54 results about "Fuzzy probability" patented technology

A fuzzy probability comprehensive judgment-based battery state-of-health estimation method belongs to the technical field of lithium iron phosphate battery estimation and aims to solve the problems that the state-of-health of a single battery cannot be ensured by a traditional health estimation technology to cause that the lifetime of a battery pack is remarkably reduced. The fuzzy probability comprehensive judgment-based battery state-of-health estimation method comprises the steps of obtaining estimation data by charge-discharge experiment on a battery to be estimated; obtaining a relation between a state-of-charge (SOC) value and a voltage during the charge-discharge process of the battery; performing normalization on voltage values of the battery under different SOCs, and then taking the voltage values as a state-of-health judgment object of each single battery; calculating an index weight forming an evaluation index coefficient, and determining the state-of-health of each single battery according to a maximum probability principle; and determining the state-of-health of the lithium iron phosphate battery pack by fuzzy comprehensive judgment according to a maximum membership principle. By health estimation on the grouped battery pack, the initialization performance of the battery pack can be greatly improved.

The invention relates to a reliability analysis method for an electromechanical actuator based on a fuzzy dynamic fault tree. According to the method, top, intermediate and bottom events of the electromechanical actuator analyzed and determined to establish the dynamic fault tree, a dynamic logic gate is replaced with an algebraic operator, an algebraic model of the dynamic fault tree is converted into and solved, data of a triangular fuzzy set is used to represent the fuzzy reliability of the bottom event, the algebraic model is decomposed into a static subtree and a dynamic subtree for solution, the fuzzy probability of failure of an electromechanical actuator system is obtained via integration, and a weak link of the electromechanical actuator system is determined by analyzing the fuzzy importance degree. The method of the invention can be used to analyze the reliability of the electromechanical actuator effectively, solve the problem that traditional dynamic fault tree analysis is high in the computational complexity, and provides reference for fault positioning of the electromechanical actuator.

The invention relates to a reliability analysis method for an embedded safety-critical system, and belongs to the technical field of information safety. The method comprises the following steps of: constructing a software and hardware fault representation set; classifying faults in the fault representation set to acquire a software and hardware fault mode set and constructing a subsequent fault mode set by combining a fault-associated probability table; constructing a static fault tree associated with a software and hardware fault on the basis of the subsequent fault mode set; and analyzing the static fault tree to acquire a fault analysis result. In the method, software and hardware basic units of the embedded safety-critical system are subdivided, a subsequent fault mode is constructed through a fuzzy probability multi-signal flow graph model by combining association of faults of each basic unit, a static fault tree model is constructed by using time sequence logic relation between the faults reflected by the subsequent fault mode set, and the reliability of the system can be more accurately and effectively evaluated by using the model.

The invention discloses a fuzzy entropy-based noisy signal processing method and an iterative singular spectrum (SSA) soft threshold denoising method. The method is suitable for noisy signals. Assuming that the noisy signal of length N xin = {x1, x2, ..., xN} and assuming that the additive white noise therein is uncorrelated with the signal, a d-dimensional vector is constructed and the similarityand fuzzy probability are defined by utilizing an original signal xin; a (d + 1)-dimensional vector is constructed and the corresponding similarity and fuzzy probability are defined by the same method; and the fuzzy entropy is defined in the drawing of the description. For components obtained by utilizing a known signal decomposition method, the singular spectrum distribution of all the components is defined as a fuzzy entropy spectrum. The fuzzy entropy for quantifying the complexity of the system in a chaos theory is utilized to characterize a noise plane and provide a more effective path for the processing of the noisy signal; the fuzzy entropy spectrum-based iterative singular spectrum (SSA-IST) soft threshold denoising method has the denoising performance better than that of the traditional truncated singular spectrum method, and wavelet transform and empirical mode decomposition denoising method.

The invention relates to a road usability performance evaluation technology, in particular to a combined type pavement usability performance evaluation method for an underground road, which can combine randomnesss with fuzzification and can accurately evaluate road condition. In order to realize the aims, according to the technical scheme adopted by the invention, the combined type pavement usability performance evaluation method for the underground road comprises the following steps: collecting the following road condition indexes: PCI (pavement condition index), RQI (riding quality index), PSSI (pavement structure strength index) and SRI (skid resistance index); computing information distribution values at sample points; computing fuzzy probability distribution of pavement usability performance in the probability theory field; confirming fuzzy and random risks of the pavement usability performance in regions; computing comprehensive fuzzy and random risk level of the pavement usability performance; outputting a module through data; and judging level of pavement usability performance evaluation. The combined type pavement usability performance evaluation method provided by the invention is mainly applied to the road usability performance evaluation.

