AI-based Framework for Deep Learning Applications in Grinding
چارچوبی مبتنی بر هوش مصنوعی برای کاربردهای یادگیری عمیق در شبکه سازی-2020
Rejection costs for a finish-machined gearwheel with grinding burn can rise to the order of 10,000 euros each. A reduction in costs by reducing rejection rate by only 5-10 pieces per year already amortizes costs for data-acquisition hardware for online process monitoring. The grinding wheel wear, one of the major influencing factors responsible for the grinding burn, depends on a large number of influencing variables like cooling lubricant, feed rate, circumferential wheel speed and wheel topography. In the past, machine learning algorithms such as Support Vector Machines (SVM), Hidden Markov Models (HMM) and Artificial Neural Networks (ANN) have proven effective for the predictive analysis of process quality. In addition to predictive analysis, AI-based applications for process control may raise the resilience of machining processes. Using machine learning methods may also lead to a heavy reduction of cost amassed due to a physical inspection of each workpiece. With this contribution, information from previous works is leveraged and an AI-based framework for adaptive process control of a cylindrical grinding process is introduced. For the development of such a framework, three research objectives have been derived: First, the dynamic wheel wear needs to be modelled and measured, because of its strong impact on the resulting workpiece quality. Second, models to predict the quality features of the produced workpieces depending on process setup parameters and materials used have to be established. Here, special focus is set on deriving models that are independent of a specific wheel-workpiece-pair. The opportunity to use such a model in a variety of grinding configurations gives the production line consistent process support. Third, the resilience of analytical models regarding graceful degradation of sensors needs to be tackled, since the stability of such systems has to be guaranteed to be used in productive environments. Process resilience against human errors and sensor failures leads to a minimization of rejection costs in production. To do so, a framework is presented, where virtual sensors, upon the failure or detection of an erroneous signal from physical sensors, will be activated and provide signals to the downstream smart systems until the process is completed or the physical sensor is changed.
Keywords: Cylindrical Grinding | Wheel Wear | Virtual Sensors | Process Resilience | Artificial Intelligence
Digital Twin-enabled Collaborative Data Management for Metal Additive Manufacturing Systems
مدیریت داده های همکاری مشترک زوج دیجیتال برای سیستم های تولید مواد افزودنی فلز-2020
Metal Additive Manufacturing (AM) has been attracting a continuously increasing attention due to its great advantages compared to traditional subtractive manufacturing in terms of higher design flexibility, shorter development time, lower tooling cost, and fewer production wastes. However, the lack of process robustness, stability and repeatability caused by the unsolved complex relationships between material properties, product design, process parameters, process signatures, post AM processes and product quality has significantly impeded its broad acceptance in the industry. To facilitate efficient implementation of advanced data analytics in metal AM, which would support the development of intelligent process monitoring, control and optimisation, this paper proposes a novel Digital Twin (DT)-enabled collaborative data management framework for metal AM systems, where a Cloud DT communicates with distributed Edge DTs in different product lifecycle stages. A metal AM product data model that contains a comprehensive list of specific product lifecycle data is developed to support the collaborative data management. The feasibility and advantages of the proposed framework are validated through the practical implementation in a distributed metal AM system developed in the project MANUELA. A representative application scenario of cloud-based and deep learning-enabled metal AM layer defect analysis is also presented. The proposed DT-enabled collaborative data management has shown great potential in enhancing fundamental understanding of metal AM processes, developing simulation and prediction models, reducing development times and costs, and improving product quality and production efficiency.
Keywords: Metal Additive Manufacturing | Digital Twin | data management | data model | machine learning | product lifecycle management
Deep learning for continuous manufacturing of pharmaceutical solid dosage form
یادگیری عمیق برای تولید مداوم فرم دوز جامد دارویی-2020
Continuous Manufacturing (CM) of pharmaceutical drug products is a new approach within the pharmaceutical industry. In the presented paper, a GMP continuous wet granulation line for production of solid dosage forms was investigated. The line was composed of the subsequent continuous unit: operations feeding – twin-screw wet-granulation – fluid-bed drying – sieving and tableting. The formulation of a commercial entity was selected for this study. Several critical process parameters were evaluated in order to probe the process and to characterize the impact on quality attributes. Seven critical process parameters have been selected after a risk analysis: API and excipient mass flows of the two feeders, liquid feed rate and rotation speed of the extruder and rotation speed, temperature and airflow of the dryer. Eight quality attributes were controlled in real time by Process Analytical Technologies (PAT): API content after blender, after dryer, in tablet press feed frame and of tablet, LOD after dryer and PSD after dryer (three PSD parameters: x10 x50 x90). The process parameter values were changed during production in order to detect the impact on the quality of the final product. The deep learning techniques have been used in order to predict the quality attribute (output) with the process parameters (input). The use of deep learning reduces the noise and simplify the data interpretation for a better process understanding. After optimization, three hidden layers neural network were selected with 6 hidden neurons. The activation function ReLU (Rectified Linear Unit) and the ADAM optimizer were used with 2500 epochs (number of learning cycle). API contents, PSD values and LOD values were estimated with an error of calibration lower than 10%. The level of error allow an adequate process monitoring by DNN and we have proven that the main critical process parameters can be identified at a higher levelof process understanding. The synergy between PAT and process data science creates a superior monitoring framework of the continuous manufacturing line and increase the knowledge of this innovative production line and the products that it makes.
