A digital twin auxiliary approach based on adaptive sparse attention network for diesel engine fault diagnosis

Condition monitoring and fault diagnosis of diesel engines are of great significance for safety production and maintenance cost control. The digital twin method based on data-driven and physical model fusion has attracted more and more attention. However, the existing methods lack deeper integration and optimization facing complex physical systems. Most of the algorithms based on deep learning transform the data into the substitution of the physical model. The lack of interpretability of the deep learning diagnosis model limits its practical application. The attention mechanism is gradually developed to access interpretability. In this study, a digital twin auxiliary approach based on adaptive sparse attention network for diesel engine fault diagnosis is proposed with considering its signal characteristics of strong angle domain correlation and transient non-stationary, in which a new soft threshold filter is designed to draw more attention to multi decentralized local fault information dynamically in real time. Based on this attention mechanism, the distribution of fault information in the original signal can be better visualized to help explain the fault mechanism. The valve failure experiment on a diesel engine test rig is conducted, of which the results show that the proposed adaptive sparse attention mechanism model has better training efficiency and clearer interpretability on the premise of maintaining performance.

The Atomic Oxygen Erosion Resistance Effect and Mechanism of the Perhydropolysilazane-Derived SiOx Coating Used on Polymeric Materials in Space Environment

In this work, the atomic oxygen (AO) erosion-resistance effect and mechanism of the Perhydropolysilazane (PHPS) coating were investigated from the perspective of element distribution in the depth direction. The results revealed that the coating demonstrated good adhesion and intrinsic AO erosion-resistance, which was attributed to the composition gradient formed in the coating. Moreover, the oxygen ratio of the SiOx on top layer of the coating could be elevated during AO exposure, strengthening the Ar ion etching durability of the coating. According to these results, an AO erosion-resistance mechanism model of the PHPS-derived SiOx coating was finally obtained.

A Mathematical Model for Characterizing the Biomass and the Physiological/Biochemical Indicators of Salvia miltiorrhiza Based on Growth-Defense Tradeoff

Carbon(C) and nitrogen(N) metabolisms are important for plant growth and defense, and enzymes play a major role in these two metabolisms. Current studies show that the enzymes of N Metabolism, C Metabolism, and defense are correlated with biomass. Then, we conducted this research under the assumption that enzymes could characterize the relationship based on growth-defense tradeoff, and some of the enzymes could be used to represent the plant growth. From the mechanism model, we picked out 18 physiological/biochemical indicators and obtained the data from 24 tissue culture seedlings of Salvia miltiorrhiza (S.miltiorrhiza) which were grafted with 11 endophytic fungi. Then, the relationship between the biomass and the physiological/biochemical indicators was investigated by using statistical analysis, such as correlation analysis, variable screening, and regression analysis. The results showed that many physiological/biochemical indicators, especially enzyme activities, were related to biomass accumulation. Through a rigorous logical reasoning process, we established a mathematical model of the biomass and 6 key physiological/biochemical indicators, including glutamine synthetase (GS), glutamate synthase (GLS), glutamate dehydrogenase (GDH), peroxidase (POD), catalase (CAT), and soluble protein from Cobb-Douglas production function. This model had high prediction accuracy, and it could simplify the measurement of biomass. During the artificial cultivation of S.miltiorrhiza, we can monitor the biomass accumulation by scaling the key physiological/biochemical indicators in the leaves. Interestingly, the coefficients of Lasso regression during our analysis were consistent with the mechanism of growth-defense tradeoff. Perhaps, the key physiological/biochemical indicators obtained in the statistical analysis are related to the indicators affecting biomass accumulation in practice.

Hybrid modeling method of dust suppression efficiency for dry fog dust suppression process

The original mechanism model of dust suppression efficiency for dry fog dust suppression could not guide the actual process. In order to accurately predict the dust suppression efficiency in the process, a new mechanism model was established by my analysis of the process. But there were some factors that I could not establish the model. So a hybrid model combining mechanism model and support vector machine (SVM) was proposed. Using the data of dry fog dust suppression oval process, the hybrid model was simulated. The simulation results show that the hybrid model can accurately predict the dry fog dust suppression.

Human Motion Tracking Using 3D Image Features with a Long Short-Term Memory Mechanism Model—An Example of Forward Reaching

Human motion tracking is widely applied to rehabilitation tasks, and inertial measurement unit (IMU) sensors are a well-known approach for recording motion behavior. IMU sensors can provide accurate information regarding three-dimensional (3D) human motion. However, IMU sensors must be attached to the body, which can be inconvenient or uncomfortable for users. To alleviate this issue, a visual-based tracking system from two-dimensional (2D) RGB images has been studied extensively in recent years and proven to have a suitable performance for human motion tracking. However, the 2D image system has its limitations. Specifically, human motion consists of spatial changes, and the 3D motion features predicted from the 2D images have limitations. In this study, we propose a deep learning (DL) human motion tracking technology using 3D image features with a deep bidirectional long short-term memory (DBLSTM) mechanism model. The experimental results show that, compared with the traditional 2D image system, the proposed system provides improved human motion tracking ability with RMSE in acceleration less than 0.5 (m/s2) X, Y, and Z directions. These findings suggest that the proposed model is a viable approach for future human motion tracking applications.

