초록 ▼

Method and system for diagnosing whether vehicular components are operating abnormally based on data obtained from sensors arranged on a vehicle. In a training stage, output from the sensors during normal operation of the components is obtained, each component is adjusted to induce abnormal operati

Method and system for diagnosing whether vehicular components are operating abnormally based on data obtained from sensors arranged on a vehicle. In a training stage, output from the sensors during normal operation of the components is obtained, each component is adjusted to induce abnormal operation thereof and output from the sensors is obtained during the induced abnormal operation. A determination is made as to which sensors provide data about abnormal operation of each component based on analysis of the output from the sensors during normal operation and during induced abnormal operation of the components. During operation of the vehicle, the output from the sensors is obtained and analyzed, e.g., by inputting it into a pattern recognition algorithm or neural network generated during the training stage, in order to output an indication of abnormal operation of any components being diagnosed.

대표청구항 ▼

The invention claimed is: 1. A method for diagnosing whether one or more components of a vehicle are operating abnormally, comprising: arranging a plurality of sensors on a vehicle; in a training stage, receiving output from the sensors during normal operation of the components, adjusting each comp

The invention claimed is: 1. A method for diagnosing whether one or more components of a vehicle are operating abnormally, comprising: arranging a plurality of sensors on a vehicle; in a training stage, receiving output from the sensors during normal operation of the components, adjusting each component to induce abnormal operation thereof and receiving output from the sensors during the induced abnormal operation, and determining which sensors provide data about abnormal operation of each component based on analysis of the output from the sensors during normal operation and during induced abnormal operation of the component; and during operation of the vehicle, receiving output from the sensors; and determining whether any of the components are operating abnormally by analyzing the output from those sensors which have been determined to provide data about abnormal operation of that component. 2. The method of claim 1, further comprising alerting a driver of the vehicle, a vehicle manufacturer, a vehicle dealer or a vehicle repair facility upon a determination of abnormal operation of a component. 3. The method of claim 1, wherein the output from the sensors is a signal, the step of determining which sensors provide data about abnormal operation of each component comprising analyzing differences between the signals from the sensors during normal operation or absence thereof and the signals from the sensors during induced abnormal operation of the component. 4. The method of claim 3, wherein the step of determining whether any of the components are operating abnormally comprises deriving numerical time series data from the signals from the sensors, entering the numerical time series data into a processor, applying at least one pattern recognition algorithm to identify and classify patterns in the numerical time series indicative of abnormal operation of a component. 5. The method of claim 4, further comprising applying a mathematical transformation on, a feature extraction technique to or a Fourier transformation to the numerical time series data prior to application of the at least one pattern recognition algorithm. 6. The method of claim 4, wherein the step of deriving numerical time series data comprises converting the signals from the sensors into electrical signals and digitizing the electrical signals to create the numerical time series data. 7. The method of claim 1, further comprising pre-processing the output from the sensors, wherein the output from the sensors and the pre-processed output are both used to determine whether any of the components are operating abnormally. 8. The method of claim 1, wherein the step of determining whether any of the components are operating abnormally comprises comparing patterns of data derived from the output from those sensors which have been determined to provide data about abnormal operation of that component with patterns derived from the output of the same sensors during normal operation of the component and abnormal operation of the component. 9. The method of claim 1, further comprising: in the training stage, generating a neural network which operatively determines abnormal operation of the components, the neural network being generated from output from sensors during normal operation and output from the sensors during induced abnormal operation of the component; and the step of determining whether any of the components are operating abnormally comprising inputting the output from the sensors into the neural network which, for each component, considers the output from those sensors which have been determined to provide data about abnormal operation of that component and outputs an indication of normal or abnormal operation of the component. 10. The method of claim 9, wherein the neural network is a combination neural network. 11. The method of claim 1, wherein the step of determining which sensors provide data about abnormal operation of each component comprises identifying at least two sensors which provide data about abnormal operation of the component such that each condition of abnormal operation of each component is reflected in output from a plurality of sensors. 