Condition monitoring systems are commonly exploited to assess the health status of equipment. A fundamental part of any condition monitoring system is data acquisition. Meaningfully estimating the current condition and predicting the future behaviour of the equipment strongly depends on the characteristic of the data measurement stage. Nowadays, condition monitoring has wide applications in the railway industry and various monitoring approaches have been proposed for the inspection of wheel and rail conditions. In-service condition monitoring of wheels provides the real-time data required for maintenance planning, while in-workshop inspection is normally done at fixed intervals carried out periodically. In-service data acquisition can be divided into on-board and wayside measurements. In this paper, on the basis of these classifications, the existing data acquisition techniques for the monitoring of railway wheel condition are reviewed, and the state-of-the-art methods and required research are discussed.

Wheel impact load detectors are widespread railway systems used for measuring the wheel-rail contact force. They usually measure the rail strain and convert it to force in order to detect high impact forces and corresponding detrimental wheels. The measured strain signal can also be used to identify the defect type and its severity. The strain sensors have a limited effective zone that leads to partial observation from the wheels. Therefore, wheel impact load detectors exploit multiple sensors to collect samples from different portions of the wheels. The discrete measurement by multiple sensors provides the magnitude of the force; however, it does not provide the much richer variation pattern of the contact force signal. Therefore, this paper proposes a fusion method to associate the collected samples to their positions over the wheel circumferential coordinate. This process reconstructs an informative signal from the discrete samples collected by multiple sensors. To validate the proposed method, the multiple sensors have been simulated by an ad hoc multibody dynamic software (VI-Rail), and the outputs have been fed to the fusion model. The reconstructed signal represents the contact force and consequently the wheel defect. The obtained results demonstrate considerable similarity between the contact force and the reconstructed defect signal that can be used for further defect identification.

The brain uses spikes in neural circuits to perform many dynamical computations. The computations are performed with properties such as spiking efficiency, i.e. minimal number of spikes, and robustness to noise. A major obstacle for learning computations in artificial spiking neural networks with such desired biological properties is due to lack of our understanding of how biological spiking neural networks learn computations. Here, we consider the credit assignment problem, i.e. determining the local contribution of each synapse to the network's global output error, for learning nonlinear dynamical computations in a spiking network with the desired properties of biological networks. We approach this problem by fusing the theory of efficient, balanced neural networks (EBN) with nonlinear adaptive control theory to propose a local learning rule. Locality of learning rules are ensured by feeding back into the network its own error, resulting in a learning rule depending solely on presynaptic inputs and error feedbacks. The spiking efficiency and robustness of the network are guaranteed by maintaining a tight excitatory/inhibitory balance, ensuring that each spike represents a local projection of the global output error and minimizes a loss function. The resulting networks can learn to implement complex dynamics with very small numbers of neurons and spikes, exhibit the same spike train variability as observed experimentally, and are extremely robust to noise and neuronal loss.

Understanding how recurrent neural circuits can learn to implement dynamical systems is a fundamental challenge in neuroscience. The credit assignment problem, i.e. determining the local contribution of each synapse to the network's global output error, is a major obstacle in deriving biologically plausible local learning rules. Moreover, spiking recurrent networks implementing such tasks should not be hugely costly in terms of number of neurons and spikes, as they often are when adapted from rate models. Finally, these networks should be robust to noise and neural deaths in order to sustain these representations in the face of such naturally occurring perturbation. We approach this problem by fusing the theory of efficient, balanced spiking networks (EBN) with nonlinear adaptive control theory. Local learning rules are ensured by feeding back into the network its own error, resulting in a synaptic plasticity rule depending solely on presynaptic inputs and post-synaptic feedback. The spiking efficiency and robustness of the network are guaranteed by maintaining a tight excitatory/inhibitory balance, ensuring that each spike represents a local projection of the global output error and minimizes a loss function. The resulting networks can learn to implement complex dynamics with very small numbers of neurons and spikes, exhibit the same spike train variability as observed experimentally, and are extremely robust to noise and neuronal loss.

A wheel impact load detector is used to assess the condition of a railway wheel by measuring the dynamic forces generated by defects. This system normally measures the impact force at multiple points by exploiting multiple sensors to collect samples from different portions of the wheel circumference. The outputs of the sensors are used to estimate the dynamic force as the main indicator for detecting the presence of the defect. This method fails to identify the defect type and its severity. Recently, a data fusion method has been developed to reconstruct the wheel defect signal from the wheel–rail contact signals measured by multiple wayside sensors. The reconstructed defect signal can be influenced by different parameters such as train velocity, axle load, number of sensors, and wheel diameter. This paper aims to carry out a parametric study to investigate the influence of these parameters. For this purpose, VI-Rail is used to simulate the wheel–rail interaction and provide the required data. Then, the developed fusion method is exploited to reconstruct the defect signal from the simulated data. This study provides a detailed insight into the effects of the influential parameters by investigating the variation of the reconstructed defect signals.