Optimal Allocation of Water Resources and Eco-Compensation Mechanism Model Based on the Interval-Fuzzy Two-Stage Stochastic Programming Method for Tingjiang River

In this work, based on the upper line of water resources utilization and the bottom line of water environmental quality of “Three Lines, Single Project”, a fuzzy optimization method was introduced into the Tingjiang River water resources optimal allocation and eco-compensation mechanism model, which is based on the interval two-stage (ITS) stochastic programming method. In addition, a Tingjiang River water resources allocation and eco-compensation mechanism model based on the interval fuzzy two-stage (IFTS) optimization method was also constructed. The objective functions of both models were to maximize the economic benefits of the Tingjiang River. The available water resources in the basin, the water environmental quality requirements, and regional development requirements were used as constraints, and under the five hydrological scenarios of extreme dryness, dryness, normal flow, abundance, and extreme abundance, the water resources allocation plan of various sectors (industry, municipal, agriculture, and ecology) in the Tingjiang River was optimized, and an eco-compensation mechanism was developed. In this work, the uncertainty of the maximum available water resources in each region and the whole basin was considered. If the maximum available water resources were too high, it would lead to a large waste of water resources, whereas if the maximum available water resources were too low, regional economic development would be limited. Therefore, the above two parameters were set as fuzzy parameters in the optimization model construction in this work. The simulation results from the IFTS model showed that the amount of water available in the river basin directly affects the water usage by various departments, thereby affecting the economic benefits of the river basin and the amount of eco-compensation paid by the downstream areas. The average economic benefit of the Tingjiang River after the optimization of the IFTS model simulation was [3868.51, 5748.99] × 108 CNY, which is an increase of [1.67%, 51.9%] compared to the economic benefit of the basin announced by the government in 2018. Compared to the ITS model, the economic benefit interval of the five hydrological scenarios of extreme dryness, dryness, normal flow, abundance, and extreme abundance was reduced by 28.54%, 44.9%, 31.49%, 40.37%, and 36.43%, respectively, which can improve the economic benefits of the basin and provide more accurate decision-making schemes. In addition, the IFTS simulation showed that the eco-compensation quota paid by downstream Guangdong Province to upstream Fujian Province is [28,116.4, 30,738.6] × 104 CNY, which is a reduction of [8461.404, 110,836] × 104 CNY compared to the 2018 compensation scheme of the government. Compared to the ITS model, the range of eco-compensation values was observed to increase by 9.94%, 54.81%, 15.85%, 50.31%, and 82.90%, respectively, under the five hydrological scenarios, which reduces the burden of ecological expenditure downstream and provides a broader decision-making space for decision-makers and thus enables improved decision-making efficiency. At the same time, after the optimization of the IFTS model, the additional water consumption of the second stage of the Tingjiang River during the extremely dry year decreased by 62.11% compared to the results of the ITS model. The additional water consumption of the industrial sector decreased by 68.39%, the municipal sector decreased by 59.27%, and in the first phase of water resources allocation for 14 districts and counties in the Tingjiang River, industrial and municipal sectors are the main two sectors. After introducing the fuzzy method into the IFTS model, the difference in the water consumption by these two sectors in the basin under different hydrological scenarios can be alleviated, and the waste of water resources caused by too low water allocation or excessive water allocation can be avoided. The national and local (the downstream region) eco-compensation quotas can be indirectly reduced, and the risk of water resources allocation and eco-compensation decision-making in the basin can be effectively reduced.

Decision Tree-based Hybrid Multiprocessor Task Scheduling for the Cyber-Physical System

Scheduling is a critical process in cyber-physical systems to ensure the computation will be over within the physical system's deadline. Under the cyber-physical system, the processor is distributive and hydrogenous. Less latency task scheduling under this distributive cyberphysical system with a hydrogenous processor and resource is challenging. This article presents a decision tree based less complex mechanism of task scheduling in a heterogeneous processor environment this proposed mechanism model the tasks and the processor resource, current load level, their individual computational capability, memory availability, communication delay in the distributive system to move the task from one point to another point is taken into account for the scheduling purpose the numerical results prove that the proposed mechanism able to schedule the task quickly and with more task deadline meet the ratio.