Stefan Jakubek

Battery Emulation for Power-HIL Using Local Model Networks and Robust Impedance Control

Battery emulation with a controllable high-power dc supply enables repeatable hardware-in-the-loop testing of powertrains for hybrid and electric vehicles. For this purpose, not only the power flow but also the nonlinear characteristic and dynamic impedance of batteries need to be emulated. In this paper, nonlinear local model networks are used to obtain dynamic battery models with high fidelity that can be computed in real time. This approach also allows the extraction of local linear impedance models for high-bandwidth impedance emulation, leading to a tighter coupling between the test bed and simulation model with predictable closed-loop dynamics. A model predictive controller that achieves optimal control with adherence to system constraints is extended to impedance control and robustness against constant power loads. This results not only in superior dynamic performance but also in stable dc-bus voltage control even for testing of tightly controlled electric motor inverters with negative differential input resistance. Since the controller design is based on a model of the test bed setup including the virtual battery model, emulator hardware, and input characteristics of the powertrain under test, it is possible to systematically analyze stability.

Fault-diagnosis using neural networks with ellipsoidal basis functions

A fault detection scheme for applications in the automotive industry is presented. The detection scheme has to process up to several hundreds of different measurements at a time and check them for consistency. Our fault detection scheme works in three steps. First, principal component analysis of training data is used to determine nonsparse areas of the measurement space. Fault detection is accomplished by checking whether a new data record lies in a cluster of training data or not. Therefore, in a second step the distribution function of the available data is estimated using kernel regression techniques. In order to reduce the degrees of freedom and to determine clusters of data efficiently in a third step the distribution function is approximated by a neural network. In order to use as few basis functions as possible a new training algorithm for ellipsoidal basis function networks is presented. This is accomplished by adapting the spread parameters using Taylors theorem. Application to measured data from a real automotive process show that the proposed algorithm yields good results.

Identification of Neurofuzzy Models Using GTLS Parameter Estimation

In this paper, nonlinear system identification utilizing generalized total least squares (GTLS) methodologies in neurofuzzy systems is addressed. The problem involved with the estimation of the local model parameters of neurofuzzy networks is the presence of noise in measured data. When some or all input channels are subject to noise, the GTLS algorithm yields consistent parameter estimates. In addition to the estimation of the parameters, the main challenge in the design of these local model networks is the determination of the region of validity for the local models. The method presented in this paper is based on an expectation-maximization algorithm that uses a residual from the GTLS parameter estimation for proper partitioning. The performance of the resulting nonlinear model with local parameters estimated by weighted GTLS is a product both of the parameter estimation itself and the associated residual used for the partitioning process. The applicability and benefits of the proposed algorithm are demonstrated by means of illustrative examples and an automotive application.

A local neuro-fuzzy network for high-dimensional models and optimization

Abstract In this paper a new iterative construction algorithm for local model networks is presented. The algorithm is focussed on building models with sparsely distributed data as they occur in engine optimization processes. The validity function of each local model is fitted to the available data using statistical criteria along with regularization and thus allowing an arbitrary orientation and extent in the input space. Local models are consecutively placed into those regions of the input space where the model error is still large thus guaranteeing maximal improvement through each new local model. The orientation and extent of each validity function are also adapted to the available training data such that the determination of the local regression parameters is a well-posed problem. The regularization of the model can be controlled in a distinct manner using only two user-defined parameters. In order to assess the quality of the obtained model, the algorithm also provides accurate model statistics. Different examples illustrate the efficiency of the proposed algorithm. One illustrative example shows how local models are adapted to the shape of the target function in the presence of noise. A second example shows results obtained with measurement databases of IC-engines.

Neuro-Fuzzy Modelling Using a Logistic Discriminant Tree

An algorithm for nonlinear static and dynamic identification using Takagi-Sugeno fuzzy models is presented. For practical applications the incorporation of prior knowledge and the interpretability of the local models is of great interest. Using a tree structured algorithm in combination with the distinction between the input arguments for the consequents and for the premises the nonlinear optimisation is performed in an efficient way. The axis oblique decomposition of the partition space is based on an expectation-maximisation (EM) algorithm. Simulation results demonstrate the capabilities of the proposed concept.

