Initial Sensor Location Research Articles

Health monitoring sensor placement optimization based on initial sensor layout using improved partheno-genetic algorithm

Optimal sensor placement is an important component of a reliability structural health monitoring system for a large-scale complex structure. However, the current research mainly focuses on optimizing sensor placement problem for structures without any initial sensor layout. In some cases, the experienced engineers will first determine the key position of whole structure must place sensors, that is, initial sensor layout. Moreover, current genetic algorithm or partheno-genetic algorithm will change the position of the initial sensor locations in the iterative process, so it is unadaptable for optimal sensor placement problem based on initial sensor layout. In this article, an optimal sensor placement method based on initial sensor layout using improved partheno-genetic algorithm is proposed. First, some improved genetic operations of partheno-genetic algorithm for sensor placement optimization with initial sensor layout are presented, such as segmented swap, reverse and insert operator to avoid the change of initial sensor locations. Then, the objective function for optimal sensor placement problem is presented based on modal assurance criterion, modal energy criterion, and sensor placement cost. At last, the effectiveness and reliability of the proposed method are validated by a numerical example of a quayside container crane. Furthermore, the sensor placement result with the proposed method is better than that with effective independence method without initial sensor layout and the traditional partheno-genetic algorithm.

INDOOR LIDAR RELOCALIZATION BASED ON DEEP LEARNING USING A 3D MODEL

Abstract. Indoor localization, navigation and mapping systems highly rely on the initial sensor pose information to achieve a high accuracy. Most existing indoor mapping and navigation systems cannot initialize the sensor poses automatically and consequently these systems cannot perform relocalization and recover from a pose estimation failure. For most indoor environments, a map or a 3D model is often available, and can provide useful information for relocalization. This paper presents a novel relocalization method for lidar sensors in indoor environments to estimate the initial lidar pose using a CNN pose regression network trained using a 3D model. A set of synthetic lidar frames are generated from the 3D model with known poses. Each lidar range image is a one-channel range image, used to train the CNN pose regression network from scratch to predict the initial sensor location and orientation. The CNN regression network trained by synthetic range images is used to estimate the poses of the lidar using real range images captured in the indoor environment. The results show that the proposed CNN regression network can learn from synthetic lidar data and estimate the pose of real lidar data with an accuracy of 1.9 m and 8.7 degrees.

Efficient Sensor Placement Optimization for Shape Deformation Sensing of Antenna Structures with Fiber Bragg Grating Strain Sensors.

This paper investigates the problem of an optimal sensor placement for better shape deformation sensing of a new antenna structure with embedded or attached Fiber Bragg grating (FBG) strain sensors. In this paper, the deformation shape of the antenna structure is reconstructed using a strain–displacement transformation, according to the measured discrete strain data from limited FBG strain sensors. Moreover, a two-stage sensor placement method is proposed using a derived relative reconstruction error equation. In this method, the initial sensor locations are determined using the principal component analysis based on orthogonal trigonometric (i.e., QR) decomposition, and then a new location is sequentially added into the initial sensor locations one by one by minimizing the relative reconstruction error considering information redundancy. The numerical simulations are conducted, and the comparisons show that the proposed method is advantageous in terms of the sensor distribution and computational cost. Experimental validation is performed using an antenna experimental platform equipped with an optimal FBG strain sensor configuration, and the reconstruction results show good agreements with those measured directly from displacement sensors. The proposed method has a large potential for the strain sensor placement of complex structures, and the proposed antenna structure with FBG strain sensors can be applied to the future wing-skin antenna or flexible space-based antenna.

Optimal sensor placement for fixture fault diagnosis using Bayesian network

PurposeFixture failures are the main cause of the dimensional variation in the assembly process. The purpose of this paper is to focus on the optimal sensor placement of compliant sheet metal parts for the fixture fault diagnosis.Design/methodology/approachBased on the initial sensor locations and measurement data in launch time of the assembly process, the Bayesian network approach for fixture fault diagnosis is proposed to construct the diagnostic model. Furthermore, given the desired number of sensors, the diagnostic ability of the sensor set is evaluated based on the mutual information of the nodes. Thereby, a new sensor placement method is put forward and validated with a real automotive sheet metal part.FindingsThe new proposed method can be used to perform the fixture fault diagnosis and sensor placement optimization effectively, especially in a data‐rich environment. And it is robust in the presence of measurement noise.Originality/valueThis paper presents a novel approach for fixture fault diagnosis and optimal sensor placement in the assembly process.