This study prognoses the remaining useful life of a turbofan engine using a deep learning model, which is essential for the health management of an engine. The proposed deep learning model affords a significantly improved accuracy by organizing networks with a one-dimensional convolutional neural network, long short-term memory, and bidirectional long short-term memory. In particular, this paper investigates two practical and crucial issues in applying the deep learning model for system prognosis. The first is the requirement of numerous sensors for different components, i.e., the curse of dimensionality. Second, the deep neural network cannot identify the problematic component of the turbofan engine due to its “black box” property. This study thus employs dimensionality reduction and Shapley additive explanation (SHAP) techniques. Dimensionality reduction in the model reduces the complexity and prevents overfitting, while maintaining high accuracy. SHAP analyzes and visualizes the black box to identify the sensors. The experimental results demonstrate the high accuracy and efficiency of the proposed model with dimensionality reduction and show that SHAP enhances the explainability in a conventional deep learning model for system prognosis.

A number of landmark-based navigation algorithms have been studied using feature extraction over the visual information. In this paper, we apply the distance information of the surrounding environment in a landmark navigation model. We mount a depth sensor on a mobile robot, in order to obtain omnidirectional distance information. The surrounding environment is represented as a circular form of landmark vectors, which forms a snapshot. The depth snapshots at the current position and the target position are compared to determine the homing direction, inspired by the snapshot model. Here, we suggest a holistic view of panoramic depth information for homing navigation where each sample point is taken as a landmark. The results are shown in a vector map of homing vectors. The performance of the suggested method is evaluated based on the angular errors and the homing success rate. Omnidirectional depth information about the surrounding environment can be a promising source of landmark homing navigation. We demonstrate the results that a holistic approach with omnidirectional depth information shows effective homing navigation.

[-10]For local homing navigation, an agent is supposed to return home based on the surrounding environmental information. According to the snapshot model, the home snapshot and the current view are compared to determine the homing direction. In this paper, we propose a novel homing navigation method using the moment model. The suggested moment model also follows the snapshot theory to compare the home snapshot and the current view, but the moment model defines a moment of landmark inertia as the sum of the product of the feature of the landmark particle with the square of its distance. The method thus uses range values of landmarks in the surrounding view and the visual features. The center of the moment can be estimated as the reference point, which is the unique convergence point in the moment potential from any view. The homing vector can easily be extracted from the centers of the moment measured at the current position and the home location. The method effectively guides homing direction in real environments, as well as in the simulation environment. In this paper, we take a holistic approach to use all pixels in the panoramic image as landmarks and use the RGB color intensity for the visual features in the moment model in which a set of three moment functions is encoded to determine the homing vector. We also tested visual homing or the moment model with only visual features, but the suggested moment model with both the visual feature and the landmark distance shows superior performance. We demonstrate homing performance with various methods classified by the status of the feature, the distance and the coordinate alignment.