Dissertation made openly available per email from author, 6/13/2016.

No description available.

This study investigates the use of vibration and strain measurements on machine tools in order to identify the propagating wear of the selected tools. Two case studies are considered, one of which was conducted in the plant of a South African piston manufacturer. The purpose of the ftrst case study was to investigate the feasibility of vibration monitoring to identify tool wear, before attempting to implement a monitoring system in the manufacturing plant. During this case study, data from a turning process was recorded using two accelerometers coupled to a PL202 real time FFT analyser. Features indicative of tool wear were extracted from the sensor signals, and then used as inputs to a Self-Organising Map (SOM). The SOM is a type of neural network based on unsupervised learning, and can be used to classify the input data into regions corresponding to new and worn tools. It was also shown that the SOM can also be used very efficiently with discrete variables. One of the main contributions of the second case study was the fact that a unique type of tool was investigated, namely a synthetic diamond tool specifically used for the manufacturing of aluminium pistons. Data from the manufacturing of pistons was recorded with two piezoelectric strain sensors and a single accelerometer, all coupled to a DSPT Siglab analyser. A large number of features indicative of tool wear were automatically extracted from different parts of the original signals. These included features from time and frequency domain data, time series model coefficients as features and features extracted from wavelet packet analysis. A correlation coefficient approach was used to auto-lJUltically select the best features indicative of the progressive wear of the diamond tools. The SOM was once again used to identify the tool state. Some of the advantages of using different map sizes on the SOM were also demonstrated. A near 100% correct classification of the tool wear data was obtained by training the SOM with two independent data sets, and testing it with a third independent data set. It was also shown that the monitoring strategy proposed in the second case study can be fully automated and can be implemented on-line if the manufacturer wishes to. Some of the contributions of this study are the use of the SOM for tool wear classification, and conclusions regarding the wear modes of the synthetic diamond tools. / Dissertation (M Eng (Mechanical Engineering))--University of Pretoria, 2006. / Mechanical and Aeronautical Engineering / unrestricted

Machining operations in automated manufacturing centers are under-performing by 20-80%. Optimizing these machining operations requires on-line knowledge about the cutting tool's condition and the process state. Currently, this information is either not reliable or not available in a timely manner. This is due to the lack of suitable sensors, which must measure on-line directly and accurately one or more of the relevant tool and process information sources in the hostile machining environment. A direct, active, ultrasonic method for on-line sensing of the tool condition and process state in turning operations was developed. Sensing is achieved by using an ultrasonic transducer operating at 10 MHz in a pulse-echo mode to send pulses through the tool. The amplitude and propagation time of the reflected pulses are modulated by the tool nose, flank, temperature, and by the material in contact with the tool. The reflected pulses are received and processed by a high speed digital signal processing system. This method has the potential to directly and accurately measure on-line several relevant processes and cutting tool parameters through the use of a single sensor. These parameters are tool-workpiece contact, tool wear, tool chipping, temperature and chatter. / Ph. D.