The present study highlights a multi-objective optimization problem by applying utility concept coupled with Taguchi method through a case study in CNC end milling of UNS C34000 medium leaded brass. ...The study aimed at evaluating the best process environment which could simultaneously satisfy multiple requirements of surface quality. In view of the fact, the traditional Taguchi method cannot solve a multi-objective optimization problem; to overcome this limitation, utility theory has been coupled with Taguchi method. Depending on Taguchi’s Lower-the-Better (LB) response criteria; individual surface quality characteristics has been transformed into corresponding utility values. Individual utility values have been aggregated finally to compute overall utility degree which serves as representative objective function for optimizing using Taguchi method. Utility theory has been adopted to convert a multi-response optimization problem into a single response optimization problem; in which overall utility degree serves as the representative single objective function for optimization. The study of combined utility theory and Taguchi method for predicting optimal setting. Based on Taguchi’s Signal-to-Noise ratio (S/N), analysis has been made on the overall utility degree and optimal process environment has been selected finally which corresponds to highest S/N Ratio. Optimal result has been verified through confirmatory test. The case study indicates application feasibility of the aforesaid methodology proposed for multiresponse optimization and off-line control of multiple surface quality characteristics in CNC end milling.
A MEMS capacitive sensor is emulated on a PCB for quick validation of CMOS interface circuit. In capacitive sensor, capacitance changes with external force; to mimic similar changes, controlled ...magnetic field is applied on emulated PCB capacitor. The dimension optimizations of interdigital capacitor are performed using CST software. The simulated values are milled on a FR4 sheet to make PCB capacitor. The simulated capacitance values are cross checked by making measurement using LCR meter on PCB capacitor and have a deviation of 6.5%. The complete MEMS emulator consists of PCB capacitor, permanent magnet controlled by screw gauge and gauss meter. A minimum change of 50 aF achieved over a base capacitance 1.9 pF.
Traditional relational databases contain a lot of latent semantic information that have largely remained untapped due to the difficulty involved in automatically extracting such information. Recent ...works have proposed unsupervised machine learning approaches to extract such hidden information by textifying the database columns and then projecting the text tokens onto a fixed dimensional semantic vector space. However, in certain databases, task-specific class labels may be available, which unsupervised approaches are unable to lever in a principled manner. Also, when embeddings are generated at individual token level, then column encoding of multi-token text column has to be computed by taking the average of the vectors of the tokens present in that column for any given row. Such averaging approach may not produce the best semantic vector representation of the multi-token text column, as observed while encoding paragraphs or documents in natural language processing domain. With these shortcomings in mind, we propose a supervised machine learning approach using a Bi-LSTM based sequence encoder to directly generate column encodings for multi-token text columns of the DrugBank database, which contains gold standard drug-drug interaction (DDI) labels. Our text data driven encoding approach achieves very high Accuracy on the supervised DDI prediction task for some columns and we use those supervised column encodings to simulate and evaluate the Analogy SQL queries on relational data to demonstrate the efficacy of our technique.