| Home | My Account | Post Article | Upload Showcase | Site Shortcuts | Feedback | About us |

  Home > Planning and consulting >  Defect warning

 
Seven Tech
Pat. Warn
Pat. Level2
Upgrade
Diagnosis
Consulting
Models
Prj cases
Model Sys
New L2
Modeling
Ind. Softw.
Simulation
Key Prjs
Li-Battery
Smart Equip
Model Prjs
Manufact.
Li Batt Ind.
Steel Ind.

Company

Defect Warn

Equip Intelli

Domain Sale

Training

- Class Time
- Classes
- Resources
- Lrn Method
- Status Need
- Metaverse
- Li Batt Tech
- Equip Softw.
- Intelli System
 


Defect Early Warning Consulting


The defect early warning system is developed on the basis of the existing lithium battery production line of a large enterprise. The system adopts the main methods of Smart Manufacturing: engineering modeling, machine learning and intelligent system architecture development. The main technology lies in the high accuracy of the model. For example, in the contract with the customer, it is required to achieve a hit rate of 85%; The actual acceptance reached 98%, and even some acceptance reached 100%! This defect early warning system is one of the key projects promoted by Shenzhen quality month. Therefore, the main designer was also invited to give a special lecture on the opening day of Shenzhen quality . Information about this product can be found in a special introduction article.

Characteristics of defect early warning system

Defect early warning system is an excellent solution developed under the specific Chinese Smart Manufacturing environment and the specific technical environment of our team. It has three characteristics: great difficulty, large market and large profit.See the document for details Characteristics of defect early warning system.

Modeling of defect early warning system

As far as the current defect early warning system is concerned, as long as the defect to be early warning is selected, the main factors affecting the defect are selected, and combined with the field data system, such as the data of manufacturing execution system or other types of data, the model can be established or the guidance for model establishment can be provided.

Production process optimization based on predicted defect data

Select a defect and establish the relationship between the defect and parameters such as process, product and equipment; Once the defect is predicted based on the online model, the production process and product quality can be optimized, See the document for details.

Data source suitability analysis

The core of industry 4.0 is customization. Through a series of special customization methods, it can be installed in various data systems, such as MES database, industrial Internet database, or SCADA data acquisition system; At the same time, the personality models of different systems can also be combined with the defect early warning system. Based on the maturity of domestic Smart Manufacturing foundation, the project mainly involves whether each MES in the manufacturing industry has enough information to install defect early warning system.

Add defect warning system when material is expensive

When the material is very expensive, the loss caused by any defective product is very large. It is necessary to add a defect early warning system on MES and other data sources to reduce defective products.

With the existing functions of MES, when there are defects in the production line, it is difficult for the operators to mobilize basic automation to solve the defects, because the operators do not have this quality, that is, how to solve the defects under what circumstances.

In order to increase the bridge between MES and basic automation, a module of defect early warning system can be added when the product has defects. This module can be understood as an extension system of MES. With this defect early warning system, as long as it can define which parameter combination and equipment combination will produce defects, the system will not allow such combination to operate, especially when defective products will appear, the system will give an alarm. After the operator knows the alarm, first check whether the parameter combination is optimized, and then determine whether to replace the worn parts, such as tools, molds, etc.

Smart Manufacturing consulting based on existing software

The main contribution of the team in Smart Manufacturing is to collect data on the factors related to on-site defective products or analyze data based on other data sources, establish engineering models, carry out machine learning and optimize production operation. The ultimate goal is to eliminate or reduce defective products in the production process and improve the yield.

Refer to the customer's MES or industrial Internet or other data obtained based on SCADA, and carry out defect early warning based on the existing software. Before the production of products is completed, the model is established through the idea of historical prediction of the future, and machine learning is carried out. The generated model is used to predict whether the relevant products will become defective after the production is completed; If it is a defective product in the future, the alarm will be given before the production is completed. The operator can make the product genuine by changing the parameter combination or even changing the wear parts. The existing software provides the recommended value of the best parameter combination.

Consulting and development of soft sensing system in defect early warning system

The lithium battery electrode slice slitting defect early warning system predicts the defect degree through model prediction, such as the burr length of lithium battery electrode slice. Among the main factors affecting the defect degree and burr length in lithium battery, the knife notch value is the most key influencing parameter. When calculating the burr length, the tool notch value at any time is required. However, the value of the knife notch is usually measured under a high-power (commonly used 1000 times) microscope, because in the production process, the knife is wrapped in the slitted pole piece, so it is difficult to see the knife notch; At the same time, the cutting speed in the production process is about 100 meters per minute. Under a 1000 times microscope, this corresponds to the speed of 100000 meters per minute, which also makes it almost impossible to directly measure the knife notch at every moment in the production process. Based on these two factors, soft sensing technology must be used to determine the value of knife notch at any time.

After cutting for a certain time, the tool is removed from the production line for grinding and continues to be used after grinding. For the cutting tool of lithium battery pole slice, remove it for the above grinding after about one week. 

In the process of using soft sensing technology to determine the value of knife notch at any time, the model accuracy of knife notch prediction should be optimized through machine learning. Therefore, the off-line tool notch measuring device is used to measure the initial tool notch value after tool grinding and before use, and then measure the end tool notch value again after tool use and before grinding.

When the defect value exceeds the maximum allowable defect value, the produced product becomes a defective product. Therefore, whether a product is a defective product can be predicted by the model before the production of a product is completed? If it is a defective product, the system will give an alarm to remind the operator to take measures, such as changing the parameter combination, or even replacing the worn parts (changing the knife in advance, etc.)

Based on the team's advantages in personality development, such as the advantages in establishing personality model and improving personality logic, the team has customized the defect early warning system, so that its core logic can be applied to a large number of manufacturing sections, so the defect early warning system can be applied to almost all manufacturing industries, Solve the problems of poor product quality and high defective rate in some manufacturing industries.
 

Defect Warning System Series
Development case of lithium battery defect early warning system
Function and application of defect early warning system products
Customer requirements of defect early warning system
Technical consultation of defect data based on Prediction
Production process optimization based on defect early warning
Introduction to defect early warning system technology

 

Planning & Consulting

  Biz discussPlanningMaturity, Consulting Area, Predict Maint.
 
Defect Early WarningModelsManufacturingLi-BatterySteel

=====
====
Contact us: Please contact Linkedin in www.Linkedin.com/in/intelli, OR scan the figure below to add Wechat (e.g. myQQfriend); Tel: (+1) 858 898 1288; E-mail BLiMetaverse@Gmail.com. See Profile of the key consultant.

 

  | Private Policy | Terms & Conditions | About Us | AdvertisePartnerInvestorSponsorlistings |  
Copyright: 2022 Metal Pass LLC. All right reserved