Genetic Wavelet Neural Network Research Articles

Daily consumption monitoring method of photovoltaic microgrid based on genetic wavelet neural network

Abstract In order to comprehensively monitor the daily consumption of photovoltaic power and power generation of photovoltaic microgrid, a daily consumption monitoring method of photovoltaic microgrid based on genetic wavelet neural network is proposed to reduce the relative error of daily consumption monitoring. Considering the power generation forms of various units such as wind power, thermal power, hydropower and photovoltaic power generation, the upper and lower limits of daily consumption of different units and the constraints of consumption calculation are analyzed to obtain the daily consumption of photovoltaic microgrid. On this basis, the daily consumption monitoring model of photovoltaic microgrid including multiple inputs and outputs is constructed by using Morlet wavelet function, and the power generation is calculated by wavelet neural network. The genetic algorithm is used to optimize the individual fitness of wavelet neural network through the training of the number of wavelet bases and related thresholds and weights, and to normalize the optimal individual fitness to realize the daily consumption monitoring of photovoltaic microgrid. The experiment shows that this method can monitor the actual photovoltaic power in sunny weather, and after 12 o’clock, the photovoltaic power gradually drops below 30 kW. In cloudy weather, the actual photovoltaic power reaches its peak at around 12 o’clock, ~45–50 kW, and drops to about 10 kW at 17 o’clock. And the power generation in cloudy days is relatively low, and the power generation in rainy days is the lowest. When the relative humidity is 30%, the power generation increases rapidly and keeps at 8 kWh. When the relative humidity is 50%, the power generation gradually drops to 2 kWh. When the temperature is 20°C, the maximum radiation intensity is about 0.6 kW m2. When the temperature is 30°C, the maximum radiation intensity is greater than 0.8 kW m2. At 11:00 and 12:00, the power generation error is 0.02 kWh. In order to improve the monitoring accuracy of photovoltaic power and daily power generation of photovoltaic microgrid in different environments.

A deep learning approach to retrieve cold-season snow depth over Arctic sea ice from AMSR2 measurements

Snowpack on sea ice can adjust changes in sea ice conditions and plays a vital role in the Earth's climate system. Snow depth, an important parameter of snowpack, is a necessary variable for retrieving sea ice thicknesses based on satellite altimeter data. Here, regression analysis (RA) is used to determine the best gradient ratio (GR) combination of brightness temperatures for estimating snow depths, and the RA model is proposed. Based on the RA model, one additional deep learning model is built, namely, the 5-variable long short-term memory (5VLSTM) model (or the RA-5VLSTM model). Meanwhile, an additional neural network model is built for comparisons, namely, the 5-variable genetic wavelet neural network (5VGWNN) model (or the RA-5VGWNN model). Using Operation IceBridge (OIB) and ice mass balance buoy (IMB) data, these three models, plus three existing algorithms, are compared to assess their performances in estimating snow depth. The results show that the RA-5VLSTM model performed pretty well among the six algorithms, with an RMSE of 7.16 cm. The RA-5VLSTM model, a robust approach, was less influenced by the uncertainty in the input data. From January to April during 2012–2020, the average monthly snow depth in the Beaufort Sea and the Chukchi Sea mainly showed a downward trend, while an upward trend was observed in the Central Arctic in most months. Variations in snow depth in the Central Arctic were mainly affected by the autumn 2-m air temperature (T2m) and the sea surface temperature (SST). Variations in snow depth in the Chukchi Sea were mainly affected by the autumn sea ice velocity.

