Search

The flexible job shop scheduling problem (FJSP) is a classic NP-hard problem, and the quality of its scheduling solution directly affects the operational efficiency of the manufacturing system. However, the traditional scheduling algorithms suffer from poor generalization when solving FJSP; there are problems such as long computational time and dimensional disasters, especially as the scale of FJSP increases. Therefore, an effective deep actor-critic reinforcement learning (DACRL) method is proposed for solving FJSP. Firstly, the FJSP is modeled as a multi-agent Markov decision process (MMDP), the state space, action space, and reward function in the MMDP are designed. Secondly, a DACRL model is constructed to solve FJSP. The actor network is responsible for choosing the most suitable scheduling rule in different states, while the critic network is responsible for outputting the value function of the actions and providing feedback to the actor network to better adjust the scheduling strategy. Finally, the proposed DACRL method is validated on benchmark FJSP instances of different scales. The experimental results show that the proposed method significantly outperforms the heuristic scheduling rules and double deep Q-network (DDQN) in terms of solution quality. Compared with the meta-heuristic algorithms and the self-learning genetic algorithm (SLGA), the proposed method has higher solution efficiency with the same solution quality. [ABSTRACT FROM AUTHOR]

In practical industrial applications, it is crucial to train a robust fault diagnosis (FD) model that can quickly adapt to new working conditions or fault modes using a few labeled fault samples. Therefore, a novel convolutional multi-head self-attention network-based meta-transfer learning approach (CMS-MTL) for few-shot fault diagnosis (FSFD) is proposed. Firstly, a convolutional multi-head self-attention network (CMHSAN) is designed, which ingeniously combines the multi-head self-attention (MHSA) blocks and convolution blocks. The local and global feature information of the input time–frequency images are fully considered through the mutual cooperation of MHSA and convolution, so as to fully extract the discriminative features among various fault classes. Secondly, a three-stage CMHSAN-based meta-transfer learning (MTL) scheme is proposed, which provides a good initialization state for the meta-training of the CMHSAN model through the pre-training stage, updates the pre-trained model with the scaling and shifting parameters in the meta-training stage, and fine-tunes the updated model in the meta-testing stage, so as to quickly adapt to new FSFD tasks from the target domain. Thirdly, aiming at the fault classes that are difficult to be diagnosed during meta-training, a meta-task re-training (MTRT) strategy is designed to learn more valuable transferable knowledge in the meta-training stage, thereby improving the adaptability of the CMHSAN model to hard FSFD tasks. Finally, extensive experiments are conducted under different FSFD scenarios to verify the effectiveness of the proposed approach. The results prove that the approach can quickly adapt to new FSFD tasks through the learned meta-knowledge and achieve high diagnosis accuracies. • Design a convolutional multi-head self-attention network to extract fault features. • Develop a three-stage CMHSAN-based MTL scheme to adapt fast to new diagnosis tasks. • Design a meta-task re-training strategy to better diagnose difficult fault classes. • Proposed CMS-MTL approach greatly improves the few-shot fault diagnosis accuracy. [ABSTRACT FROM AUTHOR]

The flexible job shop scheduling problem (FJSP) is an important production scheduling problem in intelligent manufacturing. How to model the complex FJSP more accurately and improve the efficiency and generalization of scheduling policies is an urgent challenge to be solved. Therefore, a new end-to-end deep reinforcement learning (DRL) method combined with the meta-path-based heterogeneous graph neural network (MHGNN) is proposed to effectively solve FJSP. The task of solving FJSP is decomposed into two subtasks of operation selection and machine allocation. This dual-task FJSP is represented by introducing a heterogeneous graph and modeled as the dual Markov decision process (DMDP). A MHGNN is proposed to embed the global scheduling states of the dual-task FJSP. A heterogeneous graph neural network (GNN) framework is designed for the dual-task FJSP to efficiently encode the operation nodes and machine nodes, where the extracted embedded feature information is used to represent the operation selection policy and the machine allocation policy. Two policy networks are designed to efficiently predict the operation selection policy and the machine allocation policy, and a soft double-actors critic algorithm is proposed to train these two policy networks, where the trained policies can be used to efficiently solve FJSP instances of different scales. The experiments on three public benchmarks show that the proposed method outperforms the well-known heuristic scheduling rules and some advanced methods for solving FJSP. In particular, when solving large-scale FJSPs, the proposed method performs more prominently in terms of solution quality and solution time. • A heterogeneous graph is introduced to represent the dual-task FJSP. • A dual Markov decision process is proposed to model the dual-task FJSP. • A meta-path-based heterogeneous graph neural network is proposed. • A heterogeneous graph neural network framework is designed for the dual-task FJSP. • A soft double-actors critic algorithm is designed to train the scheduling policies. [ABSTRACT FROM AUTHOR]

