•A metric adversarial domain adaptation approach is proposed to successfully achieve cross-domain RUL prediction.•A feature extraction scheme with a dual self-attention module is developed to learn ...features with multi-scale semantics.•A supervised positive contrastive module is designed to maximize the target-specific mutual information.
Many existing domain adaptation-based methods try to derive domain invariant features to address domain shifts and obtain satisfactory remaining useful life (RUL) of bearings under multiple working conditions. However, most methods may not consider local semantics about degradation features and mutual information from target-specific data when aligning distribution discrepancies, thus resulting in limitations. Additionally, the use of contrastive learning to maintain mutual information may introduce unstable negative samples. To overcome these issues, a metric adversarial domain adaptation approach (MADA) is proposed to evaluate the bearing RULs under multiple working conditions. More specifically, an adversarial domain adaptation architecture with a supervised positive contrastive module is developed to consider mutual information without a negative sample, further learning domain invariant features. Also, the dual self-attention module is designed to extract multi-scale contextual semantics between degradation features. Meanwhile, extensive experiments are conducted in twelve cross-domain scenarios for two bearing cases. The experimental results show that the proposed method is more competitive.
The promoted activity and enhanced selectivity of electrocatalysts is commonly ascribed to specific structural features such as surface facets, morphology, and atomic defects. However, unraveling the ...factors that really govern the direct electrochemical reduction of CO2 (CO2RR) is still very challenging since the surface state of electrocatalysts is dynamic and difficult to predict under working conditions. Moreover, theoretical predictions from the viewpoint of thermodynamics alone often fail to specify the actual configuration of a catalyst for the dynamic CO2RR process. Herein, we re‐survey recent studies with the emphasis on revealing the dynamic chemical state of Cu sites under CO2RR conditions extracted by in situ/operando characterizations, and further validate a critical link between the chemical state of Cu and the product profile of CO2RR. This point of view provides a generalizable concept of dynamic chemical‐state‐driven CO2RR selectivity that offers an inspiration in both fundamental understanding and efficient electrocatalysts design.
A critical link between the dynamic chemical state of Cu sites (mixed Cu+‐ and Cu0‐, Cu+‐, and Cu0‐dominated) and their unique selectivity toward the direct electrochemical reduction of CO2 (yielding C2H4/C2H5OH, CO/HCOO−, and CH4, respectively) is put forward. This may be a valuable tool for fine‐tuning the Cu surface state toward distinct CO2RR pathways.
•We present a deep twin convolutional neural network (TDNN) with multi-domain inputs.•3 input layers is constructed to fuse multi-domain features and improve performance.•TDNN are presented for ...resisting the influence of noise and operating conditions.•It shows that its accuracy and anti-noise performance outperform existing methods.•Its accuracy on four datasets is 61%, 33%, 17% and 29% higher than other methods.
Although machine learning-based intelligent detection methods have made many achievements for diesel engine misfire diagnosis, they suffer from a certain degree of performance degradation due to the strong environmental noise and the change of working conditions in the actual application scenarios. To tackle this issue, this study presents a deep twin convolutional neural networks with multi-domain inputs (DTCNNMI) for diesel engine misfire diagnosis under strong environmental noise and different working conditions. Vibration signals of engine cylinder heads at different speeds are collected experimentally and fed into input layers of the proposed model. It constructs three input layers to combine automatically extracted time-domain, time-frequency-domain and hand-craft time-domain statistical features, improving the model performance. Twin convolutional neural networks with large first-layer kernels are presented for extracting multi-domain information of vibration signals and resist influence of environmental noise and the change of operating conditions on the final diagnosis results. The effectiveness of the proposed approach is validated on the datasets collected experimentally and by making comparison with the existing representative algorithms. The results demonstrate that the accuracy and anti-noise performance of the proposed DTCNNMI outperforms the existing algorithms. On the constructed four datasets under different working conditions, the proposed method achieved at least 97.019% accuracy even when signal-to-noise ratio was −4 dB, which is much higher than those of the other methods. Moreover, the accuracy of the proposed DTCNNMI on datasets A, B, C and D is at least 61.177%, 33.334%, 17.646% and 29.961% higher than other methods, respectively.
The world of work is changing. Communications technologies and digital platforms have enabled some types of work to be delivered from anywhere in the world by anyone with a computer and an internet ...connection. This digitally-mediated work brings jobs to parts of the world traditionally characterized by low incomes and high unemployment rates. As such, it has been touted by governments, third-sector organizations, and the private sector as a novel strategy of economic development. Drawing on a four-year study with 65 workers in South Africa, Kenya, Nigeria, Ghana and Uganda, we examine the development implications of the gig economy on labour in Africa. We offer four analytical development dimensions through which platform-based remote work impacts the lives and livelihoods of African workers, i.e. freedom, flexibility, precarity and vulnerablity. We argue that these dimensions should be understood in a continuum to better explain the working conditions and lives of workers in the gig economy.