Keywords: Continuous manufacturing | Solid dosage form | Process monitoring | Process analytical technology | Deep learning | Process data science | Process data analytics
ViDAQ: A computer vision based remote data acquisition system for reading multi-dial gauges
ViDAQ: سیستم کسب اطلاعات از راه دور مبتنی بر بینایی ماشین برای خواندن سنجهای چند زبانه-2019
This paper presents and evaluates design improvements to the Visual Data Acquisition (ViDAQ) system for reading multi-dial gauges. ViDAQ in general, is targeted to occupy a niche application for a cost effective and readily deployable solution for non-intrusive and remote acquisition of data from legacy human machine interface (HMI) indicators. Legacy HMI indicators that pose numerous technological hurdles in being digitally monitored, include analogue rotary multi-dial gauges, alarm lamps, switches etc, much like those common to industrial process monitoring systems can benefit from ViDAQ. Furthermore, ViDAQ is poised to assist in realizing an overarching design goal of a generic EYE-on-HMI (Expert supervisorY systEm) framework. As a framework, EYE-on-HMI stands to integrate the burgeoning field of machine learning and computer vision for realtime detection of human-in-the-loop operator errors and gather human performance data in any commercial and/or industrial process control domain for improving operational safety. Operator interaction with HMI is vital to the operational safety of any process control such as in nuclear power plant operation, aviation, public transit vehicles, driverless vehicles, etc. and thus should be monitored actively.
Keywords: Computer vision | Human machine interface (HMI) | Human factors engineering (HFE) | Expert supervisory system | Nuclear power plant (NPP) | Cyber physical systems (CPS) | Remote monitoring
Monitoring tip-based nanomachining process by time series analysis using support vector machine
نظارت بر فرآیند نانوماشینه مبتنی بر نوک بوسیله آنالیز سری زمانی با استفاده از دستگاه بردار پشتیبانی-2019
In this paper, time-series data analysis and pattern recognition using a multi-class support vector machine (SVM) were studied to monitor the state changes of the AFM tip-based nanomachining process with respect to the machining performance and tip wear. Time series data (i.e. machining force from the process), which has transient, nonlinear, and non-stationary characteristics, was collected by a data acquisition system. Three status detection features including the maximum force, peak-to-peak force value, and the variance of the collected lateral machining force, were extracted to classify the state of the nanomachining process. Directed Acyclic Graph Support Vector Machines (DAGSVM) with a Gaussian Radial Basis Kernel Function (RBF Kernel) was constructed to identify the different process states. Using this multi-class SVM, the machining process and the tip wear can be classified into three regions, which are effective machining with a sharp tip, transition region and bad/no machining with severe tip wear. The experimental data showed that the accuracy of the SVM was over 94.73% in both binary and ternary classifications, which confirmed that the SVM-based pattern recognition technology via time series data could successfully monitor the tip wear and process performance for tip-based nanomachining process.
Keywords: AFM tip-based nanomachining | Process monitoring | Tip wear detection | Time series data | Support vector machine
Image-based process monitoring using deep learning framework
نظارت بر فرآیند مبتنی بر تصویر با استفاده از چارچوب یادگیری عمیق-2019
With the advances in optical sensing and image capture systems, process images offer new perspectives to process monitoring. Compared to the process data collected by traditional sensors at local regions, process images enhance data-driven process monitoring a lot by capturing more significant variations in the whole space. Using the easily available industrial process images, a new deep learning framework based on the deep belief network (DBN) is proposed for feature extraction and timely fault detection. Unlike the traditional DBN methods inputting the images into the network directly, in the proposed framework, the sub-networks are used to extract local features from the sub-images. The global network fuses all of them for global feature extraction to remarkably improve the training efficiency without deteriorating the fault detection accuracy. Meanwhile, a new statistic is specially developed for the proposed deep learning framework. Finally a real combustion system is introduced to demonstrate the effectiveness of the proposed method.
