Legacy Machines Research Articles

Data augmentation in predictive maintenance applicable to hydrogen combustion engines: a review

Machine-learning-based predictive maintenance models, i.e. models that predict breakdowns of machines based on condition information, have a high potential to minimize maintenance costs in industrial applications by determining the best possible time to perform maintenance. Modern machines have sensors that can collect all relevant data of the operating condition and for legacy machines which are still widely used in the industry, retrofit sensors are readily, easily and inexpensively available. With the help of this data it is possible to train such a predictive maintenance model. The main problem is that most data is obtained from normal operating conditions, whereas only limited data are from failures. This leads to highly unbalanced data sets, which makes it very difficult, if not impossible, to train a predictive maintenance model that can detect faults reliably and timely. Another issue is the lack of available real data due to privacy concerns. To address these problems, a suitable data generation strategy is needed. In this work, a literature review is conducted to identify a solution approach for a suitable data augmentation strategy that can be applied to our specific use case of hydrogen combustion engines in the automotive field. This literature review shows that, among the different state-of-the-art proposals, the most promising for the generation of reliable synthetic data are the ones based on generative models. The analysis of the different metrics used in the state of the art allows to identify the most suitable ones to evaluate the quality of generated signals. Finally, an open problem in research in this area is identified and it is the need to validate the plausibility of the data generated. The generation of results in this area will contribute decisively to the development of predictive maintenance models.

Exploration of weak-PGML Method for Efficient Stability Control During Machining Operations

Stable control of the machining process can be difficult to maintain in production environments due to many factors, but especially uncertainty about selection of optimal machining parameters. The true underlying stability model for production machines on the shop floor is generally unknown, so parameters are typically selected by operators based on manufacturer recommendations or, in most cases, their accumulated shop floor experience. A class of methods referred to as physics-guided machine learning (PGML) offers a new approach for optimal parameter selection that incorporates theoretical knowledge about machining dynamics into the data-driven machine learning workflow. The focus of this paper is a version of PGML appropriate to shop floor operations in small and medium-sized machine shops (SMMs)—referred to as weak-PGML—that does not require a priori theoretical knowledge of machining dynamics to approximate the true underlying stability model for a particular machining scenario. Rather, the weak-PGML leverages the operator’s accumulated domain knowledge to uncover the true stability model and informs parameter selection. Weak-PGML reflects the limited resources and lack of technical expertise typical of most SMMs with legacy machines and a new generation of workforce without the accumulated experience of operators who have spent many years on the shop floor.

Real-time assessment of the overall effectiveness of legacy machine tools

Real-time assessment of the overall effectiveness of legacy machine tools

Study on Smart Downtime Monitoring System in Glove Production

The manufacturing industry is pushing forward with the smart machineries, linked networks, and a smart environment to enhance Big Data’s operations – gaining intelligence and actionable real-time insights for higher efficient and smart production. However, in many parts of the manufacturing industry, manual monitoring system is still the usual practice, especially the long-established plants that consist of legacy machines. The monitoring processes of the lines in Top Glove F31 such as recording the lines’ downtime duration, checking the source of the stoppage, transferring the data into spreadsheet, and analyzing the downtime of the lines are all being carried out by human operators. There is a high tendency for the workers to overlook the maintenance of the system because of this work practice, and it will contribute to higher unplanned downtime of the lines. Thus, this project proposes to design an automatic downtime monitoring system that consists of sensors, PLC’s programming, and IoT technologies that can decrease the dependency on workers and not prone to human mistakes to reduce the unplanned downtime of the lines and increase the efficiency of the system.

IIoT based framework for data communication and prediction using augmented reality for legacy machine artifacts

Machine data automation, process feedback, and visualization are critical elements in monitoring and improving system performance. Legacy machines constitute a large part of the factory floor assets, especially in small and medium enterprises (SMEs). Digitalization enables them to seamlessly connect within the smart factory framework to exchange product and process information. This paper extends our work on extracting digitized data from legacy machines using computer vision in the Industrial Internet of things (IIoT) environment. The proposed framework includes data communication through the cloud for process automation, performing data analytics, interpretation, and visualization using Augmented Reality (AR) based smart devices through human-in-the-loop feedback. Real-time process recommendations are provided on an AR app by implementing a Bayesian Network to enable the user to input desired quality metrics. A case study of capturing injection molding data represented through different process parameters is presented to evaluate the performance. Further, its extension to using other machine learning (ML) models for process feedback, the latency of real-time data presented, communication with different IoT protocols, and authentication are discussed. This AR-based Digital Thread framework has promising applications for visualizing machine process parameters and performance, real-time feedback, troubleshooting, and maintenance activities for legacy and smart machines.

