Automatic detection devices rely on accurate and reliable sensor readings, which is a prerequisite for their good running. Self-validating sensor technology that realizes sensor operating status estimation and data validation can provide an intelligent functional framework for sensor status monitoring to improve the reliability and maintainability of the system. After nearly thirty years of development, self-validating sensors have achieved numerous theoretical and application results. In particular, the stability and reliability of gas chemical sensors in the field of artificial olfaction have been a bottleneck that limits the industrialization of the electronic nose system. Obviously, self-validating sensor technology exactly provides a potential solution for artificial olfaction application. This paper aims to systematically review the current development and typical applications of self-validating sensor technology, summarize the implementation methods to its different functional modules as well and demonstrate its potential application value in artificial olfaction. © 2024 Elsevier Ltd

Food is closely related to human life. With the development of the times, the human demand for food has changed dramatically. People pay closer attention to the safety, health, composition, brand, origin, and processing method of food, which is precisely inseparable from food testing technology. Currently, there are many food inspection technologies, and the electronic nose (E-nose), as an efficient, fast, non-destructive, and promising technology, has been successfully applied in many aspects of the food industry and has shown promising results. This paper first introduces the basic principle and composition of the E-nose. Then it describes in detail the key elements, including gas sensor selection, sampling method design, data acquisition and information processing. Further summarizes the various typical applications of E-nose technology in the food industry in recent years, including six application directions: freshness assessment, process monitoring, flavor evaluation, authenticity evaluation, quality control, origin traceability and pesticide residue detection. Finally, the critical problems that need to be solved in the current application of E-nose technology in the food industry are discussed, and the potential future research directions in this field are foreseen.

大气环境污染对人类的健康与可持续发展产生巨大威胁,我国政府高度重视并相继出台多部关于大气污染综合防治的相关文件,指导大气污染治理工作。大气环境数据为大气污染综合防治提供数据和理论支撑。因此,开展大气环境污染物实时在线监测的研究具有很强的实践意义。针对当前对低成本、多功能的大气环境污染物监测系统的需求,本文的主要研究内容如下:通过分析大气环境监测领域的国内外研究现状,得出本文的设计需求,在此基础上进行了系统方案设计,得出了由感知层、网络层、应用层组成的系统结构,划分了监测节点的硬件功能单元,选出了主要器件的具体型号。在感知层监测节点功能单元划分中,NO2传感器、CO传感器、温湿度传感器、颗粒物传感器构成传感器单元用来实现多种环境参数的获取;基于高性能微控制器STM32F103ZET6构成主控单元负责节点功能控制及算法实现;利用超低功耗远距离通信技术NBIOT实现监测节点配网;采用DC/DC变换技术构成电源单元给节点供电。在感知层监测节点软件设计中,基于μC/OS-Ⅲ编程,通过对节点功能的分析设计了6个任务,采用信号量、消息队列、事件标志组等内核对象进行任务管理。在系统网络层,完成云平台二次开发后,监测节点可通过NBIOT组网进而利用MQTT协议实现监测节点数据上传及云端存储;在应用层,利用Web界面开发工具IOT Studio设计了网页与业务逻辑,实现了监测节点的数据可视化及超阈值报警。本文提出了一种基于遗传算法（GA）优化反向传播神经网络（BPNN）的气体定量分析的方法,利用GA优化BPNN的权值和偏置,并给出了训练后模型的C语言实现流程。为了验证本文的硬件设计及所提方法的有效性,搭建了实验系统,采用平均相对误差（MRE）进行模型评价并与其他方法进行了对比。最后进行了硬件单元测试及系统测试,实验表明,系统能稳定运行,能够满足对多种大气环境污染物实时在线监测的需求。

This paper proposes a novel fault diagnosis method for rolling bearing based on hierarchical refined composite multiscale fluctuation-based dispersion entropy (HRCMFDE) and particle swarm optimization-based extreme learning machine (PSO-ELM). First, HRCMFDE is used to extract fault features in the vibration signal at different time scales. By introducing the hierarchical theory algorithm into the vibration signal decomposition process, the problem of missing high-frequency signals in the coarse-grained process is solved. Fluctuation-based dispersion entropy (FDE) has the characteristics of insensitivity to noise interference and high computational efficiency based on the consideration of nonlinear time series fluctuations, which makes the extracted feature vectors more effective in describing the fault information embedded in each frequency band of the vibration signal. Then, PSO is used to optimize the input weights and hidden layer neuron thresholds of the ELM model to improve the fault identification capability of the ELM classifier. Finally, the performance of the proposed rolling bearing fault diagnosis method is verified and analyzed by using the CWRU dataset and MFPT dataset as experimental cases, respectively. The results show that the proposed method has high identification accuracy for the fault diagnosis of rolling bearings with varying loads and has a good load migration effect.

Hyperspectral image (HSI) classification methods based on three-dimensional convolutional neural network (3DCNN) have problems of overfitting the in-sample training process and difficulty in highlighting the role of discriminant features, which reduce the classification accuracy. To solve the above problems, an HSI classification method based on M-3DCNN-Attention is proposed. First, the Mixup algorithm is used to construct HSI virtual samples to expand the original data set. The sample size of the expanded data set is twice that of the original data set, which greatly alleviates the overfitting phenomenon caused by the small sample of HSI. Second, the structure of 3DCNN is improved. A convolutional block attention module (CBAM) is added between each 3D convolutional layer and ReLU layer, and a total of three CBAMs are used so as to highlight the discriminant features in spectral and spatial dimensions of HSI and suppress the nondiscriminant features. Finally, the spectral-spatial features are transferred to the Softmax classifier to obtain the final classification results. The comparative experiments are conducted on three hyperspectral data sets (Indian Pines, University of PaviaU, and Salinas), and the overall accuracy of M-3DCNN-Attention is 99.90%, 99.93%, and 99.36%, respectively, which is better than the comparative methods. (c) 2022 Society of Photo-Optical Instrumentation Engineers (SPIE)

在“双碳”战略的背景下，针对国内对碳足迹采集终端及系统的迫切需求，提出了基于电力采集终端及通信系统的解决方案，并利用混合边界扫描技术提出了具体的“虚拟探针”可测性设计方案。还针对基于单一类型故障特征进行非线性“簇”电路故障诊断准确率低的难题，在研究小波包变换、PCA及Volterra核特征提取的基础上，提出了小波包变换与PCA特征层融合，并与基于Volterra核特征的初级诊断结果进行决策层融合的故障诊断方法。实验表明，该方法可以有效提高故障诊断的准确率。