Smart Anomaly Detection and Prediction for Assembly Process Maintenance in Compliance with Industry 4.0

RI2AP: Robust and Interpretable 2D Anomaly Prediction in Assembly Pipelines

Predicting anomalies in manufacturing assembly lines is crucial for reducing time and labor costs and improving processes. For instance, in rocket assembly, premature part failures can lead to significant financial losses and labor inefficiencies. With the abundance of sensor data in the Industry 4.0 era, machine learning (ML) offers potential for early anomaly detection. However, current ML methods for anomaly prediction have limitations, with F1 measure scores of only 50% and 66% for prediction and detection, respectively. This is due to challenges like the rarity of anomalous events, scarcity of high-fidelity simulation data (actual data are expensive), and the complex relationships between anomalies not easily captured using traditional ML approaches. Specifically, these challenges relate to two dimensions of anomaly prediction: predicting when anomalies will occur and understanding the dependencies between them. This paper introduces a new method called Robust and Interpretable 2D Anomaly Prediction (RI2AP) designed to address both dimensions effectively. RI2AP is demonstrated on a rocket assembly simulation, showing up to a 30-point improvement in F1 measure compared to current ML methods. This highlights its potential to enhance automated anomaly prediction in manufacturing. Additionally, RI2AP includes a novel interpretation mechanism inspired by a causal-influence framework, providing domain experts with valuable insights into sensor readings and their impact on predictions. Finally, the RI2AP model was deployed in a real manufacturing setting for assembling rocket parts. Results and insights from this deployment demonstrate the promise of RI2AP for anomaly prediction in manufacturing assembly pipelines.

Predictive maintenance in Industry 4.0: a survey of planning models and machine learning techniques

Equipment downtime resulting from maintenance in various sectors around the globe has become a major concern. The effectiveness of conventional reactive maintenance methods in addressing interruptions and enhancing operational efficiency has become inadequate. Therefore, acknowledging the constraints associated with reactive maintenance and the growing need for proactive approaches to proactively detect possible breakdowns is necessary. The need for optimisation of asset management and reduction of costly downtime emerges from the demand for industries. The work highlights the use of Internet of Things (IoT)-enabled Predictive Maintenance (PdM) as a revolutionary strategy across many sectors. This article presents a picture of a future in which the use of IoT technology and sophisticated analytics will enable the prediction and proactive mitigation of probable equipment failures. This literature study has great importance as it thoroughly explores the complex steps and techniques necessary for the development and implementation of efficient PdM solutions. The study offers useful insights into the optimisation of maintenance methods and the enhancement of operational efficiency by analysing current information and approaches. The article outlines essential stages in the application of PdM, encompassing underlying design factors, data preparation, feature selection, and decision modelling. Additionally, the study discusses a range of ML models and methodologies for monitoring conditions. In order to enhance maintenance plans, it is necessary to prioritise ongoing study and improvement in the field of PdM. The potential for boosting PdM skills and guaranteeing the competitiveness of companies in the global economy is significant through the incorporation of IoT, Artificial Intelligence (AI), and advanced analytics.

Anomaly Detection in a Smart Industrial Machinery Plant Using IoT and Machine Learning

In an increasingly technology-driven world, the security of Internet-of-Things systems has become a top priority. This article presents a study on the implementation of security solutions in an innovative manufacturing plant using IoT and machine learning. The research was based on collecting historical data from telemetry sensors, IoT cameras, and control devices in a smart manufacturing plant. The data provided the basis for training machine learning models, which were used for real-time anomaly detection. After training the machine learning models, we achieved a 13% improvement in the anomaly detection rate and a 3% decrease in the false positive rate. These results significantly impacted plant efficiency and safety, with faster and more effective responses seen to unusual events. The results showed that there was a significant impact on the efficiency and safety of the smart manufacturing plant. Improved anomaly detection enabled faster and more effective responses to unusual events, decreasing critical incidents and improving overall security. Additionally, algorithm optimization and IoT infrastructure improved operational efficiency by reducing unscheduled downtime and increasing resource utilization. This study highlights the effectiveness of machine learning-based security solutions by comparing the results with those of previous research on IoT security and anomaly detection in industrial environments. The adaptability of these solutions makes them applicable in various industrial and commercial environments.