Wavelet Neural Network for Modeling Chlorophyll a Concentration Affected by Artificial Upwelling

Through bringing nutrient-rich subsurface water to the surface, the artificial upwelling technology is applied to increase the primary marine productivity which could be assessed by Chlorophyll a concentration. Chlorophyll a concentration may vary with different water physical properties. Therefore, it is necessary to study the relationship between Chlorophyll a concentration and other water physical parameters. To ensure the accuracy of predicting the concentration of Chlorophyll a, we develop several models based on wavelet neural network (WNN). In this study, we build up a three-layer basic wavelet neural network followed by three improved wavelet neural networks, which are namely genetic algorithm-based wavelet neural network (GA-WNN), particle swarm optimization-based wavelet neural network (PSO-WNN), and genetic algorithm & particle swarm optimization-based wavelet neural network (GAPSO-WNN). The experimental data were collected from Qiandao Lake, China. The performances of the proposed models are compared based on four evaluation parameters, i.e., R-square, root mean square error (RMSE), mean of error (ME), and distance (D). The modeling results show that the wavelet neural network can achieve a certain extent of accuracy in modeling the relationships between Chlorophyll a concentration and the five input parameters (salinity, depth, temperature, pH, and dissolved oxygen).

Prediction of Ship Traffic Volume in Jiujiang Port Based on Genetic Wavelet Neural Network

In recent years, the traffic volume of the Yangtze River has increased dramatically. In order to provide more favorable assistance to port planning and traffic management, the accuracy of port ship traffic volume prediction is very important. In this paper, genetic algorithm and wavelet analysis and neural network are used to construct the genetic wavelet neural network model prediction model, and BP neural network prediction model is established. The ship volume of Jiujiang Port is used as experimental data to simulate and analyze. The results show that the prediction accuracy of the genetic wavelet neural network prediction model is significantly higher than that of the BP neural network prediction model. It is proved that the genetic wavelet neural network has broad application prospects for ship traffic flow prediction in the Yangtze River port. This method has practical application significance.

Research on the Robot Wrist Sensor Dynamic Characteristics Based on Improved Genetic Wavelet Neural Networks

The multi-dimensional wrist force sensor applied to Motomam V3X robot is introduced. The characteristics of genetic algorithm (GA) and artificial neural networks (ANN) are compared. A novel improved genetic algorithm (IGA) is proposed to train wavelet neural networks (WNN). A kind of new dynamic modeling and dynamic compensation methods are presented based on improved genetic algorithm and wavelet neural networks (IGAWNN) and the principle of algorithm is introduced for the multi-dimensional wrist force sensor. The dynamic model and dynamic compensation model of the robot wrist force sensor are set up according to data of the dynamic calibration, where the structure and parameters of wavelet neural networks of the dynamic model and dynamic compensation are optimized by the improved genetic algorithm. The results show that the proposed methods can overcome the shortcomings of easy convergence to the local minimum points of BP algorithm, and the network complexity, the convergence and the generalization ability are well compromised and the training speed and precision of the new dynamic modeling and dynamic compensation are increased.

Comparative Study on Prediction Effects of Short Fatigue Crack Propagation Rate by Two Different Calculation Methods

To describe the complicated nonlinear process of the fatigue short crack evolution behavior, especially the change of the crack propagation rate, two different calculation methods are applied. The dominant effective short fatigue crack propagation rates are calculated based on the replica fatigue short crack test with nine smooth funnel-shaped specimens and the observation of the replica films according to the effective short fatigue cracks principle. Due to the fast decay and the nonlinear approximation ability of wavelet analysis, the self-learning ability of neural network, and the macroscopic searching and global optimization of genetic algorithm, the genetic wavelet neural network can reflect the implicit complex nonlinear relationship when considering multi-influencing factors synthetically. The effective short fatigue cracks and the dominant effective short fatigue crack are simulated and compared by the Genetic Wavelet Neural Network. The simulation results show that Genetic Wavelet Neural Network is a rational and available method for studying the evolution behavior of fatigue short crack propagation rate. Meanwhile, a traditional data fitting method for a short crack growth model is also utilized for fitting the test data. It is reasonable and applicable for predicting the growth rate. Finally, the reason for the difference between the prediction effects by these two methods is interpreted.

