Intelligent Manufacturing Systems Research Papers (original) (raw)

Top Papers
Most Cited Papers
Most Downloaded Papers
Newest Papers
People
- by
- •
- Materials Engineering, Mechanical Engineering, Relational Database, Intelligence

The aim of this paper is to help the blind people to identify and catch the public transport vehicles with the help of Light Fidelity technology. It is a Navigation aid. When the bus arrives at the bus stand, transmitter in the bus transmits the light signals and receiver in the stick, receives the light signals and a sound signal is generated through the speaker present in the stick. The sound message contains the bus number and the destination of the bus. In addition to this, if the person is absconded or lost, details of the location will be sent to his/her family members by pressing a button. This is made possible with the help of Global System for Mobile (GSM). Finally, presence of water can be detected along the blind person's path, with the help of water sensors.

The fourth industrial revolution is rapidly changing the manufacturing landscape. Due to the growing research and fast evolution in this field, no clear definitions of these concepts yet exist. This work provides a clear description of technological trends and gaps. We introduce a novel method to create a map of Industry 4.0 technologies, using natural language processing to extract technology terms from 14,667 research articles and applying network analysis. We identified eight clusters of Industry 4.0 technologies, which served as the basis for our analysis. Our results show that Industrial Internet of Things (IIoT) technologies have become the center of the Industry 4.0 technology map. This is in line with the initial definitions of Industry 4.0, which centered on IIoT. Given the recent growth in the importance of artificial intelligence (AI), we suggest accounting for AI's fundamental role in Industry 4.0 and understanding the fourth industrial revolution as an AI-powered natural collaboration between humans and machines. This article introduces a novel approach for literature reviews, and the results highlight trends and research gaps to guide future work and help these actors reap the benefits of digital transformations.

- by Benjamin Meindl and +1
- •
- Artificial Intelligence, Natural Language Processing, Intelligent Manufacturing Systems, Advanced Manufacturing

The ability to gather manufacturing data from various workstations has been explored for several decades and the advances in sensory and data acquisition techniques have led to the increasing availability of high-dimensional data. This paper presents an intelligent metrology informatics system to extract useful information from Multistage Manufacturing Process (MMP) data and predict part quality characteristics such as true position and circularity using neural networks. The input data include the tempering temperature, material conditions, force and vibration while the output data include comparative coordinate measurements. The effectiveness of the proposed method is demonstrated using experimental data from a MMP.

- by Nathan Proudlove and +1
- •
- Algorithms, Artificial Intelligence, Manufacturing, Intelligent Manufacturing Systems

New researches in Artificial intelligence have given wide powers for many areas, which based on the fact that the performance of machine is better than humans. Widely, one of the most significant areas in Artificial Intelligence is education and learning. Occasionally the traditional teaching methods do not achieve the required goals from learning. Some teaching progra comparing to traditional class room. appropriate learning procedures are children with learning disabilities. Parents always capability to understand new subjects and to develop expertise. Early interference is very important to help children in their early stages for enhance their learning capacity. on black board system to assists the children sufferer from learning disabilities during the early levels of school. The proposed system targets the child with typical intellectual quotient (IQ). During the implementation of the system the child will go through two types of tests and experiments, which will determine the level of (IQ) and evaluate the diagnosis purposes (developmental disabilities). The rules of the inference engine are generated based on the knowledge engineering resulted from the test. Education are one of most requirements needed for children, Which mean keep the student interest and motivated for learn. Diagnosing various learning disabilities is costly process and can be highly delayed disabilities meanwhile they need to accomplish teach mission using variety of education materials. Diagnosing various LD depend exclusively on our understanding of scientific r communication with the Infected People. in various learning systems. Numerous researches demonstrate that kids are more concerned in computer games. Thus, serious games are

- by I. Jawahir and +1
- •
- Materials Engineering, Mechanical Engineering, Intelligent Manufacturing Systems, Materials
- by Paul Valckenaers
- •
- Mechanical Engineering, Applied Mathematics, Control Engineering, Agent Based
- by Mark Robinson
- •
- Organizational Behavior, Engineering, Materials Engineering, Mechanical Engineering
- by Nathan Proudlove and +1
- •
- Algorithms, Artificial Intelligence, Manufacturing, Intelligent Manufacturing Systems

Sensor-based multi-robot coverage path planning problem is one of the challenging problems in managing flexible, computer-integrated, intelligent manufacturing systems. A novel pattern-based genetic algorithm is proposed for this problem. The area subject to coverage is modeled with disks representing the range of sensing devices. Then the problem is defined as finding a sequence of the disks for each robot to minimize the coverage completion time determined by the maximum time traveled by a robot in a mobile robot group. So the environment needs to be partitioned among robots considering their travel times. Robot turns cause the robot to slow down, turn and accelerate inevitably. Therefore, the actual travel time of a mobile robot is calculated based on the traveled distance and the number of turns. The algorithm is designed to handle routing and partitioning concurrently. Experiments are conducted using P3-DX mobile robots in the laboratory and simulation environment to validate the results.