Interoperable system for automated extraction and identification of machine control data in brownfield production

In recent years, Industrial Internet of Things (IIoT) respectively Industry 4.0 have become increasingly established and thus a widespread technology among companies. By means of data acquisition, processes can not only be made more sustainable and resource-efficient but through emerging technologies like fault detection or predictive maintenance, a higher Overall Equipment Effectiveness (OEE) can be achieved. As a result, the availability of the machine tools remains high and process chains will not be disturbed. However, many companies still operate in brownfield production sites with legacy machines and therefore with limited opportunities for machine data access and use in an economically viable manner. As a result, many advantages that would increase the OEE of machine tools cannot be used. To present a solution for retrofitting brownfield machines, a low-effort system was developed that extracts machine control signals from different machine data sources and automatically identifies them using a multi-stage algorithm. This algorithm consists of analytical rule bases built using expert knowledge and a machine learning model for classification. The best performing models were selected as machine learning models, which are a Residual Network, a Fully Convolutional Network, a Long-Short-Term Memory, and a Random Forest. With different datasets from two machine tools, the overall model was tested and was able to correctly identify the signals present with an accuracy of 86.92% to 98.93% on average. Using this approach, the identified signals are assigned to an information model linking them to the respective machine tool axes. As a result, brownfield machines are also made accessible for modern technologies such as predictive maintenance or a reduction in rejects as a result of error detection.

On the potential of low-cost instrumentation for digitalization of legacy machine tools

On the potential of low-cost instrumentation for digitalization of legacy machine tools

An Efficient Siamese Network and Transfer Learning-Based Predictive Maintenance System for More Sustainable Manufacturing

Legacy machinery poses a specific challenge when integrated into modern manufacturing lines. While modern machinery provides swift methods of integration and inbuilt predictive maintenance (PdM), older machines, while physically fully functional, are less attractive to reuse, a specific reason being their lack of ready-to-implement PdM hardware and models. More sustainable manufacturing operations can be achieved if the useable lifespan of functional older machinery can be extended through retrofittable PdM and modern industrial communication systems. While PdM models can be developed for a class (make/model) of machine with retrofitted sensing, it is often found that legacy machines will deviate greatly from their original form, through nonstandard maintenance and component replacement actions during their lengthy lifespan. This would mean that each legacy machine would require a custom PdM model, a cost often leading to the removal or nonusage of legacy machines. This paper proposes a framework designed for the generation of an efficient PdM algorithm which would allow for the reuse of legacy machines retrofitted with low-cost sensing in modern manufacturing for increased sustainability. Given a limited number of data samples collected from a machine to be maintained, we aim to predict a failure or/and maintenance time by making use of the difference between the characteristics of the variation of the healthy and unhealthy data collected from the machine. We measure the healthiness of the machine by using a Siamese network trained with a public dataset and fine-tuned with data samples obtained from machines with similar characteristics. Although we use different training and testing datasets coming from completely different sources, we obtain reasonable results thanks to the proposed technique. The results of simulations and the statistical analysis enable us to devise a transfer learning technique and a Siamese network employed for failure detection in the machine. The proposed system will allow for the continued use of older machines in modern facilities, enabling more sustainable manufacturing models.

Automatic Content Creation System for Augmented Reality Maintenance Applications for Legacy Machines

Augmented reality (AR) applications have great potential to assist maintenance workers in their operations. However, creating AR solutions is time-consuming and laborious, which limits its widespread adoption in the industry. It therefore often happens that even with the latest generation machines, instead of an AR solution, the user only receives an electronic manual for the equipment operation and maintenance. This is commonplace with legacy machines. For this reason, solutions are required that simplify the creation of such AR solutions. This paper presents an approach using an electronic manual as a basis to create fast and cost-effective AR solutions for maintenance. As part of the approach, an application was developed to automatically identify and subdivide the chapters of electronic manuals via the bookmarks in the table of contents. The contents are then automatically uploaded to a central server and indexed with a suitable marker to make the data retrievable. The prepared content can then be accessed for creating context-related AR instructions via the marker. The application is characterized by the fact that no developers or experts are required to prepare the information. In addition to complying with common design criteria, the clear presentation of the contents and the intuitive use of the system offer added value for the performance of maintenance tasks. Together, these two elements form a novel way to retrofit legacy machines with AR maintenance instructions. The practical validation of the system took place in a factory environment. For this purpose, the content was created for a filter change on a CNC milling machine. The results show that inexperienced users can extract appropriate content with the software application. Furthermore, it is shown that maintenance workers, can access the content with an AR application developed for the Microsoft HoloLens 2 and complete simple tasks provided in the manufacturer's electronic manual.

