By Topic

Industrial Automation and Control, 1995 (I A & C'95), IEEE/IAS International Conference on (Cat. No.95TH8005)

Date 5-7 Jan. 1995

Filter Results

Displaying Results 1 - 25 of 83
  • Proceedings of IEEE/IAS International Conference on Industrial Automation and Control

    Publication Year: 1995
    Save to Project icon | Request Permissions | PDF file iconPDF (31 KB)  
    Freely Available from IEEE
  • Neural network application for fault diagnosis in FCCU

    Publication Year: 1995 , Page(s): 445 - 450
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (428 KB)  

    In this paper, the application of an ANN to the fault diagnosis of a fluidized catalytic cracking unit (FCCU) is studied. The ANN based system successfully diagnoses the fault it is trained to recognize. It is also able to generalize its knowledge to diagnose fault combinations it is not explicitly trained to recognize. The network can also handle incomplete data. One important development in this paper is the use of object oriented programming techniques for software development. The advantages in using OOPs for such an application is expanded. An analysis of the recall capability to trained faults and the generalization capability to symptoms resulting from novel fault combinations is attempted. The generalization proficiency versus network topology is examined View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Computer aided engineering of distributed control systems

    Publication Year: 1995 , Page(s): 441 - 444
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (272 KB)  

    For a large plant, engineering the distributed control system in the shortest possible time is extremely important. Increasingly, it is being realised that cutting down the project cycle time is the key to success in the international market place. Most companies have therefore developed computer aided tools for control systems engineering rule design. These systems are proprietary in nature. The scope exists for developing tools that are more general and can be configured for a variety of systems. Further, they should be available for low end PC platforms so that even small organisations can readily use them. The authors describe a set of tools that have been developed for designing distributed control systems/PLCs by which the engineering cycle can be reduced considerably. Further, these tools permit rapid design changes with very little extra effort and remove the drudgery of repetitive work, freeing the engineer to focus on essential design problems View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An intelligent controller using a self-learning neural net

    Publication Year: 1995 , Page(s): 235 - 238
    Cited by:  Papers (1)  |  Patents (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (192 KB)  

    This paper describes a self-learning neural controller that learns the behavior of a system or plant and makes decisions to reach the desired state. The components of the controller are a data acquisition system with a knowledge base, a control net and a scheduler. Self-learning of the controller can be in two modes: off-line and on-line. In both modes, the data acquisition system stores the learnt data in the knowledge base in the form of system state vectors. The control net is trained with learnt patterns decided by the scheduler. After training, the control net with the current weight vectors is switched on for operation View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Aspects of fuzzy logic in controller design

    Publication Year: 1995 , Page(s): 83 - 88
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (388 KB)  

    Fuzzy logic is a systematic mathematical formulation for investigating and characterizing the different types of uncertainties. This paper presents the concept of representing uncertainties in membership diagram and forming the fuzzy rules (fuzzification) specifically for the basic design of controller. The fuzzification is carried out with eleven linguistic values. A defuzzification approach developed in this paper is novel and achieves better stability. The defuzzification rule is used to determine the relevant control signal for each sampling instant. Simulation results for the system having one and two poles at the origin are presented to demonstrate the better performance of the fuzzy controller View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Industrial applications of sliding mode control

    Publication Year: 1995 , Page(s): 275 - 280
    Cited by:  Papers (4)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (468 KB)  

    Fundamental principles of variable structure control (VSC) and sliding mode control (SLMC) are presented. Use of VSC/SLMC in industrial applications is surveyed, academic research of VSC/SLMC as used in AC and DC drives is reviewed, and advantages and disadvantages of using SLMC/VSC in practical applications are analyzed View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Monitoring of tool status using intelligent acoustic emission sensing and decision based neural network

    Publication Year: 1995 , Page(s): 25 - 29
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (328 KB)  

