817 results about "Genetic algorithm optimization" patented technology

The invention discloses a harbor district road traffic demand predicting system which is based on a TransCAD macro simulated platform and is used to obtain harbor district road traffic generation amount in an objective year. The predicting system at least comprises a storage module, a harbor district road network model, a road network model application module, a road network loading distribution unit, an analysis evaluation module and a planning module, wherein the storage module is used to store data basis for predicting harbor district road traffic generation amount; the harbor district road network model inputs a harbor district project map into a TrarsCAD model platform through a harbor district project geographical information database so as to establish the harbor district road network model according to road traffic circulation in a harbor district; the road network model application module optimizes and selects traffic parameters by means of genetic algorithm to obtain a harbor district objective year OD matrix; the road network loading distribution unit is used for obtaining the traffic flow distribution state and traffic circulation state of the entire road network; the analysis evaluation module combines with the traffic distribution result to carry out traffic adaptability analysis evaluation on a future road network planning scheme; and the planning module is used to put forward guidance instructions and overall measures with regard to harbor district road traffic planning.

The invention discloses a wind power forecasting method based on a genetic algorithm optimization BP neural network, comprising the steps: acquiring forecasting reference data from a data processing module of a wind power forecasting system; establishing a forecasting model of the BP neural network to the reference data, adopting a plurality of population codes corresponding to different structures of the BP neural network, encoding the weight number and threshold of the neural network by every population to generate individuals with different lengths, evolving and optimizing every population by using selection, intersection and variation operations of the genetic algorithm, and finally judging convergence conditions and selecting optimal individual; then initiating the neural network, further training the network by using momentum BP algorithm with variable learning rate till up to convergence, forecasting wind power by using the network; and finally, repeatedly using a forecasted valve to carry out a plurality of times of forecasting in a circle of forecast for realizing multi-step forecasting with spacing time interval. In the invention, the forecasting precision is improved, the calculation time is decreased, and the stability is enhanced.

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

The invention discloses a genetic algorithm-based support vector regression shipping traffic flow prediction method, comprising the following steps: (1) reducing the dimensional number of factors possibly generating influences on shipping traffic flow by a weighted principal component analysis method, and selecting influencing factors with higher cumulative contribution rate; (2) carrying out normalization preprocessing on original vessel traffic flow time series data to generate a data set and then grouping; (3) selecting a kernel function to determine support vector machine (SVM) regression parameters; (4) constructing a support vector regression prediction model optimized by a genetic algorithm; (5) inputting the data set to generate a prediction function; and (6) predicting according to the prediction function generated in step (5), evaluating and analyzing prediction error, and if the error is relatively large, returning to step (2) and regulating the parameters again, predicting once again. The method of the invention has the advantages of higher prediction accuracy and higher stability of prediction accuracy.

The invention discloses a traffic flow prediction method based on a genetic algorithm optimized LSTM neural network. The traffic flow prediction method based on the genetic algorithm optimized LSTM neural network comprises the steps of: S1, acquiring traffic flow data, performing data normalization pre-processing, and dividing the traffic flow data into a training data set and a test data set; S2,predicting various parameters of a model by adopting the genetic algorithm optimized LSTM neural network; S3, inputting genetic algorithm optimized parameters and the training data set, and performing iterative optimization of an LSTM neural network prediction model; and S4, predicting the test data set by using the trained LSTM neural network model, and evaluating the model error. According to the traffic flow prediction method based on the genetic algorithm optimized LSTM neural network in the invention, by utilization of the rapid optimization feature of the genetic algorithm and the LSTMneural network on parameter combination, the relatively high prediction precision can be obtained; furthermore, the method has good applicability on data samples in different intervals; the calculation amount is reduced through the model; and the prediction performance is better.

