Search

Respiratory sounds reveal important information of the lungs of patients. However, the analysis of lung sounds depends significantly on the medical skills and diagnostic experience of the physicians and is a time-consuming process. The development of an automatic respiratory sound classification system based on machine learning would, therefore, be beneficial. In this study, 705 respiratory sound signals (240 crackles, 260 rhonchi, and 205 normal respiratory sounds) were acquired from 130 patients. We found that similarities between the original and wavelet decomposed signals reflected the frequency of the signals. The Gaussian kernel function was used to evaluate the wavelet signal similarity. We combined the wavelet signal similarity with the relative wavelet energy and wavelet entropy as the feature vector. A 5-fold cross-validation was applied to assess the performance of the system. The artificial neural network model, which was applied, achieved the classification accuracy and classified the respiratory sound signals with an accuracy of 85.43%.

Miniaturize multifunctional tilting type aircraft has both a VTOL capability and high cruise performance, which is significant in commercial and industrial fields. In this paper, a Y6 tilt rotor UAV is selected as the research object after comparing three kinds of most widely adopted tilting type UAVs. Research status and technical difficulties of tilt rotor aircraft in transition process are introduced, and the general properties of the Y6 tilt rotor prototype are given first. Then the multi-body mathematical model for the aircraft is derived, in which the mass of tilting mechanism and the tilting of high-speed rotating rotors is considered. After that the control strategy for the transition process is designed. Numerical simulation of transition process is built and the influence of tilt angular velocity and initial flight speed on the stability of tilting process is analyzed in order to find the optimal tilting control strategy. Finally, the mechanical structure and flight control system of the prototype are introduced, flight test results are shown to demonstrate that proposed optimal tilting control strategy make the aircraft perform stable in the transition process.

In this paper, the influence of the tilting-rotor structure parameters on the aerodynamic characteristics of a small tilt rotor unmanned aerial vehicle (UAV) is studied. The simplified model of tilt rotor unmanned aerial vehicle (UAV) is established by using SolidWorks software, and the model is divided into unstructured grid by ICEM software. Finally, set the corresponding boundary conditions in the FLUENT software and then simulated. By simulating the flight state of the tilt rotor unmanned aerial vehicle (UAV) in the fixed wing mode, the lift-drag aerodynamic characteristics of the aircraft in that flat flight mode are obtained. On the other hand, researched the effect of the tilting angle of the tilting-rotor mechanism, the size of the multi-rotor structure (the distance of the tilting-rotor mechanism from the fixed wing), and the rotor installation distance of the coaxial twin propeller mechanism on the complex flow field between rotor and fixed wing. Obtained some meaningful conclusions, which are useful for the future design of the small tilt rotor unmanned aerial vehicle.

With the development of general aviation, UAVs are increasingly used in all areas of our life. However, electric multi-rotor UAV can't achieve long-endurance, large load transport due to battery energy density. And hybrid power system is a perfect solution to this problem. This paper raised a parameter matching method of the UAV's hybrid power system related to the pulling force, required power and flight performance. The UAV's power demand was taken as an entry point for parameter matching, and the match result was based to select power components. The test results of the components performance proved the matching methods' feasibility and accuracy. The structure of hybrid coaxial rotors and multi-rotor UAV is also tested to be achievable.

Oil and gas transportation in pipeline plays an important role in the lifeline of national economy, industrial production and daily life. In China, aging phenomenon of oil and natural gas pipeline is widespread in the existing pipeline. Therefore, the safety of the pipeline has been concerned. It is a great significance for forecasting dent depth of transportation pipeline accurately. In this paper, according to the complicated radial displacement and the characteristic of RBF neural network, the model of RBF neural was constructed combining with pipeline dent depth data pipeline. The RBF model was applied to predict dent depth in the pipelines, it was testified that the RBF neural network model has higher prediction accuracy than BP neural network model.

Mass energy loss happens in the air supply through large-scale complex pneumatic pipeline grid, and it widely exists in various kinds of manufacturing enterprises. In this paper, to improve efficiency and safety of compressed air grid system, a "smart pneumatic pipeline grid" is introduced. Furthermore, based on the supply and demand characteristics of key nodes of smart pneumatic pipeline grid, an energy-saving supply strategy of smart pneumatic pipeline grid was proposed. Moreover, to test the energy-saving supply strategy of the smart pneumatic pipeline network, a typical smart pneumatic pipeline grid was studied. In this study, the feasibility of the energy-saving supply strategy can be verified through a typical smart pneumatic pipeline grid. This paper provides an intelligent energy-saving technology of the compressed air system.

