Search

From the perspective of the Industry 4.0 paradigm, the machine learning (ML) discipline has had a significant influence on the manufacturing sector. The industry 4.0 concept promotes intelligent sensors, gadgets, and equipment to create technology infrastructure sectors that collect information constantly. By analyzing the obtained data, machine learning approaches allow actionable insight to boost industrial productivity without dramatically altering the necessary resources. Furthermore, the capacity of machine learning applications to provide actionable analytics has facilitated the detection of complex manufacturing trends and paved the path for an integrated intelligent process in various activities in the supply chain, including smart and constant inspection, preventative maintenance, quality enhancement, process optimization, supply chain advancement, and workflow scheduling. This paper aims to present recent advances in the field of quality inspection in Industry 4.0 and develop a framework for quality inspection that can be fully utilized in the Industry 4.0 context using adaptive bilateral filtering and Feature Correlated Auto encoder (FCA) machine learning technique. The suggested approach makes full use of information from all sources along the manufacturing chain. Therefore, it complies with quality management standards within the context of Industry 4.0. The suggested model makes use of corrective measures based on data patterns discovered through predictive analysis. Result analysis was shown on some pre-trained deep learning models such as ResNet18, Vgg19, Alexnet, Squeezenet, auto encoder, and FCA and observed that the proposed FCA(Feature Correlated Auto encoder) achieved a better result. [ABSTRACT FROM AUTHOR]

The production industry is in a transformation towards more autonomous and intelligent manufacturing. In addition to more flexible production processes to dynamically respond to changes in the environment, it is also essential that production processes are continuously monitored and completed in time. Video-based methods such as object detection systems are still in their infancy and rarely used as basis for process monitoring. In this paper, we present a framework for video-based monitoring of manufacturing processes with the help of a physical smart factory simulation model. We evaluate three state-of-the-art object detection systems regarding their suitability to detect workpieces and to recognize failure situations that require adaptations. In our experiments, we are able to show that detection accuracies above 90% can be achieved with current object detection methods. [ABSTRACT FROM AUTHOR]

In the Industry 4.0 era, a myriad of sensors of diverse nature (temperature, pressure, etc.) is spreading throughout the entire value chain of industries, being potentially exploitable for multiple purposes, such as Predictive Maintenance (PdM): the just-in-time maintenance of industrial assets, which results in reduced operating costs, increased operator safety, etc. Nowadays, industrial processes require to be highly configurable, in order to proactively adapt their operation to diverse factors such as user needs, product updates or supply chain uncertainties. This limits current Industry 4.0-PdM solutions, typically consisting of ad-hoc developments intended for specific scenarios, i.e. they are designed to operate under certain conditions (configurations, employed sensors, etc.), being unable to manage changes in their setup. This paper presents a general Deep Learning (DL) architecture, MachNet, which deals with such heterogeneity and is able to address PdM problems of a diverse nature. The modularity of the proposed architecture enables it to deal with an arbitrary number of sensors of different types, also allowing the integration of prior information (age of assets, material type, etc.), which clearly affects performance and is often neglected. In practice, our architecture effortlessly adapts to the assets' specifications and to different PdM problems. That is, MachNet becomes an architectural template that can be instantiated for a given scenario. We tested our proposal in two different PdM-related problems: Health State (HS) and Remaining-useful-Life (RuL) estimation, achieving in both cases comparable or superior performance to other state-of-the-art approaches, with the additional advantage of the generality that MachNet offers. [ABSTRACT FROM AUTHOR]

This paper analyzes the process variable data from injection molding processes to identify the key process variables, which can be predicted by other process variables, which highlights the interdependence among different process variables in various production scenarios. The available data from injection molding machines provide information for the run-time, setup parameters of machines, and measurements of different process variables through sensors. For predictive modeling, we employed different linear regression models with the recursive backward feature selection and SVM regression models using a radial kernel to predict nonlinear process variables. We also applied the linear and SVM regression models for outlier data in the process variables assuming that the upper bound outliers represent the perturbed state of process variables during production. These perturbations are affected by material type, machine type (age and performance), regime changes, or other external effects and subsequently affect the predictability of process variables and production output. Such cases are different compared to the normal or controlled range of process variables. Our analysis shows that the predictability varies for different material types due to the interdependence of the associated process variables. We further highlight that various process variables exhibit nonlinear relationships and cannot be predicted using linear models. We additionally look for the interdependence of process variables used previously by three studies as input features to predict product quality. [ABSTRACT FROM AUTHOR]