The present invention is directed to an object recognition system. The system includes a database having stored therein a trained reference vector. The trained reference vector includes a finite string of weighted reference feature elements optimized using a genetic algorithm which uses a dynamic length chromosome. The trained reference vector is optimized relative to a fitness function. The fitness function is an information based function. The trained reference vector corresponds to a known object or class of objects. A sensor is disposed in a surveilled region and configured to generate sensor data. The sensor data corresponds to objects disposed in the surveilled region. A recognition module is coupled to the sensor and the at least one database. The recognition module is configured to generate data object vectors from the sensor data. Each data object vector corresponds to one object. The recognition module is configured to combine the reference vector with each data object vector to obtain at least one fusion value for that vector. The fusion value is compared with a predetermined threshold value to thereby measure the likeness of the at least one object relative to the known object or class of objects.

A propylene polymerization production process optimal soft-measurement meter based on genetic algorithm optimized BP neural network comprises a propylene polymerization production process, a site intelligent meter, a control station, a DCS databank used for storing data, an optimal soft measurement model based on genetic algorithm optimized BP neural network, and a melting index soft-measurement value indicator. The site intelligent meter and the control station are connected with the propylene polymerization production process and the DCS databank; the optimal soft-measurement model is connected with the DCS databank and the soft-measurement value indicator. The optimal soft measurement model based on genetic algorithm optimized BP neural network comprises a data pre-processing module, an ICA dependent-component analysis module, a BP neural network modeling module and a genetic algorithm optimized BP neural network module. The invention also provides a soft measurement method adopting the soft measurement meter. The invention can realize on-line measurement and on-line automatic parameter optimization, with quick calculation, automatic model updating, strong anti-interference capability and high accuracy.

The invention provides a neural network equalization method used for an indoor visible light communication system, and belongs to the visible light wireless communication technology field. The method includes the steps: utilizing a ceiling bounce model to calculate a VLC channel impulse response, carrying out photoelectric conversion for a visible light power signal received by a receiving end, and sending a sequence to a neutral network channel equalizer after amplification sampling; utilizing a heredity algorithm to optimize initialization weights and thresholds among neurons, establishing a neural network for training, and minimizing an error function; and judging an output, restoring the sent sequence, and finally achieving an equalization purpose. According to the scheme, interference among codes is obvious minimized, an error rate is reduced, the communication quality is further improved, a transmission rate that the system can reach is increased, the training time is shortened, and the system complexity is reduced.

The invention relates to an electromyographic signal gait recognition method for optimizing a support vector machine based on a genetic algorithm. According to the electromyographic signal gait recognition method, the penalty parameter and the kernel function parameter of the support vector machine are optimized with the genetic algorithm, the performance of the support vector machine is accordingly optimized, and the efficiency and the accuracy of the support vector machine for recognizing lower limb movement gaits based on electromyographic signals are improved. The electromyographic signal gait recognition method includes the steps of firstly, carrying out de-noising processing on the collected lower limb electromyographic signals with a wavelet modulus maximum de-noising method; secondly, extracting the time domain characteristics of the de-noised electromyographic signals to form characteristic samples; thirdly, optimizing parameters of the support vector machine with the genetic algorithm to obtain a set of optimal parameters with the minimum errors, and constructing a classifier through the parameters; finally, inputting a characteristic sample set into the optimized classifier for gait recognition. The electromyographic signal gait recognition method is easy to operate, rapid in calculation and high in recognition rate, and has the application value and the broad prospects in the human body lower limb gait recognition field.

The invention discloses a method for obtaining the energy loss analysis parameter answer value of a furnace of a thermal power set, which comprises the following steps of: building a furnace operation characteristic neural network teaching model with a neural network technology according to furnace operation history working condition data; optimizing the air distribution coal distribution combustion operation parameter of each history working condition of the furnace by taking the highest furnace efficiency as an optimal target through a genetic algorithm optimization technology according to the model; comparing the air distribution coal distribution combustion operation parameter of each history working condition with the corresponding optimizing value, and if the difference therebetween is within a given range, marking the corresponding working condition as an 'optimization working condition'; building a computation model of the exhaust gas temperature, the exhaust gas oxygen quantity and the fly ash carbon content answer value of the furnace by taking the history working condition data which is marked as the 'optimization working condition' as a sample; and being capable of computing the exhaust gas temperature, the exhaust gas oxygen quantity and the fly ash carbon content answer value of the furnace under the conditions of different loads and different coal qualities through the computation model. The method is more reasonable.

