnosis index; and determining a fault type of a transformer through calculating Grey Euclid weighted correlation degree. The transformer fault diagnosis method makes full use of all information of gas in oil data, exerts the advantage that the grey correlation is applicable to a small sample and poor information system, avoids defects of partial correlation and information loss, and can effectively increase accuracy rate of transformer fault diagnosis as shown by results of example analysis.

The invention provides a lead zinc ore exploitation process carbon emission short-term prediction method. Grey theories are synthesized to analyze carbon emission sources using motors as research objects and their influence factors in the ore exploitation process. Firstly, the carbon emission sources and their influence factors are analyzed, and the grey theories are adopted to perform clusteringanalysis for like factor merging; secondly, main influence factors are obtained through grey correlation analysis; finally, for solving the super- parameter optimization determining problem, a non-dominated sorting genetic algorithm with an elitist strategy is introduced into a gaussian process regression model, and a gaussian process regression prediction method based on the non-dominated sortinggenetic algorithm with the elitist strategy is proposed. It is proved through an experiment that the proposed prediction method can more accurately predict the carbon emission amount in the lead zincore exploitation process, can be directly achieved on a computer, is good in practicability, low in cost and easy to carry out, and prediction errors are smaller.

The invention discloses a trans-scale design method of a high-speed milling cutter and the milling cutter. At present, the research of the internal relation among a microstructure, a macrostructure and performance of cutter materials is absent, and scientific evidences of the design and the development of the novel high-speed milling cutter are absent. The method comprises the following steps of: (1) constructing a high-speed milling cutter safety decline behavioral characteristic model; (2) developing the high-speed milling cutter by using a high-speed milling cutter safety stability design model; (3) establishing a high-speed milling cutter safety decline behavioral characteristic model design matrix by a grey correlation analysis method to characterize the relation between milling cutter design parameters and safety decline; (4) establishing a high-speed milling cutter mesoscopic level safety model by a grey cluster analysis method; and (5) researching macroscopic and mesoscopic mechanical characteristics of a high-speed milling cutter component under the condition of presetting an external force boundary, and realizing force connection-based high-speed milling cutter trans-scale correlation through continuous medium-molecular dynamic characteristic zigzag mapping. The method is used for designing the high-speed milling cutter.

The invention discloses a failure mode recognition method of an epicyclic gearbox using a mixed domain feature vector and grey correlation analysis. The method comprises the steps that (1) the feature parameters ft, ff, fs and ftf of the time domain, the frequency domain, the order domain and the time-frequency domain are extracted to constitute the mixed domain feature vector Fm, and the weighted values of wt, wf, ws and wtf of all the feature parameters are calculated; (2) the vibration monitoring health state of the epicyclic gearbox and the historical data of various failure mode states are acquired, and the corresponding mixed domain feature vector value mj(k) is calculated to be used as a reference state matrix; (3) the feature vector t of a signal to be detected and the row vector of the reference state matrix m are both used as the input of a grey correlation analysis algorithm; (4) the correlation vector of the feature vector t of the signal to be detected and the standard mode matrix m is calculated to be used as an output vector of the grey correlation analysis algorithm. The failure mode recognition method of the epicyclic gearbox using the mixed domain feature vector and grey correlation analysis has the advantages of being simple in principle, simple and convenient to operate, stable and reliable, high in precision, suitable for high interference and varied working conditions and the like.

The invention discloses an unmanned aerial vehicle flight path optimization method based on deviation maximization and grey correlation analysis, belonging to the unmanned aerial vehicle flight path planning and uncertainty multiattribute decision making field. In the method, an unmanned aerial vehicle flight path scheme optimization decision-making target system is established according to different threats of the unmanned aerial vehicle, and an unmanned aerial vehicle flight path scheme optimization mathematical model is constructed by virtue of evaluation attributes. Concretely, according to a flight path planning scheme set, deviation maximization method is adopted to objectively weight all the evaluation attributes, grey correlation analytic method is adopted to solve the optimization model, grey correlation information existed among all the attributes are fully utilized, and finally an optimal flight path scheme is determined according to relevancy of decision layer. The method of the invention has strong objectivity, requires no expert advice to estimate and has strong feasibility.