Yahya H. Zweiri

A three-term backpropagation algorithm

Abstract The standard backpropagation algorithm for training artificial neural networks utilizes two terms, a learning rate and a momentum factor. The major limitations of this algorithm are the existence of temporary, local minima resulting from the saturation behaviour of the activation function, and the slow rates of convergence. In this paper, the addition of an extra term, a proportional factor, is proposed in order to speed-up the weight adjusting process. This new three-term backpropagation algorithm is tested on three example problems and the convergence behaviour of the three-term and the standard two-term backpropagation algorithm are compared. The results show that the proposed algorithm generally out-performs the conventional algorithm in terms of convergence speed and the ability to escape from local minima.

A Dual-Function Wheeled Probe for Tissue Viscoelastic Property Identification during Minimally Invasive Surgery

This paper proposes a novel approach for the identification of tissue properties in-vivo using a force sensitive wheeled probe. The purpose of such a device is to compensate a surgeon for a portion of the loss of haptic and tactile feedback experienced during robotic-assisted minimally invasive surgery. Initially, a testing facility for validating the concept ex-vivo was developed and used to characterize two different testing modalities - static (1-DOF) tissue indentation and rolling (2-DOF) tissue indentation. As part of the static indentation experiments a mathematical model was developed to classify tissue condition based on changes in mechanical response. The purpose of the rolling indentation tests was to detect tissue abnormalities, such as tumors, which are difficult to isolate under static testing conditions. During such tests, the test-rig was capable of detecting simulated miniature buried masses at depths of 12mm. Based on these experiments a portable device capable of carrying out similar tests in-vivo was developed. The device was designed to be operated through a trocar port and its key feature is the ability to transition between static indentation and rolling indentation modalities without retracting and changing the tool.

Instantaneous friction components model for transient engine operation

Abstract An engine friction model is developed in order to determine the instantaneous friction components at any crank angle during the overall engine response. In order that it can be meaningfully incorporated in overall engine control models, the engine friction model should represent the relevant trends but be relatively simple to compute. The main friction components are the piston assembly, the bearing, the valve train and the auxiliaries. The model includes new analytically derived equations for the friction components of the ring assembly, the bearing with mixed lubrication and the valve train. Many factors contribute to the successful starting of diesel engines and one of them is the effect of engine friction due to high oil viscosity (cold start) on engine startability. The model takes into consideration the effect of temperature variations on the viscosity of the oil. The friction equations are based on theoretical calculations for hydrodynamic and mixed lubrication (where the oil film has collapsed). They rely on Reynolds equation and dynamic analysis. Simulation results are presented, which compared with experimental data indicate an accuracy of more than 97 per cent.

Detailed analytical model of a single-cylinder diesel engine in the crank angle domain

Abstract A detailed analytical non-linear dynamic model for single-cylinder diesel engines is developed. The model describes the dynamic behaviour between fuelling and engine speed and includes models of the non-linear engine and dynamometer dynamics, the instantaneous friction terms and the engine thermodynamics. The model operates in the crank angle domain. The dynamometer model enables the study of the engine behaviour under loading. The instantaneous friction model takes into consideration the viscosity variations with temperature. Inertia variations with piston pin offset are presented. In-cycle calculations are performed at each crank angle, and the correct crank angles of ignition, speed variations, fuel supply and air as well as fuel burning rate are predicted. The model treats the cylinder strokes and the manifolds as thermodynamic control volumes by using the filling and emptying method. The model is validated using experimentally measured cylinder pressure and engine instantaneous speeds, under transient operating conditions, and gives good agreement. The model can be used as an engine simulator to aid diesel engines control system design and fault diagnostics.

Stability analysis of a three-term backpropagation algorithm

Efficient learning by the backpropagation (BP) algorithm is required for many practical applications. The BP algorithm calculates the weight changes of artificial neural networks, and a common approach is to use a two-term algorithm consisting of a learning rate (LR) and a momentum factor (MF). The major drawbacks of the two-term BP learning algorithm are the problems of local minima and slow convergence speeds, which limit the scope for real-time applications. Recently the addition of an extra term, called a proportional factor (PF), to the two-term BP algorithm was proposed. The third increases the speed of the BP algorithm. However, the PF term also reduces the convergence of the BP algorithm, and criteria for evaluating convergence are required to facilitate the application of the three terms BP algorithm. This paper analyzes the convergence of the new three-term backpropagation algorithm. If the learning parameters of the three-term BP algorithm satisfy the conditions given in this paper, then it is guaranteed that the system is stable and will converge to a local minimum. It is proved that if at least one of the eigenvalues of matrix F (compose of the Hessian of the cost function and the system Jacobian of the error vector at each iteration) is negative, then the system becomes unstable. Also the paper shows that all the local minima of the three-term BP algorithm cost function are stable. The relationship between the learning parameters are established in this paper such that the stability conditions are met.