Research on High-Precision, Low Cost Piezoresistive MEMS-Array Pressure Transmitters Based on Genetic Wavelet Neural Networks for Meteorological Measurements

This paper provides a novel and effective compensation method by improving the hardware design and software algorithm to achieve optimization of piezoresistive pressure sensors and corresponding measurement systems in order to measure pressure more accurately and stably, as well as to meet the application requirements of the meteorological industry. Specifically, GE NovaSensor MEMS piezoresistive pressure sensors within a thousandth of accuracy are selected to constitute an array. In the versatile compensation method, the hardware utilizes the array of MEMS pressure sensors to reduce random error caused by sensor creep, and the software adopts the data fusion technique based on the wavelet neural network (WNN) which is improved by genetic algorithm (GA) to analyze the data of sensors for the sake of obtaining accurate and complete information over the wide temperature and pressure ranges. The GA-WNN model is implemented in hardware by using the 32-bit STMicroelectronics (STM32) microcontroller combined with an embedded real-time operating system µC/OS-II to make the output of the array of MEMS sensors be a direct digital readout. The results of calibration and test experiments clearly show that the GA-WNN technique can be effectively applied to minimize the sensor errors due to the temperature drift, the hysteresis effect and the long-term drift because of aging and environmental changes. The maximum error of the low cost piezoresistive MEMS-array pressure transmitter proposed by us is within 0.04% of its full-scale value, and it can satisfy the meteorological pressure measurement.

Model for Evaluation of Water Quality Base on Improved Wavelet Neural Network

The nonlinear and uncertain of water environmental pollution,make the traditional water quality evaluation methods have limitations.In order to improve the accuracy of water quality evaluation,The paper put forward the water quality evaluation model based on improved wavelet neural network (Wavelet Neural Network, the WNN).Optimize the initial weights of wavelet neural network based on Adaptive Genetic Algorithm (Adaptive Genetic Algorithm, AGA),and then training the network by used wavelet neural network algorithm,finally,testing the trained network.The simulation results show that the combination of Adaptive genetic algorithm and wavelet neural network improved the efficiency of network training,and this method can be used in water quality evaluation, and the evaluation result has high precision and accuracy.

The Robot Wrist Sensor Dynamic Mode Building Method Based on Genetic Wavelet Neural Networks

A kind of new dynamic modeling method is presented based on improved genetic algorithm (IGA) and wavelet neural networks (WNN) and the principle of algorithm is introduced for a new type robot wrist force sensor. The dynamic model of the wrist force sensor is set up according to data of the dynamic calibration, where the structure and parameters of wavelet neural networks of the dynamic model are optimized by genetic algorithm. The results show that the proposed method can overcome the shortcomings of easy convergence to the local minimum points of BP algorithm, and the network complexity, the convergence and the generalization ability are well compromised and the training speed and precision of model are increased.

Study on Genetic Fuzzy Wavelet Neural Network Controller of Robotic Manipulator

This paper deals with the tracking controller design of robotic manipulator using genetic algorithm (GA). A genetic fuzzy wavelet neural network (GFWNN) controller is designed and implemented based on MATLAB in this paper, whose parameters are optimized by GA. The structure and algorithm of fuzzy wavelet neural network (FWNN) are described at first. Then the key content of GA used in this paper and the steps for using GA to optimize FWNN are demonstrated. Finally, a numerical simulation of tracking control for 2-link robotic manipulator is given to verify the effectiveness of the proposed method.

