Robot sensor failure detection system based on convolutional neural networks for calculation of Euler angles

• Autorzy: Świetlicka A. , Kolanowski K.

Identyfikatory

DOI

10.24425/bpasts.2020.135389

• Języki publikacji: EN

Abstrakty

EN

In this work, we present a failure detection system in sensors of any robot. It is based on the k-fold cross-validation approach and built from N neural networks, where N is the number of signals read from sensors. Our tests were carried out using an unmanned aerial vehicle (UAV, quadrocopter), where signals were read from three sensors: accelerometer, magnetometer and gyroscope. Artificial neural network was used to determine Euler angles, based on signals from these sensors. The presented system is an extension of the system that we proposed in one of our previous papers. The improvement shown in this work took place on two levels. The first one was related to improvement of a neural network՚s reproduction quality – we have replaced a recurrent neural network with a convolutional one. The second level was associated with the improvement of the validation process, i.e. with adding some new criteria to check the values of Euler՚s angles determined by the convolutional neural network in subsequent time steps. To highlight the proposed system improvement we present a number of indicators such as RMSE, NRMSE and NDR (Normalized Detection Ratio).

Słowa kluczowe

EN

quadrocopter; convolutional neural network; AHRS; attitude heading reference system

PL

quadrocopter; splotowa sieć neuronowa; AHRS; układ odniesienia kursu położenia

• Wydawca: Polska Akademia Nauk, Wydział IV Nauk Technicznych
• Czasopismo: Bulletin of the Polish Academy of Sciences. Technical Sciences
• Rocznik: 2020
• Tom: Vol. 68, nr 6
• Strony: 1525--1533
• Opis fizyczny: Bibliogr. 39 poz., rys., tab.

Twórcy

autor

Świetlicka A.

• Institute of Automation and Robotics, Poznan University of Technology, Piotrowo 3A, 60-965 Poznań, Poland

autor

Kolanowski K.

• Institute of Automation and Robotics, Poznan University of Technology, Piotrowo 3A, 60-965 Poznań, Poland

