No abstract

No abstract

A 4" silicon-on-insulator wafer was bonded to a flexible plastic substrate using indirect bonding to fabricate thin-film silicon on a flexible substrate. The bonded materials were annealed at 150oC for 48 hours. The bonding process created stress in the silicon (~20 MPa) at the interface due to thermal mismatch. Thin-film silicon was created by removing substrate material. The interfacial stress increased as the silicon was thinned. Relaxation of the stress resulted in residual defects in the silicon.

Adaptive neuro-fuzzy inference systems (ANFIS) were used for on-line classification and measurement of tool wear for the boring of titanium parts. The input vectors consist of extracted features from cutting force data. A total of fourteen features were extracted by processing cutting force signals using virtual instrumentation. Feature selection was carried out using a Sequential Forward Search (SFS) algorithm to select the best combination of features. For the on-line classification, the outputs are boring tool conditions, which are either usable or worn out. For the on-line measurement, the outputs are estimated values of the tool wear. Using ANFIS, three features were selected for the on-line classification of boring tools. They are the average longitudinal force, average of the ratio between the tangential and radial forces, and kurtosis of the longitudinal force. Only one feature, kurtosis of the longitudinal force, was needed for the on-line measurement of tool wear using ANFIS. A 3×5 ANFIS can achieve a 100% success rate for the on-line classification of boring tool conditions. Using a 1×5 ANFIS, the average flank wear estimation error is below 5% for on-line measurement of tool wear.

Cutting forces were used as indices in this research for the monitoring and measurement of tool wear during the turning of stainless steel parts. Virtual instrumentation was applied to extract the fourteen features from cutting force signals. The best combination of features, which would be used as input vectors for on-line monitoring and measurement, was selected by using a Sequential Forward Search (SFS) algorithm. Adaptive neuro-fuzzy inference systems (ANFIS) were used for the recognition of tool wear. The tool conditions, which are either usable or worn out, are the outputs for on-line monitoring. The outputs for on-line measurement are estimated values of tool wear. When ANFIS was applied, three features were needed for the monitoring of tool wear. They are the average of radial force, the average of tangential force, and the skewness of tangential force. For on-line measurement, four features were used as inputs. The input vector includes the average of radial force, the average of tangential force, the skewness of tangential force, and the kurtosis of longitudinal force. For the on-line monitoring of turning tool conditions, a 7 × 2 ANFIS can achieve a success rate of higher than 96% to distinguish usable tools from worn-out tools. For the on-line measurement of tool wear, the average flank wear estimation error is below 8.9% using a 3 × 3 ANFIS.