38 results about "Gray relational analysis" patented technology

The invention relates to a method for determining the stability of a power mode based on gray relational analysis and belongs to the field of power supply and distribution management. Based on a two-stage decision algorithm of mode recognition, the method defines a power mode time sequence by a 12-month coefficient for users with no historical electricity stealing records and having meter data more than two years, determines the power mode stability by a gray relational analysis method, predicts a reasonable range of current electricity consumption with reference to a historical power model so as to determine whether the user's current electricity consumption is abnormal. The reasonable range can improve the accuracy of the abnormal judgment without an increase in the workload of manual review, and can narrow the scope of the review, improve the efficiency of the review and the reliability of the meter data, promotes rapid improvement in the quality of a meter reading system by finding a weak link, promotes the development and operation of corresponding computer analysis software and, improve the automation and informatization level of service related to meter reading, can be widely used in the field of centralized meter reading management system design, operation and management.

The present invention discloses a transformer substation energy efficiency assessment method based on an AHP (analytic hierarchy process). The method comprises: acquiring n index values for m to-be-assessed transformer substations; establishing an original index data matrix based on a gray relational analysis method, and carrying out standardized processing to generate a to-be-assessed index data matrix; establishing an index hierarchical structure, determining a relative weight,relative to a top level index, of each energy efficiency assessment index of a bottom layer of the index hierarchical structure to acquire a relative weight matrix; as for the to-be-assessed index data matrix, separately calculating an index value of each energy efficiency assessment index of each to-be-assessed transformer substation after the standardized processing, and a correlation coefficient between reference values of corresponding energy efficiency indexes in a reference line, thereby acquiring a correlation coefficient matrix; and calculating an integrated assessment result matrix of m to-be-assessed transformer substations. According to the method disclosed by the present invention, a reasonable degree of energy efficiency of the transformer substations can be analyzed, a power saving magnitude before and after reconstruction of the transformer substations can also be analyzed and assessed, so that the method has the advantages of high data assessment accuracy, and high-speed and efficient assessment.

The invention discloses a displacement experiment artificial core analysis preparing method based on experimental and mathematical algorithms, and the method combines qualitation with quantitation. The method comprises the steps that physical parameters of an artificial core are used as target parameters for preparation of the artificial core; influencing factors of the physical parameters of theartificial core are determined; multiple sets of combined experiment schemes are made, and the artificial core is prepared according to all the combined experiment schemes, and the physical parametersof the artificial core are measured after preparation is completed; preparation condition parameters of all the combined experiment schemes are used as basis, and based on a gray correlation analysismethod, relevancy degrees of all the influencing factors and all the target parameters are determined; according to the relevancy degree rank of all the influencing factors and the target parameters,larger influencing factors and smaller influencing factors are determined; based on a statistic analysis result of the gray correlation analysis method and a BP neural network theory, a particle sizeratio prediction mathematical model is built; a matching prediction result is calculated through the particle size ratio prediction mathematical model and serves as a reference which provides data support for artificial core manufacturing.

The invention discloses a method for constructing a small and medium-sized reservoir dam safety evaluation index system based on the important contribution degree, which includes the following steps: analyzing and researching the main influencing factors of the small and medium-sized reservoir dam safety through data analysis, field investigation, expert consultation and other methods , cause and degree of influence, using the Delphi method to conduct expert questionnaire surveys, calculating the importance of indicators, and initially selecting evaluation indicators; using the gray correlation analysis method to quantitatively calculate the contribution rate of the evaluation indicators to the evaluation results; assigning the importance and contribution rate combination In order to evaluate the important contribution of indicators; determine the index screening criteria and threshold; according to the screening criteria, retain the top k indicators with a large cumulative important contribution, and eliminate the smallest important contribution indicators, and construct a small and medium-sized reservoir dam safety evaluation index system. It avoids the subjectivity of artificial index selection and the rigidity of data analysis, making the dam safety evaluation index system more scientific, refined, and pertinent.

The invention discloses a loss reduction measure making method based on synchronous line loss abnormity identification, which comprises the following steps: identifying synchronous line loss anomaly data, and taking corresponding loss reduction measures according to an identification result; extracting the fluctuation characteristics of the same-period line loss abnormal data through statistical analysis; constructing a same-period line loss electric quantity matrix, and performing singular value decomposition on the matrix to extract low-rank features of same-period line loss abnormal data; performing gray correlation analysis on the same-period line loss allocation data, and extracting homodromous correlation characteristics of the same-period allocation line loss abnormal data; and obtaining the characteristic that the rank sum of the abnormal data of the same-period line loss deviates from the normal data is approximately equal by analyzing the difference between the theoreticallycalculated line loss and the same-period line loss. According to the method, the characteristics of the same-period line loss abnormal data can be effectively extracted, the corresponding neural network is constructed for training, the same-period line loss abnormal data can be effectively identified, corresponding loss reduction measures can be taken according to different identification results,and the loss reduction efficiency can be effectively improved.

