Hybrid Modeling Technique Research Articles

Hybrid Modelling of Interstitial Free (IF) Steel

Modelling of the recrystallisation kinetics of Interstitial Free (IF) steel after hot deformation using plane strain compression (PSC) at strain rates from 0.1 to 10 s−1 over a temperature range of 700 to 900 °C has been carried out. The model is based on a hybrid modelling technique combining neuro-fuzzy models and physical equations. Explicitly. the model has been developed based on an inverse modelling strategy which involves predicting the internal states behaviour of the material based on the deformation conditions and the recrystallisation properties.

Integration of equation- and signal-based models in transient analysis of electric energy systems

The paper addresses analytical and practical aspects of integration of equation-based (classical) and signal-derived [artificial neural network (ANN)] dynamic models for transient analysis of large-scale dynamical systems. Our signal-based part is based on two ANNs, and is derived from measurements at boundary points. In this paper, we describe this hybrid modeling technique, and focus on: 1) a least square-based mechanism for on-line correction of dynamic variable predictions that is based on actual operating conditions; 2) the resilience of the algorithm to missing measurements due to failed communication links; and 3) a complete two-way interaction between the differential-algebraic equation based subsystem and the ANN-based subsystem. The paper demonstrates the feasibility of implementing our approach in standard power system software by integrating the ANN-based model with the transient analysis toolbox from Matlab. We illustrate capabilities of the proposed approach for transient analysis on a benchmark multi-machine example derived from the New England/New-York interconnected power system.

Modelling sewer failure by evolutionary computing

The sewer system is a service that is expected to function without interruptions. Continuous assessment, maintenance and rehabilitation are the key to maintaining a required level of service at an acceptable cost. An appropriate and cost effective prioritisation scheme for periodical surveys could be built based on failure data collected by sewerage companies over time. Such a scheme could be achieved using data-driven modelling techniques jointly with engineering knowledge of the failure mechanisms. This paper presents a descriptive analysis performed on a real database containing collapse and blockage incident records for a large sewer system in the UK. Starting from a statistical study of both failure types, the most important variables are identified and a classification scheme is suggested. Then, using a hybrid modelling technique, evolutionary polynomial regression, two different formulas for blockage events and collapse failures are obtained and their engineering interpretation is offered.

Multivariate hybrid modelling of air-gauge sensor

The quality of measurements depends directly on the quality of the measurement system model. With this concern, novel hybrid modelling techniques have been formulated for model performance enhancement. Air-gauge focus system sensor modelling has been accomplished by theoretical and empirical data integration. These modelling techniques combine a priori knowledge in theoretical model elaboration, and to attain the enhanced levels of adequacy, accuracy and precision they approximate the exact unknown model, simultaneously by available theoretical and appropriate polynomial empirical functions. For such a hybrid model the solution of two approaches by means of linear transformation and successive linear and nonlinear transformations have been developed. The validations of elaborated air-gauge sensor models revealed that sensor hybrid model solving by successive linear and nonlinear transformations permits us to attain minimum discrepancy with empirical evidence for the whole region of interest for model predictor variables.

Hybrid NN/HMM acoustic modeling techniques for distributed speech recognition

Distributed speech recognition (DSR) where the recognizer is split up into two parts and connected via a transmission channel offers new perspectives for improving the speech recognition performance in mobile environments. In this work, we present the integration of hybrid acoustic models using tied-posteriors in a distributed environment. A comparison with standard Gaussian models is performed on the AURORA2 task and the WSJ0 task. Word-based HMMs and phoneme-based HMMs are trained for distributed and non-distributed recognition using either MFCC or RASTA-PLP features. The results show that hybrid modeling techniques can outperform standard continuous systems on this task. Especially the tied-posteriors approach is shown to be usable for DSR in a very flexible way since the client can be modified without a change at the server site and vice versa.

QUASI-RANDOM, MANOEUVRE-BASED MOTION PLANNING ALGORITHM FOR AUTONOMOUS UNDERWATER VEHICLES

This paper presents an approach using a hybrid modelling technique known as Manoeuvre Automaton (MA) to capture the key dynamics of a nonlinear autonomous underwater vehicle (AUV) in such a way that high-level tasks such as optimal motion planning can be computationally simplified, while still allowing it to perform complicated manoeuvres when the situation arises. With respect to motion planning in an obstacle filled environment, an incremental stochastic technique derived from the Rapid-exploring Random Tree (RRT) algorithm is applied. This paper proposes a multiple nested node version of RRT and also addresses the case of a time varying final state. Simulation results as presented, using a 3 degree-of-freedom (DOF) nonlinear AUV model in order to prove the viability of the concept.

