Predictive Maintenance with Sensor Data Analytics on a Raspberry Pi-Based Experimental Platform

Development of a palm-sized bioelectronic sensing device for protein detection in milk samples

The present study relates a portable optical sensing device supported by a small single-board (SBC) computer. The electronic architectural avenue connects the SBC with a camera, LED lights and a monitor. A 'sensor integration unit' has been linked with the device where the biological reactions were performed and assessed based on the concentration-dependent optical signal outputs. This setup can detect the generation of colors and distinguish their changes in the RGB intensity scale with an accuracy of a single pixel unit. A predefined range of values was obtained and fed to the device that can quantitatively sense the molecule of interest on the sensing matrix. The device has a touchscreen interactive panel that allows users to manually set experimental conditions and connect the entire measurement process to the cloud storage for backup information. We have considered detecting Alkaline Phosphatase (ALP) quantitatively from standard solutions as well as in milk samples as a proof-of-concept protein molecule. The device has shown exceptional analytical performance for lower and higher concentration ranges (0-100 U/mL and 100-1000 U/mL) with correlation coefficient values of 0.99. The detection limit of ALP was determined to be 0.1 U/mL, and the average time of a sample assessment was recorded to be 15 s. The device has also been tested against ALP-spiked milk samples to check its effectiveness and commercial viability. The outcome of the real-time assessment was sensitive and efficient, indicating its direct commercial and clinical importance towards colorimetric detection for diverse macromolecules.

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.

Data-driven approach to predict the sequence of component failures: a framework and a case study on a process industry

Purpose

The research approach is based on the concept that a failure event is rarely random and is often generated by a chain of previous events connected by a sort of domino effect. Thus, the purpose of this study is the optimal selection of the components to predictively maintain on the basis of their failure probability, under budget and time constraints.

Design/methodology/approach

Assets maintenance is a major challenge for any process industry. Thanks to the development of Big Data Analytics techniques and tools, data produced by such systems can be analyzed in order to predict their behavior. Considering the asset as a social system composed of several interacting components, in this work, a framework is developed to identify the relationships between component failures and to avoid them through the predictive replacement of critical ones: such relationships are identified through the Association Rule Mining (ARM), while their interaction is studied through the Social Network Analysis (SNA).

Findings

A case example of a process industry is presented to explain and test the proposed model and to discuss its applicability. The proposed framework provides an approach to expand upon previous work in the areas of prediction of fault events and monitoring strategy of critical components.

Originality/value

The novel combined adoption of ARM and SNA is proposed to identify the hidden interaction among events and to define the nature of such interactions and communities of nodes in order to analyze local and global paths and define the most influential entities.

ROS-Based Smart Walker with Fuzzy Posture Judgement and Power Assistance

In recent years the increased rate of the aging population has become more serious. With aging, the elderly sometimes inevitably faces many problems which lead to slow walking, unstable or weak limbs and even fall-related injuries. So, it is very important to develop an assistive aid device. In this study, a fuzzy controller-based smart walker with a distributed robot operating system (ROS) framework is designed to assist in independent walking. The combination of Raspberry Pi and PIC microcontroller acts as the control kernel of the proposed device. In addition, the environmental information and user postures can be recognized with the integration of sensors. The sensing data include the road slope, velocity of the walker, and user’s grip forces, etc. According to the sensing data, the fuzzy controller can produce an assistive force to make the walker moving more smoothly and safely. Apart from this, a mobile application (App) is designed that allows the user’s guardian to view the current status of the smart walker as well as to track the user’s location.

