Search for: All records

This study introduces a non-invasive approach to monitor operation and productivity of a legacy pipe bending machine in real-time based on a lightweight convolutional neural network (CNN) model and internal sound as input data. Various sensors were deployed to determine the optimal sensor type and placement, and labels for training and testing the CNN model were generated through the meticulous collection of sound data in conjunction with webcam videos. The CNN model, which was optimized through hyperparameter tuning via grid search and utilized feature extraction using Log-Mel spectrogram, demonstrated notable prediction accuracies in the test. However, when applied in a real-world manufacturing scenario, the model encountered a significant number of errors in predicting productivity. To navigate through this challenge and enhance the predictive accuracy of the system, a buffer algorithm using the inferences of CNN models was proposed. This algorithm employs a queuing method for continuous sound monitoring securing robust predictions, refines the interpretation of the CNN model inferences, and enhances prediction outcomes in actual implementation where accuracy of monitoring productivity information is crucial. The proposed lightweight CNN model alongside the buffer algorithm was successfully deployed on an edge computer, enabling real-time remote monitoring.

In the modern industrial setting, there is an increasing demand for all types of sensors. The demand for both the quantity and quality of sensors is increasing annually. Our research focuses on thin-film nitrate sensors in particular, and it seeks to provide a robust method to monitor the quality of the sensors while reducing the cost of production.

We are researching an image-based machine learning method to allow for real-time quality assessment of every sensor in the manufacturing pipeline. It opens up the possibility of real-time production parameter adjustments to enhance sensor performance. This technology has the potential to significantly reduce the cost of quality control and improve sensor quality at the same time. Previous research has proven that the texture of the topical layer (ion-selective membrane (ISM) layer) of the sensor directly correlates with the performance of the sensor. Our method seeks to use the correlation so established to train a learning-based system to predict the performance of any given sensor from a still photo of the sensor active region, i.e. the ISM. This will allow for the real-time assessment of every sensor instead of sample testing. Random sample testing is both costly in time and labor, and therefore, it does not account for all of the individual sensors.

Sensor measurement is a crucial portion of the data collection process. To measure the performance of the sensors, the sensors are taken to a specialized lab to be measured for performance. During the measurement process, noise and error are unavoidable; therefore, we generated credibility data based on the performance data to show the reliability of each sensor performance signal at each sample time.

In this paper, we propose a machine learning based method to predict sensor performance using image features extracted from the non-contact sensor images guided by the credibility data. This will eliminate the need to test every sensor as it is manufactured, which is not practical in a high-speed roll-to-roll setting, thus truely enabling a certify as built framework.