Systematic Literature Review on Visual Analytics of Predictive Maintenance in the Manufacturing Industry

The widespread adoption of cyber-physical systems and other cutting-edge digital technology in manufacturing industry production facilities may motivate stakeholders to embrace the idea of Industry 4.0. Some industrial companies already have different sensors installed on their machines; however, without proper analysis, the data collected is not useful. This systematic review's main goal is to synthesize the existing evidence on the application of predictive maintenance (PdM) with visual aids and to identify the key knowledge gaps in areas including utilities, power generation, industry, and energy consumption. After a thorough search and evaluation for relevancy, 37 documents were identified. Moreover, we identified the visual analytics of PdM, including anomaly detection, planning/scheduling, exploratory data analysis (EDA), and explainable artificial intelligence (XAI). The findings revealed that anomaly detection was a major domain in PdM-related works. We conclude that most of the literature lacks depth in terms of an overall framework that combines data-driven and knowledge-driven techniques of PdM in the manufacturing industry. Some works that utilized both techniques indicated promising results, but there is insufficient research on involving maintenance personnel's feedback in the latter stage of PdM architecture. Thus, there are still pertinent issues that need to be investigated, and limitations that need to be overcome before PdM is deployed with minimal human involvement.

Edge-to-Cloud IIoT for Condition Monitoring in Manufacturing Systems with Ubiquitous Smart Sensors

The Industrial Internet of Things (IIoT) connects industrial assets to ubiquitous smart sensors and actuators to enhance manufacturing and industrial processes. Data-driven condition monitoring is an essential technology for intelligent manufacturing systems to identify anomalies from malfunctioning equipment, prevent unplanned downtime, and reduce the operation costs by predictive maintenance without interrupting normal machine operations. However, data-driven condition monitoring requires massive data collected from smart sensors to be transmitted to the cloud for further processing, thereby contributing to network congestion and affecting the network performance. Furthermore, unbalanced training data with very few labelled anomalies limit supervised learning models because of the lack of sufficient fault data for the training process in anomaly detection algorithms. To address these issues, we proposed an IIoT-based condition monitoring system with an edge-to-cloud architecture and computed the relative wavelet energy as feature vectors on the edge layer to reduce the network traffic overhead. We also proposed an unsupervised deep long short-term memory (LSTM) network module for anomaly detection. We implemented the proposed IIoT condition monitoring system for a manufacturing machine in a real shop site to evaluate our proposed solution. Our experimental results verify the effectiveness of our approach which can not only reduce the network traffic overhead for the IIoT but also detect anomalies accurately.

The Use of Artificial Neural Networks for Determining Values of Selected Strength Parameters of Miscanthus × Giganteus

The aim of this paper is to develop neural models enabling the determination of biomechanical parameters for giant miscanthus stems. The static three-point bending test is used to determine the bending strength parameters of the miscanthus stem. In this study, we assume the modulus of elasticity bending and maximum stress in bending as the dependent variables. As independent variables (inputs of the neural network) we assume water content, internode number, maximum bending force value and dimensions characterizing the cross-section of miscanthus stem: maximum and minimum stem diameter and stem wall thickness. The four developed neural models, enabling the determination of the value of the modulus of elasticity in bending and the maximum stress in bending, demonstrate sufficient and even very high accuracy. The neural networks have an average relative error of 2.18%, 2.21%, 3.24% and 0.18% for all data subsets, respectively. The results of the sensitivity analysis confirmed that all input variables are important for the accuracy of the developed neural models—correct semantic models.