The invention discloses a BP neutral network heavy machine tool thermal error modeling method optimized through a genetic algorithm. Through the establishment of the structure of a BP neutral network, global optimization is conducted on the initial weight and threshold of each layer of the BP neutral network through a training sample. After the error objective is set, global optimization is conducted on the initial weight and threshold of the BP neutral network structure through the genetic algorithm, and the optimal weight and threshold found by the genetic algorithm is substituted into the BP neutral network to be conducted with sample training. Based on the decline principle of the error gradient, quick search is conducted near the extreme point until the training is end and thermal error prediction model is obtained. Finally, robustness testing is conducted on the obtained thermal error prediction model. The global optimization is conducted on the initial weight and threshold of the BP neutral network structure through the utilization of the genetic algorithm, the self-characteristics of the BP neutral network is overcome, and the quickness, the accuracy and the robustness of convergence when the optimal weight and threshold is trained can be improved.

The invention discloses a near infrared spectrum analyzing method based on the isolated component analysis and genetic neural network, which comprises the following steps for the acquired near infrared spectrum: firstly, effectively compressing spectrum data by using wavelet transform; secondly, extracting an independent component and a corresponding mixed coefficient matrix of a near infrared spectrum data matrix by using an isolated component analysis method; thirdly, building a three-layer BP neutral network, using the mixed coefficient matrix of a training sample as the input and correspondingly measured component concentration matrix as the output, and optimizing a neutral network structure by adopting a genetic algorithm, and obtaining a GA-BP neutral network by the training of the training sample; fourthly, predicting and analyzing the measured component concentration of the predicted set sample by using the GA-BA neutral network. The method enriches the chemical measurement method, widens the application range of the isolated component analysis and has favorable application prospect.

The invention discloses a fiber optic gyroscope temperature drift modeling method by optimizing a dynamic recurrent neural network through a genetic algorithm. The fiber optic gyroscope temperature drift modeling method by optimizing the dynamic recurrent neural network through the genetic algorithm comprises the following steps of (1) initializing network parameters, and establishing an improved Elman neural network model; (2) obtaining a training and testing sample; (3) training an improved Elman neural network, and optimizing model parameters through the genetic algorithm; (4) outputting forecasts of an fiber optic gyroscope, and compensating errors. The output of the fiber optic gyroscope processed through a denoising algorithm is trained by introducing the improved Elman neural model with self-feedback connection weight, constant iterative optimization is carried out on the model parameters through the genetic algorithm, and the optimal model is obtained according to the magnitude of the errors of the model under different parameters. According to the fiber optic gyroscope temperature drift modeling method by optimizing the dynamic recurrent neural network through the genetic algorithm, the complexity of the algorithm is taken into consideration, the accuracy of the fiber optic gyroscope temperature drift model is improved, the application of the fiber optic gyroscope temperature drift model in engineering is expanded, and certain practical significance is achieved.

The invention discloses a solution method for independent and joint dispatching of a distribution network with micro-grids. The method comprises the following steps: establishing a model of the distribution network with the micro-grids; establishing an objective function for dispatching of the micro-grids and an objective function for dispatching of the distribution network; determining constraints for independent and joint dispatching of the micro-grids and the distribution network; and solving household microgrids and distribution network by a particle swarm optimization algorithm, and solving thermoelectric microgrids with a Benders decomposition method. In the household microgrids, the demand response is considered, and a load curve is optimized by a genetic algorithm. Aiming at the prediction error of wind power, a wind field model with three-parameter Weibull distribution is established. The method can be applied in the technical field of economic dispatching of a plurality of microgrids, and a plurality of stakeholders are satisfied on the premise of satisfying system constraints. The Benders decomposition method is used to solve a thermoelectric system, thereby effectivelyprotecting the privacy of the information of electric and thermal systems, and improving the accuracy of the calculation.

