The dominance-based rough set approach to cylindrical plunge grinding process diagnosis

Abstract

The dominance-based rough set approach is proposed as a methodology for plunge grinding process diagnosis. The process is analyzed and next its diagnosis is considered as a multi-criteria decision making problem based on the modelling of relationships between different process states and their symptoms using a set of rules induced from measured process data. The development of the diagnostic system is characterized by three phases. Firstly, the process experimental data is prepared in the form of a decision table. Using selected methods of signal processing, each process running is described by 17 process state features (condition attributes) and 5 criteria evaluating process state and results (decision attributes). The semantic correlation between all the attributes is modelled. Next, the phase of condition attributes selection and knowledge extraction are strictly integrated with the phase of the model evaluation using an iterative approach. After each loop of the iterative feature selection procedure the induction of rules is conducted using the VC-DomLEM algorithm. The classification capability of the induced rules is carried out using the leave-one-out method and a set of measures. The classification accuracy of individual models is in the range of 80.77-98.72 %. The induced set of rules constitutes a classifier for an assessment of new process run cases.

Investigation into Hand Scraping: A Microanalysis

“…Being a surface finishing process, hand scraping can be compared to other such processes that are based on cutting. While grinding [5,6] and honing are processes with grain kinematics defined by the tool and the machine motion [7], lapping and abrasive flow machining [8] are operating with free grains. All of the above mentioned processes can be categorized as chip removal with geometrically undefined cutting edges and are designed to generate surfaces with minimal roughness and waviness and-in the case of grinding and lapping-good evenness.…”

A data-driven predictive model of the grinding wheel wear using the neural network approach

“…The ANN could also be used for wheel condition modelling and estimation. The Dominance-based Rough Set Approach (DRSA) is proposed as a methodology for plunge grinding process diagnosis including the state of grinding wheel catting ability in [16]. A set of decision rules modeling the WCS wear propagation considering changes in its waviness and topography was generated based on a feature set extracted from the 14 features of measured signals.…”

“…Grinding monitoring data were collected during tests carried out on a modified cylindrical grinding machine equipped with adequate control and measurement units [16,21]. During the tests the workpieces made of 38HMJ steel hardened to 53 HRC were ground using the 38A80KVBE grinding wheel.…”

“…The 3000R Gap Dittel wireless AE was applied for the measurement of the raw and, after an analogue RMS circuit processing, the RMS value of the AE signal. This sensor was attached to the face of the grinding wheel spindle [16,21].…”

“…For reliable multi-criteria assessment of the process state, the STATISTICA and a software package called the DAQSYSTEM developed in LabVIEW environment were used to calculate 14 statistical and spectral features of the measured on-line signals [16].…”