One of the critical challenges in multi-sensor fusion for vehicle attitude estimation is dealing with process and measurement noise, model uncertainty, and network channel failures. This paper proposes a robust fusion estimator for multi-sensor systems (MSSs) based on constrained communication rates and random packet drops to address these issues. A robust state estimator (RSE) based on sensitivity penalty is used for local estimation. The estimation error pseudo-cross-covariance matrix of the fusion center, considering both the transmission strategy and packet drops, is derived. The fusion estimator employs a data-driven transmission strategy that guarantees comparatively good estimation performance while effectively reducing sensor energy loss and network congestion. It is investigated the conditions under which the estimation error of the fusion estimator is uniform boundedness. The simulation is performed with a tractor-car system, and the effectiveness of the derived method is verified by fusion estimation in different cases.

This paper investigates the robust fusion estimation problem for multi-sensor systems with communication constraints, parameter uncertainty, d-step state delays, and deterministic control inputs. The multi-sensor system consists of a fusion center and some sensor nodes with computational capabilities, between which there are random packet drops. The state augmentation method is utilized to transform a time-delay system into a non-time-delay one. The robust state estimation algorithm is derived based on the sensitivity penalty for each sensor node to reduce the impact of modelling errors, and modelling errors here are not limited to a unique form, which implies that the fusion estimator applies to a wide range of situations. An event-triggered transmission strategy has been adopted to effectively alleviate the communication burden from the sensor node to the fusion center. Moreover, the fusion estimator handles packet drops arising from unreliable channels, and the corresponding pseudo-cross-covariance matrix is provided. Some conditions are given to ensure that the estimation error of the robust fusion estimator is uniformly bounded. Two sets of numerical simulations are provided to illustrate the effectiveness of the derived fusion estimator.

Due to the problem that it is difficult to accurately extract and identify the hydraulic end fault of 2000 fracturing truck under complicated working conditions and high load environment, a variational mode decomposition (VMD) with deep belief network (DBN) is presented. Firstly, the variational mode decomposition is used to decompose the vibration signal collected by the hydraulic end of the fracturing vehicle into several stable intrinsic mode function (IMF) and obtain the spectrum of the reconstructed signal, which is the input of the deep belief network. Then, the deep belief network fault identification model was constructed by using the back-propagation algorithm and, the pre-training and feature learning of input spectrum are carried out, the DBN-based fault feature adaptive analysis and fault state intelligent identification is completed, realizing the fault diagnosis of the hydraulic end of the fracturing truck. The results show that the adaptive characteristic of the DBN method can effectively improve the accuracy of fault state recognition.