| 1. |
- Chandrasekaran, Sundaram, et al.
(författare)
-
Advanced opportunities and insights on the influence of nitrogen incorporation on the physico-/electro-chemical properties of robust electrocatalysts for electrocatalytic energy conversion
- 2021
-
Ingår i: Coordination chemistry reviews. - : Elsevier. - 0010-8545 .- 1873-3840. ; 449
-
Forskningsöversikt (refereegranskat)abstract
- The use of a wide range of methods for incorporating nitrogen atoms on robust catalysts has given rise to fundamental advances in the field of energy conversion and storage. Recently, nitrogen incorporation has proven to be able to fine-tune the electron densities of exposed active sites to create high-performance electrocatalysts. The preservation of a strong interface between the local atomic coordination of nitrogen atoms on bare carbon, single metal atoms, transition metal oxides, metal chalcogenides, and MXenes during synthesis plays an important role in producing an efficient electrocatalysts. In addition, the ability of nitrogen atoms to bind with carbon or metal atoms can be influenced by processing conditions. In this regard, this review is the first comprehensive overview of the range of synthetic strategies to form nitrogen incorporated catalysts and assess their chemical, structural, physical electronic property modification and their influence on electrocatalytic ORR, OER, and HER performance. This review will describe how specific strategies have been utilized to realise effective electrocatalytic systems, including the energy conversion of nitrogen incorporated catalysts, structural coordination, and material optimization. Finally, the main challenges to be considered in future investigations in order to initiate new research efforts in this promising research area are discussed.
|
|
| 2. |
- Shi, Junchuan, et al.
(författare)
-
Planetary gearbox fault diagnosis using bidirectional-convolutional LSTM networks
- 2022
-
Ingår i: Mechanical systems and signal processing. - : Elsevier. - 0888-3270 .- 1096-1216. ; 162
-
Tidskriftsartikel (refereegranskat)abstract
- Gearbox fault diagnosis is expected to significantly improve the reliability, safety and efficiency of power transmission systems. However, planetary gearbox fault diagnosis remains a challenge due to complex responses caused by multiple planetary gears. Model-based gearbox fault diagnosis techniques extract hand-crafted features from sensor data based on underlying physics and statistical analysis, which are not effective in extracting spatial and temporal features automatically. While deep learning methods such as convolutional neural network (CNN) enable automatic feature extraction from multiple sensor sources, they are not capable of extracting spatial and temporal features simultaneously without losing critical feature information. To address this issue, we introduce a novel deep neural network based on bidirectional-convolutional long short-term memory (BiConvLSTM) networks to determine the type, location, and direction of planetary gearbox faults by extracting spatial and temporal features from both vibration and rotational speed measurements automatically and simultaneously. In particular, a CNN determines spatial correlations between two measurements within one time step automatically by combining signals collected from three accelerometers and one tachometer. Long short-term memory (LSTM) networks identify temporal dependencies between two adjacent time steps. By replacing input-to-state and state-to-state operations in the LSTM cell with convolutional operations, the BiConvLSTM can learn spatial correlations and temporal dependencies without losing critical features. Experimental results have shown that the BiConvLSTM network can detect the type, location, and direction of gearbox faults with higher accuracy than conventional deep learning approaches such as CNN, LSTM, and CNN-LSTM.
|
|
| 3. |
- Wang, Zhang, et al.
(författare)
-
Fabrication and properties of freeze-cast mullite foams derived from coal-series kaolin
- 2016
-
Ingår i: Ceramics International. - : Elsevier BV. - 0272-8842 .- 1873-3956. ; 42:10, s. 12414-12421
-
Tidskriftsartikel (refereegranskat)abstract
- Hierarchically porous mullite foams were fabricated from coal-series kaolin and Al2O3 slurries by freeze-casting using tert-butyl alcohol (TBA) and water as templates. TBA developed unidirectionally aligned pore channels along the freezing direction and water developed lamellar pores. The total porosity (60.2–83.4%), density (0.49–1.23 g/cm3) and macro-pore size (10–50 µm) of mullite foams were tailored by controlling the solid content of the slurries. The mullitization reaction was completed at the sintering temperature of 1500 °C. The compressive strength of mullite foams along the freezing direction was 3.8–49.4 MPa. Lower porosity and higher compressive strength of sintered mullite foams were obtained using TBA as solvent compared to water. The thermal conductivity of low density and mechanically stable TBA templated porous mullite with 80.2% porosity was 0.18 W/m K, indicting that the freeze-cast porous mullite was a promising refractory material for applications in thermal insulation
|
|
| 4. |
- Zhang, Liangwei, et al.
