PH (potential of hydrogen) value predicting method of BP (back propagation) neutral network based on simulated annealing optimization

A technology of BP neural network and simulated annealing algorithm, applied in neural learning methods, biological neural network models, prediction, etc., can solve problems such as slow convergence speed, achieve good nonlinear fitting ability, overcome randomness, and predict accuracy high effect

Inactive Publication Date: 2015-06-10
JIANGNAN UNIV
View PDF2 Cites 44 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

But it has the following disadvantages: (1) The traditional BP network uses the gradient descent method to ca

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • PH (potential of hydrogen) value predicting method of BP (back propagation) neutral network based on simulated annealing optimization
  • PH (potential of hydrogen) value predicting method of BP (back propagation) neutral network based on simulated annealing optimization
  • PH (potential of hydrogen) value predicting method of BP (back propagation) neutral network based on simulated annealing optimization

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0034] In this embodiment, 984 sets of effective sample data are selected through experimental methods. Each set of sample data contains a pH value and its corresponding three color values ​​of R, G, and B. Among them, 884 sets of data are used for the training of BP neural network. The training data includes the maximum and minimum value samples of pH value and R , G, B extreme value samples. The remaining 100 sets of data are used to test the trained BP network. The specific steps for training on these data are as follows:

[0035] The first step is to select samples according to the sample selection strategy and input them.

[0036] The sample selection strategy described is specifically:

[0037] (1) Eliminate unqualified or invalid data. For example, data that exceeds the sample measurement range (that is, outliers), or samples with the same input value corresponding to different output values, etc.;

[0038] (2) Since the BP network is associated according to the si...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a pH (potential of hydrogen) value predicting method of a BP (back propagation) neutral network based on a simulated annealing (SA) algorithm optimization. The pH value predicting method comprises the following steps: step one, selecting a sample according to a sample selecting strategy and inputting; step two, according to the BP theorem, determining the structure of the BP neutral network; step three, according to a network training strategy, applying the simulated annealing algorithm to optimize the BP network weight parameter; training the BP network by using the input sample, and determining the optimal weight and optimal hidden node number of the BP network; step four, according to the well trained BP neutral network, structuring a predicting model of the pH value. The pH value predicting method overcomes the randomness of the BP network in terms of weight selection, improves the rate of convergence and study ability of the BP neutral network. Besides, the method optimizes the selection of the training sample and the network hidden neutral element number, and improves the generalization ability of the BP neutral network. Moreover, the pH value predicting method is high in predicting accuracy of pH value and good in nonlinear fitting ability.

Description

technical field [0001] The invention relates to a method in the field of parameter prediction and estimation, in particular to a pH value prediction method based on a simulated annealing optimized BP neural network. technical background [0002] Whether it is the detection of formation water, drinking water, or industrial water, pH value and chloride ion concentration are important parameters to be measured. At present, the determination of chloride ion concentration in formation water mostly adopts routine laboratory analysis methods, such as potentiometric titration and ion chromatography. These methods are complicated to operate and cannot be applied in the field. For the detection of pH value, in addition to the pH meter, the most widely used method is the test paper method. This method uses the human eye to compare the color card to judge the pH value. Therefore, it is greatly affected by human factors, such as differences in human color vision. In addition, prospect...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06Q10/04G06Q50/06G06N3/02
CPCG06Q10/04G06N3/088G06Q50/06
Inventor 吴静静宋淑娟尤丽华王金华
Owner JIANGNAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products