The concept of degraded images applied to hazard recognition training in mining for reduction of lost-time injuries

Introduction: This paper discusses the application of a training intervention that uses degraded images for improving the hazard recognition skills of miners. Method: NIOSH researchers, in an extensive literature review, identified fundamental psychological principles on perception that may be employed to enhance the ability of miners to recognize and respond to hazards in their dangerous work environment. Three studies were conducted to evaluate the effectiveness of the degraded image training intervention. A model of hazard recognition was developed to guide the study. Results: In the first study, miners from Pennsylvania, West Virginia and Alabama, who were taught with the aid of degraded images, scored significantly better on follow-up hazard recognition performance measures than those trained using traditional instructional methodologies. The second and third studies investigated the effectiveness of the training intervention at two mining companies. Data collected over a 3-year period showed that lost-time injuries at mines in Alabama and Illinois declined soon after the training intervention was instituted. Impact on Industry: Further exploration of the hazard recognition model and the development of other interventions based on the model could support the validity of the steps in the hazard recognition model.     

基于监督局部映射的煤矿井下人员身份鉴别方法

为提高煤矿井下人员身份识别率,在局部保持投影(LPP)算法的基础上,提出监督局部映射(SLP)算法。该方法充分利用数据的局部和非局部信息及类别信息,对数据进行维数约简,使特征空间同类数据间的距离更小,不同类数据间的距离更大。该方法能够克服煤矿井下艰苦、空间受限环境中人脸、虹膜和指纹识别率不高的问题。在真实步态数据库上的实验结果表明,基于步态的煤矿井下人员身份鉴别是可行的。     

基于FTA-SVM的车辆发动机故障识别方法

发动机结构日益复杂,其故障具有多样性和频发性的特点,收集大量故障样本存在很多实施障碍。为了提高车辆发动机的故障识别的效率和准确性,提出了一种新的结合故障树(FTA)和支持向量机(SVM)各自特点,从故障模式分析到故障类型识别的FTA-SVM故障识别方法。首先利用故障树在复杂系统故障模式分析中的优势,找出系统的故障模式,建立故障树模型,通过对故障树模型中各故障事件的分析,采集与故障事件状态相关的数据,建立数据与故障树底事件的映射模型,最后利用支持向量机在小样本数据处理中的优势,进行故障类型的识别。以发动机的失火故障为例建立了发动机失火故障树模型及故障数据与故障模式映射模型,验证了FTA-SVM方法的有效性和适用性。     

A dual-sensor-based method to recognize pipeline leakage and interference signals

During the detection of pipeline leakages, false alarms of leak detection could be markedly reduced if the interference signals resulting from pressure regulating, pump regulating or valve movements could be accurately distinguished. A digital recognition method for interference signals and leakage signals based on a dual-sensor system is proposed in this paper. It is demonstrated that the direction of the signal can be recognized by a cross-correlation calculation between two signals from the dual-sensor, one of which undergoes forward linear interpolation and backward linear interpolation. Based on this theory, the interference signal and the leak signal can be discriminated exactly, and the distance between the two sensors in the dual-sensor system can be considerably reduced without needing to increase the sampling frequency. The monotonicity of the cross-correlation function is demonstrated, and a fast discrimination algorithm based on a binary extreme search method, which decreases the computational load and maintains global optimization, is also proposed. A pre-processing method of the actual signal is proposed to decrease the identity requirement for the two sensors in a dual-sensor system. In the experiment based on artificial signals, the proposed discrimination algorithm could achieve accurate recognition of the abnormal signal, and as such, the theory and application of pipeline leak detection based on dual-sensor systems are extended.     

基于BERT-BILSTM-CRF模型的电力行业事故文本智能分析*

为解决电力行业事故报告文本较长、语义复杂,难以进行有效文本识别问题,提出1种以BERT作为底层的预训练模型,并设计1种双重注意力机制编码器,结合BILSTM-CRF深度挖掘事故文本语义特征,从而实现文本智能分析。首先构建电力词典,通过对BERT预训练,进行BIO标注,然后引入BILSTM-CRF模型实现对文本标签智能分类,最后将该模型与现行其他4种深度学习模型进行对比。研究结果表明:该模型智能识别精确率、召回率及F1值(查准率)均达到约97%,较其他4种模型中效果最好的模型分别提高0.02,0.03,0.02。研究结果可为电力行业事故报告文本分析提供1种新思路。     

