With the advent of the big data era and the timeliness requirements of dataprocessing, a large amount of streaming industrial big data is continuously obtained in real time. Facing this kind of flowing and time-varyi...
详细信息
With the advent of the big data era and the timeliness requirements of dataprocessing, a large amount of streaming industrial big data is continuously obtained in real time. Facing this kind of flowing and time-varying knowledge information form, incremental learning is necessary. Lifelong learning (LL), as a typical incremental learning method, can continuously retain and accumulate old knowledge while learning new knowledge, which is very suitable for streaming industrial big data scenarios. At the same time, Bayesian nonparametric (BNP) models can adjust the complexity of the model based on observation data. Motivated by ideas of BNP and LL, a lifelong Bayesian learning machines framework is proposed in this article, which includes model expansion and model optimization. In general, this framework not only learns new effective knowledge and accumulates knowledge through incremental variational Bayesian under model expansion but also uses optimization steps to avoid model degradation caused by unnecessary component information. As an example, Dirichlet processes Gaussian mixture regression (DPGMR) is utilized for processmodeling under this framework. To evaluate the feasibility and efficiency of the developed method, a synthetic and a real industrial case are demonstrated.
Multi-party collaborative modeling allows different participants to build machine learning models without revealing the local data. Federated Learning (FL) is currently the main technique to achieve multi-party collab...
详细信息
With over 80% of Malaysia's fields relying on gas lift, a late life crisis is evident, prompting secondary and tertiary production enhancements to sustain oil production. Challenges like gas lift gas shortages, ag...
详细信息
ISBN:
(纸本)9781959025436
With over 80% of Malaysia's fields relying on gas lift, a late life crisis is evident, prompting secondary and tertiary production enhancements to sustain oil production. Challenges like gas lift gas shortages, aging facilities, and increased water cut possess efficient oil recovery limitations, which fueled the demand for an alternative lift technology in offshore Malaysia brown fields. However, replacing a gas lift system is a tedious task. This study proposes an automated screening method swiftly identify candidates, reducing the time and workforce needed to select from hundreds of wells and streamlining production optimization activities for brown fields selected in offshore Malaysia. This data input and analysis automation system will be tested with data from multiple fields to pre-screen the strings and establish a basket of opportunities before proceeding with screening using well modeling. From the vast number of attributes used in this study, essential parameters that will be used for candidate screening have been identified. The automation of this data for screening enables narrowing down the number of potential candidates for modeling and detailed analysis. Electrical submersible pump (ESP) design and economic analysis will be done once the candidate has been finalized through well modelling. Critical parameters such as remaining reserve, absolute open flow, well angle, dog leg severity, the latest liquid rate, the latest oil rate, the latest water cut, the latest gas oil ratio, sand count and identified integrity issues are essential for a production enhancement activity. By digitalizing this data, automation will ease the path to identify a pool of production enhancement candidates out of hundreds of strings in a field. The identified candidate will proceed to the maturation process where well modeling, design, and economic analysis will be conducted. This process saves time and increases the number of candidates available for production enhancement act
This brief studies the multi-rate optimal control problem for a class of industrial processes, whose controlling rate will be set faster than the sampling rate sometimes. This multi-rate phenomenon makes the accurate ...
详细信息
This brief studies the multi-rate optimal control problem for a class of industrial processes, whose controlling rate will be set faster than the sampling rate sometimes. This multi-rate phenomenon makes the accurate modeling of control systems challenging and difficult. In this brief, we present a model-free self-learning control scheme for the real-time solution of this problem, combining the lifting technology and Q-learning. For the asynchronous periods, the lifting system is established first to reconstruct the input and output by stacking the control and sampling signals to a frame period, maintaining the original dynamic information. Then, Q-learning is adopted to learn the optimal control policy with the real-time data and the convergence analysis of the proposed algorithm is derived. In this way, the control actions are executed at a faster rate to obtain the better dynamic performance. Finally, a hardware-in-loop (HIL) simulation study for process industries is carried out, showing that the proposed approach has high tracking and real-time performance.
Recently, the rapid advancement of Industrial Internet of Things (IIoT) technology has led to the utilization of various communication protocols. Among these, the Message Queue Telemetry Transport (MQTT) protocol has ...
