Improving Efficiency Through Data Selection for Remote Injection Molding Condition Monitoring Systems Using the Mahalanobis–Taguchi Method
Keigo Kudo et al.
What the paper says
Injection molding is the most common method for manufacturing plastic products. However, products made by injection molding often exhibit various molding defects. One major contributing factor to these defects is mold temperature, especially at the cavity section where the resin enters. In our laboratory’s research, the feasibility of measuring the cavity temperature using non-contact thermometers by making simple modifications around the mold cavity area was investigated. It was also examined whether it is possible to distinguish between normal and defective molded products—specifically those with short shots—based on this temperature data. Analyzing data from predefined temperature measurement points raises concerns about significantly increased computation times. For remote monitoring applications, it is necessary to reduce the number of measurement points to decrease data volume. In this paper, an attempt is made to reduce the number of measurement points used in analysis by selecting items with an orthogonal array. As a result, the number of measurement points for analysis was reduced by 55%, thereby decreasing computation time and achieving favorable results for implementing a remote monitoring system equipped with defect detection functionality, which is reported here.
Evidence weight
Balanced mode · F 0.40 / M 0.15 / V 0.05 / R 0.40
| F · citation impact | 0.50 × 0.4 = 0.20 |
| M · momentum | 0.50 × 0.15 = 0.07 |
| V · venue signal | 0.50 × 0.05 = 0.03 |
| R · text relevance † | 0.50 × 0.4 = 0.20 |
† Text relevance is estimated at 0.50 on the detail page — for your query’s actual relevance score, open this paper from a search result.