Non-linear observer for slip estimation of skid-steering vehicles

Accurate estimation of slip is essential in developing autonomous navigation strategies for mobile vehicles operating in unstructured terrain. In this paper, a sliding mode observer is firstly constructed to estimate slip parameters based on the kinematics model of a skid-steering vehicle and trajectory measurement. The stability of the sliding mode observer is given in a mathematical context. Slip estimation schemes using an extended Kalman filter and direct mathematical inversion of the kinematic equations are also presented for comparison purposes. It is shown that the non-linear sliding mode observer is more accurate than the other two methods. The robustness and superior performance of the sliding mode observer is demonstrated using both simulation and experimental results. A camera based system is used to measure the vehicle trajectory during experimental validation

Parameter estimation for excavator arm using generalized Newton method

A robust, fast, and simple technique for the experimental identification of the link parameters (mass, inertia, and length) and friction coefficients of a full-scale excavator arm is presented. This new technique, based on the generalized Newton method (GNM), estimates unknown individual parameters of the excavator arm dynamic equations. The technique can be used when the number of equations is different from the number of estimated variables. Using experimental data from a full-scale field Combat Engineer Excavator (CEE), the values of link parameters and friction coefficients are successfully identified. The identified parameters are compared with known values, and shown to be in agreement. The method is compared with the least square method, and shows that the GNM is better in terms of prediction accuracy and robustness to noise. Further, the joint positions predicted by the analytical model using the identified parameters are validated against different experimental trajectories, showing very good agreement. The experimental data was obtained in collaboration with QinetiQ Ltd. (Hampshire, U.K.). The technique presented in this paper is general and can be applied to any manipulator.

Diesel Engine Indicated and Load Torque Estimation Using a Non-Linear Observer:

Abstract This paper presents a non-linear observer to estimate the indicated torque and the load torque of a single-cylinder diesel engine from crankshaft and coupling angular velocity measurements. Since these variables can be measured using low-cost sensors, the observer may be useful in the implementation of the control or diagnostics strategies that require cylinder indicated torque and load torque, variables that are not easily measured and need expensive sensors. The observer operates in the crank angle domain and is based on a nonlinear dynamic engine model that includes an instantaneous friction model. The effects of inertia variations of the crankshaft assembly with piston pin offset are also included, which significantly increases the accuracy of the pressure estimation at high speeds. Strong chattering is avoided by modifying the sliding gain as a non-linear function of the crank angle. The stability of the observer is proved, and simulation results of the engine indicated torque and load torque are presented, which indicate good agreement with experimental data.

Diesel Engine Indicated Torque Estimation Based on Artificial Neural Networks

This paper presents an artificial neural networks approach to estimate the indicated torque of a single- cylinder diesel engine from crank shaft angular position and velocity measurements. Since these variables can be measured using low-cost sensors, the estimator may be useful in the implementation of the control or diagnostics strategies that require cylinder indicated torque, a variables that are not easily measured and need expensive sensors. The approach is to design indicated torque estimators using feedback and an artificial neural networks model as feedforward. Such an approach can offer the advantage of being amenable to real-time implementation. The estimated results of the engine indicated torque are presented, which compared with experimental data indicate a good agreement.

DYNAMIC SIMULATION OF A SINGLE-CYLINDER DIESEL ENGINE INCLUDING DYNAMOMETER MODELLING AND FRICTION

Abstract The recent drive to reduce emissions and improve efficiency means that there is a real need for improved models for the simulation of direct-injection diesel engines. With a view to improving the transient fuel control, a model of the non-linear transient dynamics of a generic direct-injection single-cylinder diesel engine is developed in order to predict the instantaneous engine speed and torque. The instantaneous crankshaft speed is determined from the solution of the engine—external load dynamics equation, where the engine torque is tracked on a crank angle basis. The model is based on an analysis of all the major forces internal to the engine and dynamometer. The friction components of the piston assembly, the bearings, the valve train, the pumping and the pumps are also included. The model is implemented in MATLAB:SIMULINK, and simulation results of both transient and steady state dynamics are presented. The simulation results of the instantaneous engine speed are compared with measured data, and it is seen that there is excellent agreement between them.