基于人工智能算法的投诉用户质差小区定位及预测的方法研究

目前LTE及GSM的质差小区投诉定位主要是依靠用户投诉的地址回放分析附近小区是否存在性能、告警上的裂变,如无则安排人员现场测试信号强度、干扰等。为了解决自动定位投诉质差小区,创新性提出以数据驱动来实现业务规则自动化,充分考虑用户投诉的时间和问题、网络交互信令、无线性能指标和告警等海量数据,运用人工智能技术中的逻辑回归及决策树算法训练出“2G语音、VoLTE语音及数据业务的投诉质差小区定界模型、质差小区预测模型及问题网元”,更快速,更智能,更准确输出语音及数据业务投诉原因、质差小区及质差原因,并对潜在质差小区进行预测,对无线规划、基站建设、故障处理、网络改造等方面的工作也具有积极指导意义。     

Prediction of rock mass P wave velocity using blasthole drilling information

In this paper, the development of the models for the prediction of rock mass P wave velocity is presented. For model development, the database of 53 cases including widely used and recorded drilling parameters and P wave velocity was constructed from the field studies conducted in 13 open pit lignite mines. Both conventional linear, non-linear multiple regression and Adaptive Neuro Fuzzy Inference System (ANFIS) were used for model development. Prediction performance indicators showed that ANFIS model presented the best performance and it can successfully be used for the preliminary prediction of P wave velocities of rock masses.     

Experimental study on combustion stability and performance of hydrogen-enriched compressed natural gas of a free-piston linear generator

Free Piston linear Generator (FPLG) engine fueled by compressed natural gas (CNG) has recently gained increased research attention. However, due to the low-velocity burning and poor lean limit of CNG fuel, the FPLG engine combustion stability, performance, and efficiency are still low. Hydrogen has a greater burning velocity with wider flame limits that could extend the lean burn limits and combustion characteristics of CNG. This paper compares pure CNG and 10% hydrogen-enriched CNG at various ignition speeds (0.6 ms, 0.8 m/s, and 1 m/s), injection positions (0 mm, 5 mm, 10 mm and 15 mm), and lambda ratios (0.9, 1.4 and 1.7) on the combustion characteristics, performance, and conversion efficiency are duly discussed. The findings show that the FPLG combustion stability limits increase with the hydrogen addition into the CNG. The CNG in-cylinder pressure increases significantly when the injection position is advanced, whereas the hydrogen addition reduces the influence of the injection position. The heat release rate increases by 15.62% and 23.72% with hydrogen addition, corresponding to the advanced and retarded injection positions. Consequently, the hydrogen addition increases the power RMS to 209.21 W and 232.64 W with an increment of 3.46% and 3.13%, respectively. Conclusively, the hydrogen addition into the CNG evidently shortens the combustion duration while improving the heat release rate, combustion stability, power RMS, Cycle-to-Cycle variation, and conversion efficiency.     

Comparison of thermophilic and hyperthermophilic dark fermentation with subsequent mesophilic methanogenesis in expanded granular sludge bed reactors

Herein, dark fermentation (DF, V = 5.5 L) and subsequent mesophilic methanogenesis (V = 43.5 L) are run as expanded granular sludge bed reactors (EGSB) at thermophilic (υDF = 60 °C) and hyperthermophilic (υDF = 80 °C) temperatures. A synthetic glucose wastewater is run with a 22.5 g/L chemical oxygen demand (COD) and 48–9 h hydraulic retention times (HRTs), giving organic loading rates (OLRs) of 11–60 g COD/L/d for DF. The maximum hydrogen production rate (HPR) is HPR = 3.0 m³/m³/d for HRT = 9 h with a 50 L/kg COD hydrogen yield (HY) and 40 vol% H₂. Methane production rate (MPR) reaches MPR = 2.6 m³/m³/d with 70 vol% CH₄ at HRT = 2.8 d. The highest H₂ yields are HY = 180 L/kg COD with 53 vol% H₂ (thermophilic, HRT = 48 h). Hyperthermophilic temperatures led to lower HPRs (0.7 m³/m³/d) and MPRs (1.6 m³/m³/d). 53% of Thermoanaerobacterium thermosaccharolyticum as an H₂ producer are found. Discoloration of granular sludge from black to white and granule stability was observed in DF.     

Deep-blue thermally activated delayed fluorescence emitter with a very high fluorescence rate

Conventional thermally activated delayed fluorescence (TADF) molecules achieve small energy differences between the lowest singlet and triplet excited states (ΔE_ST) by enhancing the intramolecular charge transfer, which inevitably leads to a wide emission spectrum and low fluorescence rate. Here, we prepared a deep blue TADF molecule via a small ΔE_ST pyridine-phenol fluoroboron complex as the acceptor. The small ΔE_ST is maintained when carbazole donors are attached to the 4-position of the phenyl rings in the fluoroboron complex. Benefiting from the strong electron coupling between the donor (D) and acceptor (A) moieties, the compound Cz-4-BF exhibits a high fluorescence rate of 4.8 × 10⁸ s⁻¹ and a small D-A dihedral angle change in the excited state. Consequently, a photoluminescence (PL) quantum yield of nearly 100% and a PL spectrum with full-width at half-maximum (FWHM) < 60 nm were obtained in solution and low-concentration doped films. A TADF-sensitized fluorescence (TSF) device containing Cz-4-BF achieves an external quantum efficiency of 21%, which is higher than the devices employing classical fluorescent emitters and multiple resonance-type TADF emitters. The Cz-4-BF-based TSF device shows significantly improved color coordinates of (0.14, 0.10) versus a control device without Cz-4-BF.     