    Successful automation of manufacturing processes is must for production of high quality, customized and economical products demanded by todays customers. This calls for uninterrupted machining with desirable process parameters. This can be ensured by continuous monitoring of machining status, which is strongly influenced by the condition of the cutting tool. In this paper, a new scheme is proposed and evaluated for intelligent tool status monitoring. This paper describes the possibility of sensor integration in a machining process through a neural network. Experiments were conducted to study the influence of flank wear on AE and cutting forces. This collected data is then used as training patterns for the neural network. The decision based neural network is used to integrate this information and consequently for deciding on the condition of the tool. The results show that acoustic emission-cutting force based multi-sensory-monitoring methodology classifies tool status correctly View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Simulation study of advanced control strategies for Adept One SCARA robot

    Publication Year: 1995 , Page(s): 229 - 234
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (396 KB)  

    Variable structure control and adaptive control are two advanced control strategies for robot manipulator. However, the advantages and disadvantages of these two control strategies are not clear to engineers new in this field. This paper presents a comparative study of these two strategies on the Adept One SCARA robot. Four situations, namely the ideal situation, the situation where there is payload, the situation where there is joint friction and the situation where there is external disturbance are studied. Simulation studies reveal clearly the advantages and disadvantages of both schemes View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Parallel structured network for solving balanced realization problems

    Publication Year: 1995 , Page(s): 263 - 267
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (216 KB)  

    Given a state space description of a linear system, the balanced realization problem is to find a similarity transformation for the state variables. This transformation must transfer both the system energy matrix and the output energy matrix into diagonal form. In this paper a novel parallel structured network (PSN) is constructed to solve this problem. The three possible forms of realization, which are defined in the literature can be obtained using the PSNs. Furthermore, the fourth one, defined and found here, is new, and has not been mathematically defined in earlier work View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Energy conservation in India - challenges and achievements

    Publication Year: 1995 , Page(s): 365 - 372
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (740 KB)  

    The gap between supply and demand of energy is continuously increasing despite huge outlay for energy sector since independence. Further, the burning of fossil fuel is resulting in greenhouse gases which are detrimental to the environment. The gap between supply and demand of energy can be bridged with the help of energy conservation which may be considered as a new source of energy which is benign and environment friendly. The energy conservation is cost effective with a short payback period and modest investment. There is a good scope of energy conservation in various sectors, viz., industry, agriculture, transport and domestic. The energy audit can unearth huge profits to the industry. The industrial sector has failed to take full advantage of many financial incentives provided by the government to encourage energy conservation strategies. The planners have started appreciating the role and significance of energy conservation in future energy scenario of India. However, the achievements so far are far from satisfactory. It is imperative to develop energy conservation as a mass movement View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Direct adaptive control of nonlinear systems using a dynamic neural network

    Publication Year: 1995 , Page(s): 269 - 274
    Cited by:  Patents (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (464 KB)  

    In this paper the development and application of a dynamic neural network called the dynamic neural processor (DNP) are discussed. The DNP is developed based on the neuro-physiological evidence that neural activity of any complexity depends upon the interaction of assembly of cells called neural subpopulations. A single subpopulation of neurons is assumed to consist of a number of similar neurons that lie in close proximity. For simplicity, live neural subpopulations, namely excitatory and inhibitory, are assumed to exist in a neural population. The DNP consists of two dynamic neurons configured to function as excitatory and inhibitory neurons. A learning algorithm to adapt the weights of the subpopulation and the connecting weights between the subpopulations is developed. The efficacy of the DNP structure is demonstrated for the direct adaptive control of unknown nonlinear systems View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An approach to robot off-line programming and simulation for flexible manufacturing systems

    Publication Year: 1995 , Page(s): 461 - 466
    Cited by:  Papers (2)  |  Patents (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (528 KB)  

    This paper presents a new approach for off-line robot program synthesis and simulation system incorporating automatic obstacle avoidance capabilities. The software supports off-line program generation in interactive task encoding and automatic path planning using configuration space (C-space) representation. The work is addressed to the part handling needs of workcells with robot manipulators used in flexible manufacturing systems (FMS), where the knowledge about the environment is known. CAD tools are used to create the virtual model of the work environment. Hierarchical object representation provides flexibility in computing configuration obstacle. Feasible path is planned in the free regions of configuration space, collision-free path information is further used to synthesize robot application program in a standard format (IRDATA), and later translated into robot specific program codes. Visual verification of operation is done with animated graphics View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Registration and projection of multiple overlapping images on 3D structures