The invention relates to a firearm design scheme evaluation method based on a fuzzy decision diagram and a gray correlation analysis. The method comprises the steps that 1, an evaluation index system of a firearm design scheme is created; 2, global weights of evaluation indexes are calculated based on the fuzzy decision diagram; 3, by means of the global weights, gray relational degrees of alternative schemes are calculated, and evaluation on the firearm design scheme is achieved according to the gray relational degrees. According to the method, the global weights of the evaluation indexes are obtained through the fuzzy decision diagram; the gray relational analysis serves as an evaluation subject method, the defects that the fuzzy decision diagram does not provide the scheme evaluation subject method, and the gray relational analysis can not evaluate the mutual effect among the evaluation indexes are overcome, advantage complementation between the fuzzy decision diagram and the gray relational analysis is achieved, and therefore a set of complete firearm design scheme evaluation method which can evaluate evaluation index comprehensive influence relationships is formed.

The invention provides a soil suitability evaluation method and device and belongs to the soil assessment technical field. The soil suitability evaluation method comprises the following steps that: any one method is selected from a fuzzy mathematic method, a gray relational analysis method and an comprehensive index evaluation method as a first soil evaluation method; 2, any one method is selectedfrom the fuzzy mathematic method, the gray relational analysis method and the comprehensive index evaluation method as a second soil evaluation method; the soil fertility parameters of soil to be evaluated are calculated according to the selected first soil evaluation method, and with the obtained soil fertility parameters adopted as suitability evaluation factors, the second soil evaluation method is adopted to perform soil suitability evaluation to obtain a soil suitability coefficient; and a soil suitability evaluation level corresponding to the soil suitability coefficient is searched. With the above process adopted, the suitability evaluation of the quality of the soil is realized. The method and device are objective and scientific.

The invention relates to a direct dispersion separation modeling prediction control method under multiple weather types based on GRA-LMBP weights. Firstly, performing statistics and collection on meteorological radiation data of many years in Beijing area, selecting typical meteorological years according to a normal fitting method and using a revised definition index to classify the weather types;secondly, using support vector machine (SVM), gray relational analysis (GRA) based support vector machine GRA-SVM and principal component analysis (PCA) based support vector machine (PCA-SVM) prediction models to obtain prediction results of three single models under each weather type; then using the gray relational analysis to obtain the weight coefficient of each model under each weather type;then fitting an LMBP neural network prediction model according to each single model prediction result and prediction weight coefficient under each weather type; and finally, using the weight coefficients obtained by the LMBP model to calculate the combined prediction model prediction results of each weather type. Compared with the prior art, the direct dispersion separation modeling prediction control method under multiple weather types based on the GRA-LMBP weights has the advantages of high precision, good calculation stability and the like.

The invention discloses a processing method for test data of injection well casing damage, and solves the problem that different conditions about injection well casing damage of different periods in the block cannot be quantized and compared. The method comprises the following steps of firstly normalizing the data of casing damage describing corrosion main bodies of the respective wells, assigningdifferent weights for the percentage of casing in different degrees of corrosion according to the result of normalizing processing, modifying based on the number of pipe segments of non-perforation section perforation, and calculating weighted sum values of the casing damage degrees of corrosion of the respective injection wells; calculating a relative grey relational degree between the weightedsum values of the casing damage degrees of corrosion of the injection wells and the collected productive factors influencing corrosion of the injection wells and the corrosive environmental factors byusing a gray relational analysis grade method, and determining the rank of significant influencing factors and extent of the influence; finally clearly studying the corrosion mechanism of casing damage in the block, and making full use of the relevant information contained in the test data of casing damage of the injection wells, thereby extending the engineering application value of test projects of casing damage of injection wells.

The embodiment of the invention provides a method and a system for predicting grape downy mildew. The method comprises the following steps of: obtaining data from onset samples of a set of grape samples infected with downy mildew; processing the data from the onset samples to obtain a relational prediction factor based on the grey relational analysis method; inputting the relational prediction factor used as the feature vector of the SVM model, and obtaining the optimal model parameters based on the PSO algorithm to construct a grape downy mildew prediction model; obtaining prediction resultsof grape downy mildew by analyzing grapes infected with downy mildew by using the grape downy mildew prediction model. The prediction method and system provided by the embodiment of the present invention screen out the prediction factors that can better reflect the change trend of grape downy mildew through the grey relational analysis method, and combine the particle swarm optimization algorithmto optimize the model parameters of the support vector machine to establish the grape downy mildew prediction model. The model can quickly and accurately predict the disease grade of grape downy mildew in the short term, can effectively improve prediction accuracy of grape downy mildew, and can provide a basis for disease prevention.