In the context of Industry 4.0, an emerging trend is to increase the reliability of industrial process by using machine learning (ML) to detect anomalies of production machines. The main advantages of ML are in the ability to (1) capture non-linear phenomena, (2) adapt to many different processes without human intervention and (3) learn incrementally and improve over time. In this paper, we take the perspective of IT system architects and analyse the implications of the inclusion of ML components into a traditional anomaly detection systems. Through a prototype that we deployed for chemical reactors, our findings are that such ML components are impacting drastically the architecture of classical alarm systems. First, there is a need for long-term storage of the data that are used to train the models. Second, the training and usage of ML models can be CPU intensive and may request using specific resources. Third, there is no single algorithm that can detect machine errors. Fourth, human crafted alarm rules can now also include a learning process to improve these rules, for example by using active learning with a human-in-the-loop approach. These reasons are the motivations behind a microservice-based architecture for an alarm system in industrial machinery. [ABSTRACT FROM AUTHOR]

Highlights • We overview the state of art in data fusion and analysis for industrial prognosis. • Descriptive, predictive and prescriptive prognostic models are reviewed. • Future trends and challenges are provided to stimulate research on this topic. Abstract The so-called "smartization" of manufacturing industries has been conceived as the fourth industrial revolution or Industry 4.0, a paradigm shift propelled by the upsurge and progressive maturity of new Information and Communication Technologies (ICT) applied to industrial processes and products. From a data science perspective, this paradigm shift allows extracting relevant knowledge from monitored assets through the adoption of intelligent monitoring and data fusion strategies, as well as by the application of machine learning and optimization methods. One of the main goals of data science in this context is to effectively predict abnormal behaviors in industrial machinery, tools and processes so as to anticipate critical events and damage, eventually causing important economical losses and safety issues. In this context, data-driven prognosis is gradually gaining attention in different industrial sectors. This paper provides a comprehensive survey of the recent developments in data fusion and machine learning for industrial prognosis, placing an emphasis on the identification of research trends, niches of opportunity and unexplored challenges. To this end, a principled categorization of the utilized feature extraction techniques and machine learning methods will be provided on the basis of its intended purpose: analyze what caused the failure (descriptive), determine when the monitored asset will fail (predictive) or decide what to do so as to minimize its impact on the industry at hand (prescriptive). This threefold analysis, along with a discussion on its hardware and software implications, intends to serve as a stepping stone for future researchers and practitioners to join the community investigating on this vibrant field. [ABSTRACT FROM AUTHOR]

• Recognize operator's activities through a machine learning classifier. • Assess Vibration risk in real time to enhance operator's safety. • Develop a lightweight wearable device for real time monitoring. • Validate the process in real conditions through experimental tests. While being a fundamental driver of competitiveness in agroindustry, technological innovation has also introduced new critical elements related, for example, to the sustainability of the production processes as well as to the safety of workers. In such regard, the advent of the 4th industrial revolution (Agriculture 4.0) based on digitalization, is an unprecedented opportunity of rethinking the role of innovation in a new human-centric perspective. In particular, the establishment of an interconnected work environment and the augmentation of the operator's physical, sensorial, and cognitive capabilities, are two technologies which can be effectively employed for substantially improving the ergonomics and safety conditions on the workplace. This paper approaches such topic referring to the vibration risk, which is a well-known cause of work-related pathologies, and proposes an original methodology for mapping the risk exposure of the operators to the activities performed. A miniaturized wearable device is employed to collect vibration data, and the signals obtained are segmented in time windows and processed in order to extract the significant features. Finally, a machine learning classifier has been developed to recognize the worker's activity and to evaluate the related exposure to vibration risks. To validate the methodology proposed, an experimental analysis in real operating conditions has been finally carried out by monitoring the activities performed by a team of workers during harvesting operations. The results obtained demonstrate the feasibility and the effectiveness of the methodology proposed. [ABSTRACT FROM AUTHOR]