    Publication Year: 1995 , Page(s): 13 - 18
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (564 KB)  

    A system that can integrate small pieces of images (taken from a close range) into a composite 3D surface, is developed. The device, along with 3D position/orientation estimation equipment, can be used in different environments for inspection tasks. For example, inspection of hulls of ships anchored at a bay, or examination of interior of pipes and tanks. Experimental results are presented, validating the algorithms developed View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An incidence angle detection system for automatic assembly tools using the RHI neural network model

    Publication Year: 1995 , Page(s): 31 - 36
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (368 KB)  

    One problem arising from the industrial application of automatic assembly of tools controlled by artificial vision systems is the angle the tool must turn given the position of the object to be assembled. Not only are current solutions to this problem computationally expensive but also the algorithms upon which they are based are elaborate and complex. In this paper a system that works directly on digitized images to obtain the necessary pixels so that the different object oriented instances can be discerned is discussed. Such an inference will be used to compute the angle between the object and the reference position View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Use of causal knowledge in a real-time fuzzy logic controller

    Publication Year: 1995 , Page(s): 101 - 108
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (500 KB)  

    The establishment of expert control techniques and their actual industrial impact have been inhibited by the lack of a comprehensive design methodology. This paper summarizes the principal drawbacks limiting the development of a definitive methodology and addresses the key problem of acquisition of process/plant knowledge, clarifying first the types of knowledge. For a case-study, a real-time fuzzy rule-based controller employing causal knowledge is designed for the control of liquid level in a pilot plant. It is tested for closed-loop operation under different conditions, viz., set point change, noise disturbance, and structural (parametric) change. The results show that the fuzzy controller employing causal knowledge yields superior performance over a qualitative controller and the conventional PID controller implemented on the same plant and subjected to similar disturbances View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Neural network based incipient fault detection of induction motors

    Publication Year: 1995 , Page(s): 199 - 202
    Cited by:  Papers (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (248 KB)  

    A pattern recognition technique based on artificial neural networks (ANNs) is playing a significant role in identifying the incipient faults of induction motors. Requirements of the pattern recognition algorithm to detect these faults are that it should not only show high accuracy to determine the extent of the fault, but also it must report if it can not identify a particular fault so that preventive steps can be taken in recognizing the undetected faults and updating the underlying neural network in the shortest possible time. A system based on the popular feedforward neural network (FNN) suffers a problem in satisfying these requirements of pattern recognition. In this paper a new pattern recognition scheme based on the ART2 neural network is proposed to detect the incipient faults of induction motors. The design, implementation and dynamic updating of this type of system are illustrated with an example View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A stochastic model and performance measure of a multi-sensory system for robotized assembly operation

    Publication Year: 1995 , Page(s): 285 - 290
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (340 KB)  

    Robotized assembly is a potential field of manufacturing engineering research, pertaining to the scenario of advanced automation in todays' industrial environment. The paper describes the paradigms of robotic assembly with the aid of a stochastic model, based on the real-life study of a multi-sensory system. The sensory system, comprising a force sensor, a torque sensor, two proximity sensors and a laser sensor, is placed judiciously around the wrist of an industrial robot. The model has been developed on the basis of dynamic simulation of the entire robotic system, starting from the on-line calibration of each of these sensors. The model has been delineated with analysis, mathematical formulae and logical backup and has been verified through experimentations in order to perform typical assembly tasks View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • On aspects of a neural controller for a two link manipulator

    Publication Year: 1995 , Page(s): 225 - 228
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (212 KB)  

    The kinematic and dynamic relationships of a manipulator are highly non-linear. The inverse problem is computationally intensive. In this light, the learning capabilities and parallel computational architecture of neural networks seem an attractive alternative to current methods of control. A few aspects of this issue are examined View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A new controller for efficient wave power generation

