我国爆破行业发展面临的问题与思考

针对行业发展存在的相关问题与困难,为适应新形势的要求,从国内外经济形势的发展现状出发,阐述了国际经济全球化面临的挑战以及国内经济减速等影响我国爆破行业发展的新形势,对我国爆破行业的发展现状困难与机遇进行了深入分析,特别是对以互联网、大数据和云计算为代表的信息技术以及人工智能的发展对爆破行业即将带来的深刻影响进行了探讨。对当前影响我国爆破行业发展的外部环境、内部机制、监管尺度等相关问题进行了深入思考,提出了调整爆破行业结构、促进企业转型升级、推进企业信息化建设和国际化进程等解决之道,并对主管部门、行业组织如何在推进行业结构调整、企业转型升级中发挥更大作用提出建议。     

Large‐Stroke Electrochemical Carbon Nanotube/Graphene Hybrid Yarn Muscles

Artificial muscles are reported in which reduced graphene oxide (rGO) is trapped in the helical corridors of a carbon nanotube (CNT) yarn. When electrochemically driven in aqueous electrolytes, these coiled CNT/rGO yarn muscles can contract by 8.1%, which is over six times that of the previous results for CNT yarn muscles driven in an inorganic electrolyte (1.3%). They can contract to provide a final stress of over 14 MPa, which is about 40 times that of natural muscles. The hybrid yarn muscle shows a unique catch state, in which 95% of the contraction is retained for 1000 s following charging and subsequent disconnection from the power supply. Hence, they are unlike thermal muscles and natural muscles, which need to consume energy to maintain contraction. Additionally, these muscles can be reversibly cycled while lifting heavy loads.     

Shape Memory Alloy (SMA)‐Based Microscale Actuators with 60% Deformation Rate and 1.6 kHz Actuation Speed

Shape memory alloys (SMAs) are widely utilized as an actuation source in microscale devices, since they have a simple actuation mechanism and high‐power density. However, they have limitations in terms of strain range and actuation speed. High‐speed microscale SMA actuators are developed having diamond‐shaped frame structures with a diameter of 25 µm. These structures allow for a large elongation range compared with bulk SMA materials, with the aid of spring‐like behavior under tensile deformation. These actuators are validated in terms of their applicability as an artificial muscle in microscale by investigating their behavior under mechanical deformation and changes in thermal conditions. The shape memory effect is triggered by delivering thermal energy with a laser. The fast heating and cooling phenomenon caused by the scale effect allows high‐speed actuation up to 1600 Hz. It is expected that the proposed actuators will contribute to the development of soft robots and biomedical devices.     

在盐湖地区暴露48个月纯锌的腐蚀行为

采用X射线衍射(XRD)、扫描电子显微镜(SEM)、金相显微镜和电化学阻抗等手段研究了锌在青海盐湖大气环境(富盐干旱型大气环境)中的腐蚀行为。结果表明,在青海盐湖大气环境中锌的腐蚀规律遵循经验公式m=Atn。锌的向地面比向天面腐蚀严重,向天面暴晒48个月出现锈层脱落现象。两个表面的腐蚀产物均由Zn5(OH)8Cl2·H2O,Zn5(CO)3(OH)6和Zn4SO4(OH)6·3H2O组成,锈层均富含SiO2。电化学结果表明,随着暴晒时间的延长向地面的极化电阻Rp逐渐增大,而向天面的Rp逐渐增加,而暴晒48个月时减小。锈层有抑制基体腐蚀的作用,对两个表面锈层的保护性随暴晒时间的延长而增大,而向天面暴晒48个月时保护性减弱。     

Intelligent Firefly Algorithm Deep Transfer Learning Based COVID-19 Monitoring System

With the increasing and rapid growth rate of COVID-19 cases, the healthcare scheme of several developed countries have reached the point of collapse. An important and critical steps in fighting against COVID-19 is powerful screening of diseased patients, in such a way that positive patient can be treated and isolated. A chest radiology image-based diagnosis scheme might have several benefits over traditional approach. The accomplishment of artificial intelligence (AI) based techniques in automated diagnoses in the healthcare sector and rapid increase in COVID-19 cases have demanded the requirement of AI based automated diagnosis and recognition systems. This study develops an Intelligent Firefly Algorithm Deep Transfer Learning Based COVID-19 Monitoring System (IFFA-DTLMS). The proposed IFFA-DTLMS model majorly aims at identifying and categorizing the occurrence of COVID19 on chest radiographs. To attain this, the presented IFFA-DTLMS model primarily applies densely connected networks (DenseNet121) model to generate a collection of feature vectors. In addition, the firefly algorithm (FFA) is applied for the hyper parameter optimization of DenseNet121 model. Moreover, autoencoder-long short term memory (AE-LSTM) model is exploited for the classification and identification of COVID19. For ensuring the enhanced performance of the IFFA-DTLMS model, a wide-ranging experiments were performed and the results are reviewed under distinctive aspects. The experimental value reports the betterment of IFFA-DTLMS model over recent approaches.     

