Flexible Piezoelectric Acoustic Sensors and Machine Learning for Speech Processing

Flexible piezoelectric acoustic sensors have been developed to generate multiple sound signals with high sensitivity, shifting the paradigm of future voice technologies. Speech recognition based on advanced acoustic sensors and optimized machine learning software will play an innovative interface for artificial intelligence (AI) services. Collaboration and novel approaches between both smart sensors and speech algorithms should be attempted to realize a hyperconnected society, which can offer personalized services such as biometric authentication, AI secretaries, and home appliances. Here, representative developments in speech recognition are reviewed in terms of flexible piezoelectric materials, self-powered sensors, machine learning algorithms, and speaker recognition.     

S元素含量对IF钢热轧析出物的影响

在Gleeble-3500热模拟试验机上,利用模拟轧制和卷取方法研究了不同S含量Ti-IF钢热轧成品第二相粒子的析出行为。试验结果表明,Ti-IF钢的析出物类型随着S含量的增加出现明显变化,当S质量分数为140×10^-6时,大尺寸析出物中出现TiS单独析出情况,同时随着钢中S含量的增加,大尺寸析出物(200 nm以上)逐渐增多,主要析出物类型为TiS和Ti₄C₂S₂;而小尺寸析出物(20 nm以下)逐渐减少,主要析出物类型为TiC。结合钢种的热力学分析可知,当S含量增加时,基体内固溶的C原子,首先满足Ti₄C₂S₂形成的需要,其次再以TiC的形式析出,可见S元素对固定间隙C原子有明显作用,由此提出钢种设计时S元素含量按下限设定的理论。     

HVAF喷涂Inconel625涂层在生物质发电环境的高温腐蚀行为

秸秆等生物质焚烧发电时产生的含氯气体和碱金属氯化物腐蚀使受热面金属管道的服役寿命比煤电机组显著降低。 管材表面堆焊镍基耐腐蚀合金的技术尽管可显著提高管道服役寿命,但存在工作效率低、不适合现场施工、管道热变形等诸多问题。 采用可现场施工的空气超音速火焰喷涂(HVAF)在 TP347H 耐热钢表面,制备了 Inconel 镍基耐高温腐蚀涂层,研究了 TP347H 耐热钢喷涂 Inconel 625 合金涂层前后的长期高温腐蚀特性(550 ℃ ,500 h),验证了 HVAF Inconel 625 合金涂层的高温含氯腐蚀防护作用。 显微观察结果表明,优化工艺参数条件下 HVAF 涂层组织致密、 孔隙率低至 0. 72%,与基材结合良好。 腐蚀增重结果表明,采用 HVAF 制备 Inconel 625 合金涂层后,TP347H 耐热钢的腐蚀增重降低 7. 6 倍,耐腐蚀性能显著提升。 冲蚀试验结果表明,HVAF Inconel 625 合金涂层在最初阶段由于表层凸起颗粒的剥落而冲蚀性能极低,进入稳定阶段后耐冲蚀性能提高,与 TP347H 基材的耐冲蚀性能相当。     

Multiphase batch process monitoring based on higher-order cumulant analysis

In this paper, a two-step phase partitioning strategy is proposed. Firstly, the number of phases is automatically determined according to the intra-class and inter-class similarity of feature space data, thus avoiding excessive manual intervention. Secondly, the phases are partitioned by step-wise adding the kernel entropy extended load matrix (KEELM), avoiding the wrong division of phases caused by unstable state of working condition conversion. A process monitoring model based on multiway kernel entropy independent component analysis (MKEICA) is constructed in each sub-phase to deal with complex batch processes with nonlinear and non-Gaussian properties. A new statistics index based on the idea of high order cumulant analysis (HCA) is constructed in each sub-phase for process monitoring. Compared with the traditional second-order statistics, it can obtain high-order statistical information. Finally, the proposed method is applied to the penicillin simulation platform process and compared with the traditional multiway kernel independent components analysis (MKICA) and HCA methods to verify the effectiveness of the method that is mentioned above.     