(författare)
-
Intra-Domain Transfer Learning for Fault Diagnosis with Small Samples
- 2022
-
Ingår i: Applied Sciences. - : MDPI. - 2076-3417. ; 12:14
-
Tidskriftsartikel (refereegranskat)abstract
- The concept of deep transfer learning has spawned broad research into fault diagnosis with small samples. A considerable covariate shift between the source and target domains, however, could result in negative transfer and lower fault diagnosis task accuracy. To alleviate the adverse impacts of negative transfer, this research proposes an intra-domain transfer learning strategy that makes use of knowledge from a data-abundant source domain that is akin to the target domain. Concretely, a pre-trained model in the source domain is built via a vanilla transfer from an off-the-shelf inter-domain deep neural network. The model is then transferred to the target domain using shallow-layer freezing and finetuning with those small samples. In a case study involving rotating machinery, where we tested the proposed strategy, we saw improved performance in both training efficiency and prediction accuracy. To demystify the learned neural network, we propose a heat map visualization method using a channel-wise average over the final convolutional layer and up-sampling with interpolation. The findings revealed that the most active neurons coincide with the corresponding fault characteristics.
|
|
| 5. |
- Chen, Xu, et al.
(författare)
-
Ductility deterioration induced by L21 phase in ferritic alloy through Ti addition
- 2023
-
Ingår i: Journal of Materials Research and Technology. - : Elsevier Editora Ltda. - 2238-7854. ; 25, s. 3273-3284
-
Tidskriftsartikel (refereegranskat)abstract
- Ductility deterioration induced by L21-Ni2AlTi precipitates in the aged ferritic alloys was examined systematically by using a combination of scanning transmission electron microscope (STEM), mechanical tests and first-principles thermodynamic calculations. The experimental studies revealed that the strength and hardness of the aged Fe–10Cr–5Ni–1Al–1Ti ferritic alloy containing B2–NiAl and L21-Ni2AlTi precipitates were higher than that of the aged Fe–10Cr–5Ni–1Al ferritic alloy containing NiAl precipitates, whereas the elongation-to-failure decreased dramatically from 9.3% to 0.3% indicating an obvious ductility deterioration due to the formation of L21-Ni2AlTi precipitates. This was also confirmed by the observation of fracture transition mode from dimpled failure to cleavage failure. The first-principles calculations, concerning the precipitate/matrix interface, were carried out to provide a theoretical analysis for the ductile–brittle transition by means of empirical ductility criteria ratios G/B and (C12–C44)/B as well as cleavage energy. The cleavage energy results indicated an intrinsic brittleness of the L21-Ni2AlTi phase and the L21-Ni2AlTi/BCC-Fe interface. Our analysis revealed that the intrinsic brittleness of L21-Ni2AlTi phase and L21-Ni2AlTi/BCC-Fe interface plays a vital role in determining the deformation behavior of the aged Fe–10Cr–5Ni–1Al–1Ti alloy.
|
|
| 6. |
- Dai, Wenbin, et al.
(författare)
-
Modelling Industrial Cyber-Physical Systems using IEC 61499 and OPC UA
- 2018
-
Konferensbidrag (refereegranskat)abstract
- Industrial Cyber-Physical Systems (iCPS) are considered as the enabling technology for achieve Industry 4.0. One main characteristic of the iCPS is the information transparency to allow interoperability among various devices and systems. The OPC UA provides a common information model for connecting Industry 4.0 components. On the other hand, the IEC 61499 is commonly used as an executable modeling language for iCPS. The IEC 61499 function block network provides an abstract view of the system configuration. By combining IEC 61499 and OPC UA, a visual executable model for iCPS is completed. In this paper, the mapping between two standards are provided and a case study of the proposed mapping is given.
|
|
| 7. |
- Dai, Wenbai, et al.
