Indirect cutting tool wear classification using deep learning and chip colour analysis

In the growing Industry 4.0 market, there is strong need to implement automatic inspection methods to support manufacturing processes. Tool wear in turning is one of the biggest concerns that most expert operators are able to indirectly infer through the analysis of the removed chips. Automatising this operation would enable developing more efficient cutting processes that turns in easier process planning management toward the Zero Defect Manufacturing paradigm. This paper presents a deep learning approach, based on image processing applied to turning chips for indirectly identifying tool wear levels. The procedure extracts different indicators from the RGB and HSV image channels and instructs a neural network for classifying the chips, based on tool state conditions. Images were collected with a high-resolution digital camera during an experimental cutting campaign involving tool wear analysis with direct microscope imaging. The sensitivity analysis confirmed that the most sensible image channels are the hue value H that were used to teach the network, leading to performances in the range of 95 of proper classification. The feasibility of the deep learning approach for indirectly understanding the tool wear from the chip colour characterisation is confirmed. However, due to the big effects on chip colours of variables as the workpiece material and cutting process parameters, the applicability is limited to stable production flows. An industrial implementation can be foreseen by populating proper large databases and by implementing real-time chip segmentation analysis.

Genetic Variability Among the Potato (Solanum tuberosum L.) Genotypes as Affected by Harvesting Period for Processing Purpose and Tuber Yield

The experiment was conducted in Randomized Block Design (RBD) with three replications in two sets of harvest period i.e. 90 and 105 days after planting (DAP) for tuber yield and processing traits in potato. The analysis of variance revealed that mean sum of squares due to genotypes was found highly significant for all the traits under study. The genotypes of MS/06-1947, K. Sadabahar and K. Khyati for 90 days and J/10-162, K. Sadabahar and MP/06-39 for 105 DAP were found promising for tuber yield per plant based on per se performance. The genotypes of MP/09-901, MP/04-578 and MP/04-816 exhibited high tuber dry matter, while, the genotypes, K. Himsona, K.Chipsona 1 and K.Chipsona 2 had low reducing sugar under both 90 and 105 days of harvest. The low chip colour index was exerted by genotypes of K. Chipsona 2, K. Chipsona 1, K. Chipsona 3, K. Chipsona 4 and K. Frysona under 90 days, whereas, K. Chipsona 2, Atlantic and K. Chipsona 3 under 105 days of harvest. Therefore, these genotypes suited as processing purpose. The high heritability along with high genetic advance in leaf area, number of stems per hill, number of tubers per plant, processing grade tuber yield per plant, chip colour index, reducing sugar and total soluble solids under both harvesting periods, recommended that genotypic difference for the characters ascribed to high additive genetic cause and selection would be wrathful based on phenotypic performance.

Chipping quality of potatoes stored in heaps and pits in subtropical plains of India

Two potato cultivars Kufri Bahar and Kufri Jyoti were stored in heaps and pits under ambient conditions of sub-tropical plains of northern India and their chipping quality was determined after 90 days of storage. During storage there was a significant reduction (33.84%) in the reducing sugar content of potatoes and improvement (31.63%) in chip colour. Sugar levels in stored potatoes were within the acceptable limit for processing and table purposes indicating that potatoes stored up to 90 days on the farm in heap and pits are suitable for these two purposes.  

Genotype × environment interaction of potato chip colour

Ten potato genotypes were tested in replicated trials over three sites in New Brunswick. Five of them were tested in 1991, 1992 and 1993, and another five in 1992 and 1993. Tubers were harvested and put in storage rooms with two temperature regimes: 7 °C and 13 °C. Prior to testing glucose content and chip colour, a portion of tubers stored in 7 °C was sampled and subjected to reconditioning for 2 and 4 wk in a storage room with the temperature regime of 21 °C. High relative humidity (>80%) was maintained in all storage rooms. Glucose and colour score of chips were determined during November in each of the three years. Analysis of variance revealed genotype × environment interactions for both traits. Since variation of chip colour is controlled primarily by glucose content in potatoes, this causal relationship was used as a basis to perform path regression analysis for each of the genotypes, based on all available data of the two traits. The regression equation is composed of two terms: an average chip score over environments (µ) and a multiplicative term with a genotypic coefficient (g) and an environmental index (r); µ measures the overall chipping ability, whereas g responds to environment and thus represents chipping stability. The 10 genotypes were different from one another on estimates of both parameters. The estimates of r showed lesser differences between the three test sites than between storage-temperature regimes. Storing potatoes at 13 °C and 7 °C gave the best and worst chip-colour scores, respectively. Reconditioning at 21 °C after storing at 7 °C improved the colour performance. No clear association was observed between chip colour, specific gravity and marketable yield. Good chipping genotypes tested in the experiment, however, had lower yields than others. The present results indicate that path regression analysis is an effective method for detecting the role of glucose content in the control of the expression of chip colour. Key words: Potato, Solanum tuberosum, chip colour, glucose content, storage