- by Petr Kadera
- •
- Engineering, Decision Making, Intelligent Manufacturing Systems, Control Systems
- by Paul Valckenaers and +2
- •
- Engineering, Intelligent Manufacturing Systems, Control system, Holonic Manufacturing Systems

There is an increasing demand for manufacturing processes to improve product quality and production rates while minimising the costs. The quality of the products is influenced by several sources of errors introduced during the series of manufacturing operations. These errors accumulate over these multiple stages of manufacturing. Therefore, monitoring systems for product health utilising data and information from different sources and manufacturing stages is a key factor to meet these growing demands. This paper addresses the process of combining new measurement data or information with machine learning-based prediction information obtained as each product goes through a series of manufacturing steps to update the conditional probability distribution of the end product quality during manufacturing. A Bayesian approach is adopted in obtaining an updated posterior distribution of the end product quality given new information from subsequent measurements, and, in particular, On-Machine Probing (OMP). Following the steps of heat treatment, machining, and OMP, the posterior distribution of the previous step can be considered as the new prior distribution to obtain an updated posterior distribution of the product condition as new metrological information becomes available. It is demonstrated that the resulting posterior estimates can lead to more efficient product condition monitoring in multistage manufacturing.

In distributed manufacturing systems, the level of interoperability of hardware and software components depends on the quality and flexibility of their information models. Syntactic descriptions of input and output parameters, e.g., using interface description languages (IDL), are not suffcient when it comes to evaluating whether a manufacturing resource provides the capabilities that are required for performing a particular process step on a product. The semantics of capabilities needs to be explicitly modelled and must be provided together with manufacturing resources. In this paper, we introduce concepts developed by the German BaSys 4.0 initiative dealing with semantically describing manufacturing skills, orchestrating higher-level skills from basic skills, and using them in a cognitive manufacturing framework.

— Credit scoring is an important tool in financial institutions, which can be used in credit granting decision. Credit applications are marked by credit scoring models and those with high marks will be treated as " good " , while those with low marks will be regarded as " bad ". As data mining technique develops, automatic credit scoring systems are warmly welcomed for their high efficiency and objective judgments. Many machine learning algorithms have been applied in training credit scoring models, and ANN is one of them with good performance. This paper presents a higher accuracy credit scoring model based on MLP neural networks trained with back propagation algorithm. Our work focuses on enhancing credit scoring models in three aspects: optimize data distribution in datasets using a new method called Average Random Choosing; compare effects of training-validation-test instances numbers; and find the most suitable number of hidden units. Another contribution of this paper is summarizing the tendency of scoring accuracy of models when the number of hidden units increases. The experiment results show that our methods can achieve high credit scoring accuracy with imbalanced datasets. Thus, credit granting decision can be made by data mining methods using MLP neural networks.