Industrial Data Pipelines for Manufacturing Applications

Small and medium enterprises (SMEs) struggle with the uptake of industrial data in their business. SMEs have expressed interests to integrate physical legacy machines in factories and uptake Industrial Internet of Things (IIoT) for data-driven industrial processes. A widely recognizable aids for companies are testbeds or test-before-invest environments where companies can familiarize themselves with Industry 4.0 (I4.0) technologies. In this paper, an easily scalable approach to collect industrial data is presented. The environment can be used by SMEs to benchmark the developed solutions using affordable licenses and test aspects of the industrial data best suitable for their purposes before making investments. In TAMK FieldLab I4.0 pilot trial, horizontal integration is done in between 14.0 field and control layer to integrate different machines' data to common database and common format to be used for visualization and later for data analysis. The focus of the paper is on data connectivity capabilities. The trial utilize data from different machines. First phase includes exporting data from different machines to same data table with time stamps, to enable comparison of data with same time base. With common time base it's possible to produce synchronized timeseries data visualization from all TAMK FieldLab's machines. Used common database is PostgreSQL, where data from all machines is stored. For horizontal field level integration minimum amount APIs and protocols is used. For common API protocol MQTT was chosen as it's lightweight and supported widely. ABB robot data is taken trough OPC/UA and MQTT. From Omron mobile robot data is transferred trough ARCL. The paper will identify gap areas of the implementation in comparison with I4.0 and when appropriate, RAM 4.0 framework. Finally, the next steps that will be taken in near future regarding artificial intelligence (AI) and upgrading the IIoT system to match with RAMI 4.0 framework will be presented.

Generalizability of an Identification Approach for Machine Control Signals in Brownfield Production Environments

Digital transformation has been a central aspect of optimizing processes in manufacturing companies for several years now. A basic prerequisite of successful transformation is the vertical integration of all machines and machine tools to capture data at all levels. This can create further applications that enable more sustainable and resource-saving processes. At the same time cost- and quality-optimizing analyses such as failure detection, predictive maintenance or general process optimization represent major incentives for companies. While the necessary interfaces are now integrated in state-of-the-art machine tools, companies with older legacy machines face the problem that no such interfaces are readily available. Brownfield machine tools feature outdated technology that does not allow direct networking connectivity without further effort. To participate in the technological progress, a system was developed that allows to extract machine control signals from machine tools and identify them automatically as time series. This is compatible with several communication protocols (e.g., OPC UA) to be as universally applicable as possible. Since machine control signals are often not interpretable for the user due to different naming conventions, the extracted time series are analyzed by machine learning and analytical rule bases, these are based on expert knowledge, and assign a specific signal type in each case. With regard to a cross-machine generalization capability, several aspects have to be considered. Due to different data sources, the identification system must still function reliably with varying sampling frequency. Another challenge is the diversity of different types of machines and production equipment. Therefore, this publication investigates the different influences of data sources and machine types on the machine control signal identification system.

Smart retrofitting for human factors: a face recognition-based system proposal

Industry nowadays must deal with the so called “fourth industrial revolution”, i.e. Industry 4.0. This revolution is based on the introduction of new paradigms in the manufacturing industry such as flexibility, efficiency, safety, digitization, big data analysis and interconnection. However, human factors’ integration is usually not considered, although included as one of the paradigms. Some of these human factors’ most overlooked aspects are the customization of the worker’s user experience and on-board safety. Moreover, the issue of integrating state of the art technologies on legacy machines is also of utmost importance, as it can make a considerable difference on the economic and environmental aspects of their management, by extending the machine’s life cycle. In response to this issue, the Retrofitting paradigm, the addition of new technologies to legacy machines, has been considered. In this paper we propose a novel modular system architecture for secure authentication and worker’s log-in/log-out traceability based on face recognition and on state-of-the-art Deep Learning and Computer Vision techniques, as Convolutional Neural Networks. Starting from the proposed architecture, we developed and tested a device designed to retrofit legacy machines with such capabilities, keeping particular attention to the interface usability in the design phase, little considered in retrofitting applications along with other Human Factors, despite being one of the pillars of Industry 4.0. This research work’s results showed a dramatic improvement regarding machines on-board access safety.

