IOT for the manufactured parts large scale defect prédiction


 
 

This project aims to develop a software prototype to support quality managers in the Industry 4.0, by


using the data of the three-dimensional coordinate-measuring machines (CMM) collected on the


manufactured parts and using an algorithm to classify the patterns of the control cards containing


the intervals of the quality requirements of the customers.

 

 

             WHAT WE ARE DOING    




 
 

We study data from an actual CMM of a car component manufacturing plant in Montreal. Manufacturers and


production managers need a link between their CMMs (Coordinate Measuring Machines) and an SPC system

 

(Statistical Process Control) to quickly control/predict the quality of production. The objectives are:


- Eliminate all restrictions on IT infrastructure and implementation costs through the use of a secure cloud IOT collection
  platform;

- Provide an overview of plant performance using room-by-room reports, as well as overall ratios of all manufactured parts;

- Use the measurement history, in the database that accumulates all CMM data, and the trend graphs of control charts
  generated by the system to predict the trend of certain variables and characteristics and anticipate non-conformities and
  off-checks;

- Allow to configure special customer parameters and control them during production;

- Identify and even predict out-of-control and out-of-control features in real time.


Have a look at current technical reports (in French) of students, of the non-conformite follow-up module prototype and tests on Azure
 
Have a look at another part of this project where we are recruiting: IOT Data Exchange for Industry 4.0
 
     

               CHALLENGES   

 
 

- Obtain reliable historical data as well as detailed quotes of the expected quality of customers.

- Predict with few data from CMM that are captured after the parts are made.

- Identify the Machine Learning algorithm adapted to this particular problem.
 

 

 
   
  

              STUDENTS INVOLVED   I.Gagnon, P.Gbehounou, N.Lebrun, H.Zenasni, J.Congote, I.B.Takupo Chendjou, N.Hamroun, N.Cloutier, P-O.Faucher, C.Rochon, P.R.Tessier

 


              TECHNOLOGY     .Net, Azure