A grey prediction fuzzy controller for constant cutting force in turning

Lian, Ruey-Jing; Lin, Bo-Wen; Huang, Jyun-Han

doi:10.1016/j.ijmachtools.2004.11.023

Cited by 55 publications

(28 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Higher GRD signifies the input parameters corresponding to run no 16 provide superior performance. IJETST-Vol.||04||Issue||08||Pages 5487-5494||August||ISSN 2348-9480 2017 [16]. The decrease of improbability present in the GRD can be carried out by formulating Grey-fuzzy reasoning grade (GFRD) using the fuzzy inference system [17].…”

Section: Resultsmentioning

confidence: 99%

Performance evaluation of TiN coated CBN inserts during hard turning of AISI 4340 steel with using Taguchi-Grey-Fuzzy approach

Kumar¹

2017

ijetst

View full text Add to dashboard Cite

This Hard turning finds a broad range of applications in manufacturing industries. The high wear resistance along with high dimensional accuracy is the primary attributes of the process. However, the critical setback associated with hard turning is the high heat generation at the cutting zone. It lead to earlier tool wear rate and causes the decrease in the machining performance. The cutting tool material plays a significant role in deciding the performance of hard turning. Therefore in this research work, an attempt has been made to investigate the performance of TiN coated CBN tools during machining of variable hardened AISI 4340 steel. The cutting speed, feed rate, workpiece hardness and cutting tools (uncoated CBN and TiN coated CBN) were selected as process parameters during experimentation. The cutting force, chip-tool interface temperature and material removal rate (MRR) was selected as performance parameters. The L-18 orthogonal array from Taguchi approach was chosen to perform the experimental work. The grey relational technique was used to optimize the process parameters. The results from the grey relational model were verified by using fuzzy logic. The experimental results indicate that tool material and feed rate are the significant process variables which influence the machining performance.

show abstract

Section: Resultsmentioning

confidence: 99%

Performance evaluation of TiN coated CBN inserts during hard turning of AISI 4340 steel with using Taguchi-Grey-Fuzzy approach

Kumar¹

2017

ijetst

View full text Add to dashboard Cite

show abstract

“…Baradie concluded that the availability of the machining data for development of algorithms for soft computing techniques will aid in exploring and expanding the automated manufacturing system. Ruey-Jing Lian et al (2005) applied the grey theory algorithm to fuzzy control system to maintain a constant cutting force in turning operation on traditional lathe machine which was installed with load cell to measure the cutting force, servo motors to control feed rod action and induction motor to control the spindle speed. Mathematical model was developed by keeping the feed rate constant to determine the cutting force.…”

Section: Fuzzy Logicmentioning

confidence: 99%

Review on Optimization Techniques used for Determining Machining Conditions to get Effective Tool Life and Surface Finish

Kumar¹

2017

DAAAM International Scientific Book

View full text Add to dashboard Cite

“…A larger order n increases the generation time exponentially, but may not assure improvement of prediction accuracy. Hence, the GMð1; 1Þ model with first-order ODE is widely adopted for single-output control systems (Lian et al, 2005).…”

Section: Grey Theorymentioning

confidence: 99%

“…The use of a big N in LSQ estimation results in more excessive prediction, which reduces the rising time significantly but with the penalty of overshoot and oscillation in the transient state. The prediction accuracy is independent of the memory horizon, N. The corresponding computing time increases exponentially with the number of data sets (Lian et al, 2005). Thus, this study adopted the most recent four output responses, namely y½k À 3; y½k À 2; y½k À 1 and y½k, to estimate the next-step responseŷ½k þ 1.…”

Section: System Implementationmentioning

confidence: 99%