Zhiping Peng

Offshore wind turbines face harsh conditions and high maintenance costs, necessitating precise fault classiffcation based on deep learning. However, gearbox variability, scarce fault signals, and poor interpretability challenge this task. Therefore, this paper proposes a multimodal time-frequency enhancement synergistic network (TF-MESN). First, a Time-Frequency Graphic Block Compression Enhancement Method (TF-BCEM) is introduced, to highlight local feature structures and macroscopic time-frequency domain features of signals. Second, a Cascaded Heterogeneous Convolution Module (CHCM) is proposed, which uses heterogeneous convolution kernels through cascaded residual structures of standard convolution and separable convolution to build a convolutional neural network, capable of capturing signal features comprehensively. Third, an Improved Multiscale Statistics and Statistical Dynamic SCRM Module (MSDSM) is proposed, which can reasonably segment effective signals from redundant ones, making the model more suitable for complex scenarios where steady-state and transient faults coexist. Finally, multi-channel feature fusion information is input into a Multi-scale convolutional weighted classiffer (MSWC), which utilizes stride-based multi-scale down sampling convolution and multiple statistics for fault classiffcation adapted to complex information representation. Experiments on two gearbox datasets, validated via visualization, show that TFMESN outperforms four representative methods, with superior generalization and small-sample fault identiffcation capability, meeting offshore wind gearbox fault diagnosis needs.

Sequence prediction is widely applied and has significant theoretical and practical application value in fields such as meteorology and medicine. Traditional models, such as LSTM(Long Short-Term Memory) and GRU(Gated Recurrent Unit), may perform better than this model when dealing with short-term dependencies, but their performance may decline on long sequences and complex data, especially in cases where sequence fluctuations are significant. However, the Transformer requires a large amount of computing resources (parallel computing) when dealing with long sequences. Aiming to solve the problems existing in sequence prediction models, such as insufficient modeling ability of long sequence dependencies, insufficient interpretability, and low efficiency of multi-element heterogeneous information fusion, this study embeds sequential data into the knowledge graph, enabling the model to associate context information when processing complex data and providing more reasonable decision support for the prediction results. Given the historical sequence and the predicted future sequence, three groups of sequence lengths were set in the experiment. And MAE (Mean Absolute Error)and MSE (Mean Square Error) are used as indicators for sequence prediction. In sequence prediction, dynamic evolution is conducive to enhancing the ability of the prediction model to capture the changing patterns of the current time series data and significantly improving the reliability of the prediction results. Experiments were conducted using five datasets from different application fields to verify the effectiveness of the prediction model. The experimental results show that based on the randomization of the prediction time step, the prediction model proposed in this study significantly improves the expression performance of stationary sequences. It has addressed the shortcomings of these traditional methods, such as maintaining good performance in the case of short sequences with large fluctuations.

In order to achieve a good generalization ability across different prediction tasks and ensure the reliability of prediction results, this paper proposes a GAC-BiLSTM-AM prediction method based on ensemble learning. This method employs a dual-channel convolutional neural network to comprehensively extract and integrate sample features, which are then input into a composite analysis module consisting of a bidirectional long short-term memory, an attention mechanism, and a fully connected layer to achieve in-depth analysis and processing of information, jointly constructing an efficient base learner. Meanwhile, during the parameter iteration tuning process of the base learner, a mistake correction mechanism is introduced to dynamically adjust sample weights in order to correct potential attention biases, and further combined with the gold rush optimizer to optimize the key structural parameters of the model. The application evaluation in multiple benchmark prediction tasks confirms that the GAC-BiLSTM-AM method possesses excellent generalization performance.