The invention relates to a carbonylation acetic anhydride production synthetic reaction kettle explosion analyzing method based on fuzzy fault tree. According to the explosion analyzing method, a fault tress is firstly constructed for the explosion accident of the carbonylation acetic anhydride production synthetic reaction kettle, with the application of the fuzzy fault tree theory, fuzzy reliability analysis is performed on the carbonylation acetic anhydride production synthetic reaction kettle according to the fuzzy information obtained through statistics of the actual operating state of onsite equipment and the expert experience, so that the possibility distribution of fuzzy probability of the explosion accident of the carbonylation acetic anhydride production synthetic reaction kettle is worked out; and structural importance analysis is carried out on the possibility distribution by the structure importance coefficient approximate value method, the weighted structural importance analyzing method which sorts and grades the bottom events of the fault tree is utilized to determine the most principal factor which affects the system, so the invention provides a new method and a new approach for the safety analysis of the system.

The invention discloses a camera focusing method and device, and a camera. The camera focusing method and device are used for improving a focusing result of the camera. The method comprises the following steps: determining a detail region from a picture shot by the camera, wherein the detail region is a sub-region located by the details in the shot picture; setting a weight value of the detail region as a preset weight value, wherein the preset weight value is greater than the weight value of other region except the detail region; computing the definition of the shot picture based on the detail region and the preset weight value, and focusing according to the definition. Therefore, the detail region is determined from the picture shot by the camera, and then the weight of the detail regionis set as the maximum weight value in the current picture, so that the focusing result obtained through focusing can tend to the region located by the details, the picture fuzzy probability is reduced, and het focusing effect is improved.

The present invention provides an evaluation method and device of automotive fuel economy. The method comprises a step of establishing a neural network regression calculation model and obtaining a fuel economy probability sequence according to a vehicle speed data sequence, an instantaneous fuel consumption data sequence, an engine rotation speed data sequence, an acceleration data sequence, the neural network regression calculation model, and a fuzzy probability mapping model, and a step of comparing each fuel economy probability in the fuel economy probability sequence with a preset probability threshold orderly, and evaluating the automotive fuel economy according to a comparison result. Through the method and the device, the automotive fuel non-economic process in an automotive driving process can be effectively identified, the automotive fuel economy is evaluated according to the automotive driving data corresponding to the automotive fuel non-economic process, and an automotive driving experience is improved.

The invention discloses a method for analyzing the reliability of an electrical control and drive system of a heavy-duty numerical control machine tool. The method comprises the steps: firstly dividing a system into subsystems; secondly finding out a subsystem which frequently has faults, drawing a reliability block diagram of the subsystem, and converting the reliability block diagram into a Bayesian network, thereby calculating the fuzzy probability of the subsystem in different states, and achieving the quantification and processing of the uncertainty of the system.

The invention, which belongs to the technical field of radar signal sorting, especially relates to an evidence-C-mean (ECM) radar signal class sorting method. The method comprises: radar signals needing class sorting are obtained; feature elements of corresponding feature parameters of sampling sequences of the radar signals needing class sorting are extracted to form a feature vector; the feature vector is used as a computation input of an ECM, and the membership probability, belonging to a first radar signal, of each feature element, the membership probability, belonging to a second radar signal, of each feature element, and the fuzzy probability, belongs to the first radar signal and the second radar signal simultaneously, of each feature element in the feature vector are obtained; each feature element is classified; and according to the classification result of each feature parameter, a class sorting result of the radar signals needing class sorting is obtained.

The invention discloses a perturbation principle-based fuzzy reliability calculation method containing a fuzzy random variable, and is applied to the field of reliability. The objective of the invention is to solve the problem of structural function non-linear fuzzy random reliability. A perturbation theory and a fuzzy decomposition theory are used for carrying out perturbation quantization on fuzzy random variables, fuzzy characteristic parameters of the fuzzy random variables of the structure are expressed as the sum of true values and fuzzy perturbation microscale of the fuzzy characteristic parameters, the fuzzy characteristic parameters are decomposed into a series of interval quantities under horizontal truncation, the interval quantities are equivalent to random variables, and a mean value and a standard deviation are obtained through calculation. And meanwhile, equivalent selection is carried out on perturbation microscale. Secondly, decomposing the fuzzy probability density function and the fuzzy function function of the structure into interval quantities under a series of horizontal truncation sets, and performing Taylor series expansion on upper and lower limit values ofthe interval quantities to obtain perturbation values of the joint probability density function and the structure function; And finally, according to the definition of the structure reliability, introducing a sigmoid function as a step function by using a direct integration method, and solving to obtain a fuzzy reliability interval. Compared with a traditional convex set method, the reliability interval obtained through calculation is narrower under the same confidence level, and engineering application is more convenient.

