Refine Your Search




Search Results

Technical Paper

Gear Noise Diagnosis System For Automobile Transmission Using Artificial Intelligence (Convergence of Training Process)

The present study deals with a new gear noise diagnosis system for automobile transmission units with an artificial intelligence; i.e., the neural net. In order to use this system, first of all, the system must be trained with teacher signals. This training process includes iterative calculations, so that the convergence in the training process is a very important issue. In the present paper, conditions were determined for the convergence. Then, the judgement performance of the developed system was discussed. As a result, the system can realize over 70% performance of noise evaluation experts.
Technical Paper

Hierarchical Human-in-the loop Control Systems: An Application for Tactile Interfaces and Adjustable Autonomy.

The last few years have witnessed major changes both in the traditional view of artificial intelligence (AI) and in how humans interact with machines. An increasing number of researchers have been shifting their efforts towards human-centered computing, to create smarter systems and interfaces to support and leverage human capabilities. This paper introduces a research effort to develop an intelligent control system with adjustable autonomy to augment human activities on complex, high workload environments. This system is based on a multi-modular, hierarchical, variable structure control system, integrated with conventional and novel tactile displays to assist and monitor the complex plant composed by human and machine.
Technical Paper

Noise analysis and modeling with neural networks and genetic algorithms

The aim of the project is to reliably identify the set of constructive features responsible for the highest noise levels in the interior of motor vehicles. A simulation environment based on artificial intelligence techniques such as neural networks and genetic algorithms has been implemented. We used a system identification approach in order to approximate the functional relationship between the target noise series and the sets of constructive parameters corresponding to the cars. The noise levels were measured with a microphone positioned on the driver''s chair, and corresponded to a variation of the engine rotation of 600-900 rot/min. The database includes 45 different cars, each described by vectors of 67 constructive features.
Technical Paper

Artificial intelligence approach in designing of car brakes

Computer-aided technology of car brakes tribological designing is presented. It is founded on DataBases (DB), Expert Systems (ES) created by heuristic logical programming methods using an artificial intelligence approach. There are also Hybrid Expert Systems (HES) which have "pure" Expert System parts and calculation modules (developed by traditional methods of software creating). The DB include detailed information regarding materials, prototypes of the car brakes, experimental results together with description of the test conditions. The basis of the ES is a Knowledge Base (KB). The knowledge is presented as a system of rules (if...then). The ES are teachable. They can build logical chains allowing checking hypothesis by comparison of proposed fact with the rules. The logical conclusions can be explained in details automatically. First, filling of the KB and DB is done, then the added information is confronted with the KB rules and compared with numerical information from DB.
Technical Paper

Adaptive, real-time traffic control management

This paper presents an architecture for distributed control systems and its underlying methodological framework. Ideas and concepts of distributed systems, artificial intelligence, and soft computing are merged into a unique architecture to provide cooperation, flexibility, and adaptability required by knowledge processing in intelligent control systems. The distinguished features of the architecture include a local problem solving capability to handle the specific requirements of each part of the system, an evolutionary case-based mechanism to improve performance and optimize controls, the use of linguistic variables as means for information aggregation, and fuzzy set theory to provide local control. A distributed traffic control system application is discussed to provide the details of the architecture, and to emphasize its usefulness. The performance of the distributed control system is compared with conventional control approaches under a variety of traffic situations.
Technical Paper

Design of Reflector Optics with Smooth Surface for Automotive Lamps

ACRs (All Clear Reflectors), also widely referred to as FFRs (Free Form Reflectors), were designed in general and intelligent ways using a NURBS surface for the mathematical modeling of the reflector shape and artificial intelligence as the optimum design algorithm. An ACR, which consists of a continuous surface reflector and clear outer lens, offers styling advantages and provides a high quality light performance. The clear outer lens of an ACR remains efficient even with a highly inclined shape, as in the design of a sports car, plus the complete clearness of the reflector surface eliminates the nuisance of stray light caused by the steps between individual segments of multi-faced reflectors. The design technique of an ACR was also successfully applied and tested with all types of lamps, including low beams, high beams, fog lamps, and turn signal lamps.
Technical Paper