Fabricating a partial wetting structure for improving the toughness of intumescent flame-retardant HDPE

A multistep processing method was developed to fabricate a partial wetting morphology for improving toughness of flame retardant polymer. In the first step, high-density polyethylene (HDPE) and nylon 6 (PA6) were melt-extruded with intumescent flame retardant (IFR) for fabricating HDPE/PA6/IFR blends with a core–shell structure (core: IFR, shell: PA6). At the second step, maleic anhydride-grafted-linear low-density polyethylene (LLDPE-g-MAH) was melted with HDPE/PA6/IFR at processing temperatures slightly below the melting temperature of PA6 to produce a partial wetting morphology in which LLDPE-g-MAH phase with the sphere was dispersed at the HDPE/PA6 interface. The effect of the LLDPE-g-MAH content on the impact strength was investigated, and high toughness was exhibited in the blend with 2 wt % LLDPE-g-MAH. Its elongation at break and notched impact strength were 43 and 270% higher, respectively, than that of neat HDPE. The unique interface failure mode was responsible for the high impact strength. © 2019 Wiley Periodicals, Inc. J. Appl. Polym. Sci. 2020 , 137, 48735.     

SDN‐based dynamic multipath forwarding for inter–data center networking

Equal‐cost multipath (ECMP)–based traffic engineering (TE) methods are commonly used in intra–data center (DC) networks to improve the transmission performance for east‐west traffic (ie, traffic from server to server within a DC). However, applying ECMP on inter‐DC wide area network (WAN) offers limited performance enhancement as a result of irregular network topology. Since TE can be intelligently and efficiently realized with software‐defined networking (SDN), SDN‐based multipath becomes a popular option. However, SDN suffers from scalability issue caused by limited ternary content‐addressable memory (TCAM) size. In this paper, we propose an SDN‐based TE method called dynamic flow‐entry‐saving multipath (DFSM) for inter‐DC traffic forwarding. DFSM adopts source‐destination–based multipath forwarding and latency‐aware traffic splitting to reduce the consumption of flow entries and achieve load balancing. The evaluation results indicate that DFSM saves 15% to 30% of system flow entries in practical topologies and reduces the standard deviation of path latencies from 10% to 7% than do label‐switched tunneling, and also reduces average latency by 10% to 48% by consuming 6% to 20% more flow entries than do ECMP in less‐interconnected topologies. Note that the performance gain may not always be proportional to flow entry investment, with the interconnectivity between nodes being an important factor. The evaluation also indicates that per‐flow provision consumes several times the flow entries consumed by DFSM but reduces latency by 10% at most. Besides, DFSM reduces the standard deviation of path latencies from 14% to 7% than do even traffic splitting.     

Uncertainty analysis of parameters in non‐point source pollution simulation: case study of the application of the Soil and Water Assessment Tool model to Yitong River watershed in northeast China

Uncertainty analysis of the model parameters in non‐point source pollution (NPSP) simulation is important because of its great effects on predictions and decision‐making. Understanding the main parameters that effect the uncertainty of NPSP is necessary to provide the basis for formulating control measures. In this study, two methods were applied to conduct parameter uncertainty analysis for Soil and Water Assessment Tool (SWAT). Sobol’ method was used to screen out the model parameters with great effects on the runoff, sediment, total nitrogen (TN) and total phosphorus (TP). The results obtained by sensitivity analysis were used subsequent model calibration and further uncertainty analysis. Monte Carlo (MC) method was employed to analyse the effects of parameter uncertainty on the model outputs. However, such problems are time‐consuming because the MC method required to invoke simulation model thousands of times. To address this challenge, a kriging surrogate model was developed to improve the overall calculation efficiency. The results obtained by sensitivity analysis showed that curve number value (CN2), soil evaporation compensation factor (ESCO), universal soil loss equation support practice factor (USLE_P) and initial organic nitrogen concentration in soil layer (SOL_ORGN) had significant effects on the SWAT outputs. The uncertainty analysis results showed that the uncertainty of runoff is the lowest, followed by TP and TN, and the uncertainty of sediment was the greatest. The kriging surrogate model has the ability to solve this time‐consuming problem rapidly with a high degree of accuracy, and thus it is very robust.