Intelligent engineering asset management system for power transformer maintenance decision supports under various operating conditions

Large sized transformers are an important part of global power systems and industrial infrastructures. An unexpected failure of a power transformer can cause severe production damage and significant loss throughput the power grid. In order to prevent power facilities from malfunctions and breakdowns, the development of real-time monitoring and fault prediction tools are of great interests to both researches and practitioners. This research develops an intelligent engineering asset management system for power transformer maintenance. The system performs real-time monitoring of key parameters and uses data mining and fault prediction models to detect transformers’ potential failure under various operating conditions. Principal component analysis (PCA) and a back-propagation artificial neural network (BP-ANN) are the algorithms adopted for the prediction model. Historical industrial power transformer data from Taiwan and Australia are used to train and test the failure prediction models and to verify the proposed general methodology as comparative case studies. The PCA algorithm reduces the number of the primary dissolved gasses as the key factor values for BP-ANN prediction modeling inputs. The system yields effective predictions when verified using various operating condition data from Australia and Taiwan power companies. The accuracy rates are much higher when compared to the fault prediction results without using PCA. The intelligent system combining PCA and BP-ANN algorithms, developed in this research, can be adopted by asset managers in different regions to develop suitable maintenance and repair strategies for transformer failure preventions.     

A web-based screening model for climate risk to water supply systems in the northeastern United States

The aim of this study is to describe the development and application of a web-based decision support tool (ViRTUE) for performing climate risk evaluations of water supply systems. The tool is designed for small-scale water utilities in the northeastern United States that may lack the resources for detailed climate change risk investigations. Development of this tool demonstrates a relatively new approach to web application development using the Shiny framework for the R programming language to create an interactive environment for stakeholders and water managers to explore climate vulnerabilities. Using a decision-scaling framework, the tool allows the user to perform a climate stress test to evaluate the performance and vulnerability to water supply shortfalls of local reservoir systems over a wide range of potential climate change scenarios using a generic systems model. Probabilities of future climate conditions derived from climate projections then help inform utility operators of impending risk.     

偶联反应器格栅的制作和组装工艺

格栅支持板是换热器中的主要部件,尤其是大尺寸的格栅支持板,以前国内没有先例,如何编制好它的制作工艺和程序,并且在实际过程中得到很好的执行,遇到问题及时调整处置,对它的加工、组装、和整体安装有着特别重要的作用。     

Towards sensible toxicity testing for nanomaterials: proposal for the specification of test design

During the last decade, nanomaterials (NM) were extensively tested for potential harmful effects towards humans and environmental organisms. However, a sound hazard assessment was so far hampered by uncertainties and a low comparability of test results. The reason for the low comparability is a high variation in the (1) type of NM tested with regard to raw material, size and shape and (2) procedures before and during the toxicity testing. This calls for tailored, nanomaterial-specific protocols. Here, a structured approach is proposed, intended to lead to test protocols not only tailored to specific types of nanomaterials, but also to respective test system for toxicity testing. There are existing standards on single procedures involving nanomaterials, however, not all relevant procedures are covered by standards. Hence, our approach offers a detailed way of weighting several plausible alternatives for e.g. sample preparation, in order to decide on the procedure most meaningful for a specific nanomaterial and toxicity test. A framework of several decision trees (DT) and flow charts to support testing of NM is proposed as a basis for further refinement and in-depth elaboration. DT and flow charts were drafted for (1) general procedure—physicochemical characterisation, (2) choice of test media, (3) decision on test scenario and application of NM to liquid media, (4) application of NM to the gas phase, (5) application of NM to soil and sediments, (6) dose metrics, (S1) definition of a nanomaterial, and (S2) dissolution. The applicability of the proposed approach was surveyed by using experimental data retrieved from studies on nanoscale CuO. This survey demonstrated the DT and flow charts to be a convenient tool to systematically decide upon test procedures and processes, and hence pose an important step towards harmonisation of NM testing.     

千米深井大断面硐室双强壳体支护成套技术的应用

从分析深井高应力大断面巷道和硐室破碎围岩的变形破坏特点入手,指出巷道稳定性的控制机理在于及时强化失稳区围岩的残余强度,阻止初次失稳的发展,并施加高强的主动支护结构,从而使巷道进入二次稳定状态,同时采取高强的被动封闭支护技术。提出了全断面双强壳体支护设计、3S耦合协调支护设计和抗张拉强基础梁支护设计等设计方案来控制巷道变形。并对绞车房进行现场施工,支护效果良好,达到预期目标。     

综采工作面端头超前支护方式实践

该文分析了加强综采工作面超前支护的必要性,对传统的综采工作面超前支护技术存在的不足进行了分析;就如何加强新型综采工作面超前支护技术的应用进行了探讨。     

The role of Pt loading on reduced graphene oxide support in the polyol synthesis of catalysts for oxygen reduction reaction