Bibliografia

• [1] Z. Hendzel, “Collision free path planning and control of wheeled mobile robot using kohonen self-organising map”, Bull. Pol. Ac.: Tech. 53(1), 39–47 (2005).
• [2] R. Kapela, A. Świetlicka, K. Kolanowski, J. Pochmara, and A. Rybarczyk, “A set of dynamic artificial neural networks for robot sensor failure detection”, in 2017 11th International Workshop on Robot Motion and Control (RoMoCo), 2017, pp. 199‒204.
• [3] K. Kolanowski, A. Świetlicka, R. Kapela, J. Pochmara, and A. Rybarczyk, “Multisensor data fusion using elman neural networks”, Appl. Math. Comput. 319, 236 – 244 (2018).
• [4] A. Świetlicka, K. Kolanowski, and R. Kapela, “Training the stochastic kinetic model of neuron for calculation of an object’s position in space”, J. Intell. Robot. Syst. 98, 615–626 (2020).
• [5] M. Li and H. Lin, “Design and implementation of smart home control systems based on wireless sensor networks and power line communications”, IEEE Trans. Ind. Electron. 62(7), 4430–4442 (2015).
• [6] L. Manjakkal, M. Soni, N. Yogeswaran, and R. Dahiya, “Cloth based biocompatiable temperature sensor”, in 2019 IEEE International Conference on Flexible and Printable Sensors and Systems (FLEPS), 2019, pp. 1–3.
• [7] C.-H. Wu and Y.-C. Chung, “Heterogeneous wireless sensor network deployment and topology control based on irregular sensor model”, in Advances in Grid and Pervasive Computing (C. Cérin and K.-C. Li, eds.), (Berlin, Heidelberg), pp. 78–88, Springer Berlin Heidelberg, 2007.
• [8] W. Jiang, D. Liu, B. Cai, C. Rizos, J. Wang, and W. Shangguan, “A fault-tolerant tightly coupled gnss/ins/ovs integration vehicle navigation system based on an fdp algorithm”, IEEE Trans. Veh. Technol. 68(7), 6365–6378 (2019).
• [9] L.M.B. Winternitz, W.A. Bamford, and G.W. Heckler, “A gps receiver for high-altitude satellite navigation”, IEEE J. Sel. Top. Signal Process. 3(4), 541–556 (2009).
• [10] G. Cai, B.M. Chen, and T.H. Lee, Unmanned Rotorcraft Systems. Springer Publishing Company, Incorporated, 2016.
• [11] Q. Fan, B. Sun, Y. Sun, and X. Zhuang, “Performance enhancement of mems-based ins/uwb integration for indoor navigation applications”, IEEE Sens. J. 17(10), 3116‒3130 (2017).
• [12] H.G. Natke and C. Cempel, Model-Aided Diagnosis of Mechanical Systems. Springer-Verlag Berlin Heidelberg, 1997.
• [13] S. Lu, M. Jiang, Q. Sui, H. Dong, Y. Sai, and L. Jia, “Multidamage identification system of cfrp by using fbg sensors and multi-classification rvm method”, IEEE Sens. J. 15(11), 6287–6293 (2015).
• [14] S.S.R. Patange, S. Raja, B. Aravindu, V.R. Ranganath, G.T. Suchithra, B.R. Kaveri, and B. Jyothi, “Wireless based sensor damage detection system for structural applications”, in 2016 International Conference on Electrical, Electronics, Communication, Computer and Optimization Techniques (ICEECCOT), 2016, pp. 312–317.
• [15] T.Y. Wang, L.Y. Chang, D.R. Duh, and J.Y. Wu, “Distributed fault-tolerant detection via sensor fault detection in sensor networks”, in 2007 10th International Conference on Information Fusion, 2007, pp. 1–6.
• [16] L. Yuqing, Y. Tianshe, L. Jian, F. Na, and W. Guan, “A fault diagnosis method by multi sensor fusion for spacecraft control system sensors”, in 2016 IEEE International Conference on Mechatronics and Automation, pp. 748–753, 2016.
• [17] R. Isermann, Fault-diagnosis systems. an introduction from fault detection to fault tolerance, Springer-Verlag Berlin Heidelberg, 2006.
• [18] E.C. Hall, Reliability history of the apollo guidance computer, MIT, Cambridge, 1972.
• [19] F. Pirmoradi, F. Sassani, and C. de Silva, “Fault detection and diagnosis in a spacecraft attitude determination system”, Acta Astronaut. 65(5), 710–729 (2009).
• [20] Breakthrough Air Force capabilities spawned by basic research. CreateSpace Independent Publishing Platform, 2012.
• [21] M.S. Grewal and A.P. Andrews, “Applications of Kalman filtering in aerospace 1960 to the present [historical perspectives]”, IEEE Control Syst. Mag. 30(3), 69–78 (2010).
• [22] E. Denti, R. Galatolo, and F. Schettini, “An attitude & heading reference system based on a kalman filter for the integration of inertial, magnetic and gps data”, in Proceedings of the 27th International Congress on Aeronautical Sciences, (France), 2010, pp. 19–24.
• [23] N. Lwin and H. Tun, “Implementation of flight control system based on kalman and pid controller for uav”, Int. J. Sci. Technol. Res. 3, 309–312 (2014).
• [24] M. Marmion, “Airborne attitude estimation using a kalman filter”, Master’s thesis, The University Centre of Svalbard, Longyearbyen, Norway, 2006.
• [25] F. Orderud, Comparison of kalman filter estimation approaches for state space models with nonlinear measurements, 2005.
• [26] R. Swischuk and D. Allaire, “A Machine Learning Approach to Aircraft Sensor Error Detection and Correction”, J. Comput. Inf. Sci. Eng. 19, 041009 (2019).
• [27] K. Thiyagarajan, S. Kodagoda, L. Van Nguyen, and R. Ranasinghe, “Sensor failure detection and faulty data accommodation approach for instrumented wastewater infrastructures”, IEEE Access 6, 56562–56574 (2018).
• [28] K. Thiyagarajan, S. Kodagoda, R. Ranasinghe, D. Vitanage, and G. Iori, “Robust sensor suite combined with predictive analytics enabled anomaly detection model for smart monitoring of concrete sewer pipe surface moisture conditions”, IEEE Sens. J. 20(15), 8232–8243 (2020).
• [29] M. Leccadito, T. Bakker, and R. Klenke, “A neural network approach to an attitude heading reference system”, in 52nd Aerospace Sciences Meeting, Maryland, USA, 2014.
• [30] M. Battipede, M. Cassaro, P. Gili, and A. Lerro, “Novel neural architecture for air data angle estimation”, in Engineering Applications of Neural Networks (L. Iliadis, H. Papadopoulos, and C. Jayne, eds.), (Berlin, Heidelberg), pp. 313–322, Springer Berlin Heidelberg, 2013.
• [31] A.K. Ghosh, S.C. Raisinghani, and S. Khubchandani, “Estimation of aircraft lateral-directional parameters using neural networks”, J. Aircr.35(6), 876–881 (1998).
• [32] V. Kumar, O.SN.R. Ganguli, P. Sampath, and S. Suresh, “Identification of helicopter dynamics using recurrent neural networks and flight data”, J. Am. Helicopter Soc.51, 164–174, 04 (2006).
• [33] X. Kui Yue and J. Ping Yuan, “Neural network-based gps/ins integrated system for spacecraft attitude determination”, Chin. J. Aeronaut.19(3), 233–238 (2006).
• [34] S.O.H. Madgwick, “An efficient orientation filter for inertial and inertial / magnetic sensor arrays”, tech. rep., 2010.
• [35] J.J. Craig, Introduction to Robotics: Mechanics and Control. USA: Addison-Wesley Longman Publishing Co., Inc., 2nd ed., 1989.
• [36] B.A. Rozenfeld, The history of non-euclidean geometry: Evolution of the concept of a geometric space. Springer, New York, NY, 1988.
• [37] B. Jankowska and M. Szymkowiak, Machine Ranking of 2-Uncertain Rules Acquired from Real Data, pp. 198–222. Berlin, Heidelberg: Springer Berlin Heidelberg, 2013.
• [38] K. Thiyagarajan, S. Kodagoda, and L. Van Nguyen, “Predictive analytics for detecting sensor failure using autoregressive integrated moving average model”, in 2017 12th IEEE Conference on Industrial Electronics and Applications (ICIEA), 2017, pp. 1926‒1931.
• [39] Y. Wang, N. Masoud, and A. Khojandi, “Real-time sensor anomaly detection and recovery in connected automated vehicle sensors”, IEEE Trans. Intell. Transp. Syst. 1–11, (2020).

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2021).