The purpose of this work is to study the use of controlled magnetic oscillation of the electric arc according to complex geometric patterns applied to the GMAW process for root pass welding. These patterns were represented here by what is known as Figures of Lissajous. These one are parametric curves mathematically produced that can offer versatility for the creation of wetting movements similar to those practiced by experienced welders. These curves are basically produced by applying and controlling sine equations for the orthogonal axes "X" and "Y". An electrical voltage generator/controller system was developed for this work and its software combines and controls the variables, frequency (Hz), amplitude (V), phase (rad) and offset (%) of the sine equation of each axis. This system was built to feed two pairs of electromagnets magnetic field generators, each pair corresponding to its respective axis. The electromagnets, in turn, receive from the system the appropriate electrical voltage to produce magnetic fields with specific magnetic density (mT) values. Once the electromagnets are positioned on their respective orthogonal axes with reference to the vertical center line of the electric arc, it becomes possible to make weave movements through the magnetic flux that was generated and directed to the arc. With this equipment, the welding was performed in order to deflect the electric arc following the forms of Figures of Lissajous.
With this resource/equipment in the process, in addition to promoting controlled deflection of the electric arc (difficult to be achieved manually or mechanically), it was possible to deposit addition metal in specific locations, modify the characteristics of the thermal, distribution located in the welding region, contribute to the formation of a fusion pool less concentrated in the weld region and produce beads with potential to overcome obstacles such as misalignments and uneven clearances typical of the stage known as root pass.
Prior to the groove joints welding using the pulsed GMAW process, the magnetic oscillator system that was built was put to the test in a sequence of initial trials performed with the autogenous GTAW and GMAW processes with short circuit transfer. Imposing weave movements to the arc following two different Lissajous Figure in the autogenous GTAW welds was clearly evidenced transverse and longitudinal movements of the molten pool as a visual and dimensional characteristics of the beads that were produced. In short-circuited GMAW welds such movement was not clearly visualized. However, through thermographic records obtained on the opposite side of weld beads made on plate, it was possible to record thermal differences with higher or lower heat concentration between beads produced without and with weaving patterns. This fact suggests that the magnetic oscillation imposed on the process interfered in the thermal distribution of the weld.
The welds in the GMAW process pulsed in groove joints parts were produced by applying weave following four different Lissajous Figures. The results were analyzed according to dimensional characteristics of the respective beads and electrical signals recorded in oscillograms. These results showed that the application of the controlled magnetic oscillation imposed to the arc was able to produce root pass welds in flat positioned groove joints parts and these with an average clearance of the 3.7 mm between their faces, and without the application of the oscillation the average root opening was 2.4 mm.
Additionally, this Thesis established a basic concept called "Rate of variation of electrical voltage" which proved to be a consequence of the magnetic field applied in the arc.

Manufacturing processes usually consist of multiple different stages, each of which is influenced by a multitude of factors. Therefore, variations in product quality at a certain stage are contributed to by the errors generated at the current, as well as preceding, stages. The high cost of each production stage in the manufacture of high-quality products has stimulated a drive towards decreasing the volume of non-added value processes such as inspection. This paper presents a new method for what the authors have referred to as ‘inspection by exception’ – the principle of actively detecting and then inspecting only the parts that cannot be categorized as healthy or unhealthy with a high degree of certainty. The key idea is that by inspecting only those parts that are in the corridor of uncertainty, the volume of inspections are considerably reduced. This possibility is explored using multistage manufacturing data and both unsupervised and supervised learning algorithms. A case study is presented whereby material conditions and time domain features for force, vibration and tempering temperature are used as input data. Fuzzy C-Means (FCM) clustering is implemented to achieve inspection by exception in an unsupervised manner based on the normalized Euclidean distances between the principal components and cluster centres. Also, deviation vectors for product health are obtained using a comparator system to train neural networks for supervised learning-based inspection by exception. It is shown that the volume of inspections can be reduced by as much as 82% and 93% using the unsupervised and supervised learning approaches, respectively.

Understanding the variations in surface finish due to machining is a non-trivial task and cannot be very easily estimated even for a given set of machining parameters and operating conditions due to the complexity of interactions involved. In this work, an attempt has been made to propose an automated intelligent manufacturing system for the estimation and control of surface finish

This white paper will outline a path to production-ready, decision-making AI by drawing on key concepts from the history of AI and combining them with automation technology in pursuit of useful AI. We assert that useful AI provides the next evolution in industrial control, automation, and optimization and that teaching is the primary mechanism for enabling useful AI.

CIM, simultaneous scheduling and schedule execution. Abstract : This paper presents an architecture for reactive scheduling that enables concurrent scheduling and schedule execution. When disturbances occur, the system reacts to them at several levels: an on-line shop floor control system reacts immediately, and the reactive scheduler responds more slowly, but with a higher response time. This approach enables a good

- by Paul Valckenaers and +1
- •
- Intelligent Manufacturing Systems, Operations Strategy, Holonic Manufacturing Systems, Petri Net

The fourth industrial revolution is rapidly changing the manufacturing landscape. Due to the growing research and fast evolution in this field, no clear definitions of these concepts yet exist. This work provides a clear description of technological trends and gaps. We introduce a novel method to create a map of Industry 4.0 technologies, using natural language processing to extract technology terms from 14,667 research articles and applying network analysis. We identified eight clusters of Industry 4.0 technologies, which served as the basis for our analysis. Our results show that Industrial Internet of Things (IIoT) technologies have become the center of the Industry 4.0 technology map. This is in line with the initial definitions of Industry 4.0, which centered on IIoT. Given the recent growth in the importance of artificial intelligence (AI), we suggest accounting for AI’s fundamental role in Industry 4.0 and understanding the fourth industrial revolution as an AI-powered natura...