Common carbon-blacks have shown insufficient stability as cathodic catalyst supports for proton exchange membrane fuel cells (PEMFCs). In this regard, alternative supports have been proposed and, specifically graphene or reduced graphene oxide (rGO), have attracted special attention. Herein, a set of electrocatalysts using reduced graphene oxide (rGO) as support is synthetized by a modified polyol method. The influence of Pt loading on the support is studied and compared with conventional supports, considering Pt particle morphologies and oxygen reduction reaction (ORR) performance in rotating disk electrode (RDE). Despite Pt average particle size typically increases with the Pt loading, 30 wt% of Pt on rGO is the optimal Pt loading, yielding the highest ORR activity among the rGO-supported electrocatalysts. These results show that both Pt loading and type of support greatly impact on the morphology and electrochemical performance of Pt nanoparticles.     

Group decision support system for backbone-network reconfiguration

Modern power system is unprecedentedly vulnerable and the society is exposed to higher blackout risks. Therefore restoration is a key issue to power systems. Reasonable backbone-network reconfiguration is necessary for re-establishing the network and restoring loads quickly. In order to speed up network reconfiguration under security constraints, a group decision support system (GDSS) is developed. A unified data platform based on data warehouse is constructed to resolve inconsistencies of data, information and models. A three-stage restoration strategy and a two-layer restoration path searching method are proposed to establish restoration schemes. Multiple attribute decision-making is implemented to evaluate alternatives and consider various attributes about restoration speed and system security comprehensively. Group decision-making provides an aggregated cardinal ranking of candidate restoration schemes. The GDSS uses expert rules for qualitative analysis and numerical computation programs for quantitative analysis, and it can resolve the semi-structured decision problem of network reconfiguration efficiently. Restoration plan of Shandong power grid is developed with the proposed method and it has been adopted by State Grid Shandong Electric Power Company. Performance results of Shandong power grid of China demonstrate the feasibility and flexibility of the method.     

Deterministic and probabilistic ship pitch prediction using a multi-predictor integration model based on hybrid data preprocessing,reinforcement learning and improved QRNN

The deterministic and probabilistic prediction of ship motion is important for safe navigation and stable real-time operational control of ships at sea. However, the volatility and randomness of ship motion, the non-adaptive nature of single predictors and the poor coverage of quantile regression pose serious challenges to uncertainty prediction, making research in this field limited. In this paper, a multi-predictor integration model based on hybrid data preprocessing, reinforcement learning and improved quantile regression neural network (QRNN) is proposed to explore the deterministic and probabilistic prediction of ship pitch motion. To validate the performance of the proposed multi-predictor integrated prediction model, an experimental study is conducted with three sets of actual ship longitudinal motions during sea trials in the South China Sea. The experimental results indicate that the root mean square errors (RMSEs) of the proposed model of deterministic prediction are 0.0254°, 0.0359°, and 0.0188°, respectively. Taking series #2 as an example, the prediction interval coverage probabilities (PICPs) of the proposed model of probability predictions at 90%, 95%, and 99% confidence levels (CLs) are 0.9400, 0.9800, and 1.0000, respectively. This study signifies that the proposed model can provide trusted deterministic predictions and can effectively quantify the uncertainty of ship pitch motion, which has the potential to provide practical support for ship early warning systems.     

Multi-objective optimization of shield construction parameters based on random forests and NSGA-II

Metro shield construction will inevitably cause changes in the stress and strain state of the surrounding soil, resulting in stratum deformation and surface settlement (SS), which will seriously endanger the safety of nearby buildings, roads and underground pipe networks. Therefore, in the design and construction stage, optimizing the shield construction parameters (SCP) is the key to reducing the SS rate and increasing the safe driving speed (DS). However, optimization of existing SCP are challenged by the need to construct a unified multiobjective model for optimization that are efficient, convenient, and widely applicable. This paper innovatively proposes a hybrid intelligence framework that combines random forest (RF) and non-dominant classification genetic algorithm II (NSGA-II), which overcomes the shortcomings of time-consuming and high cost for the establishment and verification of traditional prediction models. First, RF is used to rank the importance of 10 influencing factors, and the nonlinear mapping relationship between the main SCP and the two objectives is constructed as the fitness function of the NSGA-II algorithm. Second, a multiobjective optimization framework for RF-NSGA-II is established, based on which the optimal Pareto front is calculated, and reasonable optimized control ranges for the SCP are obtained. Finally, a case study in the Wuhan Rail Transit Line 6 project is examined. The results show that the SS is reduced by 12.5% and the DS is increased by 2.5% with the proposed framework. Meanwhile, the prediction results are compared with the back-propagation neural network (BPNN), support vector machine (SVM), and gradient boosting decision tree (GBDT). The findings indicate that the RF-NSGA-II framework can not only meet the requirements of SS and DS calculation, but also used as a support tool for real-time optimization and control of SCP.