A method for predicting the energy consumption of automobile spare parts manufacturers
A forecasting method and spare parts technology, applied in forecasting, data processing applications, biological neural network models, etc., can solve the problem of high data input dimension, achieve high flexibility, avoid excessive forecast deviation, and improve forecast accuracy.
Inactive Publication Date: 2018-12-18
SHANGHAI ANYO ENERGY SAVING TECH
View PDF4 Cites 3 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] The technical problem to be solved by the present invention is to provide an energy consumption prediction method for auto parts manufacturers, which can avoid the problem that the data input dimension of a single neural network model is too high, and improve the overall accuracy of the model; Auto parts manufacturers have the characteristics of large product differentiation and high flexibility in product line production in the production process
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0013] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.
[0014] figure 1 It is a schematic diagram of the hierarchical modular neural network system of the present invention.
[0015] See figure 1 , the energy consumption forecasting method that the present invention provides is used for the automobile spare parts production enterprise, comprises the following steps:
[0016] Use the underlying neural network module to predict the energy consumption of a single process category;
[0017] The output of multiple underlying neural network modules is used as the input of a higher-level neural network module, combined with the higher-level input features, to make energy consumption predictions for a certain product line, a certain workshop, or the entire plant through a higher-level neural network module .
[0018] In the production of auto parts manufacturers, many different processes are often involved. Diff...
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
Login to View More Abstract
The invention discloses a method for predicting energy consumption of automobile spare parts manufacturers, which comprises the following steps: adopting a bottom layer neural network module to predict the energy consumption of a single process category; using the bottom layer neural network module to predict the energy consumption of a single process category; with the output of several bottom-level neural network modules being used as the input of a higher-level neural network module, based on the input characteristics of a higher-level, predicting the energy consumption of a product line, aworkshop or the whole plant through the higher-level neural network module. The invention provides a method for predicting the energy consumption of automobile spare parts manufacturers. By establishing a multi-level neural network model system, the fixed and invariable process parts in flexible production can be distinguished from the variable parts in flexible products, thus avoiding the problem that the data input dimension of a single neural network model is too high, and improving the accuracy of the model as a whole; the method can better adapt to the characteristics of large product differentiation and high product line flexibility in the production process of automobile spare parts manufacturers.
Description
technical field [0001] The invention relates to a method for predicting energy consumption, in particular to a method for predicting energy consumption used in auto parts manufacturers. Background technique [0002] In the field of machine learning and cognitive science, neural network system is a mathematical model that imitates the structure and function of biological neural network. The neural network is calculated by a large number of artificial neuron connections. In most cases, it can change the internal structure on the basis of external information. It is an adaptive system. The neural network has the characteristics of large-scale parallel processing, distributed information storage, and good self-organization and self-learning ability. It can approach any function in theory. The basic structure is composed of nonlinear change units, which has a strong nonlinear mapping ability. It has great flexibility and is often used in practical problems such as classification...
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
Login to View More IPC IPC(8): G06Q10/04G06Q50/04G06Q50/06G06N3/04
CPCG06Q10/04G06Q50/04G06Q50/06G06N3/045Y02P90/30
Inventor 李曼洁陈雷田洪本浩
Owner SHANGHAI ANYO ENERGY SAVING TECH