The invention discloses an arc fault diagnosis method based on time domain feature parameter fusion. The arc fault diagnosis method comprises the steps of: step 1, designing a BP neural network used for arc fault diagnosis, wherein the design is implemented by (1) determining input and output modes of the neural network, (2) acquiring training set and test set samples of the neural network, (3) determining a number of layers of the BP neural network, (4) determining a number of nerve cells of a network hidden layer, and (5) selecting training parameters of the BP neural network; step 2, optimizing the BP neural network by adopting a genetic algorithm in a process shown in the chart 7, wherein the genetic algorithm optimization process is mainly implemented by (1) coding individuals and initializing a population, (2) calculating fitness, (3) and generating a new population. The arc fault diagnosis method has the beneficial effects that: the genetic algorithm optimized BP neural networkhas better performance compared with a BP neural network trained by using random weights and threshold values, and has relatively higher arc fault identification accuracy rate.

The invention provides a parallelization method of a BP neural network optimized by genetic algorithm based on spark. The method comprises the following steps: performing global evolution optimizing on a weight value of the BP neural network through the adoption of a spark parallelization programming model improved genetic algorithm, and obtaining an optimized neural network initial weight value after performing a certain number of evolution iterations, and iterating through the adoption of the parallelized BP neural network algorithm, finally outputting a network structure. In the training process, the multi-node parallel processing can be performed in each stage, the convergence speed of the BP neural network is greatly promoted, and the training efficiency is improved.

The invention discloses a remote monitoring and fault diagnosis system based on a cloud service and a fault diagnosis method, and relates to the field of intelligent manufacturing and cloud diagnosis. The remote monitoring and fault diagnosis system comprises a data acquisition unit, a remote communication gateway unit, a cloud storage management unit and a cloud service center unit. The data acquisition unit is deployed on a data acquisition terminal; the remote communication gateway unit is deployed on a cloud front gateway server; the cloud storage management unit is deployed on a cloud data server and the cloud service center unit is deployed on a cloud application server. According to the invention, a BP neural network fault diagnosis method based on genetic algorithm optimization is creatively applied to the remote monitoring and fault diagnosis system, and a remote monitoring and fault diagnosis service suitable for a cross-region environment can be conveniently and rapidly provided; and mechanical equipment remote online working condition monitoring can be provided for technical personnel of equipment manufacturers, and rapid, accurate and efficient diagnosis on a complex fault can be provided for mechanical equipment used by production enterprises.

The invention discloses a real-coded genetic algorithm-based optimizing method for the micrositing of a wind power station. In the method, the measured wind speed in the wind farm is corrected by an index model in the direction of relative height; a power characteristic curve of a wind machine is discretized by a linearized method; for the wake flow of the wind machine, a linearized wake flow model is adopted; the wind speed of the wind machines at the wake flow of a plurality of wind machines is solved by a method of the summation of squared differences, when part of the wind machines are positioned in the wake flow, the wind speed is revised by a method of area coefficients; based on an optimizing target function of the micrositing in the design of the wind power station, when the total number of the wind machines in the wind power station is determined, the total generated energy is used as the target function, and when the total number of the wind machines in the wind power station is not determined, the kilowatt-hour cost is used as the target function; and the microcosmic arrangement site of each wind machine in the wind power station is obtained by the real-coded genetic algorithm-based optimizing method. By the method, the reliability of forecast is high, the optimizing efficiency is high and results are accurate.

The invention discloses a short-term electric load prediction method based on improved genetic algorithm for optimizing extreme learning machine. A hill climbing method is used to perform preferentialselection again in the progeny population, an initial individual is selected, another individual in a close area is select, their fitness values are compared, and one individual which has good fitness values is leaved. If the initial individual is replaced or a better individual cannot be found in several iterations, iteration is stopped, the search direction of the genetic algorithm through thehill climbing method is optimized, obtaining an optimal weight value and a threshold value, a network optimization prediction model are obtained, a network optimization prediction model is obtained, the network optimization prediction model and prediction results of BP network and the extreme learning machine are comparative analyzed, including selection of input and output of the prediction network model, algorithm of improved genetic algorithm for optimizing extreme learning machine, and analysis of prediction results. The short-term electric load prediction method based on improved geneticalgorithm for optimizing extreme learning machine has faster training speed and more accurate prediction results, and is suitable for modern short-term electric load prediction with plenty of influence factors and huge data volume.

The invention provides a method for distributing satellite receiving tasks. The method comprises the steps of decomposing the satellite receiving task planning problem by the divide-and-conquer method; decomposing the satellite data receiving task problem under a large task quantity into a plurality of sub-problems under a small task quantity; optimally configuring a ground receiving resource of each satellite data receiving task of each conflict task set by the genetic algorithm by considering the satellite-earth resource limitation, so as to reach the purpose of fully utilizing the ground receiving resource. According to the method, the parallel strategy of dividing and conquering is carried out to greatly increase the satellite receiving task planning efficiency; in addition, the genetic algorithm is performed for the satellite receiving task planning problem under each small task quantity, and therefore, the ground receiving resource is quickly and fully distributed, and the optimal satellite receiving task planning scheme can be obtained. According to the method, the automatic mode is performed, so that the brain power of operators can be relieved, and the planning efficiency and the capacity of responding to the emergency task can be greatly increased.

A mechanical temperature instrument error prediction method based on a genetic-algorithm optimized least square support vector machine is disclosed. The method comprises the following steps of (1) taking a tested characteristic parameter of a mechanical temperature instrument as model input, and taking an instrument error value and an error change rate acquired through sampling as model output; (2) carrying out pretreatment on original temperature error data; (3) selecting a Gauss radial kernel function as a kernel function of a least square support vector machine model; (4) using a genetic algorithm to optimize a parameter combination of the least square support vector machine; (5) constructing a mechanical temperature instrument error prediction model based on the genetic-algorithm optimized least square support vector machine; (6) inputting a data set and using a model obtained through training to carry out prediction; (7) comparing a temperature instrument error prediction result with an actual temperature error and analyzing a temperature error value and a change trend of a temperature error change rate. By using the method, precision is high; calculating is simple and engineering practicality is high.

The invention relates to a prediction method of transformer winding hot-spot temperature based on a neural network. After the neural network is optimized through the adoption of a genetic algorithm, the transformer winding hot-spot temperature value is obtained through the computation; the method comprises the following steps: (1) constructing the neural network; (2) normalizing input data and output data of the neural network; (3) optimizing a weight value and a threshold value of the neural network through the genetic algorithm; (4) training the neural network optimized through the genetic algorithm; (5) obtaining the output data through the utilization of real-time measured input data and trained neural network, and computing the hot-spot temperature value through computation. Compared with the prior art, the method disclosed by the invention has the advantage of being high in measurement precision.

The invention, which belongs to the field of urban traffic design, particularly relates to a genetic-algorithm-optimization-based big data analysis system and method of urban regional traffic. The system is composed of an urban road network and pedestrian travel distribution analysis module, an urban road network traffic flow analysis module, an urban rail transit system analysis module, and an urban regional transportation system decision module. According to the invention, with urban road network and resident travel distribution as an object, a genetic-algorithm-based urban-road-network optimized dual-layer planning model is established by using a dual-layer planning model in a continuous network design and introducing the urban road network and resident travel distribution index into urban road network optimization; an optimal solution is calculated by using a genetic algorithm; and the decision-making configuration of the transportation system is realized based on the optimal solution. Therefore, the data analysis ability and decision-making ability of the urban regional traffic are enhanced substantially.

The invention discloses a large visual field camera nonlinear distortion correction device and method. The device comprises a single-star starlight simulator, a two-dimensional turntable, a two-dimensional turntable control system, an optical table and a computer. The method comprises the steps of utilizing a mass center positioning algorithm to confirm mass center position coordinates of star point images at different positions in a camera visual field range, establishing a projection imaging model to calculate ideal imaging position coordinates corresponding to the star point images, fitting a nonlinear distortion model through a BP neural network optimized by a genetic algorithm and achieving distortion correction of a camera to be detected. The large visual field camera nonlinear distortion correction device has the advantages of having simple structure, automatic operation, convenient measurement and high correction algorithm accuracy and easily achieves large visual field camera nonlinear distortion correction.