Noncontact machinery operation status monitoring system with gated recurrent unit model

In manufacturing industry, assembly line monitoring provides statistical information about overall performance and reliability of the legacy machines, ensuring that the machines give maximum yield output. However, most legacy machines lack internet connectivity and advanced functionality, increasing the difficulty for tracking task. Therefore, this work seeks to introduce a noncontact acoustic method to track machines rather than the mainstream vibrational approach. In order to provide accurate tracking of the daily machine operation for our machine tracking system, we consider scenario of background noises such as environmental sounds from multiple sources as well as neighbouring machine?s sound. Thus, several neural networks are employed to recognize the machine status accurately. The objective of our work is to investigate the effect of machine types and states on recognition performance of neural network models under extremely noisy environments as well as to demonstrate the possibility of recognizing the sound on edge device. The main contribution of this article is the proposal of lightweight recurrent and convolutional-based models for machine sound recognition. The experimental results of our extensive testing included with multiple types of machines and background noises show that the proposed system with gated recurrent unit model has the best recognition accuracy of F1 score 0.913 with standard uncertainty of 0.026 with decent inference speed on edge device.

Low-Cost Digitalization Solution through Scalable IIoT Prototypes

Industry 4.0 is fast becoming a mainstream goal, and many companies are lining up to join the Fourth Industrial Revolution. Small and medium-sized enterprises, especially in the manufacturing industry, are the most heavily challenged in adopting new technology. One of the reasons why these enterprises are lagging behind is the motivation of the key personnel, the decision-makers. The factories in question often do not have a pressing need for advancing to Industry 4.0 and are wary of the risk in doing so. The authors present a rapid, low-cost prototyping solution for the manufacturing companies with legacy machinery intending to adopt the Industry 4.0 paradigm with a low-risk initial step. The legacy machines are retrofitted through the Industrial Internet of Things, making these machines both connectable and capable of providing data, thus enabling process monitoring. The machine chosen as the digitization target was not connectable, and the retrofit was extensive. The choice was made to present the benefits of digitization to the stakeholders quickly and effectively. Indeed, the solution provides immediate results within manufacturing industrial settings, with the ultimate goal being the digital transformation of the entire factory. This work presents an implementation cycle for digitizing an industrial broaching machine, supported by state-of-the-art literature analysis. The methodology utilized in this work is based on the well-known DMAIC strategy customized for the specifics of this case study.

Implementation of DDS Cloud Platform for Real-Time Data Acquisition of Sensors for a Legacy Machine

Industry 4.0 (I4.0) is a multidisciplinary engineering principle combing the IoT (Internet of things), big data, and cloud computing to cope with the dynamic changing industry. In this paper, the DDS (data distribution service) communication protocol was employed to implement a cloud platform for data acquisition from various sensors on a precision legacy machine tool including an accelerometer and sound, temperature, brightness, and humidity sensors. The sensor signals were acquired using Raspberry Pi as the edge device, then published to the cloud using the DDS application, and stored in the MySQL database. Using the Django web server, the acquired sensor signals could be shown in real time on the webpage via a combination of MQTT and Node-RED. In addition, the motion displacement of the machine tool detected by the encoder could be recorded through the edge device for further performance examination. With the proposed DDS cloud platform, it is demonstrated that a legacy machine can enable sensing and communication abilities such that the development of a smart machine is achievable for future I4.0 application.

The implementation of Industry 4.0 in manufacturing: from lean manufacturing to product design

With the emergence of Industry 4.0, digitalization and intelligent manufacturing are vital to ensure competitivity, especially for manufacturers reliant on legacy machines. Upgrading legacy machines with cyber physical technology under Industry 4.0 frameworks can enable connection of these machines to existing IoT networks to allow the sharing and exchange of production information. In this paper, a legacy machine used in sheet metal folding operations is upgraded by integrating switch sensors which provide detailed data on the machine status to stakeholders, enabling in-depth analysis of the production activity before and after the implementation of lean manufacturing methods. Furthermore, it is shown that the data collected can be applied to conduct dynamic value stream mapping (DVSM) in near real time to provide deeper level insight into manufacturing processes. More detailed mapping enables identification of wastes involved with labour and design. Therefore, an innovative graphical technique is proposed to improve the flattened pattern to reduce manual handling and ease bottlenecks identified by VSM. From the collected VSM data, a leanness measure was established to provide objective and quantitative evaluation of the process performance.

