PROJECT TITLE :

The Application of LVQ Neural Network for Weld Strength Evaluation of RF-Welded Plastic Materials

ABSTRACT:

Radio-frequency welding may be a material joining method based on the dielectric loss principle, which is compatible to join plastic materials used in biomedical applications such as drainage and resolution baggage. For these reasonably applications, it's terribly vital that welds are of fine quality because of the sterility and biological hazard concerns. This sometimes suggests that that welds must have a bound predetermined strength. In production environment, destructive testing of sample product may be a commonly used methodology of quality control. This can be, however, time consuming and the results obtained on sample testing will by no means that be fully relied upon for all the products among a batch. Thus, a call was created to design an artificial intelligence monitoring system that would determine the quality of each weld based mostly on the measurements performed in real time. The main signal being measured is the displacement of the upper electrode. Numerous parameters of the displacement curve were revealed to be in relation with the weld strength. Thanks to disturbances in air offer that end in variable welding force, a force sensor was added yet. The measurements obtained from both the sensors were used to form the input vector for linear vector quantization neural network. This sort of network is suitable to put the input vectors in numerous categories. In our case, this implies if a sure measurement corresponds to a sensible quality weld or a unhealthy quality weld. The experiments have shown that the proposed neural network performs very well and might be of nice value during a production environment.