A smart manufacturing methodology for real time chemical process diagnosis using causal link assessment

The cloud manufacturing platform needs to allocate the endlessly emerging tasks to the resources scattered in different places for processing. However, this real-time scheduling problem in the cloud environment is more complicated than that in a traditional workshop because constraints, such as type matching, task precedence, resource occupation, and logistics duration, need to be met, and the internal manufacturing plan of providers must also be considered. Since the platform aggregates massive manufacturing resources to serve large-scale manufacturing tasks, the space of feasible solutions is huge, resulting in many conventional search algorithms no longer being applicable. In this paper, we considered resource allocation as the key procedure for real-time scheduling, and an ANN (Artificial Neural Network) based model is established to predict the task completion status for resource allocation among candidates. The trained ANN model has high prediction accuracy, and the ANN-based scheduling approach performs better than the preferred method in terms of the optimization objectives, including total cost, service satisfaction, and make-span. In addition, the proposed approach has potential in the application for smart manufacturing or Industry 4.0 because of its high response performance and good scalability.

Download Full-text

Task Scheduling Based on a Hybrid Heuristic Algorithm for Smart Production Line with Fog Computing

Sensors ◽

10.3390/s19051023 ◽

2019 ◽

Vol 19 (5) ◽

pp. 1023 ◽

Cited By ~ 14

Author(s):

Juan Wang ◽

Di Li

Keyword(s):

Energy Consumption ◽

Fault Detection ◽

Real Time ◽

Task Scheduling ◽

Fog Computing ◽

Superior Performance ◽

Smart Manufacturing ◽

Hybrid Heuristic ◽

Scheduling Strategy ◽

Terminal Equipment

Fog computing provides computation, storage and network services for smart manufacturing. However, in a smart factory, the task requests, terminal devices and fog nodes have very strong heterogeneity, such as the different task characteristics of terminal equipment: fault detection tasks have high real-time demands; production scheduling tasks require a large amount of calculation; inventory management tasks require a vast amount of storage space, and so on. In addition, the fog nodes have different processing abilities, such that strong fog nodes with considerable computing resources can help terminal equipment to complete the complex task processing, such as manufacturing inspection, fault detection, state analysis of devices, and so on. In this setting, a new problem has appeared, that is, determining how to perform task scheduling among the different fog nodes to minimize the delay and energy consumption as well as improve the smart manufacturing performance metrics, such as production efficiency, product quality and equipment utilization rate. Therefore, this paper studies the task scheduling strategy in the fog computing scenario. A task scheduling strategy based on a hybrid heuristic (HH) algorithm is proposed that mainly solves the problem of terminal devices with limited computing resources and high energy consumption and makes the scheme feasible for real-time and efficient processing tasks of terminal devices. Finally, the experimental results show that the proposed strategy achieves superior performance compared to other strategies.

Download Full-text

Implementing the Transformation of Discrete Part Manufacturing Systems Into Smart Manufacturing Platforms

Volume 3: Manufacturing Equipment and Systems ◽

10.1115/msec2018-6726 ◽

2018 ◽

Cited By ~ 3

Author(s):

Bhaskar Botcha ◽

Zimo Wang ◽

Sudarshan Rajan ◽

Natarajan Gautam ◽

Satish T. S. Bukkapatnam ◽

...

Keyword(s):

Real Time ◽

High Performance ◽

Manufacturing Systems ◽

Energy Savings ◽

Advanced Materials ◽

Smart Manufacturing ◽

Shop Floor ◽

Workflow System ◽

Manufacturing Technologies ◽

Discrete Part

Prior R&D efforts point to substantial performance enhancements and energy savings from adopting the Smart Manufacturing (SM) paradigm for process optimization and real-time quality assurance. Significant barriers and risks disincentivize the industry from investing in the adoption and training of SM component suites for discrete manufacturing applications. A diverse discrete part manufacturing enterprises, SM tools and platform vendors are yearning for a testbed reconfigurable to achieve three objectives of performance benchmarking, demonstration, and workforce training for a spectrum of their industrial scenarios and workflows. This paper presents the key ingredients towards the successful transformation of present machine tool and manufacturing environments into SM platform-integrated environments. The present implementation focuses on demonstration of the use of the Smart Manufacturing (SM) platform towards qualification of advanced materials and manufacturing technologies to meet an industry-specified functionality. This initial implementation uses Kepler workflow system residing as part of an Amazon Web Services environment to allow flexible workflows on multiple machines, each of which is integrated with an innovative sensor wrapper that integrates Commercial Off The Shelf (COTS) components from National Instruments (NI) to connect a legacy equipment to the SM platform. Here, an advanced analytics engine with modules customizable for both high-performance computing and shop floor environments was integrated into the commercial web service (from Amazon) to provide real-time monitoring and anomaly detection capability. This implementation indicates the potential of SM platform to achieve drastic reductions in the time and effort taken towards qualification of advanced materials and manufacturing technologies.

Download Full-text

Sensor-Based Real-Time Detection in Vulcanization Control Using Machine Learning and Pattern Clustering

Sensors ◽

10.3390/s18093123 ◽

2018 ◽

Vol 18 (9) ◽

pp. 3123 ◽

Cited By ~ 4

Author(s):

Jonghyuk Kim ◽

Hyunwoo Hwangbo

Keyword(s):

Real Time ◽

Chemical Properties ◽

Innovation Process ◽

Smart Manufacturing ◽

Paradigm Shifts ◽

Manufacturing Environment ◽

Pattern Clustering ◽

Sensing Technology ◽

Input Variables ◽

Manual Testing

Recent paradigm shifts in manufacturing have resulted from the need for a smart manufacturing environment. In this study, we developed a model to detect anomalous signs in advance and embedded it in an existing programmable logic controller system. For this, we investigated the innovation process for smart manufacturing in the domain of synthetic rubber and its vulcanization process, as well as a real-time sensing technology. The results indicate that only analysis of the pattern of input variables can lead to significant results without the generation of target variables through manual testing of chemical properties. We have also made a practical contribution to the realization of a smart manufacturing environment by building cloud-based infrastructure and models for the pre-detection of defects.