Recent trends in intelligent manufacturing are transforming shop floor environments into digital factories, thanks to a pervasive integration of information and communication technologies in production lines. Industrial processes become the source of high-volume heterogeneous data, paving the way to create manufacturing intelligence by means of machine learning and data-driven methodologies. In such settings, predictive diagnostics play a crucial role, as they promise to predict future critical conditions in the production process. Unfortunately, the diffusion of data-driven predictive maintenance methodologies is limited by (i) the absence of timely ground-truth knowledge (i.e., class labels), required in the learning phase of data-driven supervised approaches, and (ii) the limited availability of data-mining expertise among application-domain experts, required to harness the power of machine learning techniques. Innovative data-driven services are needed to support domain experts in (i) applying powerful self-learning intelligent techniques with limited technical expertise and (ii) easily understanding results and choices operated by such intelligent techniques, to increase trust by means of transparency. To this aim, this paper presents UDaMP, an integrated platform to support manufacturing intelligence by providing a transparent, self-tuning, unsupervised discovery and assisted data labelling service for predictive maintenance, specifically targeted at cyclic industrial processes. UDaMP includes (i) production-cycle-aware feature engineering, (ii) unsupervised discovery of production-cycle categories, (iii) self-tuning of the optimal number of categories, (iv) human-readable characterisation of production-cycle categories, and (v) assisted data labelling for domain experts. Scalable clustering algorithms automatically discover groups of production cycles sharing common time-independent properties. A self-tuning strategy is integrated to automatically configure the specific input parameter and select the best approach for the data under analysis. Each cluster is then locally characterised through the data distribution of the top 10 most relevant features to support domain experts in uncovering its meaning. Experimental evaluation of UDaMP has been performed on real-world data collected in two different industrial settings. • Semi-supervised labelling of production cycles for predictive maintenance. • Wide applicability to any cycle-based production process without ground truth labels. • Exploitable by domain experts thanks to transparent self-tuning techniques. [ABSTRACT FROM AUTHOR]

• Data-driven models (DDMs) will become widespread across manufacturing. • Paramount to DDMs is the collection of an accurate set of model development data. • Process manufacturers face unique considerations and challenges in collecting data. • These points are presented in the context of the CRISP-DM framework. • This supports the development of DDMs to meet manufacturers' requirements. The increasing availability of data, due to the adoption of low-cost industrial internet of things technologies, coupled with increasing processing power from cloud computing, is fuelling increase use of data-driven models in manufacturing. Utilising case studies from the food and drink industry and waste management industry, the considerations and challenges faced when developing data-driven models for manufacturing systems are explored. Ensuring a high-quality set of model development data that accurately represents the manufacturing system is key to the successful development of a data-driven model. The cross-industry standard process for data mining (CRISP-DM) framework is used to provide a reference at to what stage process manufacturers will face unique considerations and challenges when developing a data-driven model. This paper then explores how data-driven models can be utilised to characterise process streams and support the implementation of the circular economy principals, process resilience and waste valorisation. [ABSTRACT FROM AUTHOR]

The concept of modeling the behavior of industrial processes is of great importance as it describes the possible states of equipment used in large industries, which once damaged, it usually costs both in time and money. In this paper, we propose a data-driven methodology for depicting three distinct states of a chemical reactor, (1) normal, (2) warning, (3) alert, by using machine learning techniques. A method for predicting the classification of data input, assists in prevention (early prognosis) of possible malfunctions. This method uses a combined linear trend analysis of the involved data which form the warning state of the reactor where the pre-incident conditions are fulfilled. Afterwards, it checks the possibility of the subsequent input to be classified in the alert state which is an indication that the reactor's active equipment, such as heating resistance, will start malfunctioning. The objective of the three main steps of the proposed methodology are: first, to reveal the number of clusters based on past data, second to train normal, warning and alert behavior-models and validate them and third to test them as well as verify the accuracy of linear trend analysis. The proposed methodology is based on the analysis of real data sets​ derived from the automation system of a chemical process located at CERTH/CPERI in order to identify real-life models for prognostic behavior for malfunction prevention. This approach is especially suitable for modern industrial systems that follow Industry 4.0 principles. The results reveal a robust modeling of the reactor's behavior with accuracy reaching 88,94%. • Novel data-driven architecture for behavior modeling of chemical reactors. • Data-driven prognosis framework for detection of electromechanical malfunctions. • Trained models based on real-life experimental data for high classification accuracy. • Online trend analysis and machine learning methods for 24/7 process monitoring. [ABSTRACT FROM AUTHOR]