×

The application of a two-step AI model to an automated pneumatic drilling process. (English) Zbl 1192.68721

Summary: Real-world processes may be improved through a combination of artificial intelligence and identification techniques. This work presents a multidisciplinary study that identifies and applies unsupervised connectionist models in conjunction with modelling systems. This particular industrial problem is defined by a data set relayed through sensors situated on a robotic drill used in the construction of industrial storage centres. The first step entails determination of the most relevant structures in the data set with the application of the connectionist architectures. The second step combines the results of the first one to identify a model for the optimal working conditions of the drilling robot that is based on low-order models such as black box that approximate the optimal form of the model. Finally, it is shown that the most appropriate model to control these industrial tasks is the Box-Jenkins algorithm, which calculates the function of a linear system from its input and output samples.

MSC:

68T99 Artificial intelligence
68U99 Computing methodologies and applications
68P05 Data structures
68T05 Learning and adaptive systems in artificial intelligence
PDFBibTeX XMLCite
Full Text: DOI Link

References:

[1] DOI: 10.1007/BF02911655 · Zbl 0198.51202 · doi:10.1007/BF02911655
[2] DOI: 10.1142/S0218001403002915 · doi:10.1142/S0218001403002915
[3] DOI: 10.1080/09528130310001611603 · Zbl 1105.68368 · doi:10.1080/09528130310001611603
[4] DOI: 10.1023/B:DAMI.0000023673.23078.a3 · Zbl 05660825 · doi:10.1023/B:DAMI.0000023673.23078.a3
[5] DOI: 10.1214/aos/1176346703 · Zbl 0559.62002 · doi:10.1214/aos/1176346703
[6] DOI: 10.1109/T-C.1974.224051 · Zbl 0284.68079 · doi:10.1109/T-C.1974.224051
[7] Fyfe, C. 1993.PCA Properties of Interneurons: From Neurobiology to Real World Computing, Vol. 93, 183–188. Amsterdam, The Netherlands: Springer-Verlag. Proceedings of the International Conference on Artificial Neural Networks (ICANN 1993)
[8] Fyfe, C. and Corchado, E. 2002.Maximum Likelihood Hebbian Rules, 143–148. Bruges, Belgium: d-side Publishers. Proceedings of the 10th European Symposium on Artificial Neural Networks (ESANN 2002)
[9] Haber R., Nonlinear System Identification, Input–Output Modeling Approach, Part 2: Nonlinear System Structure Identification (1999) · Zbl 0934.93004
[10] Haber R., Nonlinear System Identification, Input–Output Modeling Approach, Part 1: Nonlinear System Parameter Estimation (1999) · Zbl 0934.93004
[11] He, X. and Asada, H. 1993. Proceedings of the American Control Conference. 1993, S. F, California. A New Method for Identifying Orders of Input–Output Models for Nonlinear Dynamic Systems, pp.2520–2523.
[12] DOI: 10.1037/h0071325 · doi:10.1037/h0071325
[13] Ljung L., System Identification, Theory for the User,, 2. ed. (1999) · Zbl 0615.93004
[14] Lorenzo, M., Bravo, P. and Preciado, M. 2004. ”Parametrización del Corte en Hormigón Fuertemente Armado Mediante Coronas de Diamante”. Spain IX Congreso Nacional de Propiedades Mecánicas de Sólidos
[15] Nelles O., Nonlinear System Identification, from Classical Approaches to Neural Networks and Fuzzy Models (2001) · Zbl 0963.93001
[16] DOI: 10.1007/978-1-4471-0453-7 · doi:10.1007/978-1-4471-0453-7
[17] DOI: 10.1007/BF00275687 · Zbl 0488.92012 · doi:10.1007/BF00275687
[18] DOI: 10.1080/14786440109462720 · doi:10.1080/14786440109462720
[19] Seung H. S., Adv. Neural Inf. Processing Syst. 10 pp 350– (1998)
[20] Söderström T., System Identification (1989)
[21] Stoica P., IEEE Trans. Automatic. Control 27 (1982)
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.