Fractional Order Nonlinear Bone Remodeling Dynamics Using the Supervised Neural Network

This study aims to solve the nonlinear fractional-order mathematical model (FOMM) by using the normal and dysregulated bone remodeling of the myeloma bone disease (MBD). For the more precise performance of the model, fractional-order derivatives have been used to solve the disease model numerically. The FOMM is preliminarily designed to focus on the critical interactions between bone resorption or osteoclasts (OC) and bone formation or osteoblasts (OB). The connections of OC and OB are represented by a nonlinear differential system based on the cellular components, which depict stable fluctuation in the usual bone case and unstable fluctuation through the MBD. Untreated myeloma causes by increasing the OC and reducing the osteoblasts, resulting in net bone waste the tumor growth. The solutions of the FOMM will be provided by using the stochastic framework based on the Levenberg-Marquardt backpropagation (LVMBP) neural networks (NN), i.e., LVMBPNN. The mathematical performances of three variations of the fractional-order derivative based on the nonlinear disease model using the LVMPNN. The static structural performances are 82% for investigation and 9% for both learning and certification. The performances of the LVMBPNN are authenticated by using the results of the Adams-Bashforth-Moulton mechanism. To accomplish the capability, steadiness, accuracy, and ability of the LVMBPNN, the performances of the error histograms (EHs), mean square error (MSE), recurrence, and state transitions (STs) will be provided.     

A Secure and Effective Energy-Aware Fixed-Point Quantization Scheme for Asynchronous Federated Learning

Asynchronous federated learning (AsynFL) can effectively mitigate the impact of heterogeneity of edge nodes on joint training while satisfying participant user privacy protection and data security. However, the frequent exchange of massive data can lead to excess communication overhead between edge and central nodes regardless of whether the federated learning (FL) algorithm uses synchronous or asynchronous aggregation. Therefore, there is an urgent need for a method that can simultaneously take into account device heterogeneity and edge node energy consumption reduction. This paper proposes a novel Fixed-point Asynchronous Federated Learning (FixedAsynFL) algorithm, which could mitigate the resource consumption caused by frequent data communication while alleviating the effect of device heterogeneity. FixedAsynFL uses fixed-point quantization to compress the local and global models in AsynFL. In order to balance energy consumption and learning accuracy, this paper proposed a quantization scale selection mechanism. This paper examines the mathematical relationship between the quantization scale and energy consumption of the computation/communication process in the FixedAsynFL. Based on considering the upper bound of quantization noise, this paper optimizes the quantization scale by minimizing communication and computation consumption. This paper performs pertinent experiments on the MNIST dataset with several edge nodes of different computing efficiency. The results show that the FixedAsynFL algorithm with an 8-bit quantization can significantly reduce the communication data size by 81.3% and save the computation energy in the training phase by 74.9% without significant loss of accuracy. According to the experimental results, we can see that the proposed AsynFixedFL algorithm can effectively solve the problem of device heterogeneity and energy consumption limitation of edge nodes.     

XA-GANomaly: An Explainable Adaptive Semi-Supervised Learning Method for Intrusion Detection Using GANomaly

Intrusion detection involves identifying unauthorized network activity and recognizing whether the data constitute an abnormal network transmission. Recent research has focused on using semi-supervised learning mechanisms to identify abnormal network traffic to deal with labeled and unlabeled data in the industry. However, real-time training and classifying network traffic pose challenges, as they can lead to the degradation of the overall dataset and difficulties preventing attacks. Additionally, existing semi-supervised learning research might need to analyze the experimental results comprehensively. This paper proposes XA-GANomaly, a novel technique for explainable adaptive semi-supervised learning using GANomaly, an image anomalous detection model that dynamically trains small subsets to these issues. First, this research introduces a deep neural network (DNN)-based GANomaly for semi-supervised learning. Second, this paper presents the proposed adaptive algorithm for the DNN-based GANomaly, which is validated with four subsets of the adaptive dataset. Finally, this study demonstrates a monitoring system that incorporates three explainable techniques—Shapley additive explanations, reconstruction error visualization, and t-distributed stochastic neighbor embedding—to respond effectively to attacks on traffic data at each feature engineering stage, semi-supervised learning, and adaptive learning. Compared to other single-class classification techniques, the proposed DNN-based GANomaly achieves higher scores for Network Security Laboratory-Knowledge Discovery in Databases and UNSW-NB15 datasets at 13% and 8% of F1 scores and 4.17% and 11.51% for accuracy, respectively. Furthermore, experiments of the proposed adaptive learning reveal mostly improved results over the initial values. An analysis and monitoring system based on the combination of the three explainable methodologies is also described. Thus, the proposed method has the potential advantages to be applied in practical industry, and future research will explore handling unbalanced real-time datasets in various scenarios.     

An approach to integrating intelligentdiagnostics and supervision of machine tools

Arguments are presented for the necessity of integrating diagnostics and supervision in technological machines. An example of integrated diagnostics and supervision of the machine tool main drive, based on an expert system and neural network, is shown. Problems of intelligent thermal displacement supervision and questions related to practical supervision of machining centres are presented.     

基于人工神经网络的智能型自适应保护──(Ⅰ)原理和模型结构

介绍了一种基于人工神经网络的智能型自适应继电保护原理其基本思想是利用了比传统保护多得多的信息量它比传统保护能区分更多的故障类型,提高了继电保护的适用范围,如从原理上解决了经高阻抗的短路故障保护问题．本保护的人工神经网络由３个子网络组成：先采用第一个三层ＢＰ网络对输电线路一侧的电流、电压信号进行前置处理,得到其特征量（各次谐波的幅值）;然后,在不同运行工况和不同类型的区内外故障时,再把特征量输入第二个三层ＢＰ网络,以判别区内外故障;第三个ＢＰ网络用于故障相判别．