A thermal fault detection method for High-speed direct-driven blower components is proposed, utilizing thermal and visible image fusion along with semantic segmentation. The proposed method follows three steps: multimodal image fusion, component semantic segmentation of the fused image, and temperature level segmentation. Firstly, an end-to-end image fusion network based on an improved denoising diffusion model is used, a perceptually prioritized weighted loss is introduced for training, and an alternate training strategy is used to improve the quality of the fused images. In the second step, a lightweight segmentation network is proposed to reduce the model size and inference time while improving the segmentation accuracy. At last, thermal images are processed by clustering methods. Experiments on real industrial objects show that the proposed method composed of infrared and optical image fusion, semantic segmentation and temperature clustering networks improves significantly the fault temperature detection on different blower components.

Infrared thermography is widely used to detect abnormal body temperature thanks to its non-contact and large scale. Attenuation during infrared propagation causes the measured temperature to always be less than the actual value. This paper proposes a novel method of temperature calibration based on Bayesian inference. In the first step, we propose an improved infrared radiation model (IIRM), which accounts for emissivity and measures the distance between the radiation source and the infrared imager. This study leverages Naive Bayesian Inference (NBI) to derive surface emissivity. Then, using the improved model, the parameters of the model and the temperature distribution are reconstructed by Joint Maximum A Posterior (JMAP). The improved infrared radiation model and JMAP method (IIRM-JMAP) improved the accuracy of temperature measurement. The improved infrared thermal radiation model is suitable for measuring scenarios with different measuring distances, different humidity factors, and different emissivities. The proposed method has been validated to have small errors through various experiments on a black body and high-speed direct-drive blower.

In this paper, a hierarchical prior model based on the Haar transformation and an appropriate Bayesian computational method for X-ray CT reconstruction are presented. Given the piece-wise continuous property of the object, a multilevel Haar transformation is used to associate a sparse representation for the object. The sparse structure is enforced via a generalized Student-t distribution ( $\mathcal{S}{t}_g$ ), expressed as the marginal of a normal-inverse Gamma distribution. The proposed model and corresponding algorithm are designed to adapt to specific 3D data sizes and to be used in both medical and industrial Non-Destructive Testing (NDT) applications. In the proposed Bayesian method, a hierarchical structured prior model is proposed, and the parameters are iteratively estimated. The initialization of the iterative algorithm uses the parameters of the prior distributions. A novel strategy for the initialization is presented and proven experimentally. We compare the proposed method with two state-of-the-art approaches, showing that our method has better reconstruction performance when fewer projections are considered and when projections are acquired from limited angles.

Inverse problems arise anywhere we have an indirect measurement. In general, they are ill-posed to obtain satisfactory solutions, which needs prior knowledge. Classically, different regularization methods and Bayesian inference-based methods have been proposed. As these methods need a great number of forward and backward computations, they become costly in computation, particularly when the forward or generative models are complex, and the evaluation of the likelihood becomes very costly. Using deep neural network surrogate models and approximate computation can become very helpful. However, in accounting for the uncertainties, we need first to understand Bayesian deep learning, and then we can see how we can use it for inverse problems. In this work, we focus on NN, DL, and, more specifically, the Bayesian DL particularly adapted for inverse problems. We first give details of Bayesian DL approximate computations with exponential families; then, we see how we can use them for inverse problems. We consider two cases: First, we consider the case where the forward operator is known and used as a physics constraint, and the second examines more general data-driven DL methods.