Processing time estimation in precision machining industry using AI / Lim Say Li

Lim, Say Li (2017) Processing time estimation in precision machining industry using AI / Lim Say Li. Masters thesis, University of Malaya.

PDF (Thesis M.A)
Download (2398Kb) | Preview


    Processing time estimation of a machining process is a crucial task in order to gain higher profits, stand out amongst the competition and also grow the customer portfolio in precision machining industry. By having an accurate processing time estimation, a wellplanned production schedule can be established and machine capacity availability can be checked to meet customer�s estimated time of delivery (ETD). These time estimations are usually done and revised by a tooling process expert. However, the estimation of each and every individual is different based on their knowledge and experiences. In this research, a system is designed to estimate processing time by using artificial intelligence knowledge. Wire electrical discharge machining (WEDM) process is focused and the time taken for the processing is analysed. Input variables such as material type of job, size of copper wire used to run the process, operation mode set for the WEDM machine, number of cuts and the thickness of workpiece are considered as important in estimating the processing time. The objectives of this project are to design a system for processing time estimation, to estimate the processing time required for specific machining process and to verify the accuracy of processing time estimation. Neural Network (NN) model is chosen as the artificial intelligence approach used in this research. Levenberg-Marquardt algorithm is used as the training algorithm. The results show that the data best validation performance is 7.1085 at epoch 27. An AI approach for processing time estimation by implementing desired input parameters and machining data is tested and completed. Keywords: artificial intelligence, artificial neural network, precision machining, time estimation

    Item Type: Thesis (Masters)
    Additional Information: Thesis (M.A.) - Faculty of Engineering, University of Malaya, 2017.
    Uncontrolled Keywords: Artificial intelligence; Artificial neural network; Precision machinine estimation.
    Subjects: T Technology > T Technology (General)
    T Technology > TJ Mechanical engineering and machinery
    Divisions: Faculty of Engineering
    Depositing User: Mr Prabhakaran Balachandran
    Date Deposited: 14 Feb 2019 08:31
    Last Modified: 16 Jun 2020 03:40

    Actions (For repository staff only : Login required)

    View Item