Study published in the international journal “Sensors” (Section Smart Agriculture) by CREA-IT (Rome), CREA-AA (Padua) and University of Tuscia (Viterbo).
“Sensors” is the leading international, peer-reviewed, open access journal on the science and technology of sensors. Sensors is published semimonthly online by MDPI.
Automated prototype for Bombyx mori cocoon sorting attempts to improve silk quality and production efficiency through multi-step approach and machine learning algorithms
ABSTRACT
Cocoon sorting is one of the most labor-demanding activities required both at the end of the agricultural production and before the industrial reeling process to obtain an excellent silk quality. In view of the possible relaunch of European sericulture, the automatization of this production step is mandatory both to reduce silk costs and to standardize fiber quality. The described research starts from this criticality in silk production (the manual labor required to divide cocoons into different quality classes) to identify amelioration solutions.
To this aim, the automation of this activity was proposed, and a first prototype was designed and built. This machinery is based on the use of three cameras and imaging algorithms identifying the shape and size of the cocoons and outside stains, a custom-made light sensor and an AI model to discard dead cocoons. The current efficiency of the machine is about 80 cocoons per minute. In general, the amelioration obtained through this research involves both the application of traditional sensors/techniques to an unusual product and the design of a dedicated sensor for the identification of dead/alive pupae inside the silk cocoons. A general picture of the overall efficiency of the new cocoon-sorting prototype is also outlined.
CONCLUSIONS
Silk textile processing represents an agro-based industry engaged in manufacturing primary (cocoons) and secondary (silk skeins) products of agriculture. Like other industrial chains, it needs the standardization of the raw material to obtain high-quality goods for consumers. As cocoons are obtained through a biological activity from living organisms, they cannot be perfectly homogenous, and farmers should intervene in their selection through a high-labor and cost-demanding manual method. The mechanization of this operation can lower the production costs consistently and contribute to increasing the quality of the obtained silk.
Therefore, the prototype described in this paper might be enlisted among the current efforts in reintroducing sericultural activity in Europe through regional and European projects based on the transfer of research innovations into practice and aimed at increasing the added value of the fiber intended for use in the textile luxury market or new smart applications. This prototype is a good workbench for future applications developed with new sensors or new AI algorithms, and it offers a chance to consistently improve the actual techniques used in cocoon sorting.
Moreover, From the performance perspective, is possible to improve the accuracy of the machine, increasing the length of the belt, thus adding more control stations for cocoons processing. The speed of the selection process can be increased by adding one or more machines in parallel, all synced with each other, leading to a higher cocoons-per-minute rate.
FUNDING
This research was funded by Veneto Region, Measure 16.1-2 Programme of Rural Development for the Veneto Region, 2014-2020-DGR 2175 del 23 December 2016, grant number:55-04/12/2017 SERINNOVATION.
Authors
Simone Vasta (1), Simone Figorilli (1), Luciano Ortenzi (1,2), Simona Violino (1), Corrado Costa (1), Lavinia Moscovini (1), Francesco Tocci (1), Federico Pallottino (1), Alberto Assirelli (1), Alessio Saviane (3), Silvia Cappellozza (3).
(1) Council for Agricultural Research and Economics, Research Centre for Engineering and Agro-Food Processing (CREA-IT) – Monterotondo, Rome – Italy
(2) Department of Agricultural and Forestry Sciences (DAFNE), Tuscia University of Viterbo – Italy
(3) Council for Agricultural Research and Economics, Research Centre for Agriculture and Environment (CREA-AA) – Sericulture Laboratory of Padua – Italy