High temperature deformation behavior of Al–5.9%Cu–0.5%Mg alloy and Al–5.9%Cu–0.5%Mg alloy containing 0.06 wt.% Sn was studied by hot compression tests conducted at different temperatures and strain rates. Trace content of Sn resulted in a significant increase of flow stress for various processing conditions. Artificial neural network (ANN) modeling was applied providing excellent prediction of flow stress at different combinations of strain, strain rate and deformation temperature. While validation, it was possible to predict 100 % and 89 % of the flow stress values of the respective alloys within an error less than ± 10 %. The flow stress data thus generated using the ANN architectures, was used to develop power dissipation efficiency maps, instability maps and subsequently the processing maps, which would delineate the process domains for safe metal working. Optimum hot processing window was suggested for the investigated alloys, providing intelligent processing and manufacturing system of these wrought microalloyed Al alloys, extensively used in aircraft and space applications. The power dissipation efficiency maps revealed a maximum efficiency of 60 % for the alloy without Sn content, while a comparatively lower value of 40 % for the microalloyed material. The instability maps generated for the alloy containing Sn, revealed only one instability regime. The safe regimes for hot working of the base alloy without Sn content were observed at (i) very low strain rate (< 0.003 s-1) with temperature < 450 ºC and (ii) high temperature (> 400 ºC) with strain rate > 0.02 s-1. The safe processing zone of the alloy with trace content of Sn, is at low strain rate (< 0.01 s-1) for the entire range of temperatures studied. Microstructural analysis confirmed that dynamic recovery (DRV) and dynamic recrystallization (DRX) characterized the safe processing regimes of both the alloys. Instability during hot deformation was observed to be driven mainly by shear band formation and/or intercrystalline cracking for the investigated Al alloys. keywords: Aluminum alloy; Microalloying; High temperature deformation behavior; Artificial neural network, Processing map.

- by Subhashish Baruah
- •
- Marketing, Mathematics, Operations Research, Intelligent Manufacturing Systems

Today's complex manufacturing systems operate in a changing environment rife with uncertainty. The performance of manufacturing companies ultimately hinges on their ability to rapidly adapt their production to current internal and external circumstances. On the base of a running national research project on digital enterprises and production networks, the paper illustrates how the concepts of intelligent manufacturing systems and digital

Modern manufacturing is in need of flexible and adaptive concepts for process planning, production control, and scheduling. However, strong borderlines exist in industrial production caused by an extreme specialisation and seperated historical paths of system evolution. Thus, a gap exists between the involved systems, which implies loss of time and information and in consequence a prolonged time-to-market. The application of

Abstract: In this paper a concept of designing and building intelligent decision support systems in production management is introduced. The new approach to the design of intelligent management systems is proposed based on integration of artificial intelligence technologies (fuzzy logic, artificial neural networks, expert systems and genetic algorithms) with exact methods and models of decisions search and simulation techniques. The proposed approach allows for creating intelligent decision support systems of complex, unstructured management problems in fuzzy conditions. The systems learn based on accumulated data and adapt to changes in operation conditions.

Manufacturing informatics aims to optimize productivity by extracting information from numerous data sources and making decisions based on that information about the process and the parts being produced. Manufacturing processes usually include a series of costly operations such as heat treatment, machining, and inspection to produce high-quality parts. However, performing costly operations when the product conformance to specifications cannot be achievable is not desirable. This paper develops a new machine learning-based informatics system capable of predicting the end product quality so that non-value-adding operations such as inspection can be minimized and the process can be stopped before completion when the part being manufactured fails to meet the design specifications.

A system devoted to the planning of motion and assembly operations n robotized assembly cells at abstract level is presented. The goal is to achieve an interactive planning system for assembly tasks. Automatic plan generation techniques are interplayed with external interactive help from the human expert. The interaction is realized through a graphical simulation system. For instance, a collision-free skeleton-trajectory can be specified by the human expert via the simulation system. Proposed architecture for a cell programming system has a multilevel structure in which a task can
be. described at multiple abstraction levels. The problem is analyzed
in a CIM context in which the integration of information and knowledge plays an important role. A detailed description of the planning activity is m,de and experimental results already achieved are described. Finally, current status of work and future plan are presented.