(författare)
-
Semantic Integration of Plug-and-Play Software Components for Industrial Edges Based on Microservices
- 2019
-
Ingår i: IEEE Access. - : IEEE. - 2169-3536. ; 7, s. 125882-125892
-
Tidskriftsartikel (refereegranskat)abstract
- The industrial cyber-physical system enables collaboration between distributed nodes across industrial clouds and edge devices. Flexibility and interoperability could be enhanced significantly by introducing the service-oriented architecture to industrial edge devices. From the industrial edge computing perspective, software components shall be dynamically composed across heterogeneous edge devices to perform various functionalities. In this paper, a knowledge-driven Microservice-based architecture to enable plug-and-play software components is proposed for industrial edges. These software components can be dynamically configured based on the orchestration of microservices with the support of the knowledge base and the reasoning process. These semantically enhanced plug-and-play microservices could provide rapid online reconfiguration without any programming efforts. The use of the plug-and-play software components is demonstrated by an assembly line example.
|
|
| 8. |
- Dai, Wenbin, et al.
(författare)
-
Service-oriented data acquisition and management for industrial cyber-physical systems
- 2017
-
Ingår i: Proceedings. - Piscataway, NJ : Institute of Electrical and Electronics Engineers (IEEE). - 9781538608371 ; , s. 759-764
-
Konferensbidrag (refereegranskat)abstract
- With rapid improvement in information and communication technologies, industrial automation systems are under the revolution. Legacy industrial automation systems lack flexibility and interoperability due to multi-layered architecture. From industrial cyber-physical system point of view, a new system architecture is needed to allow vertical and horizontal integration between all devices and systems from enterprise level to sensor level. In this paper, a RESTful service-oriented architecture is proposed for industrial controllers. By adopting RESTful services over HTTP methods, better efficiency for data acquisition from sensors, actuators, and controllers is achieved. In addition, service-oriented device management for industrial controllers is also implemented along with data acquisition. The reference architecture experiments on a car manufacturing demonstration line
|
|
| 9. |
- Deng, Jifei, et al.
(författare)
-
Imbalanced multiclass classification with active learning in strip rolling process
- 2022
-
Ingår i: Knowledge-Based Systems. - : Elsevier. - 0950-7051 .- 1872-7409. ; 255
-
Tidskriftsartikel (refereegranskat)abstract
- In the strip rolling process, conventional supervised methods cannot effectively address data with an imbalanced number of normal and faulty instances. In this paper, based on a deep belief network, a resampling method is combined with active learning (AL) to address imbalanced multiclass problems. The support vector machine-based synthetic minority oversampling technique was adapted to enrich the training data, whereas the true data distribution and model generalization were changed. A new selection strategy of AL is proposed that forms a function using uncertainty and diversity. AL uses an optimizing set that has a similar distribution with the whole dataset to calculate the informativeness of instances to optimize the model. Based on this step, the model study instances approach decision boundaries to promote performance. The proposed method is validated by five UCI benchmark datasets and strip rolling data, and experiments show that it outperforms conventional methods in tackling imbalanced multiclass problems.
|
|
| 10. |
- Li, Jianjiang, et al.
(författare)
-
Category Preferred Canopy-K-means based Collaborative Filtering algorithm
- 2019
-
Ingår i: Future generations computer systems. - : Elsevier. - 0167-739X .- 1872-7115. ; 93, s. 1046-1054
-
Tidskriftsartikel (refereegranskat)abstract
- It is the era of information explosion and overload. The recommender systems can help people quickly get the expected information when facing the enormous data flood. Therefore, researchers in both industry and academia are also paying more attention to this area. The Collaborative Filtering Algorithm (CF) is one of the most widely used algorithms in recommender systems. However, it has difficulty in dealing with the problems of sparsity and scalability of data. This paper presents Category Preferred Canopy-K-means based Collaborative Filtering Algorithm (CPCKCF) to solve the challenges of sparsity and scalability of data. In particular, CPCKCF proposes the definition of the User-Item Category Preferred Ratio (UICPR), and use it to compute the UICPR matrix. The results can be applied to cluster the user data and find the nearest users to obtain prediction ratings. Our experimentation results performed using the MovieLens dataset demonstrates that compared with traditional user-based Collaborative Filtering algorithm, the proposed CPCKCF algorithm proposed in this paper improved computational efficiency and recommendation accuracy by 2.81%.
|
|