A Deep Learning Model for Predictive Maintenance in Cyber-Physical Production Systems Using LSTM Autoencoders

Condition monitoring of industrial equipment, combined with machine learning algorithms, may significantly improve maintenance activities on modern cyber-physical production systems. However, data of proper quality and of adequate quantity, modeling both good operational conditions as well as abnormal situations throughout the operational lifecycle, are required. Nevertheless, this is difficult to acquire in a non-destructive approach. In this context, this study investigates an approach to enable a transition from preventive maintenance activities, that are scheduled at predetermined time intervals, into predictive ones. In order to enable such approaches in a cyber-physical production system, a deep learning algorithm is used, allowing for maintenance activities to be planned according to the actual operational status of the machine and not in advance. An autoencoder-based methodology is employed for classifying real-world machine and sensor data, into a set of condition-related labels. Real-world data collected from manufacturing operations are used for training and testing a prototype implementation of Long Short-Term Memory autoencoders for estimating the remaining useful life of the monitored equipment. Finally, the proposed approach is evaluated in a use case related to a steel industry production process.

Impact of Industry 4.0 on Environmental Sustainability

Industry 4.0 is a concept that originated from the German industry, and whose essence is the use of technology for efficient production. In business today, the emergence of Industry 4.0 for production, and its related technologies, such as the Internet of Things (IoT) and cyber-physical systems, amongst others, have, however, a negative impact on environmental sustainability as a result of air pollution, the poor discharge of waste, and the intensive use of raw materials, information, and energy. The method used in this study is an analysis of a literature review of manuscripts discussing topics related to Industry 4.0 and environmental sustainability published between 2000 and 2020. There is currently a gap existing between the actual and the desired situation, in that production occurs in a weak sustainability model, and, therefore, this research debates the effects on environmental sustainability and the challenges facing Industry 4.0. Four scenarios are discussed: a deployment scenario, an operation scenario, integration and compliance with sustainable development goals, and a long-run scenario. The results indicate that there is a negative relationship related to the flow of the production process from the inputs to the final product, including raw materials, energy requirements, information, and waste disposal, and their impacts on the environment. However, the integration of Industry 4.0 and the sustainable development goals enhance environmental sustainability to create ecological support that guarantees high environmental performance with a more positive impact than before. This paper will help stakeholders and companies to provide solutions to the existing environmental challenges that can be mediated through adopting new technologies. The novelty of this study is its depiction of Industry 4.0 and its technologies integrated with sustainable development goals to create a sustainable Industry 4.0 combining environmental protection and sustainability.

Reflections and Methodological Proposals to Treat the Concept of "Information Precision" in Smart Agriculture Practices

Smart Agriculture (SA) is an evolution of Precision Farming (PF). It has technological basis very close to the paradigms of Industry 4.0 (Ind-4.0), so that it is also often referred to as Agriculture 4.0. After the proposal of a brief historical examination that provides a conceptual frame to the above terms, the common aspects of SA and Ind-4.0 are analyzed. These are primarily to be found in the cognitive approaches of Knowledge Management 4.0 (KM4.0, the actual theoretical basis of Ind-4.0), which underlines the need to use Integrated Information Systems (IIS) to manage all the activity areas of any production system. Based upon an infological approach, “raw data” becomes “information” only when useful to (or actually used in) a decision-making process. Thus, an IIS must be always designed according to such a view, and KM4.0 conditions the way of collecting and processing data on farms, together with the “information precision” by which the production system is managed. Such precision needs, on their turn, depend on the hierarchical level and the “Macrodomain of Prevailing Interest” (MPI) related to each decision, where the latter identifies a predominant viewpoint through which a system can be analyzed according to a prevailing purpose. Four main MPIs are here proposed: (1) physical and chemical, (2) biological and ecological, (3) productive and hierarchical, and (4) economic and social. In each MPI, the quality of the knowledge depends on the cognitive level and the maturity of the methodological approaches there achieved. The reliability of information tends to decrease from the first to the fourth MPI; lower the reliability, larger the tolerance margins that a measurement systems must ensure. Some practical examples are then discussed, taking into account some IIS-monitoring solutions of increasing complexity in relation to information integration needs and related data fusion approaches. The analysis concludes with the proposal of new operational indications for the verification and certification of the reliability of the information on the entire decision-making chain.