Robust Assembly Assistance Using Informed Tree Search with Markov Chains

Manual work accounts for one of the largest workgroups in the European manufacturing sector, and improving the training capacity, quality, and speed brings significant competitive benefits to companies. In this context, this paper presents an informed tree search on top of a Markov chain that suggests possible next assembly steps as a key component of an innovative assembly training station for manual operations. The goal of the next step suggestions is to provide support to inexperienced workers or to assist experienced workers by providing choices for the next assembly step in an automated manner without the involvement of a human trainer on site. Data stemming from 179 experiment participants, 111 factory workers, and 68 students, were used to evaluate different prediction methods. From our analysis, Markov chains fail in new scenarios and, therefore, by using an informed tree search to predict the possible next assembly step in such situations, the prediction capability of the hybrid algorithm increases significantly while providing robust solutions to unseen scenarios. The proposed method proved to be the most efficient for next assembly step prediction among all the evaluated predictors and, thus, the most suitable method for an adaptive assembly support system such as for manual operations in industry.

Identifying and Characterizing Conveyor Belt Longitudinal Rip by 3D Point Cloud Processing

Real-time and accurate longitudinal rip detection of a conveyor belt is crucial for the safety and efficiency of an industrial haulage system. However, the existing longitudinal detection methods possess drawbacks, often resulting in false alarms caused by tiny scratches on the belt surface. A method of identifying the longitudinal rip through three-dimensional (3D) point cloud processing is proposed to solve this issue. Specifically, the spatial point data of the belt surface are acquired by a binocular line laser stereo vision camera. Within these data, the suspected points induced by the rips and scratches were extracted. Subsequently, a clustering and discrimination mechanism was employed to distinguish the rips and scratches, and only the rip information was used as alarm criterion. Finally, the direction and maximum width of the rip can be effectively characterized in 3D space using the principal component analysis (PCA) method. This method was tested in practical experiments, and the experimental results indicate that this method can identify the longitudinal rip accurately in real time and simultaneously characterize it. Thus, applying this method can provide a more effective and appropriate solution to the identification scenes of longitudinal rip and other similar defects.

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.

Analyzing Particularities of Sensor Datasets for Supporting Data Understanding and Preparation

Data scientists spend much time with data cleaning tasks, and this is especially important when dealing with data gathered from sensors, as finding failures is not unusual (there is an abundance of research on anomaly detection in sensor data). This work analyzes several aspects of the data generated by different sensor types to understand particularities in the data, linking them with existing data mining methodologies. Using data from different sources, this work analyzes how the type of sensor used and its measurement units have an important impact in basic statistics such as variance and mean, because of the statistical distributions of the datasets. The work also analyzes the behavior of outliers, how to detect them, and how they affect the equivalence of sensors, as equivalence is used in many solutions for identifying anomalies. Based on the previous results, the article presents guidance on how to deal with data coming from sensors, in order to understand the characteristics of sensor datasets, and proposes a parallelized implementation. Finally, the article shows that the proposed decision-making processes work well with a new type of sensor and that parallelizing with several cores enables calculations to be executed up to four times faster.

Sound Detection Monitoring Tool in CNC Milling Sounds by K-Means Clustering Algorithm

Computer numerical control (CNC) is a machine used in the manufacturing industry to produce components quickly for the engineering field or the desired shape. In the milling process carried out by CNC machines, sometimes vibrations occur that cause unwanted cracks or damage, which if left unchecked, will cause more severe damage. For this reason, this study describes how to monitor and analyze the sound produced by CNC during the milling process. This study uses six sound sample videos from YouTube, and there are two modes: (1) the operating mode is three different shapes with XY, XZ, and XYZ axes, and the second (2) is based on material differences. Namely, wood, Styrofoam, and plastic. The sound generated from all samples of the CNC milling processes will be detected using a sound detection program that has been designed in the LabVIEW using a simple microphone. The resulting sound frequency will be analyzed using the fast Fourier transform (FFT) process in spectral measurements, which will produce the amplitude and frequency of the detected sound in real time in the form of a graph. All frequency results that have been obtained from the sound detection monitoring tool in the CNC milling machine will be imported into the K-means clustering algorithm where the different frequencies between the resonant frequency and noise will be classified. Based on the experiments conducted, the sound detection program can detect sounds with a significant level of sensitivity.