A novel approach for VOC source apportionment combining characteristic factor and pattern recognition technology in a Chinese industrial area

Volatile organic compound (VOC) emission control and source apportionment in small-scale industrial areas have become key topics of air pollution control in China. This study proposed a novel characteristic factor and pattern recognition (CF-PR) model for VOC source apportionment based on the similarity of characteristic factors between sources and receptors. A simulation was carried out in a typical industrial area with the CF-PR model involving simulated receptor samples. Refined and accurate source profiles were constructed through in situ sampling and analysis, covering rubber, chemicals, coating, electronics, plastics, printing, incubation and medical treatment industries. Characteristic factors of n-undecane, styrene, o-xylene and propane were identified. The source apportionment simulation results indicated that the predicted contribution rate was basically consistent with the real contribution rate. Compared to traditional receptor models, this method achieves notable advantages in terms of refinement and timeliness at similar accuracy, which is more suitable for VOC source identification and apportionment in small-scale industrial areas.     

基于视频识别的直接作业环节安全管控

概述了石化行业现场直接作业环节的安全管控现状,分析了现场管控过程中存在的问题。考虑现场安全管理和监督监控的实际需要,设计了石化行业直接作业现场智能化管控系统,并深入研究作业现场违章行为图像识别的关键技术。现场应用表明,系统充分体现了日常管理、实时监控、智能报警、统计分析等方面的便利性和有效性,各类违章行为图像识别准确率达到80%以上,具有一定的推广价值。     

Nestmate recognition in three species of stenogastrine wasps (Hymenoptera,Vespidae)

The capacity to recognise a conspecific intruder was investigated in Parischnogaster jacobsoni, Liostenogaster flavolineata and L. vechti, three species of primitively social wasps of the subfamily Stenogastrinae. Results of behavioural experiments carried out in the field showed that females of all three species react pacifically if presented with female nestmates, but aggressively reject an intruder from a conspecific colony. As L. flavolineata and L. vechti both build large clusters of nests, often very close to each other, the recognition capacity among females from different nests, but in the same conspecific cluster, was also investigated. Females of both species were more aggressive towards females from a different colony in the same cluster than towards their female nestmates. Additional experiments on L. flavolineata showed that there was no difference in reaction towards females from colonies nearer or further from the tested colony but within the same cluster, nor towards females from a different cluster. The capacity to recognise an alien conspecific nest containing immature brood was investigated in P. jacobsoni. Adult females of this species, invited to land on an alien nest which had experimentally been exchanged for their own, accepted the new nest and partially destroyed the immature brood. The behaviour of the females when they land on an alien nest, however, suggests that they do recognise the nest as foreign. Acceptance of foreign nests coupled with low immature brood destruction is probably due to the high energetic costs of egg-deposition and larval rearing in stenogastrine wasps. These results suggest that nestmate recognition in these wasps is very efficient, even though they belong to the most primitive subfamily of social wasps. Received: 16 April 1996/Accepted after revision: 9 August 1996     

The chemical basis for trail recognition in Lasius nipponensis (Hymenoptera: Formicidae)

Summary. In this paper we report on the chemical basis for trail recognition in Lasius nipponensis. On and near trails in the field, workers became aggressive against conspecific intruders and succeeded in protective contests, while intruders usually avoided confrontation. Such asymmetric interactions were also observed in the laboratory when two non-nestmate workers were sequentially placed in a clean glass dish, while mutual aggression was observed when they were placed simultaneously. Asymmetric aggression was also observed when the workers were placed in a dish previously conditioned by other workers, or when the dish was treated with the hexane rinse of the conditioned dish. The rinse contained a series of hydrocarbons, in which components and proportion were almost identical to those of the cuticular hydrocarbons of the workers, except for a lack of n-alkanes. Amounts of the hydrocarbons that remained on the dish were very small when all the tarsi of the workers were incapacitated. We therefore consider that the hydrocarbons are not adhesion of the cuticular hydrocarbons but secretion from the tarsi of workers, and serve as a key signal for trail recognition in this ant.     

论生态省建设

本文以吉林生态省建设为例,对生态省建设提出了看法和建议。