The present disclosure provides a selection method of base asphalt for rubber asphalt based on grey relational analysis, which belongs to the technical field of selection methods of base asphalt. The selection method includes the following steps: determining factors affecting the performance of rubber asphalt and rubber asphalt performance evaluation indicators; ranking the factors affecting the performance of rubber asphalt according to respective affecting degrees thereof on each of the rubber asphalt performance evaluation indicators by using a grey relational method; and determining affecting factors of chemical components of base asphalt to the performance of rubber asphalt, and selecting base asphalt according to the affecting factors. The present disclosure uses the grey relational analysis method to systematically study the influences of chemical components of base asphalt on the performance of rubber asphalt.

The invention discloses a mechanical failure state monitoring method based on gray relational analysis and a method thereof. The system comprises the components of a data acquisition module which is used for acquiring state data of a machine; a data processing module which is used for performing preprocessing on the acquired state data and processes the state data to a vector; a data analyzing module which analyzes the acquired vector through a gray relational analysis method and determines a mechanical fault state; and a result display module which displays a result that is analyzed by the data analyzing module. Compared with the prior art, the mechanical failure state monitoring system based on gray relational analysis and the method thereof have advantages of settling problems such as non-unique correlation value caused by resolution coefficient influence in a traditional method, using the gray relational analysis method as a mechanical fault state monitoring method, effectively improving accuracy and reliability of the mechanical failure state monitoring result, and realizing high practicability, wide application range and easy popularization.

The invention discloses a new method for obtaining the weight of geological target evaluation parameters, which includes the following steps: S1: determining the parameter characteristic value of the geological target evaluation; S2: determining the expert weight of the evaluation parameter, and obtaining an expert experience scoring table; S3: constructing Parameter evaluation matrix; S4: Construct expert constraints to determine the mother sequence of grey relational matrix; S5: Construct parameter evaluation matrix under expert constraints; S6: Normalization of grey relational analysis evaluation index parameters; S7: Calculate grey relational degree coefficient ; S8: Calculate the grey relational degree; S9: Obtain the weight of the target evaluation parameter; S10: Target evaluation. The constraints of the evaluation parameters are constructed by using the expert experience value, and then the parameter matrix under the constraints of the experts is established, and the weights of the parameters are obtained. The method can objectively determine the parameter weights under the constraints of regional geological background, overcome the direct intervention of human beings in the previous methods, and then evaluate favorable targets reasonably and effectively, and realize the optimization of favorable exploration targets.

The invention provides a pipeline integrity evaluation method and device and electronic equipment. The method comprises the steps that an analytic hierarchy process is adopted, and the initial weight of each evaluation index in an evaluation index system is determined; based on the data set of each evaluation index of each pipeline, a gray correlation analysis method is adopted to determine a coupling relationship among the evaluation indexes, and the initial weight is corrected according to the coupling relationship among the evaluation indexes to obtain a comprehensive weight of each evaluation index; and evaluating the integrity of the pipeline based on the comprehensive weight. According to the embodiment of the invention, the initial weight of each evaluation index in the evaluation index system is determined and the initial weight is corrected according to the coupling relationship among the evaluation indexes to obtain the comprehensive weight of the integrity evaluation index, so that the subjective randomness caused by purely using a subjective weighting method is avoided; and data information distortion possibly caused by purely using an objective weighting method is avoided, and accurate judgment and evaluation of the integrity state of the pipeline are realized.

The invention belongs to the technical field of tourism performance value evaluation, and relates to a tourism performance service value evaluation method, which comprises the steps of 1, obtaining influence factor indexes of tourism performance service values; 2, obtaining comment data and a comprehensive score; 3, obtaining a travel performance service value feature word list; 4, extracting feature sentences; 5, training an LSTM model; acquiring an emotion value; 6, calculating a gray correlation degree; 7, determining a topological structure of a gray neural network model; 8, training the gray neural network model; 9, obtaining the evaluation value of specific tourism performance play services. According to the invention, cultural elements are added to the evaluation of the tourism performance service value. An LSTM-based fine-grained sentiment analysis and gray neural network model is provided, so that the tourism performance service value evaluation method is enriched, and the evaluation is more intelligent and accurate. An index system is determined through gray correlation analysis, subjective and objective combination is achieved, and the method is more scientific.