    Publication Year: 1995 , Page(s): 357 - 363
    Cited by:  Papers (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (380 KB)  

    Based on the stator current control of induction machine, a new current control scheme is developed for making the peak power to average power ratio of the wave power feeding in to the mains around unity. The proposed scheme is realised using an AC voltage controller. The induction machine operates both in motor and generating modes. Both simulation and test results have been presented View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Implementation of fail-safe control systems using programmable logic controllers

    Publication Year: 1995 , Page(s): 395 - 400
    Cited by:  Papers (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (388 KB)  

    In order to obtain a safety electronic system of control, in general it will be necessary to assign a redundancy approach. Nevertheless this makes the equipments more expensive. Throughout this paper, a method based on dynamic logic is set out in order to achieve safety systems with programmable logic controllers View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Learning fuzzy concepts for machine vision

    Publication Year: 1995 , Page(s): 127 - 131
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (468 KB)  

    This paper discusses a technique that effectively combines conceptual graph theory with fuzzy logic for 3D object recognition. The suitability of fuzzy conceptual graphs for learning continuous valued features is brought out with a machine vision system that employs model-based object recognition. The object recognition system learns instances of segmented range objects from different views, represented in terms of fuzzy conceptual graphs as a memory aggregate. Recognition is done by deriving a conceptual graph for a query and performing graph matching. The technique is found suitable for continuous valued concepts and hence used as with a powerful capability for learning View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A novel adaptive vector control system for temperature compensation in induction motors

    Publication Year: 1995 , Page(s): 185 - 188
    Cited by:  Papers (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (308 KB)  

    A new method for the improvement of temperature variation in induction motor (IM) speed control is presented in this paper. A direct measurement of the rotor temperature is assumed. The compensation of the temperature effect is made not only by adjusting a digital filter flux model coefficients but also by calculating the on-line proportional integral (PI) controller coefficients. These corrections yield matching of the flux model and the induction motor model, consequently the magnitude of the reference rotation and the induction motor model angles are equal so the matching of the command estimated variables and the real variables of the induction motor is obtained. This method uses the direct field-oriented vector control and eliminates its main disadvantage which is the decoupling of flux and torque when a rotor time constant varies. The simulations have shown an improvement mainly in the transient state response View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Intelligent real time reactive motion planning for multiple robotic configurations

    Publication Year: 1995 , Page(s): 301 - 304
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (292 KB)  

    This paper presents a hierarchical control system which enables the collision free operation of a multiple robot workcell. The method assumes that the motions to be performed are known beforehand, and initial collision free paths are planned offline. A monitor then tracks the actual robot motions. Any deviation from the preplanned path may result in a collision situation thus a collision detection algorithm is activated. Prediction of a collision situation results in the invocation of an intelligent reactive motion planner which replans the paths to avoid the collision situation. The algorithms associated with the monitor are presented and their application discussed View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Fuzzy control of integrated current controlled converter-inverter fed cage induction motor drive

    Publication Year: 1995 , Page(s): 153 - 159
    Cited by:  Papers (1)  |  Patents (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (508 KB)  

    The paper presents the performance analysis of a vector controlled cage induction motor drive. The drive is fed from a current controlled converter-inverter system. The switching technique being used in the control of the converter as well as inverter is PWM current control. Closed loop control of the cage induction motor utilizes the fuzzy PID speed controller. Advantages offered by the current control converter-inverter link are exploited. In order to examine the dynamic performance of the drive system its model is simulated and results are analyzed. The potential applications of this particular drive system are outlined View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A robust adaptive controller using fuzzy logic approach

    Publication Year: 1995 , Page(s): 95 - 99
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (220 KB)  

    This paper deals with the synthesis of a robust adaptive controller considering the nonlinearities of SISO system. Processes such as blast furnace, cement kiln, digesters etc. are nonlinear and their order of mathematical model is not known. These processes are nonlinear to the extent that they can be controlled only by expert human operator. A fuzzy interface is introduced in this paper to model such a process into piecewise linear system online. This model is identified and is used by an adaptive pole placement controller to make the system robust. Simulation results are shown for verification View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.