The conventional diagnostic techniques for ethylene cracker furnace tube coking rely on manual expertise, offline analysis and on-site inspection. However, these methods have inherent limitations, including prolonged inspection times, low accuracy and poor real-time performance. This makes it challenging to meet the requirements of chemical production. The necessity for high efficiency, high reliability and high safety, coupled with the inherent complexity of the production process, results in data that is characterized by multimodal, nonlinear, non-Gaussian and strong noise. This renders the traditional data processing and analysis methods ineffective. In order to address these issues, this paper puts forth a novel soft measurement approach, namely the ‘Mixed Student’s t-distribution regression soft measurement model based on Variational Inference (VI) and Markov Chain Monte Carlo (MCMC)’. The initial variational distribution is selected during the initialization step of VI. Subsequently, VI is employed to iteratively refine the distribution in order to more closely approximate the true posterior distribution. Subsequently, the outcomes of VI are employed to initiate the MCMC, which facilitates the placement of the iterative starting point of the MCMC in a region that more closely approximates the true posterior distribution. This approach allows the convergence process of MCMC to be accelerated, thereby enabling a more rapid approach to the true posterior distribution. The model integrates the efficiency of VI with the accuracy of the MCMC, thereby enhancing the precision of the posterior distribution approximation while preserving computational efficiency. The experimental results demonstrate that the model exhibits enhanced accuracy and robustness in the diagnosis of ethylene cracker tube coking compared to the conventional Partial Least Squares Regression (PLSR), Gaussian Process Regression (GPR), Gaussian Mixture Regression (GMR), Bayesian Student’s T-Distribution Mixture Regression (STMR) and Semi-supervised Bayesian T-Distribution Mixture Regression (SsSMM). This method provides a scientific basis for optimizing and maintaining the ethylene cracker, enhancing its production efficiency and reliability, and effectively addressing the multimodal, non-Gaussian distribution and uncertainty of the coking data of the ethylene cracker furnace tube.

Cloud task scheduling and resource allocation (TSRA) constitute a core issue in cloud computing. Batch submission is a common user task deployment mode in cloud computing systems. In this mode, it has been a challenge for cloud systems to balance the quality of user service and the revenue of cloud service provider (CSP). To this end, with multi-objective optimization (MOO) of minimizing task latency and energy consumption, we propose a cloud TSRA framework based on deep learning (DL). The system solves the TSRA problems of multiple task queues and virtual machine (VM) clusters by uniting multiple deep neural networks (DNNs) as task scheduler of cloud system. The DNNs are divided into exploration part and exploitation part. At each scheduling time step, the model saves the best outputs of all scheduling policies from each DNN to the experienced sample memory pool (SMP), and periodically selects random training samples from SMP to train each DNN of exploitation part. We designed a united deep learning (UDL) algorithm based on this framework. Experimental results show that the UDL algorithm can effectively solve the MOO problem of TSRA for cloud tasks, and performs better than benchmark algorithms such as heterogeneous distributed deep learning (HDDL) in terms of task scheduling performance.

With the development and popularity of cloud computing, various artificial intelligence algorithms have been applied more and more widely in the field of cloud computing. While the complexity of artificial intelligence technology itself is also increasing, modern people are not satisfied with directly using artificial intelligence algorithm to solve complex practical problems, more and more researchers turn their eyes to explore the theoretical basis behind artificial intelligence algorithm, and try to explain artificial intelligence algorithm from various angles. This paper selects the latest application mode in the current field of cloud computing, and helps relevant researchers to clarify the development context of artificial intelligence technology in this typical mode by sorting out the latest artificial intelligence algorithm, so as to further explain the purpose of artificial intelligence technology.

This study aimed to develop a 5G + "mixed computing" + deep learning-based next-generation intelligent health-monitoring platform for an ethylene cracking furnace tube based on 5G communication technology, with the goal of improving the health management level of the key component of ethylene production, that is, the cracking furnace tube, and focusing on the key common technical difficulties of ethylene production of tube outer-surface temperature sensing and tube slagging diagnosis. It also integrated the edge-fog-cloud "mixed computing" technology and deep learning technology in artificial intelligence, which had a higher degree in the research and development of automation and intelligence, and was more versatile in an industrial environment. The platform included a 5G-based tube intelligent temperature-measuring device, a 5G-based intelligent peep door gearing, a 5G-based edge-fog-cloud collaboration mechanism, and a mixed deep learning-related application. The platform enhanced the automation and intelligence of the enterprise, which could not only promote the quality and efficiency of the enterprise but also protect the safe operation of the cracking furnace device and lead the technological progress and transformation and upgrading of the industry through the application.