Download Full-text

A Digital Twin Concept for Manufacturing Systems

Volume 2: Advanced Manufacturing ◽

10.1115/imece2018-87737 ◽

2018 ◽

Cited By ~ 1

Author(s):

Wesley Ellgass ◽

Nathan Holt ◽

Hector Saldana-Lemus ◽

Julian Richmond ◽

Ali Vatankhah Barenji ◽

...

Keyword(s):

Virtual Reality ◽

Real Time ◽

Manufacturing Systems ◽

Manufacturing System ◽

Virtual Space ◽

Smart Manufacturing ◽

Shop Floor ◽

Digital Twin ◽

Physical Resources ◽

Virtual Resources

With the developments and applications of the advanced information technologies such as cloud computing, internet of thing, artificial intelligence and virtual reality, industry 4.0 and smart manufacturing era are coming. In this respect, one of the specific challenges is to achieve a connection of physical resources on the shop floor with virtual resources, for real-time response, real time process optimization, and simulation, which is merged by big data problem. In this respect, Digital Twins (DT) concept is introduced as a key technology, which includes physical resources, virtual resources, service system, and digital twin data. DT considers current condition of physical resource and prediction of future events to make a responsive decision. However, due to the complexity of building a digital equivalent in virtual space to its physical counterpart, very little applications have been developed with this purpose, especially in the industrial manufacturing area. Therefore, the types of data and technology required to build the DT for a manufacturing system are presented in this work, trying to develop a framework of DT based manufacturing system, which is supported by the virtual reality for virtualization of physical resources.

Download Full-text

Real-Time Optimization and Control of Nonlinear Processes Using Machine Learning

Mathematics ◽

10.3390/math7100890 ◽

2019 ◽

Vol 7 (10) ◽

pp. 890 ◽

Cited By ~ 5

Author(s):

Zhihao Zhang ◽

Zhe Wu ◽

David Rincon ◽

Panagiotis Christofides

Keyword(s):

Neural Network ◽

Machine Learning ◽

Real Time ◽

Network Model ◽

Neural Network Model ◽

First Principles ◽

Chemical Process ◽

Feed Forward Neural Network ◽

Time Optimization ◽

Real Time Optimization

Machine learning has attracted extensive interest in the process engineering field, due to the capability of modeling complex nonlinear process behavior. This work presents a method for combining neural network models with first-principles models in real-time optimization (RTO) and model predictive control (MPC) and demonstrates the application to two chemical process examples. First, the proposed methodology that integrates a neural network model and a first-principles model in the optimization problems of RTO and MPC is discussed. Then, two chemical process examples are presented. In the first example, a continuous stirred tank reactor (CSTR) with a reversible exothermic reaction is studied. A feed-forward neural network model is used to approximate the nonlinear reaction rate and is combined with a first-principles model in RTO and MPC. An RTO is designed to find the optimal reactor operating condition balancing energy cost and reactant conversion, and an MPC is designed to drive the process to the optimal operating condition. A variation in energy price is introduced to demonstrate that the developed RTO scheme is able to minimize operation cost and yields a closed-loop performance that is very close to the one attained by RTO/MPC using the first-principles model. In the second example, a distillation column is used to demonstrate an industrial application of the use of machine learning to model nonlinearities in RTO. A feed-forward neural network is first built to obtain the phase equilibrium properties and then combined with a first-principles model in RTO, which is designed to maximize the operation profit and calculate optimal set-points for the controllers. A variation in feed concentration is introduced to demonstrate that the developed RTO scheme can increase operation profit for all considered conditions.

Download Full-text

Intelligent Real-Time Predictive Diagnostics for Cutting Tools and Supervisory Control of Machining Operations

Journal of Engineering for Industry ◽

10.1115/1.2901660 ◽

1993 ◽

Vol 115 (3) ◽

pp. 268-277 ◽

Cited By ~ 10

Author(s):

K. Ramamurthi ◽

C. L. Hough

Keyword(s):

Real Time ◽

Metal Cutting ◽

Failure Modes ◽

Cutting Tools ◽

Diagnostic System ◽

Training Time ◽

Process Diagnosis ◽

Modes Of Failure ◽

On Line ◽

Cutting Processes

Machining economics may be improved by automating the replacement of cutting tools. In-process diagnosis of the cutting tool using multiple sensors is essential for such automation. In this study, an intelligent real-time diagnostic system is developed and applied towards that objective. A generalized Machining Influence Diagram (MID) is formulated for modeling different modes of failure in conventional metal cutting processes. A faster algorithm for this model is developed to solve the diagnostic problem in real-time applications. A formal methodology is outlined to tune the knowledge base during training with a reduction in training time. Finally, the system is implemented on a drilling machine and evaluated on-line. The on-line response is well within the desired response time of actual production lines. The instance and the accuracy of diagnosis are quite promising. In cases where drill wear is not diagnosed in a timely manner, the system predicts wear induced failure and vice versa. By diagnosing at least one of the two failure modes, the system is able to prevent any abrupt failure of the drill during machining.

Download Full-text