In recent years, many researchers have attempted to achieve cross-domain diagnosis of faults through domain adaptation (DA) methods. However, owing to the complex physical environments, applications of DA-based approach are not guaranteed to unknown operating environments. Some existing domain generalization (DG) methods require enough fully labeled source domains to train, which are often unavailable in practical settings. In this study, an adversarial domain generalization network (ADGN) based on class boundary feature detection is proposed. The ADGN can diagnose faults in unknown operating environments, and only one fully labeled domain is used in training. Although ADGN has to access fully unlabeled auxiliary domains, a large number of unlabeled samples exist under actual working conditions. In our method, fuzzy features at a classification boundary are detected by maximizing the classifier differences. Better feature mapping functions and domain-invariant features are obtained by adversarial training. As the training proceeds, the differences in the distribution of features among the source, auxiliary, and unknown domains become smaller so domain-invariant features can be used for fault diagnosis in unknown operating environments. Comprehensive experiments showed that ADGN can achieve higher fault diagnosis accuracies than other methods when only one fully labeled domain is used in an unknown operating environment. The ADGN can even cope comfortably with complex transfer tasks with different speeds and loads.

Deep learning (DL)-based fault diagnosis models need to collect sufficient fault information for each fault type to ensure high-precision diagnosis. Some unexpected and new fault types will inevitably appear in actual conditions, which are called incremental fault types or class increment. Traditional DL models require the costly collection of all known data for retraining; while the use of new fault data may lead to catastrophic forgetting of old tasks. To solve the problem of bearing diagnosis with incremental fault types, a lifelong learning method based on generative feature replay (LLMGFR) is proposed in this study. A feature distillation method is put forward in this method to avoid forgetting in the feature extractor. The generator is trained to produce old task features. The generated features are mixed with real features of the current task to solve the imbalance problem and catastrophic forgetting of the classifier effectively. According to incremental fault diagnosis cases, LLMGFR can learn constantly and adaptively in dynamic environments with incremental fault types.

Deep slearning (DL)-based fault diagnosis models have to collect the most comprehensive data of mechanical fault types to ensure reliability. In real scenarios, due to complex, variable operating conditions, machines often generate unexpected faults that lead to an increment of fault types, causing the diagnosis model to be invalid. Therefore, the data of new fault types are needed to retrain the model. However, DL models suffer from catastrophic forgetting when incrementally learning new classes. To solve the problem of the diagnosis of increasing fault types, a lifelong learning method for fault diagnosis (LLMFD) is proposed in this article under the lifelong learning paradigm. The key of LLMFD is a proposed dual-branch aggregation networks (DBANets) framework that is combined with reserved exemplars to learn the new fault types without forgetting the old ones. In DBANets, each residual block layer has a dynamic block and a steady block to solve the stability–plasticity dilemma in lifelong learning. The aggregation weights are adopted to balance stability and plasticity. LLMFD is applied to a diagnosis case of incremental fault types. Results verify that LLMFD is superior to other lifelong learning methods and has satisfactory robustness.

Fault diagnosis approaches based on deep learning (DL) are subject to a prerequisite that training samples follow the same distribution as the test samples. Traditional transfer learning (TL)-based fault diagnosis approaches are mainstreamed on a single-source transfer and consider simple variable working conditions. However, rotating machineries work under variable working conditions, making the prerequisite for DL methods hard to satisfy in practical scenarios. Moreover, more than one factor, such as load and speed, can simultaneously affect the working conditions, resulting in complex transfer tasks. Therefore, we propose a new multi-source TL approach, named Optimal transport-based Multi-Source Student–teacher learning Network (OMSSN), to address bearing fault diagnosis under variable working conditions. The target-domain student classifier gains knowledge from the multi-source fault diagnostic teacher by applying optimal transport and continue optimizing along with iterations. A cluster optimization is also introduced to help the model make accurate fault predictions. A well-designed experiment is performed to prove the effectiveness of OMSSN, wherein the proposed and compared methods are tested under four working conditions composed of four load and speed conditions. Detailed experiments, including comparative evaluation and ablation study, confirm the effectiveness of the proposed method.

In order to resolve the large fluctuations in temperature range problem of Luojia 1-01 satellite caused by low heat inertia and poor thermal conductivity of structure, a quasi-all-passive thermal control system (TCS) design is presented under the conditions of limited resources including mass and power consumption. The effectiveness of the TCS design is verified by both ground thermal balanced test and related telemetry data of on-orbit performance. Firstly, according to the structural features and working modes of the satellite, isothermal design was implemented and the effectiveness was verified by thermal analysis using finite element method. Secondly, based on the results of the thermal analysis, thermal design was optimized and verified by the thermal balanced test. Finally, the thermal design was proved to be effective by temperature data acquired from telemetry data of on-orbit performance, and the thermal analysis model was improved and updated based on the results of thermal balanced test and temperature data of on-orbit performance. The on-orbit data indicates that temperature of optical camera stables at about 12 °C, temperature of battery stables at 19 °C, temperature of instruments inside and outside the satellite cabin is ranging from 10 °C to 25 °C. Temperature fluctuation range of optical camera is less than 2 °C when it is not imaging. Temperature fluctuation range of instruments not facing the sun is less than 4 °C. The data suggests that the temperature level of the satellite meets general design requirements, and the quasi-all-passive TCS design of the satellite is practicable.

Recently, the study on learned iterative shrinkage thresholding algorithm (LISTA) has attracted increasing attentions. A large number of experiments as well as some theories have proved the high efficiency of LISTA for solving sparse coding problems. However, existing LISTA methods are all serial connection. To address this issue, we propose a novel extragradient based LISTA (ELISTA), which has a residual structure and theoretical guarantees. Moreover, most LISTA methods use the soft thresholding function, which has been found to cause a large estimation bias. Therefore, we propose a thresholding function for ELISTA instead of soft thresholding. From a theoretical perspective, we prove that our method attains linear convergence. Through ablation experiments, the improvements of our method on the network structure and the thresholding function are verified in practice. Extensive empirical results verify the advantages of our method.