ANALYSIS & STUDY OF AI TECHNIQUES FORAUTOMATIC CONDITION MONITORING OFRAILWAY TRACK INFRASTRUCTURE : Artificial Intelligence Techniques

Since the last decade the problem of surface inspection has been receiving great attention from the scientific community, the quality control and the maintenance of products are key points in several industrial applications.The railway associations spent much money to check the railway infrastructure. The railway infrastructure is a particular field in which the periodical surface inspection can help the operator to prevent critical situations. The maintenance and monitoring of this infrastructure is an important aspect for railway association.That is why the surface inspection of railway also makes importance to the railroad authority to investigate track components, identify problems and finding out the way that how to solve these problems. In railway industry, usually the problems find in railway sleepers, overhead, fastener, rail head, switching and crossing and in ballast section as well. In this thesis work, I have reviewed some research papers based on AI techniques together with NDT techniques which are able to collect data from the test object without making any damage. The research works which I have reviewed and demonstrated that by adopting the AI based system, it is almost possible to solve all the problems and this system is very much reliable and efficient for diagnose problems of this transportation domain. I have reviewed solutions provided by different companies based on AI techniques, their products and reviewed some white papers provided by some of those companies. AI based techniques likemachine vision, stereo vision, laser based techniques and neural network are used in most cases to solve the problems which are performed by the railway engineers.The problems in railway handled by the AI based techniques performed by NDT approach which is a very broad, interdisciplinary field that plays a critical role in assuring that structural components and systems perform their function in a reliable and cost effective fashion. The NDT approach ensures the uniformity, quality and serviceability of materials without causing any damage of that materials is being tested. This testing methods use some way to test product like, Visual and Optical testing, Radiography, Magnetic particle testing, Ultrasonic testing, Penetrate testing, electro mechanic testing and acoustic emission testing etc. The inspection procedure has done periodically because of better maintenance. This inspection procedure done by the railway engineers manually with the aid of AI based techniques.The main idea of thesis work is to demonstrate how the problems can be reduced of thistransportation area based on the works done by different researchers and companies. And I have also provided some ideas and comments according to those works and trying to provide some proposal to use better inspection method where it is needed.The scope of this thesis work is automatic interpretation of data from NDT, with the goal of detecting flaws accurately and efficiently. AI techniques such as neural networks, machine vision, knowledge-based systems and fuzzy logic were applied to a wide spectrum of problems in this area. Another scope is to provide an insight into possible research methods concerning railway sleeper, fastener, ballast and overhead inspection by automatic interpretation of data.In this thesis work, I have discussed about problems which are arise in railway sleepers,fastener, and overhead and ballasted track. For this reason I have reviewed some research papers related with these areas and demonstrated how their systems works and the results of those systems. After all the demonstrations were taking place of the advantages of using AI techniques in contrast with those manual systems exist previously.This work aims to summarize the findings of a large number of research papers deploying artificial intelligence (AI) techniques for the automatic interpretation of data from nondestructive testing (NDT). Problems in rail transport domain are mainly discussed in this work. The overall work of this paper goes to the inspection of railway sleepers, fastener, ballast and overhead.

DC Motor Speed Control via Fuzzy / Pole Placement / PI Controller

This report presents a new way of control engineering. Dc motor speed controlled by three controllers PID, pole placement and Fuzzy controller and discusses the advantages and disadvantages of each controller for different conditions under loaded and unloaded scenarios using software Matlab. The brushless series wound Dc motor is very popular in industrial application and control systems because of the high torque density, high efficiency and small size. First suitable equations are developed for DC motor. PID controller is developed and tuned in order to get faster step response. The simulation results of PID controller provide very good results and the controller is further tuned in order to decrease its overshoot error which is common in PID controllers. Further it is purposed that in industrial environment these controllers are better than others controllers as PID controllers are easy to tuned and cheap. Pole placement controller is the best example of control engineering. An addition of integrator reduced the noise disturbances in pole placement controller and this makes it a good choice for industrial applications. The fuzzy controller is introduce with a DC chopper to make the DC motor speed control smooth and almost no steady state error is observed. Another advantage is achieved in fuzzy controller that the simulations of three different controllers are compared and concluded from the results that Fuzzy controller outperforms to PID controller in terms of steady state error and smooth step response. While Pole placement controller have no comparison in terms of controls because designer can change the step response according to nature of control systems, so this controller provide wide range of control over a system. Poles location change the step response in a sense that if poles are near to origin then step response of motor is fast. Finally a GUI of these three controllers are developed which allow the user to select any controller and change its parameters according to the situation.

