{"references": ["S. Sinha, P. Franciosa, and D. Ceglarek, \"Object Shape Error Response using Bayesian 3D Convolutional Neural Networks for Assembly Systems with Compliant Parts,\" IEEE Trans. Ind. Informatics, 2020, doi: 10.1109/TII.2020.3043226.", "S. Sinha, E. Glorieux, P. Franciosa, and D. Ceglarek, \"3D convolutional Neural networks to estimate assembly process parameters using 3D point-clouds,\" in Proceedings of SPIE, 2019, vol. 11059, doi: 10.1117/12.2526062.", "P. Franciosa, M. Sokolov, S. Sinha, T. Sun, and D. Ceglarek, \"Deep learning enhanced digital twin for Closed-Loop In-Process quality improvement,\" CIRP Ann., vol. 69, no. 1, pp. 369\u2013372, Jan. 2020, doi: 10.1016/j.cirp.2020.04.110.", "P. Franciosa et al., \"A novel hybrid shell element formulation (QUAD+ and TRIA+):A benchmarking and comparative study,\" Finite Elem. Anal. Des., vol. 166, 2019, Art. no. 103319.", "S. Sinha, P. Franciosa, and D. Ceglarek, \"Bayesian deep learning for manufacturing,\" 2020. [Online]: Available. https://github.com/sumitsinha/Deep_Learning_for_Manufacturing"]}

The dataset consists of supervised shape error datasets (point clouds) and corresponding process parameters. It is genrated using the Variation Response Method (VRM) kernel. The dataset can be used for training deep learning frameworks to test performance for Root Cause Analysis (RCA) of Multi-Station Assembly Systems. The python library for implementation of the work can be found at this link: https://github.com/sumitsinha/Deep_Learning_for_Manufacturing