详细信息
Recently, the rapid advancement of Industrial Internet of Things (IIoT) technology has led to the utilization of various communication protocols. Among these, the Message Queue Telemetry Transport (MQTT) protocol has become prevalent. Operating on a publish/subscribe model, MQTT's popularity in IIoT because of simplicity, lightweight nature, and ease of implementation. However, traditional MQTT protocol standards have neglected critical security concerns during the communication process, such as ineffective identity authentication, weak data confidentiality, and a lack of access control functions. To address these challenges, this paper introduces a security -enhanced scheme for the MQTT protocol based on domestic cryptographic algorithms. The proposed method enforces mutual identity authentication between the MQTT Client and the MQTT Broker using digital certificates. It also implements access control through an Access control List (ACL) and ensures end -to -end data security via the symmetric encryption algorithm SM4. Through comprehensive security analysis and experimental validation, this paper demonstrates that the enhanced scheme effectively rectifies the MQTT protocol's security deficiencies, achieving these improvements with small overhead.
In the dynamic landscape of advanced manufacturing, the confluence of laser powder bed fusion (LPBF) and machine learning (ML) has recently garnered significant attention in many applications. This review investigates...
详细信息
In the dynamic landscape of advanced manufacturing, the confluence of laser powder bed fusion (LPBF) and machine learning (ML) has recently garnered significant attention in many applications. This review investigates the confluence of LPBF and ML, specifically within the specific domain of stainless steel. Firstly, it delves into LPBF principles, including an overview of critical process parameters and associated defects. Secondly, the paper meticulously addresses the distinct challenges posed by steel in additive manufacturing (AM), highlighting factors such as chemical composition, anisotropic microstructure, and oxide film formation, all of which require specialized considerations. Thirdly, the spotlight shifts to the pivotal role of ML, covering predictive modeling for process parameters, real-time defect detection, and quality control. This paper highlights recent advances, revealing how data-driven approaches can accelerate process understanding and part qualification. Eventually, this review offers insights into the future integration of ML in LPBF for steel, providing valuable perspectives on potential advancements in the field of AM.
process analytical technology (PAT) tools are an important part of process monitoring and control in pharmaceutical continuous manufacturing (CM) that help ensure product quality. However, there is hesitancy to adopt ...
详细信息
process analytical technology (PAT) tools are an important part of process monitoring and control in pharmaceutical continuous manufacturing (CM) that help ensure product quality. However, there is hesitancy to adopt PAT due, in part, to the high start-up costs. A portion of the cost is the calibration burden associated with developing an appropriate multivariate dataanalysis (MVDA) method to extract the desired information from the spectral outputs of spectroscopic PAT tools. This has generated research interest in reduced calibration burden MVDA methods, such as iterative optimization technology (IOT) algorithms, as alternatives to conventional modeling approaches like partial least squares (PLS) regression. The goal of the presented research is to compare the calibration burden of three different MVDA methods (direct IOT, indirect IOT, PLS regression) at two drug loading levels (low and high) of pharmaceutical powder blends in a CM line. The blends were binary mixtures consisting of an active pharmaceutical ingredient and a coprocessed excipient blend. The coprocessed excipient blend was leveraged to reduce formulation complexity and streamline process development, benefiting the application of IOT algorithm. Calibration burden was assessed in terms of time, material, and financial costs. Utilizing a near-infrared spectroscopic PAT tool, it was found that MVDA methods that utilized IOT algorithms demonstrated a notably reduced calibration burden compared to the PLS models, while predicting blend potency with similar accuracy.
In order to improve the accuracy of low voltage ride-through (LVRT) control parameter identification for direct-drive wind turbines, a identification method based on the GRU-ISSA algorithm is proposed. Firstly, the ke...
详细信息
The expansion of urban centers necessitates enhanced efficiency and sustainability in their transportation infrastructure and mobility systems. The big data obtainable from various transportation modes potentially off...
详细信息
作者:
Rakov, Dmitry
Department of technological processes and systems control Moscow Russia
Clustering of the morphological set of engineering solutions in the synthesis of systems is the process of grouping similar solutions in order to facilitate their analysis and selection of the best option. This method...
详细信息
暂无评论