Use of artificial neural network and multi-objective genetic algorithm approach to predict and ascertain stable cutting zone in conventional turning process

Abstract

This article is focused on the investigation of stable cutting zone in turning operation. Experiments have been conducted to acquire raw chatter signals. Generally, raw chatter signals are contaminated with ambient noise. Wavelet transform has been used for preprocessing and denoising these signals. In order to predict the severity of tool chatter, a new parameter denoted as chatter index has been evaluated considering the aforesaid denoised signals. In the present work, mathematical models have been developed for chatter index and metal removal rate using feedforward backpropagation-based artificial neural network considering three activation functions: TANSIG, LOGSIG and PURELIN. Furthermore, multi-objective genetic algorithm technique has been applied to evaluate stable cutting zones with maximized metal removal rate. TANSIG activation function found to be best option to achieve the aforesaid objectives. Good correlation between the artificial neural network predicted results and experimental ones validate the developed technique.

Ride performance of driver’s seat suspension system using various dynamics models

“…This is also the reason that the NSE and NSE-SM were researched and embedded into the seat suspension, [9][10][11][12][13][14][15][16][17][18][19][20] concurrently, the damping coefficients of the vehicle suspension systems were independently controlled. [2][3][4][5][6][7][8] However, combining both the NSE-SM and the control of the damping coefficient c s for the seat suspension has not been considered. Thus, this issue needs to be further studied in future work.…”

“…Equation (15) could be also rewritten by:where normalΓ∼, λ 1 , and λ 2 have been defined in equation (6).…”

“…In order to ameliorate the ride performance of the vehicles, the traditional suspensions of the seat and cab were replaced by using the air spring or semi-active seat suspension with its controlled damping coefficient had been researched. 1,2 The optimal control methods of the genetic algorithm and cultural algorithm-fuzzy controls [3][4][5] or the combined control methods of the fuzzy-PID control, machine learning algorithm, and neuro-fuzzy [6][7][8] had been also researched to further enhance the vehicle's ride comfort as well as the seat suspension's performance. The study results indicated that the vehicle's ride performance was remarkably ameliorated by semi-active suspensions.…”

A comparative study of isolation performance of electric automobile seat’s suspension added by negative-stiffness structure models

“…The ride quality of the vehicle had been mainly assessed based on the quarter vehicle model or half vehicle model. 2,5,[9][10][11] However, the ride quality of the driver's seat is affected by the vibration excitations from four wheels and four IWM of the EA. Thus, to evaluate the isolation performance of NSS-TMD and NSS-AP on improving the EA's ride quality, a three-dimensional dynamics model of the EA is built in Figure 1 to calculate the vehicle's mathematical equations.…”

“…With the suspension system of the driver's seat used on traditional vehicles, the air-spring of the suspension seat and controlled suspension of the driver's seat were studied and applied to further ameliorate the ride quality. [9][10][11] The ride quality of the driver was significantly ameliorated in comparison with the passive seat suspension. Moreover, a simple structure of the negative-stiffness structures (NSS) was also researched and added into the passive suspension system of the driver's seat to improve the vehicle's ride quality.…”