Preventive replacement policies with time of operations,mission durations,minimal repairs and maintenance triggering approaches

When a mission arrives at a random time and lasts for a duration, it becomes an interesting problem to plan replacement policies according to the health condition and repair history of the operating unit, as the reliability is required at mission time and no replacement can be done preventively during the mission duration. From this viewpoint, this paper proposes that effective replacement policies should be collaborative ones gathering data from time of operations, mission durations, minimal repairs and maintenance triggering approaches. We firstly discuss replacement policies with time of operations and random arrival times of mission durations, model the policies and find optimum replacement times and mission durations to minimize the expected replacement cost rates analytically. Secondly, replacement policies with minimal repairs and mission durations are discussed in a similar analytical way. Furthermore, the maintenance triggering approaches, i.e., replacement first and last, are also considered into respective replacement policies. Numerical examples are illustrated when the arrival time of the mission has a gamma distribution and the failure time of the unit has a Weibull distribution. In addition, simple case illustrations of maintaining the production system in glass factories are given based on the assumed data.     

Effect of surcharge loading rate and mobilized load ratio on the performance of vacuum–surcharge preloading with PVDs

The results from three laboratory model tests performed under various vacuum and surcharge loads with PVDs are reported. Different SLRs were adopted to investigate the effect on the consolidation of dredged soil. To measure the lateral displacement, a refitted inclinometer was developed and tested. In the tests, the settlement, lateral displacement, and vane shear strength were measured, and the degree of consolidation (DOC), horizontal coefficient of consolidation (C_h), and bearing capacity were calculated. The results indicate that larger SLR values promote consolidation. The largest vane shear strength, settlement, and C_h values were all obtained under the highest SLR, and the bearing capacity under this SLR was more than double that under the lowest SLR. The DOC was found to increase with the growth of the SLR. However, considering the vacuum pressure was higher in Case-III, the influence of SLR on reinforcement effect may not be so significant.     

Parallel quality-related dynamic principal component regression method for chemical process monitoring

Traditional quality-related process monitoring mainly focuses on the magnitude change of the quality variables caused by additive faults. However, the abnormal fluctuations in the quality variables caused by multiplicative faults are often overlooked. In this paper, a novel parallel dynamic principal component regression (P-DPCR) algorithm is proposed to monitor the changes in the magnitude and fluctuation of the quality variables simultaneously. Firstly, in order to eliminate the interference of quality-unrelated variables, the quality-related process variables are selected on the basis of correlation analysis. Secondly, the dynamic extension and moving window are carried out for process variables and quality variables, in which the dynamic variables space (called X-space/Y-space) and the variance space (called VX-space/VY-space) are constructed. Afterwards, double quality-related statistics based on the regression model of these four spaces are given, and the comprehensive monitoring decision can be obtained. Finally, two numerical cases and the Tennessee Eastman process are used to show the effectiveness of the proposed method.     

基于深度学习的人体姿态估计方法综述

基于深度学习的人体姿态估计方法旨在通过构建合适的神经网络，直接从二维的图像特征中回归出人体姿态信息。主要按照2D人体姿态估计到3D人体姿态估计的顺序，并从单人检测与多人检测、稀疏的关节点检测与密集的模型构建等方面，对近年来基于深度学习的人体姿态估计方法进行系统介绍，从而初步了解如何通过深度学习的方法得到人体姿态的各个要素，包括肢体部件的相对朝向和比例尺度、骨骼关节点的位置坐标和连接关系，甚至更为复杂的人体蒙皮模型信息。最后,对当前研究面临的挑战以及未来的热点动向进行概述，清晰地呈现出该领域的发展脉络。     

含水率对砂岩动态拉伸强度的影响

工程中的岩石具有不同的含水性，研究不同含水率岩石动态力学性质的变化规律，对岩石工程的设计和建设具有很强的指导意义。为研究不同含水率对砂岩动态拉伸强度的影响，利用霍普金森压杆（SHPB）试验装置对不同含水率试样进行了一系列动态巴西劈裂试验，研究了不同含水率砂岩在不同加载率条件下的动态拉伸强度变化规律。试验结果表明：岩石的动态拉伸强度随着加载率的增加而增加，其率相关性与含水率有关，饱和试样的率相关性较强，而干燥岩石的动态强度对加载率的变化不敏感。当加载率较低时，岩石的拉伸强度随着含水率的增加而降低；当加载率较高时，由于水的Stefan效应，水对岩石裂纹产生抗力，阻碍其扩展，导致岩石强度增加，饱和试样的动态拉伸强度出现高于非饱和试样强度的现象。