Fault diagnosis of closed control loops and its components is a topic which requires deeper investigation. Main problems are the different targets of control and fault diagnosis. control loops are designed to reduce t...
详细信息
Fault diagnosis of closed control loops and its components is a topic which requires deeper investigation. Main problems are the different targets of control and fault diagnosis. control loops are designed to reduce the influence of deviations of controller, actuator, the process itself and the sensors with regard to the desired input/output behaviour. On the other hand, the aim of fault diagnosis procedures is to detect these deviations in order to decide whether they cause a failure, damage or not allowed process behaviour, and to arrange appropriate actions. State space approaches are first investigated for fault detection in control loops because they need not necessarily excitation, a cirumstance which is given in many control loops. As a first stage of the current investigations, control loops with linear components will be examined.
Fault diagnosis of closed control loops and its components is a topic which requires deeper investigation. Main problems are the different targets of control and fault diagnosis. control loops are designed to reduce t...
详细信息
Fault diagnosis of closed control loops and its components is a topic which requires deeper investigation. Main problems are the different targets of control and fault diagnosis. control loops are designed to reduce the influence of deviations of controller, actuator, the process itself and the sensors with regard to the desired input/output behaviour. On the other hand, the aim of fault diagnosis procedures is to detect these deviations in order to decide whether they cause a failure, damage or not allowed process behaviour, and to arrange appropriate actions. State space approaches are first investigated for fault detection in control loops because they need not necessarily excitation, a cirumstance which is given in many control loops. As a first stage of the current investigations, control loops with linear components will be examined.
The integration of microelectronics within the actuator allows to not only replace the analog position controller but to add several functions which give the actuator more intelligent functions. The actuator control i...
详细信息
The integration of microelectronics within the actuator allows to not only replace the analog position controller but to add several functions which give the actuator more intelligent functions. The actuator control is performed in different levels and includes adaptive nonlinear control, optimization of speed and precision, supervision and fault diagnosis. The actuator knowledge base comprises actuator models based on parameter estimation, controller design and a storage of the learned behavior. An inference mechanism makes decisions for control and fault diagnosis and a communication module operates internally and externally. As examples electromagnetic and pneumatic actuators are considered and it is shown how the control can be improved considerably by model based nonlinear control, taking into account time varying nonlinear characteristics and hysteresis effects. The supervision with fault detection indicates faults in the electrical and mechanical subsystems of the actuator. Several experimental results are shown including the implementation on a low-cost microcontroller.
In modern manufacturing systems it is very important to increase the safety, reliability and availability of the involved components, e.g. industrial robots. Downtime of the entire production line as a result of a sin...
详细信息
In modern manufacturing systems it is very important to increase the safety, reliability and availability of the involved components, e.g. industrial robots. Downtime of the entire production line as a result of a single component breakdown will cause high costs which have to be avoided. Hence automaticcontrolled systems of high complexity should be supervised by automatic means and supplemented by appropriate diagnosis methods. Continuous time model-based procedures have been proven to present powerful tools for this purpose. In the present contribution specific approaches of parameter estimation and state estimation are applied to the mechanical components of an industrial robot. Several changes which represent typical mechanical faults were established artificially to the robot. Finally the different approaches are compared.
作者：
J. BöhmInstitute of Automatic Control
Laboratory of Control Engineering and Process Automation Technical University Darmstadt Landgraf-Georg-Strasse 4 D-6100 Darmstadt Germany
A model—based method for sensing external forces between a workpiece and the robot’s end-effector from drive current signals will be presented. To estimate these active forces only the natural process signals (armat...
详细信息
A model—based method for sensing external forces between a workpiece and the robot’s end-effector from drive current signals will be presented. To estimate these active forces only the natural process signals (armature current and actual joint position) of the robot are used. These signals are usually available in the control system of the robot. So no additional sensor is required. The force signal in the armature current will be interpreted as a disturbing torque which is estimated by a third order adaptive disturbance observer based on mathematical dynamic models for the robot. Finally first experimental results will be presented which were obtained with an industrial robot with six degrees of freedom.
作者：
R. IsermannInstitute of Automatic Control
Laboratory of Control Engineering and Process Automation Technical University Darmstadt Landgraf Georg Straße 4 D-6100 Darmstadt Germany
For further improvement of the reliability and safety of machines the automatic early detection and localization of faults is of high interest. The conventional approach is to monitor some important variables like tem...