Optimal experiment design based on local model networks and multilayer perceptron networks

This paper addresses the topic of model based design of experiments for the identification of nonlinear dynamic systems. Data driven modeling decisively depends on informative input and output data obtained from experiments. Design of experiments is targeted to generate informative data and to reduce the experimentation effort as much as possible. Furthermore, design of experiments has to comply with constraints on the system inputs and the system output, in order to prevent damage to the real system and to provide stable operational conditions during the experiment. For that purpose a model based approach is chosen for the optimization of excitation signals in this paper. Two different modeling architectures, namely multilayer perceptron networks and local model networks are chosen and the experiment design is based on the optimization of the Fisher information matrix of the associated model architecture. The paper presents and discusses feasible problem formulations and solution approaches for the constrained dynamic design of experiments. In this context the effects of the Fisher information matrix in the static and the dynamic configurations are discussed. The effectiveness of the proposed method is demonstrated on a complex nonlinear dynamic engine simulation model and an analysis as well as a comparison of the presented model architectures for model based experiment design is given.

Total least squares in fuzzy system identification: An application to an industrial engine

Takagi-Sugeno fuzzy models have proved to be a powerful tool for the identification of nonlinear dynamic systems. Their generic nonlinear model representation is particularly useful if information about the structure of the nonlinearity is available. In view of a practical applicability in industrial applications two important issues are addressed. First, the problem of unbiased estimation of local model parameters in the presence of input and output noise is considered. For that purpose the concept of total least squares for parameter estimation is reviewed and a related partitioning algorithm based on statistical criteria is presented. Second, the steady-state accuracy of dynamic models is addressed. A concept of constrained TLS parameter optimisation is introduced which enforces the adherence of the model to selected steady-state operating points and thus significantly improves the model accuracy during steady-state phases. Results from a simulation model and from an industrial gas engine power plant demonstrate the capabilities of the proposed concepts.

Local model network identification for online engine modelling

In this paper an evolving local model network (LMN) which is especially suited for engine modelling is presented and discussed. The incremental construction of the model tree allows to gradually increase the model complexity while a proper initialisation of new model parameters is easily possible when the LMN is extended. Especially in dynamic system identification the computational speed is an important requirement for online training. Therefore, a new evolving optimisation algorithm for the online training of the LMN is proposed which allows for a recursive computation of the model parameters. while the local interpretability of the consequent parameters is conserved. The decision when to grow the tree is based on an effective statistical criterion. The proposed concepts are validated by means of an illustrative example and by real dynamic measurement data from a state-of-the-art 4-cylinder EURO5 diesel engine.

Proprioceptive Navigation, Slip Estimation and Slip Control for Autonomous Wheeled Mobile Robots

For a two-wheeled differentially driven mobile robot a navigation and slip control algorithm is developed. The presented concept for purely proprioceptive navigation combines state estimation via extended Kalman filter from inertial sensor data (i.e. gyro and acceleration sensors) and odometric measurements (i.e. wheel angular encoders). The advantages of both types of sensors are exploited by selective mixing. Tangential slip detection and side-slip angle measurement enable slip control by transiently overriding a pre-planned trajectory. Experimental results demonstrating the performance of the proposed system are presented

Model predictive control of a battery emulator for testing of hybrid and electric powertrains

Thorough testing of the powertrain is a key aspect for the development of reliable hybrid and electric vehicles. Instead of a real traction battery, a battery emulator is used to supply the electric motor inverters of hybrid powertrains on a testbed. This approach avoids time-consuming preconditioning of batteries and allows automated testing of hybrid powertrains. An electric motor inverter acts as a constant power load towards the battery emulator. This degrades the dynamic performance and can even destabilize a supply with a conventional controller. The contributions are a model predictive controller design approach that includes a model of the system and the constant power load. A robustness concept is utilized in order to achieve stable operation. An algorithm for real-time execution of constrained model predictive control is proposed as well. Simulation results and experimental results are presented.