BP neural network-based medium and large stamping die quotation prediction method

A BP neural network and stamping die technology, applied in biological neural network models, neural learning methods, market forecasting, etc., can solve the problems of long quotation cycle and low accuracy

Pending Publication Date: 2019-10-11
SHANDONG UNIV OF SCI & TECH
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] At present, the mold quotation in enterprises mainly has the problems of low accuracy and long quotation cycle, and computer-aided quotat

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
  • BP neural network-based medium and large stamping die quotation prediction method
  • BP neural network-based medium and large stamping die quotation prediction method
  • BP neural network-based medium and large stamping die quotation prediction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0083] A BP neural network-based quotation prediction method for medium and large stamping dies, the steps are as follows:

[0084] Assume that the number of input layer nodes of the neural network is m, the number of hidden layer nodes is h, and the number of output layer nodes is n; the connection weight coefficient from the i-th neuron in the input layer to the j-th neuron in the hidden layer is W ji , the threshold is θ j (i=1, 2...m; j=1, 2...h); the connection weight coefficient from the jth neuron in the hidden layer to the kth neuron in the output layer is V kj , the threshold is η k (j=1, 2...h; k=1, 2...n); Sigmoid function f(x)=1 / [1+exp(-x)]; then follow the steps below:

[0085] (1) Initialize, assign random numbers between [-1, 1] to the weights and thresholds of each layer;

[0086] (2) Select the l-th group of samples (l=1, 2...p) from the samples, and output the i node of the input layer to hidden layer j node output The conversion relationship between t...

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 relates to the technical field of cost prediction, in particular to a BP neural network-based medium and large stamping die quotation prediction method. Artificial neural network technology and a cost prediction method of a die are integrated to perform quotation prediction on the medium-large stamping die. During preliminary prediction sub-item detailed cost in quotation cost of themedium-and-large-scale stamping die is accurately evaluated and partially and independently calculating the sub-item detailed cost; wherein mold testing and packaging transportation fees are directlygiven by quotation personnel. The cost in the machining process is estimated by referring to a large and medium-sized stamping die calculation method in a die pricing method reference manual 'compiled by the Chinese die industrial association and then an improved BP algorithm network model is applied to predict possible errors and a final quotation result is adjusted. Various complex nonlinear mappings can be effectively simulated, cost influence factors are comprehensively considered, errors possibly generated by system quotation are predicted, then a final result is adjusted, adjustment ofa large number of coefficients is avoided, and the problem that quotation accuracy is low is solved.

Description

technical field [0001] The invention relates to the technical field of cost forecasting, in particular to a BP neural network-based quotation forecasting method for medium and large stamping dies. Background technique [0002] Due to the single-batch and small-scale production of molds and the characteristics of different products, the cost prediction method of molds is also different from that of general products. In traditional mold production, most enterprises use the method of manual cost estimation based on experience, which often causes large deviations and unnecessary losses; and requires professionals to spend a lot of time on complicated calculations, resulting in the prediction method It cannot be popularized and the cycle is long. In recent years, more and more mold companies have turned their attention to the direction of computer-aided cost forecasting, and have successively developed a series of computer-aided mold cost forecasting systems and quotation system...

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): G06Q30/02G06N3/08
CPCG06Q30/0206G06N3/084
Inventor 王海霞刘胜张法奎丁淑辉于涛高丽魏军英李学艺苏春建戴向云
Owner SHANDONG UNIV OF SCI & TECH
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap