Detecting anomalies in time series data is a problem of great practical interest in many manufacturing and signal processing applications. This paper presents a novelty detection algorithm inspired by the negative-selection mechanism of the immune system, which discriminates between self and other. Here self is defined to be normal data patterns and non-self is any deviation exceeding an allowable variation. An example application, simulated cutting dynamics in a milling operation, is presented, and the performance of the algorithm in detecting the tool breakage is reported. 1 INTRODUCTION The normal behavior of a system is often characterized by a series of observations over time. The problem of detecting novelties or anomalies can be viewed as finding non permitted deviations of a characteristic property in the system of interest. The detection of novelty is an important task in many diagnostic and monitoring systems. In safety-critical applications, it is essential to detect the o...

Detection of tool breakage is very important for automated machining operations. This paper presents a negative-selection algorithm for tool breakage detection. The method is inspired by the defense mechanism of the immune system, which discriminates between self and non-self. Here self is defined to be normal cutting operations and non-self is any deviation beyond allowable variation of the cutting force. The proposed algorithm is illustrated with a simulation study of milling operations and the performance of the algorithm in detecting the occurrence of tool breakage is reported. The negative-selection algorithm detected tool breakage in all the test cases. 1 Introduction Manufacturers are always looking for ways to improve productivity without compromising on quality of manufacturing processes. To this end, much attention has been directed towards automated manufacturing. In drilling or high-speed milling industries, on-line monitoring of the tool breakage is a key component in unm...