Data Mining - Concepts and Techniques.

Ensemble machine learning model for corrosion initiation time estimation of embedded steel reinforced self-compacting concrete

Machine and production line operations, systems analysis, manufacturing planning, quality control, information infrastructure

Manufacturing Engineering Technology

Undergraduate teaching audit and evaluation (UTAE) is a new type of evaluation pattern, which is extremely important for a university to improve its quality assurance system and enhance teaching quality. Selecting an optimal university for benchmarking through UTAE to promote the quality of teaching can be regarded as a complex multicriteria decision making (MCDM) problem. Furthermore, in the process of UTAE, experts' evaluations over the teaching quality of universities are often imprecise and fuzzy due to the subjective nature of human thinking. In this paper, we propose a new UTAE approach based on q‐rung orthopair fuzzy sets and the multiattribute border approximation area comparison (MABAC) method for evaluating and selecting the best university for benchmarking. The introduced method deals with the linguistic assessments given by experts by using q‐ROFSs, assigns the weights of audit elements based on the indifference threshold‐based attribute ratio analysis method, and acquires the ranking of universities with an extended MABAC method. The feasibility and effectiveness of the proposed q‐rung orthopair fuzzy MABAC method is demonstrated through a realistic UTAE example. Results show that the UTAE method being proposed is valid and practical for UTAE.

Undergraduate teaching audit and evaluation using an extended MABAC method under q‐rung orthopair fuzzy environment

Occupational health and safety (OHS) is a systemic and multidisciplinary activity for anticipating, recognizing, evaluating and controlling the hazards that may impair the health of workers. Risk assessment of hazards plays a critical role in the OHS. However, due to the vagueness and uncertainty of information, it is difficult for experts to express their opinions with crisp numbers in the risk assessment process. In this paper, we present a new OHS model, which integrates bipolar fuzzy sets (BFSs) and multi-attributive border approximation area comparison (MABAC) method, for the risk assessment of occupational hazards. Specifically, the BFSs are utilized to deal with the vague and uncertain assessment information of hazards provided by experts and the MABAC method is used to determine the risk ranking of hazards. Moreover, we extend the stepwise weight assessment ratio analysis (SWARA) method with BFSs to obtain the weights of risk criteria. Finally, the occupational hazard risk assessment example on construction sites is conducted and a comparative analysis is performed to verify the effectiveness and availability of our proposed OHS model. The results show that the new integrated model provides a more effective and practical method for the risk prioritization of occupational hazards in OHS.

Occupational health and safety risk assessment using an integrated SWARA-MABAC model under bipolar fuzzy environment

Non-traditional machining processes selection and evaluation: A rough multi-attributive border approximation area comparison approach

With continuous automation of the manufacturing industries and the development of advanced data acquisition systems, a huge volume of manufacturing-related data is now available which can be effectively mined to extract valuable knowledge and unfold the hidden patterns. In this paper, a data mining tool, in the form of the rough sets theory, is applied to a grinding process to investigate the effects of its various input parameters on the responses. Rotational speed of the grinding wheel, depth of cut and type of the cutting fluid are grinding parameters, and average surface roughness, amplitude of vibration and grinding ratio are the responses. The best parametric settings of the grinding parameters are also derived to control the quality characteristics of the ground components. The developed decision rules are quite easy to understand and can truly predict the response values at varying combinations of the considered grinding parameters.

http://casopisi.junis.ni.ac.rs/index.php/FUMechEng/article/download/5869/3494

Parametric analysis of a grinding process using the rough sets theory

The quality of cotton fibre is often characterized by its various physical properties, like bundle strength, elongation at break, fineness, mean length, maturity ratio, short fibre content, neps etc As cotton is a natural fibre, all of its properties are always subjected to variation, thereby, influencing the characteristics of the final yarn In this paper, these cotton fibre properties are analyzed in details using various tools of data mining Decision tree is at first developed so as to identify the most predominant property affecting the spinnability of cotton fibres It is also adopted to study the effects of different cotton fibre properties on yarn tenacity and unevenness The developed dendograms help in identifying pairs or groups of cotton fibres having almost similar properties On the other hand, cluster analysis acts as a visual decision aid in segregating the considered cotton fibres into different groups having maximum intraclass similarity and minimum interclass similarity to determine the constituent fibres in the final blend These data mining techniques can also be implemented to study the physical characteristics of other natural fibres

Analysis of Cotton Fibre Properties: A Data Mining Approach

Non-traditional machining (NTM) processes have already emerged out as the suitable substitutes for the conventional metal removal methods due to their capability of generating complicated shape geometries on diverse difficult-to-machine engineering materials. For these NTM processes, it is always proposed that they should be operated while setting their various input parameters at the optimal levels for achieving better machining performance. In this paper, the application of a data mining tool in the form of development of association rules is explored to determine the best machining conditions for three NTM processes, i.e. electrochemical machining process, ultrasonic machining process and electrical discharge machining process. These rules, presented as simple ‘If-Then’ statements, would also guide the concerned process engineers in investigating the effects of various NTM process parameters on the considered responses. It is observed that the most preferred parametric combinations identified based on the generated association rules closely match with those as perceived by the past researchers.

/pdf/development-of-association-rules-to-study-the-parametric-3q1o3v9i7w.pdf

Development of association rules to study the parametric influences in non-traditional machining processes

Due to several unique characteristics, such as high tensile strength, low extensibility, high frictional resistance, biodegradability, eco-friendliness and cheapness, Jute ranks second just after cotton with respect to its worldwide consumption and production. To overcome the difficulties of the existing Jute grading procedure, this paper aims to focus on the application of decision-making trial and evaluation laboratory (DEMATEL) and multi-attributive border approximation area comparison (MABAC) methods for evaluation of 10 Tossa Jute fiber lots based on strength, defects, root content, color, fineness and bulk density properties.,The DEMATEL method divides all the six physical properties of Jute fiber into cause and effect groups. The most influencing property is also identified. On the other hand, the considered Jute fiber lots are ranked using MABAC method along with the identification of the strengths and weaknesses of each of them.,This combined approach would provide a more scientific and realistic way of Jute grading and evaluation based on various properties of the considered Jute fiber lots. The positions of the superior and the inferior Jute lots perfectly match with those as identified by the earlier researchers.,It is concluded that the adopted combined decision-making tool can be effectively applied for grading and evaluation of other natural fibers with diverse heterogeneous physical properties.

Subham Agarwal

Papers

Non-traditional machining processes selection and evaluation: A rough multi-attributive border approximation area comparison approach

Parametric analysis of a grinding process using the rough sets theory

Analysis of Cotton Fibre Properties: A Data Mining Approach

Development of association rules to study the parametric influences in non-traditional machining processes

A DEMATEL-MABAC-based approach for grading and evaluation of jute fibers