A Comparison of Machine Learning Techniques for the Quality Classification of Molded Products

Quality Control of Carbon Look Components via Surface Defect Classification with Deep Neural Networks

Many "Industry 4.0" applications rely on data-driven methodologies such as Machine Learning and Deep Learning to enable automatic tasks and implement smart factories. Among these applications, the automatic quality control of manufacturing materials is of utmost importance to achieve precision and standardization in production. In this regard, most of the related literature focused on combining Deep Learning with Nondestructive Testing techniques, such as Infrared Thermography, requiring dedicated settings to detect and classify defects in composite materials. Instead, the research described in this paper aims at understanding whether deep neural networks and transfer learning can be applied to plain images to classify surface defects in carbon look components made with Carbon Fiber Reinforced Polymers used in the automotive sector. To this end, we collected a database of images from a real case study, with 400 images to test binary classification (defect vs. no defect) and 1500 for the multiclass classification (components with no defect vs. recoverable vs. non-recoverable). We developed and tested ten deep neural networks as classifiers, comparing ten different pre-trained CNNs as feature extractors. Specifically, we evaluated VGG16, VGG19, ResNet50 version 2, ResNet101 version 2, ResNet152 version 2, Inception version 3, MobileNet version 2, NASNetMobile, DenseNet121, and Xception, all pre-trainined with ImageNet, combined with fully connected layers to act as classifiers. The best classifier, i.e., the network based on DenseNet121, achieved a 97% accuracy in classifying components with no defects, recoverable components, and non-recoverable components, demonstrating the viability of the proposed methodology to classify surface defects from images taken with a smartphone in varying conditions, without the need for dedicated settings. The collected images and the source code of the experiments are available in two public, open-access repositories, making the presented research fully reproducible.

Data-Driven Insights through Industrial Retrofitting: An Anonymized Dataset with Machine Learning Use Cases

Small and medium-sized enterprises (SMEs) often encounter practical challenges and limitations when extracting valuable insights from the data of retrofitted or brownfield equipment. The existing literature fails to reflect the full reality and potential of data-driven analysis in current SME environments. In this paper, we provide an anonymized dataset obtained from two medium-sized companies leveraging a non-invasive and scalable data-collection procedure. The dataset comprises mainly power consumption machine data collected over a period of 7 months and 1 year from two medium-sized companies. Using this dataset, we demonstrate how machine learning (ML) techniques can enable SMEs to extract useful information even in the short term, even from a small variety of data types. We develop several ML models to address various tasks, such as power consumption forecasting, item classification, next machine state prediction, and item production count forecasting. By providing this anonymized dataset and showcasing its application through various ML use cases, our paper aims to provide practical insights for SMEs seeking to leverage ML techniques with their limited data resources. The findings contribute to a better understanding of how ML can be effectively utilized in extracting actionable insights from limited datasets, offering valuable implications for SMEs in practical settings.

On the Problem of State Recognition in Injection Molding Based on Accelerometer Data Sets

The last few decades have been characterised by a very active application of smart technologies in various fields of industry. This paper deals with industrial activities, such as injection molding, where it is required to monitor continuously the manufacturing process to identify both the effective running time and down-time periods. Supervised machine learning algorithms are developed to recognize automatically the periods of the injection molding machines. The former algorithm uses directly the features of the descriptive statistics, while the latter one utilizes a convolutional neural network. The automatic state recognition system is equipped with an 3D-accelerometer sensor whose datasets are used to train and verify the proposed algorithms. The novelty of our contribution is that accelerometer data-based machine learning models are used to distinguish producing and non-producing periods by means of recognition of key steps in an injection molding cycle. The first testing results show the approximate overall balanced accuracy of 72-92% that illustrates the large potential of the monitoring system with the accelerometer. According to the ANOVA test, there are no sufficient statistical differences between the comparative algorithms, but the results of the neural network exhibit higher variances of the defined accuracy metrics.