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.     

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。     

基于改进SOA-VMD的磁声发射信号去噪算法

磁声发射（MAE）是铁磁性材料磁化过程中产生的声发射信号，在构件应力检测和微观损伤检测中有着广泛的应用。针对MAE信号非稳态、复杂性、衰减性等特点，提出海鸥算法结合变分模态分解（SOA-VMD）的去噪方法，为克服海鸥算法求解过程中易陷入局部最优解问题，利用柯西变异算子产生随机迭代过程，使改进算法即柯西变异海欧算法（CVSOA）跳出早熟收敛。采用以幅值谱熵为适应度函数，优化VMD算法中分解模态个数K和二次惩戒因子α两个参数，将含噪声的MAE信号进行VMD分解重构。经仿真信号和实际检测信号分析表明，改进后的CVSOA-VMD算法全局寻优能力和去噪性能优于传统的SOA-VMD算法，降噪后的MAE信号特征值对于不同应力下均方根、偏斜度特征值的重复性更好，可靠性更高。     

Oxidative characteristics and gel properties of porcine myofibrillar proteins affected by l-lysine and l-histidine in a dose-dependent manner at a low and high salt concentration

This study investigated the effects of l -lysine (Lys) and l -histidine (His) on the oxidative characteristics and gel properties of porcine myofibrillar proteins (MP). Results showed that Lys and His had a strong ferrous ion-chelating ability and hydroxyl radical-scavenging activity. Moreover, Lys and His inhibited the protein carbonyl formation and MP aggregation at 0.2 M and 0.6 M NaCl, respectively, in a dose-dependent manner. Furthermore, 2 and 4 mg mL⁻¹ Lys and His decreased the oxidation-induced loss of the tertiary structure of MP accompanied by the lower surface hydrophobicity. The water-holding capacity and gel strength of MP gels increased with increasing Lys and His concentrations due to more regular and lamellar structures with smaller and homogeneous pores at 0.6 M NaCl and more orderly crosslinking via fibrous filament at 0.2 M NaCl. In summary, Lys and His chelated the ferrous ions and scavenged hydroxyl radicals, decreased the oxidation-induced physicochemical changes, thus preventing oxidative damage during the formation of a three-dimensional gel network, which resulted in better gel quality.     

Pigmented flower extracts of plant species from the Geraniaceae and Lamiaceae families as natural food colourants: anthocyanin composition,thermal and oxidative stability

This study determined the anthocyanin profile of pigmented flower extracts from some Geraniaceae and Lamiaceae plant species found in South Africa, and their thermal and oxidative stability to assess their potential food application. Anthocyanins in the Geraniaceae (Pelargonium grandiflorum Willd. and Pelargonium × hortorum L.H. Bailey, Pelargonium zonale hybrid) were 3,5-diglucosides of delphinidin, petunidin, pelargonidin, peonidin and malvidin and acetyl-acylated malvidin, delphinidin and petunidin. The Lamiaceae species (Salvia aurea × dolomitica Bae’s blue, Salvia dolomitica Codd and Plectranthus zuluensis T. Cooke) mainly contained rutinosides of pelargonidin, glucosides of petunidin, pelargonidin and p-coumaric acid- and malonyl-acylated delphinidin and malvidin. Lamiaceae pigments had higher thermal and oxidative stability. This could be due to aromatic malonyl-acylated anthocyanin self-association and strong intermolecular interactions with phenolic acids and derivatives. Flowers from Lamiaceae and Geraniaceae have potential application as natural food colourants, but temperature and oxidising conditions must be considered depending on the particular species being used.     

Analytical approach on magnetohydrodynamic Casson fluid flow past a stretching sheet via Adomian decomposition method

Flow phenomena of three-dimensional conducting Casson fluid through a stretching sheet are proposed in the present investigation with the impact of the magnetic parameter in a permeable medium. The adaptation of particular transformations is useful to modify the governing equations into their nondimensional as well as the ordinary form. However, these transformed equations are nonlinear and approximate analytical methods for the solution of the complex form of governing equations. In particular, the Adomian decomposition method is proposed for the solution. The behavior of several variables, such as the magnetic and porous matrix, on the flow profile as well as the rate of shear stress, are discussed via graphs and tables. The conformity of the current result with the earlier study shows a road map for further investigation. The major concluding remarks are; the retardation in the velocity distribution is rendered due to an increase in the Casson parameter moreover, the Casson parameter favors in reducing the rate of shear stress coefficient in magnitude.     

