作者:
H. KonradIsermann R.Technical University of Darmstadt
Institute of Automatic Control Laboratory of Control Engineering and Process Automation Landgraf-Georg-Str. 4 D-64283 Darmstadt Germany Phone: +496151 163927 Fax: +49 6151 293445
A new method of fault detection in milling is described. The method uses exclusively drive signals and is based on models for the feed drive and the milling process. Using parameter estimation features are generated w...
详细信息
A new method of fault detection in milling is described. The method uses exclusively drive signals and is based on models for the feed drive and the milling process. Using parameter estimation features are generated which are independent of cutting conditions. A subsequent classifier evaluates the process state and provides a reliable diagnosis of the milling process.
作者:
H. KonradTechnical University of Darmstadt
Institute of Automatic Control Laboratory of Control Engineering and Process Automation Landgraf-Georg-Str.4 D-64283 Darmstadt Germany Phone: +49 6151 163927 Fax: +49 6151 293445
In this paper a new method of fault detection in milling is reported. Based on measured cutting forces, model parameters are estimated for each insert of the milling cutter. Using a classifier, the patterns of these e...
详细信息
In this paper a new method of fault detection in milling is reported. Based on measured cutting forces, model parameters are estimated for each insert of the milling cutter. Using a classifier, the patterns of these estimated parameters are processed further and the state of the milling process is determined. The method is first tested with simulated data and then verified with measurements on a machining center.
As individual and commercial traffic flow on roads and highways grows enormously, rhe number of accidents increases as well. Therefore, modern vehicle research is focused on improving driving comfort as well as passen...
详细信息
As individual and commercial traffic flow on roads and highways grows enormously, rhe number of accidents increases as well. Therefore, modern vehicle research is focused on improving driving comfort as well as passengers' safety. Aiming at that, recent advances in control engineering and modern computer technology enable the engineer to design special control and supervision systems supporting the driver. Exemplary, this contribution presents two possible solutions. On the one hand, an Adaptive Cruise control system which assists the driver during highway traffic, whereas a vehicle supervision method is applied to detect critical driving situations and sensor faults.
Due to the rising consciousness of safety aspects the supervision of vehicles' tire pressure is a major effort to improve active car safety. Therefore, in this contribution a method for monitoring the tire pressur...
详细信息
Due to the rising consciousness of safety aspects the supervision of vehicles' tire pressure is a major effort to improve active car safety. Therefore, in this contribution a method for monitoring the tire pressure is presented using body acceleration signals. Analysing the frequency spectrum of the virtual transfer function between the body acceleration at the front and the rear wheel of one side of the vehicle characteristic features are generated. Thereby, external interferences to the spectrum and their influences to the symptoms are discussed. Then, a neuro-fuzzy classification of the characteristics is applied to quantify the tire pressure.
A two-step scheme for identification of a vehicle suspension is presented which combines parameter estimation and neural networks for approximation. At first, the parameters of the discrete time transfer function are ...
详细信息
A two-step scheme for identification of a vehicle suspension is presented which combines parameter estimation and neural networks for approximation. At first, the parameters of the discrete time transfer function are estimated using a RLS-algonthm. These parameters are nonlinear functions of the physical coefficients, but a direct calculation of these is often not possible or leads to large errors due to the nonlinear amplification of noise. Therefore, to approximate the coefficients, a nonlinear mapping using a RBF network is performed. For training of the network and to test generalization abilities, the coefficients of a vehicle suspension were varied. The study shows that an approximation of the physical coefficients by application of the presented scheme is possible. The method was tested by simulated data and measurements from a test rig at the Technical University of Darmstadt.
Rising demands in automotive development and strict emission standards enforce the application of modern conrrol and supervision strategies to combustion engines. This contribution shows the shaping and adaption of mo...
详细信息
Rising demands in automotive development and strict emission standards enforce the application of modern conrrol and supervision strategies to combustion engines. This contribution shows the shaping and adaption of model based fault detection and direct signal analysis methods when applied to a turbocharged diesel engine. First a real lime supervision of fuel mass and injection angle based on dynamic cylinder pressure measurement is described. This is followed by a method for engine misfire detection using only a low resolution crankshaft speed signal. Then fault detection for a diesel engine turbocharger with nonlinear neural networks is proposed. Finally the results of a diagnosis of multiple faults with a neural network are presented. All methods have been implemented and tested experimentally on a dynamical engine test stand at the Technical University of Darmstadt.
作者:
Oliver NellesRolf IsermannTechnical University of Darmstadt
Institute of Automatic Control Laboratory of Control Engineering and Process Automation Landgraf-Georg-Str. 4 D-64283 Darmstadt Germany Phone: +49/6151/16-4524 Fax: +49/6/5//293445
Radial basis function (RBF) networks are often used for identification of nonlinear dynamic systems. The main reason why RBF networks are so successful is that the hidden layer parameters can be fixed in a very reason...
详细信息
Radial basis function (RBF) networks are often used for identification of nonlinear dynamic systems. The main reason why RBF networks are so successful is that the hidden layer parameters can be fixed in a very reasonable way and only the weights are optimized by a standard least squares technique. Thus for the case of Gaussian RBFs a good choice of the centers and standard deviations is crucial for good network performance. We show that Ihe most widely used clustering approach has many drawbacks. An alternative technique for center determination is presented, that is not completely unsupervised but exploits error information. It is based on a fusion of linear parameter estimation and the RBF network. First, a linear system is estimated from data. Then only the nonlinear part is approximated by an RBF network.
In order to apply the best fault-detection and diagnosis scheme, it is required to investigate the process model profoundly and the kinds of faults to be detected. Especially, the process excitation and the effect of ...
详细信息
In order to apply the best fault-detection and diagnosis scheme, it is required to investigate the process model profoundly and the kinds of faults to be detected. Especially, the process excitation and the effect of the fault being considered play an important role. This is the starting point for the choice of one of the various model-based fault-detection methods. According to this strategy, two different approaches, an observer-based and a signal-based approach, are selected for the two given faults of the benchmark task. It is shown that the use of adaptive thresholds can significantly improve the performance of the fault-detection scheme with respect to the false alarm rate and the delay in detection.
This paper compares radial basis function networks for identification of nonlinear dynamic systems with classical methods derived from the Volterra series. The performance of these different approaches, such as Hammer...
详细信息
This paper compares radial basis function networks for identification of nonlinear dynamic systems with classical methods derived from the Volterra series. The performance of these different approaches, such as Hammerstein, Wiener and NDE models, is analysed. Since the centres and variances of the Gaussian radial basis functions will be fixed before learning and only the weights are learned, a linear optimization problem arises. Therefore training the network and parameter estimation becomes comparable in computational effort. It is shown that the classical methods can compete or even perform better than the neural network, if the assumptions for the structure are valid. However, in practical applications when the structure is not known the radial basis function network performs much better than the classical methods.
This paper considers the application of neural networks with distributed dynamics to the identification of nonlinear systems. The primary objective is to establish a neural model bank which generates prediction errors...
详细信息
This paper considers the application of neural networks with distributed dynamics to the identification of nonlinear systems. The primary objective is to establish a neural model bank which generates prediction errors. These estimation residuals can be treated as analytic symptoms to supervise the plant operating state. The practical approach applicability has been illustrated using a thermal plant. Here, two sensor faults of interest are localized by means of the so-called residual pattern.
暂无评论