•The two-stage RUL prediction framework is investigated in this paper.•The two-level alarm mechanism is proposed to detect FPT of each entity adaptively.•DSCN-DTAM is built for cross-domain ...prognostic with incomplete target domain data.•Double transferable attention mechanism is designed for the fined-grained transfer.•Four transfer prognostic tasks verify the effectiveness of the proposed method.
The remaining useful life (RUL) prediction provides an essential basis for improving mechanical equipment reliability. In practical application, the variant of working conditions and incomplete degradation data seriously deteriorate the performance of the prognostic models. In order to conquer this problem, a two-stage RUL prediction method is proposed for the cross-domain prognostic task with insufficient degradation data. At first, the two-level alarm mechanism is employed to detect the first predicting time (FPT) of each mechanical entity adaptively. Then, the deep separable convolutional network with the double transferable attention mechanism (DSCN-DTAM) is proposed to construct the cross-domain prognostic model. In DSCN-DTAM, multiple regularization strategies can guide the model to extract domain-invariant features, and the double transferable attention mechanism is designed to select the degradation information with high transferability. Finally, the proposed method is verified by multiple transfer prognostic tasks designed by two bearing datasets. Compared with other methods, the proposed method shows superior performance.
Automatic and reliable fault diagnosis of rotating machinery cross working conditions is of practical importance. For this purpose, ensemble transfer convolutional neural networks (CNNs) driven by ...multi-channel signals are proposed in this paper. Firstly, a series of source CNNs modified with stochastic pooling and Leaky rectified linear unit (LReLU) are pre-trained using multi-channel signals. Secondly, the learned parameter knowledge of each individual source CNN is transferred to initialize the corresponding target CNN which is then fine-tuned by a few target training samples. Finally, a new decision fusion strategy is designed to flexibly fuse each individual target CNN to obtain the comprehensive result. The proposed method is used to analyze multi-channel signals measured from rotating machinery. The comparison result shows the superiorities of the proposed method over the existing deep transfer learning methods.
•CNN is modified with stochastic pooling and Leaky rectified linear unit.•Multi-channel signals are used to pre-train a series of CNNs.•Transfer CNN is constructed with parameter transfer strategy.•A new decision fusion strategy is designed based on flexible weight assignment.
Commuting can be tiring and stressful. An unavoidable part of life for many people, it is almost always associated with negative outcomes. This study examined the implications of commuting time for ...the commitment and well-being of employees. This paper uses 'conservation of resources' theory and job demands-resources approaches to argue that employees with long commutes will be less committed and experience lower well-being. These effects are also expected to be mediated by the work-life balance of the employees and interact with the level of autonomy they perceive themselves to have. Data from the fifth European Working Conditions Survey indicate that there is a negative relationship between commuting time, commitment and well-being. Results also suggest that work-life balance mediates part of these relationships and, finally, that autonomy can act as a buffer against the effects of commuting time on both commitment and well-being.
...conditions such as free accommodation, free meals, and maid service, which suggest valued and respected employees, are replaced with the grudging provision of limited mileage allowance for on-call ...shifts, which suggests that employees are viewed as commodities whose long term loyalty and morale are of no consequence.
•A novel method called DRHRML is proposed for bearing fault diagnosis with small samples under different working conditions.•Improved sparse denoising autoencoder (ISDAE) is proposed to preprocess ...the raw vibration data.•Two novel task datasets are constructed for verifying the proposed method.
Recently, intelligent fault diagnosis has made great achievements, which has aroused growing interests in the field of bearing fault diagnosis due to its strong feature learning ability. Sufficient bearing fault samples are taken for granted in existing intelligent fault diagnosis methods generally. In practice, however, the lack of fault samples has been a knotty problem. Therefore, in this paper, a novel method called data reconstruction hierarchical recurrent meta-learning (DRHRML) is proposed for bearing fault diagnosis with small samples under different working conditions. This approach contains data reconstruction and meta-learning stages. In the data reconstruction stage, noise is reduced and the useful information hidden in the raw data is extracted. In the meta-learning stage, the proposed method is trained by a recurrent meta-learning strategy with one-shot learning way. This approach is demonstrated on the bearing fault database with 92 working conditions from Case Western Reserve University and with 56 working conditions from laboratory. Results show that the proposed method is effective for bearing intelligent fault diagnosis with small samples under different working conditions.