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.     

Thermo-economic investigation on the hydrogen production through the stored solar energy in a salinity gradient solar pond: A comparative study by employing APC and ORC with zeotropic mixture

In this paper, a salinity gradient solar pond (SGSP) is used to harness the solar energy for hydrogen production through two cycles. The first cycle includes an absorption power cycle (APC), a proton exchange membrane (PEM) electrolyzer, and a thermoelectric generator (TEG) unit; in the second one, an organic Rankine cycle (ORC) with the zeotropic mixture is used instead of APC. The cycles are analyzed through the thermoeconomic vantage point to discover the effect of key decision variables on the cycles’ performance. Finally, NSGA-II is used to optimize both cycles. The results indicate that employing ORC with zeotropic mixture leads to a better performance in comparison to utilizing APC. For the base mode, unit cost product (UCP), exergy, and energy efficiency when APC is employed are 59.9 $/GJ, 23.73%, and 3.84%, respectively. These amounts are 47.27 $/GJ, 29.48%, and 5.86% if ORC with the zeotropic mixture is utilized. The APC and ORC generators have the highest exergy destruction rate which is equal to 6.18 and 10.91 kW. In both cycles, the highest investment cost is related to the turbine and is 0.8275 $/h and 0.976 $/h for the first and second cycles, respectively. In the optimum state the energy efficiency, exergy efficiency, UCP, and H₂ production rate of the system enhances 42.44%, 27.54%,15.95%, and 38.24% when ORC with the zeotropic mixture is used. The maximum H₂ production is 0.47 kg/h, and is obtained when the mass fraction of R142b, LCZ temperature, pumps pressure ratio, generator bubble point temperature are 0.603, 364.35 K, 2.12, 337.67 K, respectively.     

《安徽省农村供水工程运行管理指南（试行）》解析

“十四五”期间，通过强化供水工程运行管理，巩固维护好已建农村供水工程成果，是水利部门实施乡村振兴的基本任务。2021年4月，《安徽省农村供水工程运行管理指南（试行）》正式印发实施。《指南》是在安徽省农村供水工作重点由工程建设转入运行管理的背景下，指导推进农村供水工程规范化管理的重要文件。通过介绍《指南》编制的有关背景、编制目标和特点，解析《指南》的主要内容和条款，可帮助供水管理人员快速掌握《指南》要点，助力《指南》在安徽省内贯彻和实施。     

海上热采防砂封隔器研制与室内试验

海上稠油热采开发过程中,通常采用蒸汽吞吐的方式进行原油开采。为满足稠油热采长效密封要求,研制了HPHT-215型热采防砂封隔器。封隔器胶筒采用特制的氟硅基复合材料+玻璃纤维网结构,并开展了材料性能评价测试。通过有限元分析和室内胶筒组合测试,对胶筒材料和组合结构进行了评价优化。室内全尺寸整机测试表明:封隔器能够满足耐温350 ℃、耐压21 MPa密封性能要求,并开展了高低温多轮次密封性能评价测试。该型热采防砂封隔器的研制成功,为海上稠油蒸汽吞吐多轮次开发提供了保障,具有广泛的应用前景。     

高深溜井井筒堵塞的爆破处理实践

溜井是采用平硐-溜井方式开拓矿山的运输咽喉,溜井正常与否对矿山生产影响极大。本文通过黑沟铁矿高深溜井井筒堵塞处理实例,对其堵塞爆破处理方法及经验做了系统分析。重点介绍的爆破冲击波破拱疏通高深溜井井筒高位堵塞的爆破方法,富有新意,可供国内外同类型矿山参考借鉴。     

Use of La2O3 with 8YSZ as thermal barrier coating and its effect on thermal cycle behavior,microstructure, mechanical properties and performance of diesel engine operated by hydrogen-algae biodiesel blend

In this present work, the effect of lanthanum oxides (La₂O₃) on the thermal cycle behavior of TBC coatings and mechanical properties such as adhesion strength and microhardness of 8% Yttria Stabilized Zirconia (8YSZ) TBCs were investigated. CoNiCrAlY and aluminium alloy (Al–13%Si) were used as bond coat and substrate materials. 8YSZ and different wt % of La₂O₃ (10, 20, and 30%) top coatings were applied using the atmospheric plasma spray (APS) method. The thermal cycling test for TBC coated samples were conducted at 800 °C in the electric furnace. The XRD pattern shows that the La₂O₃ doped 8YSZ material transformed to cubic pyrochloric structured La₂Zr₂O₇ during thermal cycling. Further, the Taguchi-based grey relation analysis (GRA) method was applied to optimize the TBC coating parameters to achieve better mechanical properties such as adhesion strength and microhardness. And the optimized La₂O₃/8YSZ TBC coating was coated on CRDI engine combustion chamber components. The engine was tested with microalgae biodiesel and hydrogen, and the results were promising for the TBC-coated engine. The engine performance increased while using La₂O₃/8YSZ coated components, and the emissions from engine exhaust gas such as CO, HC, and smoke reduced considerably. It was found that there was no separation crack and spallation of the coating layer in the microstructure. Ultimately, the microstructural analysis of the optimized TBC coated piston sample after 50 h of running in the diesel engine confirmed that the developed coating had a superior thermal insulation effect and longer life.     