Case studies for contract-based systems

Of the ways in which agent behaviour can be regulated in a multiagent system, electronic contracting – based on explicit representation of different parties' responsibilities, and the agreement of all parties to them – has significant potential for modern industrial applications. Based on this assumption, the CONTRACT project aims to develop and apply electronic contracting and contract-based monitoring and verification techniques in real world applications. This paper presents results from the initial phase of the project, which focused on requirements solicitation and analysis. Specifically, we survey four use cases from diverse industrial applications, examine how they can benefit from an agent-based electronic contracting infrastructure and outline the technical requirements that would be placed on such an infrastructure. We present the designed CONTRACT architecture and describe how it may fulfil these requirements. In addition to motivating our work on the contract-based infrastructure, the paper aims to provide a much needed community resource in terms of use case themselves and to provide a clear commercial context for the development of work on contract-based system.

Determination of lower-bound ductility for AZ31 magnesium alloy by use of the bulge specimens

Despite the high demand for industrial applications of magnesium, the forming technology for wrought magnesium alloys is not fully developed due to the limited ductility and high sensitivity to the processing parameters. The processing window for magnesium alloys could be significantly widened if the lower-bound ductility (LBD) for a range of stresses, temperature, and strain rates was known. LBD is the critical strain at the moment of fracture as a function of stress state and temperature. Measurements of LBD are normally performed by testing in a hyperbaric chamber, which is highly specialized, complex, and rare equipment. In this paper an alternative approach to determine LBD is demonstrated using wrought magnesium alloy AZ31 as an example. A series of compression tests of bulge specimens combined with finite element simulation of the tests were performed. The LBD diagram was then deduced by backward calculation.

Constitutive modelling of drawing and extrusion with cyclic torsion

In the current work, constitutive models are developed to describe the cyclic hardening and softening led by the strain path chaneg.  The contribution of deformation conditions such as drawing and extrusion speed, cyclic rotating angle on the drawing and extrusion force will be investigated.  The development of such constitutive models will provide insight into the optimization of operation conditions to explore the potential of industrial applications.

One-dimensional nanomaterials synthesized using high-energy ball milling and annealing process

One-dimensional (1D) nanomaterials including nanotubes, nanowires and nanorods have many new properties, functionalities and a large range of promising applications. A major challenge for these future industrial applications is the large-quantity production. We report that the ball milling and annealing process has the potential to achieve the mass production. Several examples including C, BN nanotubes and SiC, Zn nanowires are presented to demonstrate such capability. In addition, both size and structure of 1D nanomaterials can be controlled by varying processing conditions. New growth mechanisms involved in the process have been investigated and the high-energy ball milling has an important role in the formation of these 1D nanomaterials.

Heavy tools manipulation by low powered direct-drive five-bar parallel robot

This paper presents a simple and available system for manipulation of heavy tools by low powered manipulator for industrial applications. In the heavy manufacturing industries, sometimes, heavy tools are employed for different types of work. But the application of robots with heavy tools is not possible due to the limited torque limits of actuators. Suspended tool systems (STS) have been proposed to manipulate heavy tools by low powered robot-arm for this purpose. A low powered five-bar direct-drive parallel manipulator is designed and constructed to manipulate heavy tools suspended from a spring balancer. The validity, usefulness, and effectiveness of the suspended tool system are shown by experimental results.

Application of the Hottel-Whillier equations to the analysis of a building integrated photovoltaic/thermal solar collector

The idea of combining photovoltaic and solar thermal collectors (PVT collectors) to provide electrical and heat energy is not new, however it is an area that has received only limited attention. With concern growing over energy sources and their usage, PVTs have become an area receiving more attention. Although PVTs are not as prevalent as solar thermal systems, the integration of photovoltaic and solar thermal collectors into the walls or roofing structure of a building could provide greater opportunity for the use of renewable solar energy technologies in domestic, commercial and industrial applications. As such, the design of a novel building integrated photovoltaic/thermal (BIPVT) solar collector is theoretically analysed through the use of a modified Hottel-Whillier model. The thermal and electrical efficiency under a range of conditions are subsequently determined and results showing how key design parameters influence the performance of the BIPVT system are presented.