The invention belongs to the technical field of power distribution risk evaluation and power distribution risk identification, and particularly relates to a medium-voltage power distribution network weak link identification method based on risk evaluation. Compared with a traditional risk assessment method, the invention innovatively provides a new modeling method combining a fuzzy model and a traditional probability distribution model. A hybrid fuzzy probability model of a system peak load is provided aimed at the problems of heavy overload of a distribution network medium-voltage line, heavyoverload of a transformer area distribution transformer and the like. On the basis of the traditional Monte Carlo simulation method, a risk index fuzzy membership function construction method and risk index defuzzification are provided, and the risk degree of the distribution network system is measured through the specific quantity value of the risk index after defuzzification, so that the identification of the weak link of the distribution network is realized. The method provided by the invention can help a power supply company to analyze the risk degree of the urban distribution network system and identify the weak link of the distribution network system, thereby providing a valuable theoretical basis for distribution network generation decision.

The invention discloses an intelligent prediction method for meandering river sedimentary microfacies, which comprises the following steps of: extracting waveform, amplitude and wave impedance data indifferent frequency band ranges, and generating five earthquake combination characteristics according to the protocol that a given time window is divided into three sections to carry out combinationcharacteristic on the earthquake attribute of a current point; constructing a machine learning sample library through selection of an optimal time window; according to the method, by means of a randomforest MDI method, evaluating the sample features, and performing fuzzy probability prediction on the microfacies of the optimized sample features through a random forest algorithm, then performing overlapping display on the high-probability results of each microphase, thereby acquiring a prediction result of the microfacies. Compared with the prior art, the method has the advantages that the problem that the distribution rule of each sedimentary microfacies on a plane cannot be accurately reflected due to a large well distance is solved, a sedimentary microfacies prediction model is established through sedimentary microfacies sample data construction and a random forest machine learning method, and intelligent prediction of the sedimentary microfacies of the meandering river is realized.

The embodiment of the invention discloses a three-dimensional trapezoid fuzzy method for calculating the power generation of a water-cooled photovoltaic photothermal integrated system, and the method is used for solving a technical problem that a calculation method of daily power generation of a new energy user distributed photovoltaic power generation system does not comprehensively consider uncertainty and randomness of influence factors and the applicability, practicality and application of the calculation method are difficult to satisfy in the prior art. The method of the embodiment of the invention comprises the steps of introducing a generalized three-dimensional trapezoid fuzzy set concept and a calculation method in considering uncertainty, randomness and fuzziness of sunlight intensity, a sunshine duration, a sunshine shadow, a sunshine angle of inclination and the like, and calculating the power generation of the water-cooled photovoltaic-photothermal power generation system based on fuzzy probability analysis with an assumption that the parameters of the sunlight intensity, the sunshine duration, the sunshine shadow, the sunshine angle of inclination and the like and a user battery energy storage event obey a generalized three-dimensional trapezoid fuzzy distribution rule.

The invention discloses a method for tracking the maximum power point of a photovoltaic cell on the basis of fuzzy probability. The tracking method comprises the steps that N sampling points [ui, P(ui)] are obtained by taking epsilon as a sampling interval, wherein i is a positive integer which is smaller than or equal to N, epsilon ranges from 0.05 UOC / Ns to 0.5 UOC / Ns, UOC represents the open-circuit voltage of the photovoltaic cell, and Ns represents the serial number of the photovoltaic cell; probability functions Pro(i) are solved by constructing a spread function fD and a subordinating degree function fM, results of the probability functions Pro(i) are ordered from large to small, and union sets of Xi corresponding to front probabilities are sequentially selected as the searching range of the maximum power point, so that the sum of the front probability functions Pro(i) is larger than or equal to a probability threshold value delta; the maximum power point[uMPP, P(uMPP)] is solved in the searching range of the maximum power point. According to the method, the defect that close sampling is needed in a global scanning method under the multi-extremum condition is overcome, and the advantages of being high in tracking speed and good in environmental adaptability are achieved.