Cheese ripening in nonconventional conditions: A multiparameter study applied to Protected Geographical Indication Canestrato di Moliterno cheese

A multiparameter study was performed to evaluate the effect of fondaco, a traditional ripening cellar without any artificial temperature and relative humidity control, on the chemical, microbiological, and sensory characteristics of Protected Geographical Indication Canestrato di Moliterno cheese. Ripening in such a nonconventional environment was associated with lower counts of lactococci, lactobacilli, and total viable bacteria, and higher presence of enterococci, in comparison with ripening in a controlled maturation room. Moreover, fondaco cheese underwent accelerated maturation, as demonstrated by faster casein degradation, greater accumulation of free AA, and higher formation of volatile organic compounds. Secondary proteolysis, as assessed by liquid chromatography-mass spectrometry of free AA and low molecular weight peptides, did not show any qualitative difference among cheeses, but fondaco samples evidenced an advanced level of peptidolysis. On the other hand, significant qualitative differences were observed in the free fatty acid profiles and in the sensory characteristics. Principal component analysis showed a clear separation of the fondaco and control cheeses, indicating that ripening in the natural room conferred unique sensory features to the product.     

Western Canadian dairy farmers' perspectives on the provision of outdoor access for dairy cows and on the perceptions of other stakeholders

The provision of pasture and outdoor access for dairy cattle differs around the globe. For example, in Ireland, New Zealand, and Australia, dairy farms are largely pasture based, whereas dairy farms in the United States and Canada are largely confinement based. There is a high level of public support for pasture and outdoor access for dairy cows, and the available evidence shows that dairy cattle are highly motivated to access pasture, especially at night. The decision as to whether to provide outdoor access is typically made by farmers, but little is known about dairy farmers' perspectives on this topic. We investigated perspectives of Western Canadian dairy farmers on outdoor access, as well as how they believe different stakeholders (i.e., the dairy industry, the dairy cows, and the general public) regard outdoor access for dairy cows. Data were collected via (1) 11 focus group discussions with a total of 50 Western Canadian dairy farmers, and (2) semi-structured individual interviews with an additional 6 dairy farmers of Hutterite colonies. Data were analyzed using template analysis. Although most participants in this study did not provide outdoor access on their farms, or only provided outdoor access to certain cow groups, participants generally mentioned that they enjoyed seeing cows on pasture or outdoors. However, participants shared that the Canadian supply management system (including processors) required a consistent flow of production, which was thought to be easier and more economically realized with indoor housing of lactating cows. Participants believed that pasture or outdoor access for dairy cows was desired by the public. Some participants believed that dairy cows prefer to spend time outside under favorable weather conditions, but others felt that cows preferred to stay indoors in modern, ventilated freestall barns. The results of this study describe the perspectives of dairy farmers regarding the views of dairy industry stakeholders as they relate to outdoor access, helping to inform conversations around the provision of outdoor access for dairy cattle.     

Process knowledge-based random forest regression for model predictive control on a nonlinear production process with multiple working conditions

In process industry, predictive control approaches have been widely used for nonlinear production processes. Practically, the predictor in a predictive controller is extremely important since it provides future states for the optimization problem of controllers. The conventional predictive controller with precise mathematical predictors approximating the state space of physical systems is difficult and time-consuming for nonlinear production processes, and it performs poorly over a wide range of working conditions and with significant disturbances. To address the challenges, the trend of applying artificial intelligence emerges. However, the industrial process-specific knowledge is ignored in most cases. In this study, a predictive controller with a control process knowledge-based random forest (RF) model is proposed. Specifically, working data are clustered at first to handle diverse working conditions. Then, a process knowledge-based forest predictor, namely MIW-RF model with a redesigned cascading RF structure, is proposed to incorporate control process knowledge into modeling. Thus, future states of controlled variables could be more accurately acquired for the optimizer. A simplified version of the predictive model is also developed with quick model training and updating. The proposed predictive methods are finally introduced into the controller design. According to the empirical results, the proposed methods deliver a better control performance against benchmarks, including more accurate anticipated controlled-variable responses, better set-point tracking and disturbance rejection capability.