Integrated Approach to the Selection of Cost-Effective and Lean Process and Equipment in Forming

A significant number of formed parts constitute the components of an automobile or aircraft. The formed blanks for the components are produced at different temperatures ranging from room temperature to 2250 degrees Fahrenheit for steel. Forming progressions convert a basic shape or geometry (a cylindrical billet, for example) of metal into a more complex shape close to the required final component geometry. The progression steps, choice of temperatures and equipment significantly impact the cost of the blank. A ‘Discriminating Cost Model’ was developed to capture the cost effectiveness of a given choice of process or equipment, and an AI (Artificial Intelligence) search algorithm implemented to quickly search through the large number of process and equipment selection options to arrive at the most cost effective choice. Two applications of this methodology to existing plant processes to significantly reduce cost and implement ‘lean’ principles of manufacturing are discussed.
Technical Paper

Revisiting Thermodynamic Analysis and Design of Power Cycles with an Intelligent Instruction Software

Thermodynamic design and analyses have been carried out on a multiple extraction regenerative Rankine cycle employing a recent software called CyclePad. A synergistic combination of qualitative physics and artificial intelligence techniques have been used to develop Cycle-Pad to assist in teaching, design and research in applied thermodynamics and advanced energy conversion systems. It provides an articulate virtual laboratory, in terms of visualisation of the schematic combination of a variety of thermodynamic cycles. A thorough sensitivity analysis has been carried out to help optimise the regenerative Rankine cycle in terms of thermal efficiency as a function of the extraction pressures and the splitting fractions. Numerical results and trend plots are provided. Such studies demonstrate that analyses of complex cycles can now be carried out, as part of classroom instruction as well, employing such a tool.
Technical Paper


The sources of data on materials used in the automotive industry are reviewed and their shortcomings discussed including limited availability, obsolescence, limited coverage of materials, limited information on materials covered, and lack of information on the variability of properties. The way that data from presently available “hard copy” data sources are presently used in automotive design is outlined. Several of the small number of currently available computerized materials data bases are briefly described. Finally, anticipated benefits from the use of greatly expanded computerized systems are enumerated. These include the use of “artificial intelligence” for the selection of materials, making very extensive information on many materials available to all designers on the screens of their terminals, allowing instantaneous dissemination of warnings of materials problems, and serving as a repository of engineering know-how for transfer from one generation of engineers to the next.
Technical Paper

Towards Autonomous Cruising on Highways

Owing to the remarkable progress of artificial intelligence technologies, automobile engineers may be able to produce an exciting innovation for the automobile: that is “vehicle autonomy.” It is no longer a dream to build a car which can perceive the outside world and run by itself. A modern automobile goes out of control without proper operations by a human driver. An autonomous vehicle, on the other hand, is a car which is capable of navigating roads and avoiding dangers even without human operation. However, the purpose of vehicle autonomy is not the mere replacement of human labor by machines, but the creation of a new value for the automobile. The objectives of this paper are to discuss how vehicle autonomy technology can be used to benefit car drivers and also to propose a concept of an autonomous highway vehicle which improves highway driving safety.
Technical Paper

A Neural Network for Fault Recognition

In both the marine and power industries there are now a choice of off-the-shelf condition monitoring systems available that utilise artificial intelligence techniques to analyse engine performance data. These systems are proving to be a valuable aid in optimising performance and reducing down-time by assisting with maintenance planning. These systems rely on careful monitoring of an engine's performance, for instance engine speed, fuelling, boost pressure, turbine inlet pressure, turbocharger speed, and exhaust temperature. With this data, they utilise a variety of interpolation and pattern recognition algorithms to compare it with previously recorded data stored in lookup tables. This paper describes how a neural network approach can be used as a cheap alternative for the analysis of this data, greatly reducing the need for such large lookup tables and complex pattern recognition programs.
Technical Paper

Some of the issues in the Implementation of Artificial Intelligence in Engineering Design