Hybrid Modeling Techniques for Multilayered Printed Circuit Board in Power Electronics: Association of Electromagnetic Methods

With the fast development of power electronics circuits at increasing switching frequency (over 10 MHz), the multilayered printed circuits boards (PCBs) are being used more and more in the field of power electronics. In this paper, two main computational methods are presented to simulate the dynamic behavior of power electronics interconnection systems. Our aim is to present a methodology to analyze the electromagnetic (EM) behavior of power PCB regarding parasitic effects ( EM couplings) or dynamic effects (impedance): a general procedure is given to calculate EM couplings between strip conductors in multilayered configurations based on the principle of hybrid methods. Finally, we propose a new method to limit computation time based on matrix sparsification.

Inverse Modelling of FE3%SI Steel Using a Hybrid Approach

Modelling of the recrystallisation kinetics of Fe3%Si steel after hot rolling and plane strain compression at strain rates from 0.05 to 5s-1 over a temperature range of 900 to 1100°C has been carriedout. The model is based on a hybrid modelling technique developed for aluminium alloys via a combination of neuro-fuzzy models and physical equations. Explicitly, the model has been developed on a reverse modelling strategy which involves predicting the internal states behaviour of the material based on the deformation conditions and the recrystallisation properties.

Damper Modelling Using Neural Networks

As a result of an internal research initiative called Integrated Corner Technology (ICT), MIRA has increased its analytical and experimental capability for the development of vehicle suspension systems. MIRA has not only explored the possibilities that off-the-shelf modelling tools offer, but has also developed its own experimental, analytical and hybrid modelling techniques.

Application of hybrid modeling and control techniques to desalination plants

One of the most recent and most intense efforts in control theory deals with handling systems whose behavior of interest is determined by interacting continuous and discrete dynamics. This approach can be applied not only to intrinsic hybrid processes but also to other systems as for example continuous processes with supervisory logic, multi-model control systems, switching control, etc. In this paper, hybrid systems are briefly introduced and possible applications to desalination plants are given by means of illustrative examples.

Modelling and simulation of hybrid rotating shafts

Response of a rotating cantilevered shaft with an end point load is analysed by hybrid modelling techniques using a distributed-lumped parameter approach. The flexural vibration of the distributed shaft is investigated first in the frequency domain and the frequency response of the system is computed. In the problem considered, the damped natural frequency of the system is calculated and compared with the results obtained from an approximation using influence coefficients. Future applications of hybrid modelling methods are discussed and computational accuracy improvements are predicted.

Design of optimal configuration for generating A0 Lamb mode in a composite plate using piezoceramic transducers.

This work concerned a technique for a health monitoring system based on the generation and sensing of Lamb waves in composite structures by thin surface-bonded piezoceramic transducers. The objective was to develop transducers that are adapted for the damage detection in orthotropic composites. The key problem with the investigated Lamb waves was to select a mode to be sensitive to the damage. A hybrid modeling technique was therefore used to conceive transducers that were adapted to achieve such a feature. This modeling technique enabled studying the influence of the transducer characteristics on the Lamb waves propagating in orthotropic plates. It was demonstrated that a Lamb mode could be generated dominantly to other modes by using a multi-element transducer. The effectiveness of this technique was successfully verified experimentally on composite plates. It was shown that the dominant Lamb mode, obtained by use of dual-element transducers, was an appropriate mode for successfully detecting a damage in composites.

Hybrid modelling of the rolling force in a plate mill

Different empirical and hybrid modelling techniques were evaluated in order to improve the modelling compared with the present situation in the plate rolling mill at Rautaruukki, Raahe. Logged data from the production were used to develop new models and to compare them with each other and with the present model. The data describe the chemical composition and various process parameters of the rolling process, including thermal, geometric and kinematic parameters. Various neural networks and multivariate models were evaluated in order to take non‐linear effects into account. Hybrid methods use a combination of physically based models and empirical models. The simple physically based formula, force = area x yield strength factor, proved useful. A more advanced model solving von Karman's differential equation was evaluated as a stand‐alone model and as part of a hybrid model. The measured force of the previous rolling pass was tested as an additional input variable. Various aspects of the different modelling techniques are discussed and compared. Simple but improved models are described as suitable candidates to replace the present on‐line model.

Issues for Automation in Semiconductor Manufacturing

This survey sketches the importance of Automatic Control Engineering with all its flavors for state-of-the-art semiconductor manufacturing. Many automation disciplines are required for maximization of production yield, high throughput, low delivery times and little lateness. Tools for accomplishing these goals are hybrid dynamic modeling, advanced simulation and scheduling techniques, complex robustness calculations and comprehensive performance monitoring and justification methods.