The invention discloses a method for acquiring target values of boiler optimized operation economic parameters. The method comprises the following steps of: establishing a boiler combustion characteristic neural network mathematical model by using a neural network technology according to boiler variable coal type combustion optimized operation working condition data; according to the boiler combustion characteristic neural network mathematical model, optimizing air distribution and coal distribution combustion operation parameters of each historic working condition of a boiler by using an optimized combination method of a thermal test algorithm and a genetic algorithm and by taking the maximization of boiler comprehensive efficiency as an optimization target; comparing the air distribution and coal distribution combustion operation parameters of each historic working condition with corresponding optimized values, determining an optimized working condition, and establishing a target value calculation model for boiler main steam parameters, auxiliary engine power consumption, smoke exhaust temperature, fume oxygen content and fly-ash carbon content by taking data of a historic working condition which is marked as the optimized working condition as a sample and by using the neural network technology; and calculating a boiler main steam parameter target value, an auxiliary engine power consumption target value, a smoke exhaust temperature target value and a fume oxygen content target value under the conditions of different loads and different coals by using the obtained target value calculation model.

The invention discloses a rolling bearing weak fault feature early extraction method. The method includes the following steps that: a sensor is utilized to pick up the vibration signals of a rolling bearing under an operating condition, and the vibration signals are adopted as signals to be analyzed; with the spectrum auto-correlation feature factor SACFF of a spectrum auto-correlation function adopted as a fitness function, a genetic algorithm is adopted to optimally search variation modal decomposition parameters; parameter combinations which are optimally searched by the genetic algorithm are selected to perform VMD (variation modal decomposition) processing on the signals to be analyzed, so that finite bandwidth intrinsic mode functions are obtained; components corresponding to local maximum feature factors of spectrum autocorrelation are selected to be subjected to spectrum autocorrelation analysis, so that a spectrum autocorrelation function graph can be obtained; and if the fault feature frequency in the spectrum autocorrelation function graph or the peak value of the frequency multiplication thereof reaches a set threshold value, it is indicated that an early weak fault occurs on the rolling bearing. According to the method of the invention, the respective advantages of the VMD and the spectrum autocorrelation analysis are combined, and therefore, limitations of the spectrum autocorrelation analysis method in extracting the weak fault feature information of the bearing can be broken through, and the earlier diagnosis of the weak fault of the rolling bearing can be realized.

The invention discloses a short-term photovoltaic power prediction method based on a meteorological factor weight similar day. The method comprises the following steps that: S01: calculating the Pearson coefficient of photovoltaic power and a meteorological factor to extract a main impact factor; S02: classifying historical days by a k-means clustering algorithm; S03: according to grey relationalanalysis, obtaining the weight of the meteorological factors for generation power in different categories; S04: according to similarity statistic magnitude with weight, calculating a similarity between a new sample and each clustering center, and taking the category with the high similarity as the category of the new sample; S05: selecting seven historical days with the highest similarity as similar days to obtain a similar day sample training set; and S06: establishing an RBF-BF (Radial Basis Function-Back Propagation) combined neural network model based on genetic algorithm optimization forprediction. By use of the short-term photovoltaic power prediction method based on the meteorological factor weight similar day, photovoltaic power prediction accuracy can be effectively improved, andthe method is high in practicality.

The invention provides a large-scale flexible work workshop scheduling optimization method. A large-scale production task is reorganized to be downscaled and then solving and optimization are performed by using the adaptive improved genetic algorithm. The method comprises the following concrete steps that (1) the workpieces of which the processing technology is similar, the workpiece dimension iswithin the same range and the blank material is the same are clustered and grouped for batching so as to reduce the problem solving scale; and (2) the initial parameter of the algorithm is set, the three-layer gene coding technology, the OBX crossover mode and the certain variation strategy are adopted, the crossover length is selected through combination of the simulation experiment and optimization and solving are performed by using the adaptive improved genetic algorithm. According to the method, the problem solving scale can be reduced and the solving speed can be improved; and the workpiece completion time and delay time can be reduced.

A genetic algorithm determines a plan for payment of payment obligations in accounts payable of a finance account. The genetic algorithm operates to satisfy certain objectives, including maximizing the minimum daily cash on hand in the finance account. A genome population including a number of vectors is generated. The genome population is modified using a genetic algorithm, until at least one vector represents a plan for the payment obligations such that payment of each payment obligation in accordance with the vector most nearly satisfies one or more objectives.