Federated transfer learning (FTL) can effectively address the data silos and domain shift that exist in data-driven rotating machinery fault diagnosis (RMFD). However, in FTL used for RMFD, the huge communication overhead, idle waiting between the source clients and the target client, and negative transfer caused by model aggregation are all pressing challenges. Therefore, a ring-based decentralized federated transfer learning (RDFTL) method for intelligent fault diagnosis is proposed. Firstly, a ring-based decentralized federated transfer learning framework is designed, which can be fully integrated with the bandwidth-optimal Ring-AllReduce algorithm, thereby greatly reducing the communication overhead. Secondly, an asynchronous domain adaptation strategy is proposed, which can effectively avoid idle waiting between the source clients and the target client in the collaborative model training, thereby improving the overall training efficiency of FTL. Thirdly, a multi-perspective distribution discrepancy aggregation (MPDDA) strategy is proposed to alleviate the negative transfer caused by model aggregation. The diagnosis performance of the local model of a source client on the target domain is evaluated from the three perspectives of statistical distance, domain adversarial, and stability, and these three evaluation metrics are jointly used to determine the aggregation weights, which can effectively improve the diagnosis performance of the global model. Finally, a series of experiments are carried out to verify the effectiveness of the proposed method. The results demonstrate that the proposed method can obtain a cross-domain fault diagnosis model with excellent performance in RMFD with data privacy at a fast training speed. • A ring-based decentralized federated transfer learning framework is designed. • An asynchronous domain adaptation strategy is proposed to avoid idle waiting. • The domain adversarial and stability are introduced to the aggregation strategy. • A multi-perspective distribution discrepancy aggregation strategy is proposed. [ABSTRACT FROM AUTHOR]

Many parallel algorithms have recently been developed to accelerate solving the subset-sum problem on a heterogeneous CPU–GPU system. However, within each compute node, only one CPU core is used to control one GPU and all the remaining CPU cores are in idle state, which leads to a large number of CPU cores being wasted. In this paper, based on a cost-optimal parallel two-list algorithm, we propose a novel heterogeneous cooperative computing approach to solve the subset-sum problem on a hybrid CPU–GPU cluster, which can make full use of all available computational resources of a cluster. The unbalanced workload distribution and the huge communication overhead are two main obstacles for the heterogeneous cooperative computing. In order to assign the most suitable workload to each compute node and reasonably partition it between CPU and GPU within each node, and minimize the inter-node and intra-node communication costs, we design a communication-avoiding workload distribution scheme suitable for the parallel two-list algorithm. According to this scheme, we provide an efficient heterogeneous cooperative implementation of the algorithm. A series of experiments are conducted on a hybrid CPU–GPU cluster, where each node has two 6-core CPUs and one GPU. The results show that the heterogeneous cooperative computing significantly outperforms the CPU-only or GPU-only computing. [ABSTRACT FROM AUTHOR]

The traditional rolling bearing fault diagnosis methods are difficult to achieve effective cross-domain fault diagnosis. Therefore, a novel deep convolution multi-adversarial domain adaptation (DCMADA) model for rolling bearing fault diagnosis is proposed, which includes a feature extraction module, a domain adaptation module, and a fault identification module. In the feature extraction module, an improved deep residual network (ResNet) is used as the feature extractor to extract the transferable features from the raw vibration signals. In the domain adaptation module, the marginal and conditional distributions are adjusted using multi-kernel maximum mean discrepancy (MK-MMD) and multiple domain discriminators in the source and target domains, and an adaptive factor is designed to dynamically measure the relative importance of these two distributions. In the fault identification module, the classifier uses the extracted domain-invariant features to complete cross-domain fault identification. Experiments show that the model has superior transfer capability in cross-domain bearing fault diagnosis. • A novel deep convolution multi-adversarial domain adaptation model is proposed. • An improved deep residual network is used to extract the transferable features. • MK-MMD and multiple domain discriminators are used to adjust the joint distribution. • An adaptive factor is designed to achieve better domain adaptation. [ABSTRACT FROM AUTHOR]

To address the problems of low recognition accuracy, slow convergence speed and weak generalization ability of traditional LeNet-5 network used in rolling-element bearing fault diagnosis, a rolling-element bearing fault diagnosis method using improved 2D LeNet-5 network is put forward. The following improvements to the traditional LeNet-5 network are made: the convolution and pooling layers are reasonably designed and the size and number of convolution kernels are carefully adjusted to improve fault classification capability; the batch normalization (BN) is adopted after each convolution layer to improve convergence speed; the dropout operation is performed after each full-connection layer except the last layer to enhance generalization ability. To further improve the efficiency and effectiveness of fault diagnosis, on the basis of improved 2D LeNet-5 network, an end-to-end rolling-element bearing fault diagnosis method based on the improved 1D LeNet-5 network is proposed, which can directly perform 1D convolution and pooling operations on raw vibration signals without any preprocessing. The results show that the improved 2D LeNet-5 network and improved 1D LeNet-5 network achieve a significant performance improvement than traditional LeNet-5 network, the improved 1D LeNet-5 network provides a higher fault diagnosis accuracy with a less training time in most cases, and the improved 2D LeNet-5 network performs better than improved 1D LeNet-5 network under small training samples and strong noise environment. [ABSTRACT FROM AUTHOR]