Physically based and neuro-fuzzy hybrid modelling of thermomechanical processing of aluminium alloys

Modelling of the microstructural evolution of aluminium alloys during thermomechanical processing is a desirable method for predicting the alloy's properties and designing the process variables to achieve the desired goals. A dynamic model has been developed in terms of the internal states variables of the process comprising the dislocation density, the subgrain size, and the misorientation between the subgrains. The developed model is based on a hybrid modelling technique known as grey-box modelling where intelligent models and physical equations are merged to predict the material properties with respect to the deformation conditions. The model predicts the evolution of the internal states variables under transient deformation conditions, as well as the static subsequent recrystallisation behaviour, nucleation of recrystallisation based on experimental results and quantitative metallurgical observations. In the model, the flow stress and recrystallisation behaviour are predicted with respect to temperature, strain rate and strain for different aluminium alloys providing a reasonable agreement with experimental data.

An Overview of New Techniques and Effects in Model-based Sound Synthesis

Physical modeling and model-based sound synthesis have recently been among the most active topics of computer music and audio research. In the modeling approach one typically tries to simulate and duplicate the most prominent sound generation properties of the acoustic musical instrument under study. If desired, the models developed may then be modified in order to create sounds that are not common or even possible from physically realizable instruments. In addition to physically related principles it is possible to combine physical models with other synthesis and signal processing methods to realize hybrid modeling techniques. This article gives an overview of some recent results in model-based sound synthesis and related signal processing techniques. The focus is on modeling and synthesizing plucked string sounds, although the techniques may find much more widespread application. First, as a background, an advanced linear model of the acoustic guitar is discussed along with model control principles. Then the methodology to include inherent nonlinearities and time-varying features is introduced. Examples of nonlinearities are studied in the context of two string instruments, the kantele and the tanbur, which exhibit interesting nonlinear effects.

Modelling of AL-MG Microstructure Using Grey-Box Techniques

Modelling of the microstructure evolution of aluminium alloys during thermomechanical processing is a desirable method in predicting the alloys properties and designing the process variables to achieve the desired goals. A dynamic model has been developed based on the internal states variables of the process such as the internal dislocation density, the subgrain size, and the misorientation between the subgrains. The developed model consists of a hybrid modelling techniques known as grey-box modelling where intelligent models and physical equations are mixed to predict the material properties with respect to the deformation conditions. In the model, the stress and recrystallisation conditions are predicted and compared to experimental data for Al-l%Mg alloy.

A parametric model for axial and bending stress concentration factors in API drillstring threaded connectors

This paper presents a study of the variation of stress concentration factor in threaded connectors due to application of external axial and bending loads. The study is based on a hybrid modelling technique previously developed to conduct such analysis. The paper considers the case of API threaded connectors used in drill string applications and uses a particular FEA sub-modelling method of calculating stress concentration factors. The method is used to conduct a parametric study on the effect of geometric thread parameters on axial and bending stress concentration factors.

Numerical model of acoustic interactions between class IV flextensional transducers using a modal method

Acoustic projectors assembled in an array experience an interaction effect as a result of the coupling of their individual radiated powers through the acoustic medium. The acoustic interaction may be expressed as a superposition of modal–mutual radiation impedances. A hybrid modeling technique is presented that combines the boundary integral method with a piece-parts equivalent circuit. The circuit consists of assembling a motional branch for the piezoelectric driver and for a set of flexural modes of the flextensional shell. The in vacuo eigenmodes of the shell are determined using the atila finite element method. Modal radiation impedances are generated using the chief boundary integral equation method. The resulting modal–mutual impedances are applied to the motional branches through a set of source-coupling terms. The circuit then provides a set of modal participation factors. Results compare well to measurements and to full finite element models of small close-packed arrays. [Work supported by ONR and NUWC ILIR.]

A machine learning approach to modeling and identification of automotive three-way catalytic converters

The working of three-way catalytic converters (TWCs) is based on chemical reactions whose rates are nonlinear functions of temperature and reactant concentrations all along the device. The choice of suitable expressions and the tuning of their parameters is particularly difficult in dynamic conditions. In this paper, we introduce a hybrid modeling technique which allows one to preserve the most important features of an accurate, distributed parameter TWC model, while it circumvents both the structural and the parameter uncertainties of classical reaction kinetics models, and saves the computational time; in particular, we compute the rates within the TWC dynamic model by a neural network which becomes a static nonlinear component of a larger dynamic system. A purposely designed genetic algorithm, in conjunction with a fast ad hoc partial differential equation integration procedure, allows one to train the neural network, embedded in the whole model structure, using currently available measurement data and without computing gradient information.