Deep drawing behaviour of ultrafine grained copper : modelling and experiment

Ultrafine grained materials produced by severe plastic deformation methods possess attractive mechanical properties such as high strength compared with traditional coarse grained counterparts and reasonable ductility. Between existing severe plastic deformation methods the Equal Channel Angular Pressing is the most promising for future industrial applications and can produce a variety of ultrafine grained microstructures in materials depending on route, temperature and number of passes during processing. Driven by a rising trend of miniaturisation of parts these materials are promising candidates for microforming processes. Considering that bi-axial deformation of sheet (foil) is the major operation in microforming, the investigation of the influence of the number of ECAP passes on the bi-axial ductility in micro deep drawing test has been examined by experiments and FE simulation in this study. The experiments have showed that high force was required for drawing of the samples processed by ECAP compare to coarse grained materials. The limit drawing ratio of ultrafine grained samples was in the range of 1.9–2.0 with ECAP pass number changing from 1 to 16, while a higher value of 2.2 was obtained for coarse grained copper. However, the notable decrease in tensile ductility with increase in strength was not as pronounced for bi-axial ductility. The FE simulation using standard isotropic hardening model and von Mises yielding criterion confirmed these findings.

Stabilisation of brown coal fly ash using geopolymers

This research explores geopolymer technology as a means of stabilising fly ash from power stations. By controlling the synthesis process, geopolymeric materials incorporating fly ash were synthesised. Successful stabilisation of strontium and barium was achieved, though attributed to side reactions. The geopolymer did not contribute significantly to stabilisation of fly ash.

Investigation into and control of microwave induced thermal run-away

Analyses the mechanisms that cause thermal run-away in some materials. A control strategy was devised to provide effective temperature control independent of material characteristics. The set of control criteria derived from mathematical models allowed the control limits of a microwave processing system to calculated.

Processing of fine-grained aluminum foam by spark plasma sintering

Porous materials are now becoming attractive to researchers interested in both scientific and industrial applications due to their unique combinations of physical, mechanical, thermal, electrical and acoustic properties in conjunction with excellent energy absorption characteristics. Metallic foams allow efficient conversion of impact energy into deformation work, which has led to increasing applications in energy absorption devices. In particular, foams made of aluminum and its alloys are of special interest because they can be used as lightweight panels, for energy absorption in crash situations and sound or heat absorbing functions in the automotive industry with the aim to reduce weight to improve crashworthiness, safety and comfort.

Innovations in knowledge processing and decision making in agent-based systems

This chapter introduces knowledge processing and decision making using agent-based technologies. The importance of creating effective and efficient computerized systems for extracting information and processing knowledge as well as for supporting decision making activities is highlighted. Then, an overview covering agent-based software tools and development methodologies, and usability and challenges of agent-based systems in industrial applications is presented. The contribution of each chapter included in this book is also described.

Composite yarns fabricated from continuous needleless electrospun nanofibers

In this work, a spinning metal wire collector was employed to continuously collect polyacrylonitrile (PAN) nanofibers produced by a disc fiber generator and coil them around a polyethylene terephthalate (PET) yarn. The obtained composite yarns exhibited a core/shell structure (PET yarn/PAN nanofibers) with nanofibers orderly arranged on the surface of the PET yarn. The electric field analysis showed that the position of metal wire had insignificant effect on the formed electric field and high intensity electric field was formed at the disc circumferential area, which provided a constant electric field for the production of uniform nanofibers. The spinning solution, spinning speed of metal wire, and winding speed were found to play an important role in producing good quality nanofiber yarns, in terms of morphology, strength, and productivity. Pure nanofiber yarns were obtained after dissolving the core yarns in a proper solvent. This method has shown potential for the mass production of nanofiber yarns for industrial applications.