Title :
Bandsaw diagnostics by neurocomputing-two are better than one!
Author_Institution :
Ind. Res. Ltd., Auckland, New Zealand
Abstract :
In industrial sawmills, bandsaws must work at a high production rate. Two major factors which limit cutting performance are cracking and instability of the saw blades. This paper describes the results from the development of a diagnostic system which monitors blade vibration and blade tension sensor data to estimate crack length using neurocomputing techniques, to help predict blade failure. It was found that a multi-layered feedforward artificial neural network with two hidden layers produces the most reliable results. The results indicate that this system should enable the detection of cracking in blades while in a running but unloaded (between cuts) state. This may help allow longer run times to be planned with confidence increasing production uptime and minimising maintenance
Keywords :
computerised monitoring; crack detection; cutting; feedforward neural nets; production engineering computing; vibration measurement; wood processing; bandsaw diagnostics; blade failure prediction; blade tension sensor data; blade vibration; crack length; cutting performance; diagnostic system; industrial sawmills; multi-layered feedforward artificial neural network; neurocomputing; production uptime; Artificial neural networks; Blades; Machinery production industries; Neuroscience; Pattern recognition; Preventive maintenance; Robustness; Sensor phenomena and characterization; Sensor systems; Sonar detection;
Conference_Titel :
Artificial Neural Networks and Expert Systems, 1995. Proceedings., Second New Zealand International Two-Stream Conference on
Conference_Location :
Dunedin
Print_ISBN :
0-8186-7174-2
DOI :
10.1109/ANNES.1995.499501