Keywords: Process monitoring | Fault detection | Deep learning | Deep belief network | Process images
The barriers to the progression of additive manufacture: Perspectives from UK industry
موانع پیشرفت ساخت افزودنی: دیدگاههایی از صنعت انگلیس-2018
Additive manufacture (AM) is receiving significant attention globally, reflected in the volume of research being carried out to support the commercialisation of the technology for industrial applications and the interest shown by government and policy makers in the technology. The lack of distinction between 3D printing and AM, as well as the portrayal of some highly publicised applications, may imply that the technology is now firmly established. However, this is not the case. The aim of this study is to identify the current barriers to the progression of AM for end-use products from an industrial perspective and to understand the nature of those barriers. Case study research has been conducted with organisations in the UK aerospace, automotive, defence, heavy machinery and medical device industries. Eighteen barriers are identified: education, cost, design, software, materials, traceability, machine constraints, in-process monitoring, mechanical properties, repeatability, scalability, validation, standards, quality, inspection, tolerances, finishing and sterilisation. Explanation building and logic models are used to generalise the findings. The results are discussed in the context of current academic research on AM. The outcomes of this study help to inform the frontiers of research in AM and how AM research agendas can be aligned with the requirements for industrial applications.
keywords: 3D printing |Case study research |Additive layer manufacture |Aerospace |Automotive |Biomedical
Real-Time business data acquisition: How frequent is frequent enough?
دستیابی به داده های تجاری واقعی: چند مدت یکبار کافی است؟-2018
Effective data acquisition for business process monitoring has become a critical element in today’s business world. While the need for monitoring is generally agreed upon by both re- searchers and practitioners alike, the means and mechanisms are often vague. This is especially salient with the fast growing availability of various technologies to monitor in real-time through recent advances such as the Internet of Things (IoT) with specific emphasis on Radio-Frequency IDentification (RFID) and associated sensor networks. This study is motivated by the lack of published literature in data acquisition and analytics that specifically addresses sufficient real-time data acquisition for effective managerial monitoring. As a step in addressing this void, we review and extend existing literature in this general area by studying various requirements and information sources that relate to effective management monitoring. We then design an exploratory study to evaluate current managerial monitoring needs and the importance of automated data collection technologies. Results from this study show that the most important latent factor that influences an organization’s information need is its dynamic competitiveness, and consequently, companies with a dynamic supply chain would need a faster transaction and operations data system. The second important latent factor is the behavioral performance, which renders it essential to have a human-centric data system. This study provides evidence for the significance in adopting technologies such as RFID and other IoT systems for real-time monitoring in highly dynamic organizations and offers guidelines for analytical technology adoption for various industries.
keywords: RFID| Process monitoring| Monitoring frequency| Real-time data acquisition
زبان الکترونیکی هیبرید به عنوان ابزاری برای پایش تخمیر شراب و روند ذخیره سازی آن
سال انتشار: 2018 - تعداد صفحات فایل pdf انگلیسی: 8 - تعداد صفحات فایل doc فارسی: 21
زبان الکترونیکی هیبرید مبتنی بر حسگرهای ولتامتری و پتانسیومتری برای پایش فرآیند تولید شراب مورد استفاده قرار گرفت. آرایه ی حسگری از الکترودهای گزینش یونی مینیاتوری و الکترودهای کربن شیشه ای تشکیل شده و آنالیز میزان پیشرفت و صحت تخمیر شراب و روند ذخیره سازی آن، تشخیص وجود عوامل مزاحم و ارزیابی کیفیت فرآورده ی نهایی را ممکن می سازد. کارایی رویکرد پیشنهادی با پایش تولید شراب انجام گرفته با استفاده از روش های مرجع استاندارد مقایسه شد. نتایج نشان می دهد زبان الکترونیکی هیبرید را می توان به عنوان ابزار تحلیلی ساده و قابل اطمینان برای ارزیابی کیفی و کمّی فرآورده ی شراب مورد استفاده قرار داد.
کلیدواژه ها: تخمیر شراب | ذخیره سازی شراب | پایش فرایند | حسگرهای الکتروشیمیایی | زبان الکترونیکی هیبرید
|مقاله ترجمه شده|
Big data approach to batch process monitoring: Simultaneous fault detection and diagnosis using nonlinear support vector machine-based feature selection
رویکرد داده های بزرگ برای نظارت بر فرآیند دسته ای: تشخیص و تشخیص همزمان خطایی با استفاده از ویژگی های مبتنی بر بردار پشتیبانی غیرخطی-2018
This paper presents a novel data-driven framework for process monitoring in batch processes, a critical task in industry to attain a safe operability and minimize loss of productivity and profit. We exploit high dimensional process data with nonlinear Support Vector Machine-based feature selection algorithm, where we aim to retrieve the most informative process measurements for accurate and simultaneous fault detection and diagnosis. The proposed framework is applied to an extensive benchmark data set which includes process data describing 22,200 batches with 15 faults. We train fault and time-specific models on the pre-aligned batch data trajectories via three distinct time horizon approaches: one-step rolling, two-step rolling, and evolving which varies the amount of data incorporation during modeling. The results show that two-step rolling and evolving time horizon approaches perform superior to the other. Regardless of the approach, proposed framework provides a promising decision support tool for online simultaneous fault detection and diagnosis for batch processes.
Keywords: Process monitoring ، Data-driven modeling ، Big data ،Feature selection ، Support vector machines