Spraying production monitoring data storage and feature analysis method and device

A technology of monitoring data and feature analysis, applied in the direction of neural learning methods, genetic rules, biological neural network models, etc., can solve the problems of poor analysis effect and low accuracy of spraying production monitoring data, achieve good data analysis effect, eliminate Useless features, fitness-enhancing effects

Inactive Publication Date: 2019-12-03
INNER MONGOLIA UNIVERSITY
View PDF2 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to solve the technical problem that the analysis effect of the existing spraying production monitoring data is not good, and the prediction accuracy is low, the present invention provides a storage and feature analysis method and device for the spraying production monitoring data

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
  • Spraying production monitoring data storage and feature analysis method and device
  • Spraying production monitoring data storage and feature analysis method and device
  • Spraying production monitoring data storage and feature analysis method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0122] The inventor of this case found through research that the daily output of the spraying workshop is relatively large. During the investigation, it was found that the unqualified products were basically unqualified in appearance, so data mining and analysis were carried out on the appearance quality. Products with unqualified appearance are found to have obvious daily production fluctuations and lack of stability. Please refer to Table 1, which counts the data of products that failed the product quality inspection within a week.

[0123] Table 1 Weekly Product Statistical Results Table

[0124]

[0125]

[0126] The mean value and standard deviation related to the unqualified products of the 6 products can be obtained through the calculation in the above table, as shown in Table 2.

[0127] Table 2 Statistical table of mean and standard deviation of unqualified product rate of 6 kinds of products

[0128]

[0129] It is found from Table 2 that the quality inst...

Embodiment 2

[0233] This embodiment provides a method for storing and analyzing characteristics of spraying production monitoring data, and step S0 is added to the method in Embodiment 1. Wherein, step S0: store the monitoring data through the cloud server. In this embodiment, the cloud server is preferably an Alibaba Cloud server, and a development environment is built through Node.js and Express.js frameworks. see Figure 19 , in this embodiment, a non-relational database MongoDB is used for distributed file storage. In the process from workpiece processing to data storage, there will be a large number of sensors to collect current information. This kind of sensor equipment will monitor all the time, and will send data at a certain frequency without interruption to generate a data stream. The MongoDB database will be stored in the form of documents. If it is said that every piece of sensor data is stored in the form of a document, then a large number of documents will be generated, and...

Embodiment 3

[0235] This embodiment provides a storage and feature analysis device for spraying production monitoring data, the device applies the storage and feature analysis method for spraying production monitoring data in embodiment 1 or implementation 2, and includes a preprocessing module and a neural network prediction module .

[0236]The preprocessing module is used to preprocess the monitoring data of spraying production, and includes a missing value processing unit, a normalization unit, a correlation inspection unit, and a data dimensionality reduction unit. The missing value processing unit is used to supplement missing values ​​in monitoring data and obtain a complete monitoring data table. The normalization unit is used to scale the data in the monitoring data table according to a preset ratio to obtain normalized data with a mean of 0 and a standard deviation of 1. The correlation test unit is used to mine the linear correlation coefficient between normalized data. The da...

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 spraying production monitoring data storage and feature analysis method and a spraying production monitoring data storage and feature analysis device. The method comprises the steps of supplementing missing values in monitoring data, conducting scaling operation, and obtaining standardized data; mining linear correlation coefficients, and screening data features; determining a network topology structure and constructing a model; initializing and determining a fitness function; training the individual; calculating individual fitness; judging whether the evolutionary frequency is reached or not, if so, obtaining an optimal weight and an optimal threshold, otherwise, carrying out selection, crossover and variation; calculating output values and output errors of the hidden layer and the output layer; judging whether the output error meets the precision requirement or not, if yes, converting the output value into a prediction result and outputting the prediction result, and otherwise, reversely adjusting the weight and the threshold of each layer. According to the method, the data analysis accuracy is improved, the data analysis amount is reduced, the data analysis and prediction efficiency is improved, the error rate, the maximum error and the average error are reduced, the spraying production cost is reduced, and the spraying efficiency and effect are improved.

Description

technical field [0001] The invention relates to a feature analysis method in the technical field of spraying production, in particular to a storage and feature analysis method for spraying production monitoring data, and also to a storage and feature analysis device for the spraying production monitoring data of the method. Background technique [0002] As a popular manufacturing technology, spraying is widely used in various industries, including hardware, military, furniture, etc., to improve the corrosion resistance and oxidation resistance of products. On the one hand, the high-temperature environment required for spraying can easily cause accidents, and the spraying environment needs to be monitored. On the other hand, due to the complexity of the current spraying process, there are many factors that affect the qualified rate of sprayed products, and it is necessary to analyze the characteristics of the production data. [0003] At present, the adjustment of environmen...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/62G06N3/04G06N3/08G06N3/12
CPCG06N3/086G06N3/126G06N3/048G06N3/045G06F18/211G06F18/213G06F18/10
Inventor 王树彬李博
Owner INNER MONGOLIA UNIVERSITY
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