The embodiment of the invention discloses a n-dimensional trapezoidal fuzzy set method and device for calculating the output power of a photovoltaic-photothermal integration system, which are used for solving technical problems in the prior art that calculation for the daily generating capacity of a new energy distributed photovoltaic power generation system does not comprehensively consider the uncertainty and randomness of influence factors and that the applicability and the practicability of the calculation method are difficult to be met. The method disclosed by the embodiment of the invention comprises the steps of introducing a generalized n-dimensional trapezoidal fuzzy set concept and a calculation method thereof when the sunshine intensity, the sunshine duration, the sunshine shadow and the sunshine inclination angle are considered, assuming that parameters such as the sunshine intensity, the sunshine duration, the sunshine shadow and the sunshine inclination angle and an energy storage and charging event of a user battery all obey a generalized n-dimensional trapezoidal fuzzy distribution law, and calculating the daily generating capacity of the new energy user distributed photovoltaic power generation system on the basis of fuzzy probability analysis.

The embodiments of the invention disclose a daily generation fuzzy probability calculation method and device for a photovoltaic power generation system, which are used for solving the technical problems that the daily generation calculation method for a distributed photovoltaic power generation system does not comprehensively consider uncertainty and randomness of influence factors and the applicability, practicability and application of the calculation method are difficult to meet in the prior art. The method comprises: according to daily generation data of the photovoltaic power generation system, calculating an n-dimensional generalized trapezoidal fuzzy set for determining daily generation fuzzy uncertainty of the photovoltaic power generation system; calculating an n-dimensional generalized trapezoidal fuzzy set of time period generation of the photovoltaic power generation system according to the influence of sunshine intensity, sunshine temperature rise, sunshine shadow and sunshine deflection angle on the photovoltaic power generation system; calculating the daily generation of the photovoltaic power generation system according to the n-dimensional generalized trapezoidal fuzzy set of time period generation of the photovoltaic power generation system; and determining the daily generation fuzzy probability of the photovoltaic power generation system by calculation according to the daily generation of the photovoltaic power generation system.

The embodiment of the invention discloses an image detection method and device, a computer readable storage medium and computer equipment. The method comprises the steps of obtaining training sample data; respectively inputting the sample image into at least two neural network models to obtain an output fuzzy probability value set; calculating to obtain a loss parameter of each sample image according to the fuzzy probability value set and the label information; selecting a target sample image from the plurality of sample images according to the distribution of the loss parameters, and updating the at least two neural network models based on the target sample image; returning to execute the above steps until the at least two neural network models converge to obtain at least two trained neural network models; and detecting the to-be-detected image by using the trained at least two neural network models to obtain a detection result. Therefore, according to the method, the machine learning technology is adopted, the noise samples are screened through multi-model cooperative training, the model training effect is improved, and then the accuracy of image detection is improved.

The invention provides a bill image processing method and device, a storage medium and electronic equipment, and belongs to the field of image processing. The method comprises the steps of obtaining ato-be-audited target image; inputting the target image into a target feature extraction network in a target classification model to obtain target fuzzy features of the target image output by the target feature extraction network; inputting the target fuzzy feature into a target full-connection layer of a target classification model to obtain a target fuzzy probability output by the target full-connection layer; determining a target classification result of the target image according to the target fuzzy probability and a preset fuzzy probability threshold; and under the condition that the target classification result is used for indicating that the target image is not the blurred image, determining that the target image passes auditing. According to the method, the problem that the image recognition effect has certain limitation due to the fact that the bill image quality is clear and the blurred identification boundary is not clear in the prior art is solved.

The invention relates to an electric vehicle discharging electricity price negotiation method based on fuzzy Bayesian learning, and belongs to the intelligent power grid field. An electric power company and EV agent negotiation function is established, and various parameters are categorized and analyzed. The cost of the electric power company invoking a standby generator unit is used as the maximum value of the electric power company invoking the EV (electric vehicle), and by combining with the power of the electric power company invoking the EV, a relation between the upper limit of the EV invoking acceptable to the electric power company and EV network access power is acquired. Charging price, battery loss, and lowest expected revenue are calculated from the perspective of the EV, and are used as the lower limit of the EV participating in the system scheduling, and then a bilateral negotiation function is established. Another limit value of the electric power company and the EV agent is estimated based on a fuzzy probability idea, and the learning correction of the estimated parameter is carried out based on a fuzzy Bayesian learning model, and the electricity price is acquired by the negotiation function. Under a precondition of considering the benefits of the electric power company, the electricity price acquired by adopting the above mentioned method is closer to a theoretical equilibrium point by comparing with conventional methods, and EV users can gain more benefits, and the behaviors of the users are effectively stimulated during V2G early-stage promotion.

