在线传感器网络智能预知维修诊断技术在空压机组上的运用

为解决企业传统设备管理中离线点巡检存在的问题,结合在线传感器网络的优点,以空压机组为实例,提出了一种在线智能预知维修诊断控制策略,进一步做好企业设备的运行管理工作。     

Equations to predict female manual arm strength based on hand location relative to the shoulder

The purpose of this study was to develop regression equations to predict manual arm strength for a wide variety of hand locations within the reach envelope. Maximum voluntary manual arm strength was determined from 71 female participants in six exertion directions (superior, inferior, anterior, posterior, medial and lateral), in a total of 28 hand locations. Forces ranged from 51.3 to 164.4 N, and had a pooled coefficient of variation of 29.9%. Across all 168 combinations of hand locations and exertion directions, the multivariate regression equations explained 92.5% of the variance and had a root mean square error (RMSE) of only 6.4 N, using only the anterior, lateral and vertical location of the hand relative to the active shoulder joint as inputs. These equations provide a proof-of-principle for our novel regression approach, and represent a first step towards a more comprehensive equation to estimate maximum acceptable forces for occupational tasks.     

Binary classification of imbalanced datasets using conformal prediction

Aggregated Conformal Prediction is used as an effective alternative to other, more complicated and/or ambiguous methods involving various balancing measures when modelling severely imbalanced datasets. Additional explicit balancing measures other than those already apart of the Conformal Prediction framework are shown not to be required. The Aggregated Conformal Prediction procedure appears to be a promising approach for severely imbalanced datasets in order to retrieve a large majority of active minority class compounds while avoiding information loss or distortion.     

Sensory Data Prediction Using Spatiotemporal Correlation and LSTM Recurrent Neural Network

The Wireless Sensor Networks (WSNs) are widely utilized in various industrial and environmental monitoring applications. The process of data gathering within the WSN is significant in terms of reporting the environmental data. However, it might occur that certain sensor node malfunctions due to the energy draining out or unexpected damage. Therefore, the collected data may become inaccurate or incomplete. Focusing on the spatiotemporal correlation among sensor nodes, this paper proposes a novel algorithm to predict the value of the missing or inaccurate data and predict the future data in replacement of certain nonfunctional sensor nodes. The Long-Short-Term-Memory Recurrent Neural Network (LSTM RNN) helps to more accurately derive the time-series data corresponding to the sets of past collected data, making the prediction results more reliable. It is observed from the simulation results that the proposed algorithm provides an outstanding data gathering efficiency while ensuring the data accuracy.     

Electrochemical impedance spectroscopy analysis of V–I characteristics and a fast prediction model for PEM-based electrolytic air dehumidification

PEM-based electrolytic air dehumidification is innovative due to its high efficiency, compact size and cleanness. However, high polarization loss and severe performance degradation have been observed, especially at high applied voltages (>2.5 V). Understanding the V–I characteristics is critical to performance optimization. This study experimentally investigated the V–I characteristics and internal response of materials under various operating conditions, with in-situ Electrochemical Impedance Spectroscopy (EIS) methods. Real-time mass transfer, electrochemical polarization and reaction dynamics of PEM components during dehumidification were derived by EIS. Then, a fast prediction model was built to directly predict the dehumidification rate and attenuation without any iteration, suitable for online monitoring and adjustment. Compared to other models, this model can take a quick understanding of the impact of operating conditions on the material characteristics inside the PEM element. The deviations of current density, PEM proton conductivity and moisture removal were 3%, 11.2% and 15.3%, respectively, compared to experiment data. Results showed that when the applied voltage changed from 1.5 to 3.5 V, the high-frequency resistance of the PEM element increased from 1.69 to 2.69 Ω, and the PEM proton conductivity decreased by about 38 times. The sharp drop in PEM proton conductivity resulted in a current attenuation. With this model, requirements for key components of PEM dehumidification were also obtained. Analysis of the overpotential distribution showed that increasing the water retention and reducing the dependence of proton conductivity on water molecules of the PEM can effectively improve the performance. This research provides guidance for the performance optimization and material selection of PEM-based dehumidification.     

This month ‘Technik ist alles’

The objective of this prospective cohort study was to evaluate if peak or cumulative musculoskeletal discomfort may predict future low-back, neck or shoulder pain among symptom-free workers. At baseline, discomfort per body region was rated on a 10-point scale six times during a working day. Questionnaires on pain were sent out three times during follow-up. Peak discomfort was defined as a discomfort level of 2 at least once during a day; cumulative discomfort was defined as the sum of discomfort during the day. Reference workers reported a rating of zero at each measurement. Peak discomfort was a predictor of low-back pain (relative risk (RR) 1.79), neck pain (RR 2.56), right or left shoulder pain (RR 1.91 and 1.90). Cumulative discomfort predicted neck pain (RR 2.35), right or left shoulder pain (RR 2.45 and 1.64). These results suggest that both peak and cumulative discomfort could predict future musculoskeletal pain.     

Developing multiple regression models from the manufacturer's ground-source heat pump catalogue data

The performance of ground-source heat pumps (GSHP), often expressed as Power drawn and/or the COP, depends on several operating parameters. Manufacturers usually publish such data in tables for certain discrete values of the operating fluid temperatures and flow rates conditions. In actual applications, such as in dynamic simulations of heat pump system integrated to buildings, there is a need to determine equipment performance under operating conditions other than those listed. This paper describes a simplified methodology for predicting the performance of GSHPs using multiple regression (MR) models as applicable to manufacturer data. We find that fitting second-order MR models with eight statistically significant x-variables from 36 observations appropriately selected in the manufacturer catalogue can predict the system global behavior with good accuracy. For the three studied GSHPs, the external prediction error of the MR models identified following the methodology are 0.2%, 0.9% and 1% for heating capacity (HC) predictions and 2.6%, 4.9% and 3.2% for COP predictions. No correlation is found between residuals and the response, thus validating the models. The operational approach appears to be a reliable tool to be integrated in dynamic simulation codes, as the method is applicable to any GSHP catalogue data.     

基于灰色关联故障树的运营期隧道病害风险研究

隧道运营期的管理决定了铁路运行的安全,为保证运营安全,必须对隧道运营期病害的风险进行管理研究。用故障树方法对隧道病害进行分析,找出影响隧道运营安全作为底事件,分析出故障树系统任意一个底事件相关割集的重要度。利用灰色关联的思想得出任意最小割集的关联度,再依据关联度得出需要重视的底事件(既有排水设施年久失修阻塞,材料强度下降,隧道内照明不良),并提出具有针对性的管理改进建议。     

微震三维建模动态分析在冲击地压预测预报中的应用

在采掘工程平面图的基础上建立微震三维模型,从不同角度观察微震监测事件空间分布规律,达到预测工作面推进前方顶底板活动规律的目的,文章以3206工作面、W121集轨等区域微震三维建模动态分析为实例,说明微震三维动态分析在冲击地压预测预报中的应用。