详细信息
For further improvement of the reliability and safety of machines the automatic early detection and localization of faults is of high interest. The conventional approach is to monitor some important variables like temperatures, pressures, vibrations and to generate alarms if certain limits are exeeded. However, developing internal faults are in this way only detected at a rather late stage. By applying static and dynamic process models and common process input and output measurements the inherent relationships and redundancies can be used to detect faults earlier and to localize them better. Changes in process and signal parameters are very well suited for fault detection. The paper describes a general methodology for machines and other processes by using few measurements, dynamic process and signal models and parameter estimation to generate symptoms. The detected symptoms are fed into a knowledge based fault diagnosis procedure. Analytical and heuristic knowledge is treated via fault-symptom trees, process history and plausibility measures. The considered machines consist of a motor, a drive chain and a working process or load. They may be electrical motor or combustion engine driven pumps, fans or machine tools with gear or belt drive chains. The described methodology was developed and tested experimentally for several machines. As one example, experimental results are shown for a d.c. motor powered feed drive of a machine tool.
作者：
T. ReißInstitute of Automatic Control
Laboratory of Control Systems and Process Automation Technical University Darmstadt Landgraf-Georg-Str. 4 D-6100 Darmstadt Germany
The supervision of manufacturing processes is of primary interest in the course of progressive automation. This paper paper presents a new approach in fault diagnosis and supervision of the drilling process. The super...
详细信息
The supervision of manufacturing processes is of primary interest in the course of progressive automation. This paper paper presents a new approach in fault diagnosis and supervision of the drilling process. The supervision of manufacturing processes with additional sensors is mostly expensive or not possible at all. Therefore mathematical process models were developed for the drilling process. By means of least squares estimation techniques the physical parameters are determined based on easily measurable signals of the drives. Changes of those process parameters during operation are used for fault diagnosis. Experimental results on two flexible machining centers show the detected parameter changes during operation in dependence on tool wear.
作者：
D. NeumannTechnical University of Darmstadt
Institute of Automatic Control Laboratory of Control Systems and Process Automation Landgraf-Georg-Str. 4 D-6100 Darmstadt Germany
In this paper a method for the signal model based estimation of frequency spectra from sampled signals is presented. The algorithm uses discrete, parametric signal models in z-space, whose parameters are determined by...
详细信息
In this paper a method for the signal model based estimation of frequency spectra from sampled signals is presented. The algorithm uses discrete, parametric signal models in z-space, whose parameters are determined by a two step identification algorithm. From these parameters significant oscillations, described by their frequency and concatenated amplitude, are calculated to develop a method for the supervision and fault diagnosis of dynamic systems. The shown results and conclusions are taken from practical tests at machine-tools.
作者：
D. NeumannTechnical University of Darmstadt
Inst. of Control Engineering Laboratory for Automatic Control and Process Automation Landgraf-Georg-Str. 4 D-6100 Darmstadt FRG
The paper describes a personal-computer-based fault diagnosis system, which is designed for the analysis of periodically working machine tools. The used algorithms are described from signal analysis to the diagnosis s...
详细信息
The paper describes a personal-computer-based fault diagnosis system, which is designed for the analysis of periodically working machine tools. The used algorithms are described from signal analysis to the diagnosis system including some tests with real machines. The system was synthesized modularly. so that it can easily be adapted to other processes. Only few standard signals are needed. which have to be measured for controlling purposes anyway. so normally no special sensors have to be added. The knowledge based diagnosis system uses furtheron heuristic knowledge from machine history and expert knowledge. which is not exactly quantifiable.
The early detection and localization of faults in machines and drives is of primary interest to make further improvements of the reliability and safety. The conventional way is to monitor some important variables like...
详细信息
The early detection and localization of faults in machines and drives is of primary interest to make further improvements of the reliability and safety. The conventional way is to monitor some important variables like temperatures, pressures, vibrations and to generate alarms if certain limits are exceeded. However, developing internal process faults are only detected at a rather late stage. In recent years research has shown that many process faults can be detected earlier and localized better by using static and dynamic models together with some definite robust sensors. For machines and drives many faults appear as process and signal parameter changes. The contribution describes a general methodology for the fault diagnosis of machines and drives by using few sensors, dynamic process and signal models and parameter estimation. Changes of process and signal parameters are then symptoms, which are fed into a knowledge based fault diagnosis component. Then analytical and heuristic knowledge is treated via fault trees and plausibility measures. The results were obtained in several research projects with machine tools and robots driven by d. c., a.c. and synchroneous motors. Examples show some experimental results.
暂无评论