The invention relates to a reliability analysis method for an electromechanical actuator based on a fuzzy dynamic fault tree. According to the method, top, intermediate and bottom events of the electromechanical actuator analyzed and determined to establish the dynamic fault tree, a dynamic logic gate is replaced with an algebraic operator, an algebraic model of the dynamic fault tree is converted into and solved, data of a triangular fuzzy set is used to represent the fuzzy reliability of the bottom event, the algebraic model is decomposed into a static subtree and a dynamic subtree for solution, the fuzzy probability of failure of an electromechanical actuator system is obtained via integration, and a weak link of the electromechanical actuator system is determined by analyzing the fuzzy importance degree. The method of the invention can be used to analyze the reliability of the electromechanical actuator effectively, solve the problem that traditional dynamic fault tree analysis is high in the computational complexity, and provides reference for fault positioning of the electromechanical actuator.

The invention provides a method that uses a fuzzy sets-based mathematic method to calculate the fuzzy probability of generating accidents, thus assisting to analyze influences by various uncertain artificial factors on the rules and features of power accidents, mal-operation accidents and unprofessional operation accidents, and fully utilizing data; in addition, considering mass linear non-fractional data exist in the power accident, mal-operation accident and unprofessional operation accident data, a kernel k-Means Clustering method is employed to firstly map original space sample data to a high dimension space, i.e., the kernel space, thus enabling the sample data to be linear fractional (or nearly linear fractional), and classifying data in the kernel space. The classification results can help users to determine high risk behaviors that cause power accidents, mal-operation accidents and unprofessional operation accidents, thus deriving weak links of the accidents, making targeted prevention measures and control strategies, and reducing generation probabilities or preventing repeated formations of power accidents, mal-operation accidents and unprofessional operation accidents.

The invention provides an offshore platform facility collapse risk assessment method and device, and the method comprises the steps: constructing a collapse fault tree based on the obtained offshore platform facility fault information; according to a fuzzy theory, calculating a fuzzy failure probability of each bottom event in the collapse fault tree based on an evaluation value of each bottom event occurrence possibility in the collapse fault tree by an expert; and calculating the fuzzy failure probability of offshore platform facility collapse according to the fuzzy failure probability of the bottom event and the collapse fault tree. According to the method, the fuzzy failure probability of the bottom event is calculated on the basis of the fuzzy theory and the evaluation value of the expert, and the collapse fuzzy estimation probability is calculated by utilizing the fuzzy probability, so that the problems of objective inadequacy and subjective inadequacy of expert judgment caused by insufficient effective balance factors are reduced, and the estimation is more reasonable.

The invention is applicable to the technical field of surveying and mapping geographic information, and provides a quality control method and device for geographic national condition monitoring data and terminal equipment, and the method comprises the steps: obtaining an uncertain event of the geographic national condition monitoring data in a production process and a logic relation between uncertain events; Constructing a Bayesian network-based geographic national condition monitoring data production process error propagation model; Performing fuzzification processing on the error rate of each basic event in the geographic national condition monitoring data production process error propagation model to obtain a fuzzy probability; Based on the fuzzy probability and the conditional probability between the uncertain events, calculating an error rate of the geographic national condition monitoring data; Based on the fuzzy probability and the error rate, calculating fuzzy importance and posterior probability of each basic event; And feeding back the fuzzy importance and the posterior probability of the basic event to the user. The technical problem that a quantitative quality control method is lacked in the prior art is solved.

The embodiment of the present invention discloses a three-dimensional trapezoidal fuzzy method for calculating the power generation of a water-cooled photovoltaic photothermal integrated system, which is used to solve the problem that the calculation method of the daily power generation of a distributed photovoltaic power generation system for new energy users in the prior art does not fully consider the impact Uncertainty and randomness of factors, applicability, practicability and applicability of calculation methods are difficult to meet technical problems. The method of the embodiment of the present invention includes: when considering the uncertainty, randomness and ambiguity of sunshine intensity, sunshine time, sunshine shadow, and sunshine angle Parameters such as time, sunshine shadow, sunshine angle and user battery energy storage charging events all obey the generalized three-dimensional trapezoidal fuzzy distribution law, and the power generation of the water-cooled photovoltaic-photothermal power generation system is calculated on the basis of fuzzy probability analysis.