基于SVD和SSA-VMD降噪的轴承故障特征提取

针对强噪声背景下轴承故障特征提取困难的问题，提出一种基于奇异值分解和参数优化变分模态分解联合降噪的轴承故障特征提取方法(SSVMD)：首先，对原始信号进行奇异值分解(Singular Value Decomposition，SVD)处理，运用奇异值差分谱法选取有效奇异值并将原始信号重构得到初步降噪信号；其次，为防止故障信息丢失，将残余信号进行麻雀算法(Sparrow Search Algorithm，SSA)优化的变分模态分解(Variational Mode Decomposition，VMD）算法处理，得到最佳的模态个数K和惩罚参数α，选取峭度值最大、包络熵最小的IMF分量与初步降噪信号叠加得到最终降噪信号，并对信号进行包络分析；最后，通过仿真和试验数据分析得出，该方法能在信噪比很低的情况下降低噪声含量并提取轴承故障特征，为设备的状态监测和故障诊断提供理论依据。     

基于VMD和改进TCN的短期光伏发电功率预测

光伏发电功率存在波动性,且光伏出力易受各种气象特征影响,传统TCN网络容易过度强化空间特性而弱化个体特性。针对上述问题,文中提出一种基于VMD和改进TCN的短期光伏发电功率预测模型。通过VMD将原始光伏发电功率时间序列分解为若干不同频率的模态分量,将各个模态分量以及相对应的气象数据输入至改进TCN网络进行建模学习。利用中心频率法确定VMD的最优分解模态分解个数。在传统TCN预测模型的基础上,使用DropBlock正则化取代Dropout正则化以达到抑制卷积层中信息协同的效果,并引入注意力机制自主挖掘并突出关键气象输入特征的影响,量化各气象因素对光伏发电的影响,从而提高预测精度。以江苏省某光伏电站真实数据为例进行仿真实验,结果表明所提预测方法的RMSE为0.62 MW,MAPE为2.03%。     

Direct high-purity hydrogen production from ammonia by using a membrane reactor combining V-10mol%Fe hydrogen permeable alloy membrane with Ru/Cs2O/Pr6O11 ammonia decomposition catalyst

The hydrogen production capabilities of the membrane reactor combining V-10 mol%Fe hydrogen permeable alloy membrane with Ru/Cs₂O/Pr₆O₁₁ ammonia decomposition catalyst are studied. The ammonia conversion is improved by 1.7 times compared to the Ru/Cs₂O/Pr₆O₁₁ catalyst alone by removing the produced hydrogen through the V-10mol%Fe alloy membrane during the ammonia decomposition. 79% of the hydrogen atoms contained in the ammonia gas are extracted directly as high-purity hydrogen gas. Both the Ru/Cs₂O/Pr₆O₁₁ catalyst and the V-10 mol% Fe alloy membrane are highly durable, and the initial performance of the hydrogen separation rate lasts for more than 3000 h. The produced hydrogen gas conforms to ISO 14687–2:2019 Grade D for fuel cell vehicles because the ammonia and nitrogen concentrations are less than 0.1 ppm and 100 ppm, respectively.     

基于VMD和BSA-KELM的高陡边坡位移预测模型研究

边坡位移的时间序列曲线存在复杂的非线性特性,传统的预测模型精度不足以满足预测要求。为此提出了基于变分模态分解的鸟群优化-核极限学习机的预测模型,并用于河北省某水泥厂的边坡位移预测。该方法首先采用VMD把边坡位移序列分解为一系列的有限带宽的子序列,再对各子序列分别采用相空间重构并用核极限学习机预测,采用鸟群算法优化相空间重构的嵌入维度和KELM中惩罚系数和核参数三个数值,以取得最优预测模型。最后将各个子序列预测值叠加,得到边坡位移的最终预测值。结果表明：和KELM、BSA-KELM、EEMD-BSA-KELM模型相比,基于VMD的BSA-KELM预测精度更高,为边坡位移的预测提供一种有效的方法。