The Designer Model, a model based on the design methodology of a human designer, is examined to identify in detail the role of the Systems Design View Point (SDVP) in the solution of a design problem. The SDVP reflects complexity of a multidomain design problem due to coupling of domains, and introduces iteration or the element of search in solving the design problem. It is, thus, possible to use an appropriate performance index to direct the search techniques which are available in Artificial Intelligence in implementing the design solution.
Technical Paper

Expert Systems: Misconceptions and Reality

In just one decade the field of expert systems, a subfield of artificial intelligence, has progressed from an intellectual endeavor pursued by researchers at universities to commercial systems used by major corporations. Expert systems have been developed by Digital Equipment Corporation to configure VAX computers (XCON). SRI International to perform geological exploration (PROSPECTOR), the U.S. Navy to train personnel in the operation of steam propulsion plants (STEAMER), and Intellicorp to help molecular biologists perform nucleotide sequence analysis (SEQ), just to name a few. The hopes and dreams of everyone have been raised by the performance of these and other systems and by the future potential of what expert systems could do. But are these aspirations to be realized? Will expert systems prove to be “white knights” assisting us In solving our problems or will they be “wolves in sheep's clothing” tormenting us as we strive towards our goal?
Technical Paper

Embedding Artificial Intelligence in Existing Applications

Artifical intelligence concepts and features-are becoming popular in many application fields. This paper describes a system of programming modules that can be embedded in conventional applications programs.
Technical Paper

Integrating Design and Manufacturing By Combining Artificial Intelligence and Database Approach

Integration of design and manufacturing rely on a bidirectional information process of converting knowledge to data and data to knowledge in the frame work of the information hierarchy. This paper describes the first four levels of this hierarchy and argues that approaches from artificial intelligence and data base technology needs to be combined to complete this hierarchy.
Technical Paper

Knowledge Representation for Expert Systems: A Survey and Evaluation of Techniques

Knowledge representation plays a key role in the development of any Artificial Intelligence based system. A good representation can significantly shorten development time and execution speed, while a poor representation can doom a project. Four representation techniques are commonly used to model knowledge in expert systems: logic, production rules, semantic networks, and frames. This paper describes the application of each of these techniques in modelling mechanical systems. Advantages and disadvantages for each of these techniques are presented.
Technical Paper

New System Of Automotive Engineering For The 21st Century

The demands on automotive engineering, worldwide, are increasing rapidly; the tools for it have become far different from and more powerful than those available in the past. Combined, those forces portend a discontinuity in the nature of automotive engineering. The new automotive engineering systems will combine computerized information bases, different and better organized bodies of organized engineering information and experience and the techniques and information structures of expert systems and artificial intelligence. But they must and will capture, maintain, and highlight sound fundamental engineering principles and know-how and allow for creativity, initiative and judgments. They will expand capabilities and enhance the proficiency and cost effectiveness of automotive engineering.
Technical Paper

Artificial Intelligence applied to Diagnostics

Research into the use of AI to enhance the detection of faults and the diagnosis of multiple failure conditions on U.S. Army tactical vehicles is reported. The approach uses existing troubleshooting knowledge (in the form of programmed automated test logic) as the basis for an expert system. A deep model of vehicle systems is incorporated in the diagnostic machine. A pilot model will be implemented on a presently fielded portable microprocessor test system, the Simplified Test Equipment (STE), to demonstrate that the technique is both practical and that it can be realized on a small field portable test set.
Technical Paper

Using Artificial Intelligence in Vehicle Diagnostic Systems

Expert systems are becoming increasingly important in the application of artificial intelligence technology to real-world problems. An expert system is defined as a computer program which models the decision making process of an expert. This paper explores the concept using expert systems as external diagnostic aids in the repair of motor vehicles. The applicability of expert systems to vehicle diagnosis is first described. The paper then discusses general principles to be considered when building expert systems for vehicle diagnosis. The concept of using expert systems for repairing electronically controlled engine systems is explored in greater detail, and a discussion is provided on a prototype expert system to perform this type of diagnosis. Recommendations are provided on what would be required to develop a commercial expert system based upon the prototype expert system discussed in this paper.