The invention discloses a reliability analysis method for a high-voltage electrical system of a pure electric commercial vehicle. The method comprises the following steps: dividing the high-voltage electrical system of the pure electric commercial vehicle into three subsystems, and building a fuzzy fault tree for each subsystem; dividing each fuzzy fault tree into a function failure mode sub-fault tree and a state degradation mode sub-fault tree; solving the failure probability of the function failure mode sub-fault tree and the importance degree of bottom events according to a fuzzy probability of each bottom event by utilizing a fuzzy mathematical theory and a triangular fuzzy operator; obtaining the fuzzy probability through linguistic variables, and processing the fuzzy probability to obtain a probability when a polymorphic bottom event is in a failure state; solving a failure probability of the state degradation mode sub-fault tree, and combining the failure probability of the function failure mode sub-fault tree and the failure probability of the state degradation mode sub-fault tree to obtain the reliability of each subsystem. According to the invention, the fault diagnosis time is saved, and theoretical guidance is provided for reliability design of a high-voltage electrical system of a pure electric commercial vehicle.

The invention discloses a method for determining the daily generating capacity of a distributed type photovoltaic power generation system. The method is carried out through the following steps: obtaining data information on the maximum value, the average value and the minimum value of the sunshine-related parameters at a user's location at all times through a meteorological data platform; obtaining data information on the generating capacity of the distributed type photovoltaic power generation system at all times through a local data monitoring center; obtaining data information on grid operation through a grid energy management system; assuming that the sunshine-related parameters and the user's battery charging events comply with the general multidimensional trapezoidal fuzzy distribution rules to determine the general multidimensional trapezoidal fuzzy set for the sunshine-related parameters and the battery energy storage charging active power control value; and based on the fuzzy probability analysis, determining the daily generating capacity of the distributed type photovoltaic power generation system. The invention can calculate the generating capacity of a photovoltaic power generation system in a day, and provides necessary technical support for distributed type new energy generation and smart grid dispatching operation.

The invention discloses a micro-grid dispatching method, device and equipment and a storage medium. The micro-grid dispatching method comprises the steps of constructing an operation model corresponding to a micro-grid; wherein the operation model represents operation constraints of a distributed power supply, a power flexible load and an energy storage device in the microgrid; acquiring historical prediction error data of distributed power supply output to determine real probability distribution and empirical probability distribution of the distributed power supply output, and constructing a fuzzy probability distribution set of distributed power supply output uncertainty through a distribution robust optimization method based on the real probability distribution and the empirical probability distribution; and constructing a scheduling model meeting scheduling optimization conditions based on the operation model and the fuzzy probability distribution set, so as to schedule the micro-grid by using an optimized scheduling strategy generated by the scheduling model. The scheduling flexibility and accuracy can be improved, the maximum utilization rate of power is ensured, and meanwhile, the calculation time is saved, so that the scheduling efficiency is improved.

The present invention provides an evaluation method and device of automotive fuel economy. The method comprises a step of establishing a neural network regression calculation model and obtaining a fuel economy probability sequence according to a vehicle speed data sequence, an instantaneous fuel consumption data sequence, an engine rotation speed data sequence, an acceleration data sequence, the neural network regression calculation model, and a fuzzy probability mapping model, and a step of comparing each fuel economy probability in the fuel economy probability sequence with a preset probability threshold orderly, and evaluating the automotive fuel economy according to a comparison result. Through the method and the device, the automotive fuel non-economic process in an automotive driving process can be effectively identified, the automotive fuel economy is evaluated according to the automotive driving data corresponding to the automotive fuel non-economic process, and an automotive driving experience is improved.

The invention provides a method and device for assessing economic efficiency of automobile fuel. The method for assessing the economic efficiency of the automobile fuel comprises the steps that a multiple regression model is established; an automobile speed data sequence in travelling of an automobile is acquired, and an acceleration data sequence is acquired according to the automobile speed data sequence; a probability sequence of the fuel economic efficiency is obtained according to the automobile speed data sequence, the acceleration data sequence, the multiple regression model and a fuzzy probability mapping mode; each fuel economic efficiency probability in the fuel economic efficiency probability sequence is successively compared with a preset probability threshold, so that comparison results are obtained; and the automobile fuel economic efficiency is assessed according to the comparison results. By the method and the device provided by the invention, automobile fuel non-economic courses in the automobile travelling can be effectively recognized; the automobile fuel economic efficiency can be assessed according to automobile travelling data information corresponding to the non-economic courses of the automobile fuel; and automobile driving experience is improved.