To effectively predict the rolling bearing fault under different working conditions, a rolling bearing fault prediction method based on quantum particle swarm optimization (QPSO) backpropagation (BP) neural network and Dempster–Shafer evidence theory is proposed. First, the original vibration signals of rolling bearing are decomposed by three-layer wavelet packet, and the eigenvectors of different states of rolling bearing are constructed as input data of BP neural network. Second, the optimal number of hidden-layer nodes of BP neural network is automatically found by the dichotomy method to improve the efficiency of selecting the number of hidden-layer nodes. Third, the initial weights and thresholds of BP neural network are optimized by QPSO algorithm, which can improve the convergence speed and classification accuracy of BP neural network. Finally, the fault classification results of multiple QPSO-BP neural networks are fused by Dempster–Shafer evidence theory, and the final rolling bearing fault prediction model is obtained. The experiments demonstrate that different types of rolling bearing fault can be effectively and efficiently predicted under various working conditions. [ABSTRACT FROM AUTHOR]

The 0–1 knapsack problem has been extensively studied in the past years due to its immediate applications in industry and financial management, such as cargo loading, stock cutting, and budget control. Many algorithms have been proposed to solve this problem, most of which are heuristic, as the problem is well-known to be NP-hard. Only a few optimal algorithms have been designed to solve this problem but with high time complexity. This paper proposes the cost-optimal parallel algorithm (COPA) on an EREW PRAM model with shared memory to solve this problem. COPA is scalable and yields optimal solutions consuming less computational time. Furthermore, this paper implements COPA on two scenarios – multicore CPU based architectures using Open MP and GPU based configurations using CUDA. A series of experiments are conducted to examine the performance of COPA under two different test platforms. The experimental results show that COPA could reduce a significant amount of execution time. Our approach achieves the speedups of up to 10.26 on multicore CPU implementations and 17.53 on GPU implementations when the sequential dynamic programming algorithm for KP01 is considered as a baseline. Importantly, GPU implementations outstand themselves in the experimental results. [ABSTRACT FROM AUTHOR]

MapReduce is a promising distributed computing platform for large-scale data processing applications. Hadoop MapReduce has been considered as one of the most extensively used open-source implementations of MapReduce frameworks for its flexible customization and convenient usage. Despite these advantages, a relatively slow running task called straggler task impedes job progress. In this study, two novel speculative strategies, namely, Estimate Remaining time Using Linear relationship model (ERUL) and extensional Maximum Cost Performance (exMCP), are developed to improve the estimation of the remaining time of a task. ERUL is a dynamic system load-aware strategy; using this strategy, we can overcome some drawbacks of the Longest Approximate Time to End (LATE) that misleads speculative execution in some cases. In exMCP, different slot values are considered. Extensive experiments show that ERUL and exMCP are applied to accurately estimate the remaining execution times of running tasks and reduce the running time of a job. [ABSTRACT FROM AUTHOR]

Sparse matrix–vector multiplication (SpMV) is of singular importance in sparse linear algebra, which is an important issue in scientific computing and engineering practice. Much effort has been put into accelerating SpMV, and a few parallel solutions have been proposed. This paper focuses on a special type of SpMV, namely sparse quasi-diagonal matrix–vector multiplication (SQDMV). The sparse quasi-diagonal matrix is the key to solving many differential equations, and very little research has been done in this field. This paper discusses data structures and algorithms for SQDMV that are efficiently implemented on the compute unified device architecture (CUDA) platform for the fine-grained parallel architecture of the graphics processing unit (GPU). A new diagonal storage format, a hybrid of the diagonal format (DLA) and the compressed sparse row format (CSR) (HDC) will be presented, which overcomes the inefficiency of DLA in storing irregular matrices and the imbalances of CSR in storing non-zero elements. Furthermore, HDC can adjust the storage bandwidth of the diagonal to adapt to different discrete degrees of sparse matrix, so as to get a higher compression ratio than DLA and CSR, and reduce the computational complexity. Our implementation in a GPU shows that the performance of HDC is better than that of other formats, especially for matrices with some discrete points outside the main diagonal. In addition, we combine the different parts of HDC to make a unified kernel to get a better compression ratio and a higher speedup ratio in the GPU. [ABSTRACT FROM AUTHOR]