End-user development in industrial contexts: the paper mill case study

ABSTRACT This work aims to explore the potentialities of an end-user personalisation platform in industrial settings. In such a context, stakeholders with different roles and competencies collaborate to manage and control an environment where legacy machines coexist and interact with newer ones. Our goal is to provide a rule-based tool that allows end-users to build personalised solutions to respond quickly to the dynamic needs of factories. We report on a case study in the paper factory domain, in which the industrial aspects identified with expert stakeholders through interviews have been simulated and addressed through an extension of a personalisation platform. A first user test of the resulting environment has been carried out with a representative set of users, and has provided useful and encouraging feedback in terms of the potentialities of the proposed approach in industrial contexts.

Schloss: Blockchain-Based System Architecture for Secure Industrial IoT

Industrial companies can use blockchain to assist them in resolving their trust and security issues. In this research, we provide a fully distributed blockchain-based architecture for industrial IoT, relying on trust management and reputation to enhance nodes’ trustworthiness. The purpose of this contribution is to introduce our system architecture to show how to secure network access for users with dynamic authorization management. All decisions in the system are made by trustful nodes’ consensus and are fully distributed. The remarkable feature of this system architecture is that the influence of the nodes’ power is lowered depending on their Proof of Work (PoW) and Proof of Stake (PoS), and the nodes’ significance and authority is determined by their behavior in the network. This impact is based on game theory and an incentive mechanism for reputation between nodes. This system design can be used on legacy machines, which means that security and distributed systems can be put in place at a low cost on industrial systems. While there are no numerical results yet, this work, based on the open questions regarding the majority problem and the proposed solutions based on a game-theoretic mechanism and a trust management system, points to what and how industrial IoT and existing blockchain frameworks that are focusing only on the power of PoW and PoS can be secured more effectively.

Retrofitting-Based Development of Brownfield Industry 4.0 and Industry 5.0 Solutions

The ongoing Industry 4.0 is characterized by the connectivity between components in the manufacturing system. For modern machines, the Internet of Things is a built-in function. In contrast, there are legacy machines in deployment functioning without digital communication. The need to connect them became popular to improve overall production efficiency. As building a new smart factory as a greenfield investment is a capital-intensive choice, retrofitting the existing infrastructure with IoT capability is more reasonable than replacing them. However, this so-called brownfield development, or retrofitting, requires specific prerequisites, e.g., digitization status assessment, technical and connectivity development, management requirement, and operational need, representing a significant disadvantage: lack of scalability. In the meantime, Industry 5.0 is under human-centric priority, which poses new challenges to the retrofitted system. Aware of the challenge, this paper provides a systematic overview of brownfield development regarding technical difficulties, supporting technologies, and possible applications for the legacy system. The research scope focuses on available Industry 4.0 advancements but considers preparing for the forthcoming Industry 5.0. The proposed retrofitting project approach can be a guideline for manufacturers to transform their factories into intelligent spaces with minimal cost and effort but still gain the most applicable solution for management needs. The future direction for other research in brownfield development for Industry 5.0 is also discussed.

Retrofitting of legacy machines in the context of Industrial Internet of Things (IIoT)

In the context of Industry 4.0 (I 4.0), one of the most important aspects is data, followed by the capital required to deploy advanced technologies. However, most Small and Medium Enterprises (SMEs) are neither data ready nor have the capital to upgrade their existing machinery. In SMEs, most of the legacy machines do not have data gathering capabilities. In this scenario, the concept of retrofitting the existing machinery with sensors and building an Industrial Internet of Things (IIoT) is more beneficial than upgrading the equipment to newer machinery. The current research paper proposes a simple architecture on retrofitting a legacy machine with external sensors for data collection and feeding the cloud-based databases for analysis/monitoring purposes. The design and functional aspects of the architecture are then tested in a laboratory environment on a drilling machine with no embedded sensors. Data related to the speed of the drill head and the bore depth are collected using newly retrofitted sensors to validate the proposed architecture.