Impact on Inference Model Performance for ML Tasks Using Real-Life Training Data and Synthetic Training Data from GANs

Collecting and labeling of good balanced training data are usually very difficult and challenging under real conditions. In addition to classic modeling methods, Generative Adversarial Networks (GANs) offer a powerful possibility to generate synthetic training data. In this paper, we evaluate the hybrid usage of real-life and generated synthetic training data in different fractions and the effect on model performance. We found that a usage of up to 75% synthetic training data can compensate for both time-consuming and costly manual annotation while the model performance in our Deep Learning (DL) use case stays in the same range compared to a 100% share in hand-annotated real images. Using synthetic training data specifically tailored to induce a balanced dataset, special care can be taken concerning events that happen only on rare occasions and a prompt industrial application of ML models can be executed without too much delay, making these feasible and economically attractive for a wide scope of industrial applications in process and manufacturing industries. Hence, the main outcome of this paper is that our methodology can help to leverage the implementation of many different industrial Machine Learning and Computer Vision applications by making them economically maintainable. It can be concluded that a multitude of industrial ML use cases that require large and balanced training data containing all information that is relevant for the target model can be solved in the future following the findings that are presented in this study.

Prediction of Material Failure Time for a Bucket Wheel Excavator Boom Using Computer Simulation

Breakdown of stackers and excavators in opencast mines is possible because of operating, manufacturing and structural causes, and it produces high financial losses. These can be prevented by using various measures, including analyses and strength tests, with computerized modeling and simulation using FEA or other techniques being implemented in the recent years. In this paper a fatigue study is conducted on the boom of a BWE. Based on a computer model of the boom previously developed in SOLIDWORKS by our author team, first the modal analysis is conducted for three positions of the boom by studying the frequency response during the excavation process. This is followed by the time response determination corresponding to the maximum displacement frequency, in order to assess the stress during the excavation process, which causes the material fatigue in the boom structure. It was found that the maximum displacements appear when the BWE boom operates in a horizontal position. The aim was to estimate the period of time to failure in order to prevent unwanted accidents, and to develop a method that is applicable to any surface mining or industrial machine with similar structure.

Research of Light Field Technology

Light field technology is a relatively new theory and technical direction. At present, it has played a significant role in scientific research, production and life, national defense and military, but there are still many problems to be solved in terms of theoretical description, technical implementation, software and hardware processing capabilities, commercialization costs, and ease of use. Therefore, research the light field technology, explore the principle and application of light field imaging, and put forward some enlightenments for its application in industrial machine vision.

Investigating Human-Machine Interfaces’ Efficiency in Industrial Machinery and Equipment: A Kenyan Context

The twenty-first century has seen a vast technological revolution characterized by the development of cyber-physical systems, integration of things, and new and computationally improved machines and systems. However, there have been seemingly little strides in the development of user interfaces, specifically for industrial machines and equipment. The aim of this study was to assess the efficiency of the human-machine interfaces in the Kenyan context in providing a consistent and reliable working environment for industrial machine operators. The researcher employed a convenient purposive sampling to select 15 participants who had at least two years of hands-on experience in machines operation, control, or instrumentation. The results of the study are herein presented, including the recommendations to enhance workforce productivity and efficiency.

Acoustic Anomaly Detection of Mechanical Failures in Noisy Real-Life Factory Environments

Anomaly detection without employing dedicated sensors for each industrial machine is recognized as one of the essential techniques for preventive maintenance and is especially important for factories with low automatization levels, a number of which remain much larger than autonomous manufacturing lines. We have based our research on the hypothesis that real-life sound data from working industrial machines can be used for machine diagnostics. However, the sound data can be contaminated and drowned out by typical factory environmental sound, making the application of sound data-based anomaly detection an overly complicated process and, thus, the main problem we are solving with our approach. In this paper, we present a noise-tolerant deep learning-based methodology for real-life sound-data-based anomaly detection within real-world industrial machinery sound data. The main element of the proposed methodology is a generative adversarial network (GAN) used for the reconstruction of sound signal reconstruction and the detection of anomalies. The experimental results obtained in the Malfunctioning Industrial Machine Investigation and Inspection (MIMII) show the superiority of the proposed methodology over baseline approaches based on the One-Class Support Vector Machine (OC-SVM) and the Autoencoder–Decoder neural network. The proposed schematics using the unscented Kalman Filter (UKF) and the mean square error (MSE) loss function with the L2 regularization term showed an improvement of the Area Under Curve (AUC) for the noisy pump data of the pump.

Monitoring of Industrial Machine Using a Novel Blind Feature Extraction Approach

Machinery with several rotating and stationary components tends to produce non-stationary and random vibration signatures due to the fluctuations in the input loads and process defects due to long hours of operation. Traditional heuristics methods are suitable for the detection of fault signatures, however, they become more complicated when the level of uncertainty or randomness exceeds beyond control. A novel methodology to identify these fault signatures using optimal filtering of vibration data is proposed to eliminate any false alarms and is expected to provide a higher probability of correct diagnosis. In this paper, a detailed pipeline of the algorithms are presented along with the results of the investigation that was carried out. These investigations are performed using open-source vibration data published by the NASA prognostics centre. The performance of these algorithms are evaluated based on the ground truth results published by NASA researchers. Based on the performance of these algorithms several parameters are fine-tuned to ensure generalisation and reliable performance.