An expert target recognition system using a genetic wavelet neural network

In this paper, a target recognition system is presented for target recognition using target echo signals of High Range Resolution (HRR) radars. This paper especially deals with a combination of an adaptive feature extraction and classification using optimum wavelet entropy parameter values. The features are obtained from measured target echo signals using a X-band pulse radar. A genetic wavelet neural network model is developed for target recognition. This model consists of three layers. These layers are genetic algorithm, wavelet analysis and multi-layer perceptron respectively. The genetic algorithm layer is used for selecting the feature extraction method and obtaining the optimum wavelet entropy parameter values. Here, the optimal one of four different feature extraction methods is selected by using a genetic algorithm. The proposed four feature extraction methods are: (i) standard wavelet decomposition, (ii) wavelet decomposition—short-time Fourier transform, (iii) wavelet decomposition—Born-Jordan time-frequency representation, (iv) wavelet decomposition—Choi-Williams time-frequency representation. The wavelet layer is used for optimum feature extraction in the time-frequency domain. It is composed of wavelet decomposition and wavelet entropies. The multi layer perception is used for evaluating the fitness function of the genetic algorithm and for classifying radar targets. The performance of the developed system is evaluated by using noisy radar target echo signals. The test results show that this system is effective in rating real radar target echo signals. The correct classification rate is about 90% for target subjects.

The Coal Mine Flooding Emergency Ability Evaluation Based on GA-WNN

For the coal resources working which are affected by the coal mine flooding seriously, this paper make an analysis on the factors which affect the coal mine flooding emergency ability evaluation model based on GA-WNN is established through the wavelet neural network value which is optimized with genetic algorithm. This model combined the global optimization ability of genetic algorithm with the time-frequency localization of wavelet neural network. This combination can make up for many defects (for example, the neural network structure should be given artificially, the function can got local minimum easily and so on). Therefore, the local mine flooding emergency ability evaluation model based on genetic algorithm and wavelet neural network have higher reliability and calculation ability, and is beneficial to the pre-control management for coal mine flooding rescue.

Forecasting chaotic time series based on improved genetic WNN

The chaotic time series forecast using Wavelet Neural Networks(WNN) was researched in this paper.An improved training method for WNN was presented.This method combines the Genetic Arithmetic(GA) and gradient descent BP method,and the BP method was embedded in the GA operation in order to resolve the GA's limitation in detail search capability.In the last step of this method the WNN trained by GA searches the best solution using BP method once again.The experiment on predicting the chaotic time series from Henon map validates the performance of the method in this paper;the experimental result also shows the method could assure the WNN convergence and have high forecasting precision.

A prediction method of borehole stability based on seismic attribute technology

Borehole instability in drilling engineering can bring about serious problems of drilling quality and safety. Based on the close relationships between seismic and well log information, the prediction method of borehole stability is presented to effectively control borehole instability. Conventional and nonlinear seismic attributes are extracted from borehole-side seismic traces of impending drilling well and drilled offset well respectively. Then the optimal attributes combinations sensitive to log properties are selected by using genetic algorithm and wavelet neural network technology together. A series of mapping models which reflect the nonlinear relationships between seismic attributes and acoustic and density log data of various formation intervals in drilled well are constructed through neural network modeling. With analysis of cutting logging data, seismic attributes of the formation under bit and corresponding mapping model can be used to predict acoustic and density log curves of this formation. Based on the predicted log data, log interpretation method, analysis technology of in-situ stress and mechanics model of borehole stability are employed to calculate in-situ stress, pore pressure, collapse pressure and fracture pressure, thus the safe drilling fluid density window which can keep borehole stable is determined. Prediction precision and real-time operation ability of the proposed method are satisfying, which have been proved in practical application in TR oil field.

Research on the dynamic modeling based on genetic wavelet neural network for the robot wrist force sensor

A kind of new dynamic modeling method is presented based on improved genetic algorithm (IGA) and wavelet neural networks (WNN) and the algorithm is applied to a new type of robot wrist force sensor. The dynamic model of the wrist force sensor is set up according to data of the dynamic calibration, where the structure and parameters of wavelet neural networks of the dynamic model are optimized by genetic algorithm. The results show that the proposed method can overcome the shortcoming of easy convergence to the local minimum points of BP algorithm, and the network complexity, the convergence and the generalization ability are well compromised and the speed and precision of modeling are increased.