FPGA implementation of predictive degradation model for engine oil lifetime

International Conference on Applied Electronic and Engineering 2017

无线电电子学;工业技术

Idros, M.F.M.^1,2 ; Razak, A.H.A.^1,2 ; Junid, S. A. M. Al^1,2 ; Suliman, S.I.^2 ; Halim, A.K.^1,2

Electronic Architecture and Application (EArA), Research Group, Malaysia^1

Faculty of Electrical Engineering, Universiti Teknologi, MARA, Shah Alam Selangor

40450, Malaysia^2

关键词: Degradation model;    Degradation predictions;    Engine oil;    FPGA implementations;    Least square methods;    Linear regression models;    Online monitoring;    Time series method;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/341/1/012024/pdf
DOI  :  10.1088/1757-899X/341/1/012024

学科分类：工业工程学

来源: IOP

【 摘 要 】

This paper presents the implementation of linear regression model for degradation prediction on Register Transfer Logic (RTL) using QuartusII. A stationary model had been identified in the degradation trend for the engine oil in a vehicle in time series method. As for RTL implementation, the degradation model is written in Verilog HDL and the data input are taken at a certain time. Clock divider had been designed to support the timing sequence of input data. At every five data, a regression analysis is adapted for slope variation determination and prediction calculation. Here, only the negative value are taken as the consideration for the prediction purposes for less number of logic gate. Least Square Method is adapted to get the best linear model based on the mean values of time series data. The coded algorithm has been implemented on FPGA for validation purposes. The result shows the prediction time to change the engine oil.