12. The method of claim 1, further comprising: adjusting a plurality of components simultaneously to induce abnormal operation thereof and receiving output from the sensors during the induced abnormal operation of the components; and determining which sensors provide data about abnormal operation of the components based on analysis of the output from the sensors during normal operation and during induced abnormal operation of the components. 13. The method of claim 1, further comprising adjusting operation of another component when a determination is made of abnormal operation of one of the components being diagnosed. 14. A vehicle including a system for diagnosing whether one or more components of a vehicle are operating abnormally, comprising: a plurality of sensors arranged on the vehicle; and a processor coupled to said sensors and including a pattern recognition algorithm which receives output from said sensors and determines whether each component is operating abnormally by analyzing output from specific ones of said sensors determined to provide data about abnormal operation of that component, said pattern recognition algorithm being generated by analyzing output from said sensors during normal operation of the components and during induced abnormal operation of the components. 15. The vehicle of claim 14, wherein said pattern recognition algorithm is generated in consideration of which specific sensors provide data about abnormal operation of each component based on the output from said sensors. 16. The vehicle of claim 14, further comprising a notification device coupled to said processor for notifying a driver of the vehicle of abnormal operation of one of the components being diagnosed. 17. The vehicle of claim 14, further comprising a transmission device coupled to said processor for wirelessly notifying a vehicle manufacturer, a dealer or repair facility of abnormal operation of a component. 18. The vehicle of claim 14, wherein said pattern recognition algorithm is a neural network. 19. The vehicle of claim 14, wherein said pattern recognition algorithm is a combination neural network. 20. The vehicle of claim 14, wherein at least one of the components has no dedicated sensor associated therewith. 21. A method for diagnosing whether one or more components of a vehicle are operating abnormally, comprising: arranging a plurality of sensors on a vehicle; in a training stage, receiving output from the sensors during normal operation of the components, adjusting the components to induce abnormal operation thereof and receiving output from the sensors during the induced abnormal operation, and generating a neural network which operatively determines abnormal operation of the components, the neural network being generated from the output from sensors during normal operation and the output from the sensors during induced abnormal operation of the components; and during operation of the vehicle, receiving output from the sensors; and providing data derived from the output from the sensors to the neural network which outputs an indication of abnormal operation of any of the components. 22. The method of claim 21, wherein the neural network is a combination neural network. 23. The method of claim 22, wherein the step of providing data to the combination neural network comprises providing data to a first neural network which determines whether the data corresponds to data received during normal operation of the components; and when the data does not correspond to data received during normal operation of the components, providing the data to a second neural network which determines whether any of the components are operating abnormally. 24. The method of claim 23, wherein the step of providing data to the combination neural network further comprises, when the second neural network determines that one of the components is operating abnormally, providing all of the data or a subset of the data to a third neural network which determines the particular manner in which that component is operating abnormally. 25. The method of claim 22, wherein the step of providing data to the combination neural network comprises providing the data to a first neural network which outputs an indication of the normal or abnormal operation of the components and when an indication of abnormal operation of a component is output, selecting a subset of the sensors based on the component, and inputting data derived from the output of the sensors in the subset of sensors into a second neural network to determine the particular manner in which that component is operating abnormally. 26. The method of claim 21, further comprising alerting a driver of the vehicle, a vehicle manufacturer, a vehicle dealer or a vehicle repair facility upon a determination of abnormal operation of any of the components being diagnosed. 27. The method of claim 21, further comprising adjusting operation of another component when a determination is made of abnormal operation of any of the components being diagnosed. 28. The method of claim 21, wherein the output from the sensors are signals, the step of generating the neural network comprising deriving numerical time series data from the signals from the sensors, pre-processing the numerical time series data, entering the numerical time series data into a neural network generating program to thereby generate the neural network. 29. The method of claim 28, wherein the step of pre-processing of the numerical time series data comprises applying a mathematical transformation on, a feature extraction technique to or a Fourier transformation to the numerical time series data.