As one of the most important nursing interventions of ventilated patients' respiratory tract, secretion clearance is usually used to keep the respiratory tract clear, improve alveolar ventilation and patients' breathing function. However, the existing secretion clearance technologies have serious defects in efficiency, safety and automation. Considering these disadvantages above, this paper proposes an intelligent secretion system, which combines doctors' theoretical knowledge, clinical experience and engineering technology. In this system, three key technologies will be broken through to form a set of simple, safe, efficient and automatic secretion clearance technology, which are 1. On-line identification technology of the time when to clear secretion; 2.1ntelligent control technology of the secretion clearance system based on simulation of the human natural cough; 3. Breathing simulation technology with self-learning function. This system will provide an intelligent method to keep patients' respiratory tract clear, prevent respiratory system infection, avoid the damage to respiratory tracts and ensure mechanical ventilation treatment goals. The technology proposed in this paper is poised to replace catheter suction technology as the most common secretion clearance technology in clinic. Ultimately, this technology will improve the secretion clearance technology level of China, save lives of ventilated patients', reduce patients' pain and the work intensity of medical staffs.

Energy-saving of compressed air system was very important for the sustainable development of enterprises, which could be achieved though fast and accurate load forecasting. In this paper, according to the distribution rules and characteristics of 24 hours compressed air supply, the 24h compressed air flow demand model was firstly built with least square support vector machine (LSSVM). In order to avoid the long time consumption for determining the model parameters in the traditional cross validation method, Bayesian evidence framework was selected to train the parameters, and then identified and optimized them. Meanwhile, Nystrom low- rank approximation decomposition algorithm was used to accelerate kernel matrix decomposition process. Though the experimental verification with real industrial data, the modeling time of LSSVM within Bayesian evidence framework is reduced to 1/20 compared with traditional cross-validation method; in the contrast with Practical Swarm Optimization (PSO), the modeling time is reduced to 80%, and the prediction accuracy can increase 14.3%, proving this method quite suitable for fast and accurate forecasting for large flow compressed air load.

In this paper, the main form of energy consumption of typical compressed air system is introduced, to analyze basic potentials of energy saving. Then the current situation of energy saving in compressed air systems is also given. Four major energy saving measures according to present problems of energy saving in compressed air systems and prospects of energy saving of air system are proposed.

Pneumatic system operation status and problems were analyzed in the industrial production site; Considering the 24 hours as a time unit, the feature of compressed air consumption was studied every 20 seconds in 24 hours in the industrial production site. Then, presenting a forecasting method, which is workable and the overall mean in line with air consumption changes in the law. This forecasting method is for the purpose of the operation dispatching of air compressors in the industrial site, and the forecasting accuracy meets the requirement of air compressors operation dispatching. Finally, with the forecasting consumption of compressed air, a optimal scheduling algorithm of compressor group is given.

To increase the energy utilization rate of compressed air, the expansion ration is optimized based on single-staged compressed air power system by building mathematical method with the basic thermodynamic theory. Two-staged compressed air power system mathematical model is built on the basis of research on single-staged compressed air power system. Exergy analysis on air power system is researched on different expansion ratio in 10 MPa pressure and 300K temperature as input condition. Research results indicate two-staged compressed air power system expander is better than single-stage system. Results also show that the first stage expansion ratio is larger impact than the second expansion in two-staged expansion work. The work is foundation for designing valve train system for compressed air powered system

This paper discusses how to determine the interest degree of user for product information by mathematical method. The membership function is used to analysis the product properties, fuzzy calculation is used to classify and evaluate the product properties, and the weighted value is used to modify the relationships among the product properties.

Compressed air leak is a serious problem in the process of being used. This paper firstly presents the existing problem of detecting error caused by reflected ultrasonic signal in compressed air leak detection. Secondly, direct ultrasonic signal and reflected ultrasonic signal were measured experimentally and we found that there are some obvious differences between their spectrums. Then, a differentiating algorithm is proposed which can differentiate direct ultrasonic signal and reflected ultrasonic signal exactly. Finally, a compressed air leak detecting instrument is studied and designed.

The actuators’ mechanical properties evaluation is a fuzzy concept with multiple properties and classes. The fuzzy data quantification, analytic hierarchy process and fuzzy comprehensive evaluation (AHP-FCE) methods are combined to establish the actuators’ mechanical properties evaluation (MPE) model. The flowchart of actuators’ MPE and selection on AHP-FCE was considered and characterized in detail. The weighted average principle has been taken to replace the maximum membership principle in dealing with the actuator’ mechanical properties comprehensive value. One pneumatic actuator and one electric actuator in same working demand are taken as an example to verify the evaluation model. The result shows that it is effective, correct, easy to apply and worth to being recommended in similar evaluation field.

The actuators' mechanical properties evaluation is a fuzzy concept with multiple properties and classes, and there are still some limits of fuzzy comprehensive evaluation method. The fuzzy data quantification and information entropy methods are combined to establish the actuators' mechanical properties evaluation (MPE) model. The weighted average principle has been taken to replace the maximum membership principle when dealing with weighted coefficient of the actuaors' mechanical properties. The pneumatic actuator and electric actuator in actual working field are taken as an example to verify the model. The result shows that it is effective, efficient, easy to apply and worth to being recommended in similar electromechanical products.

This paper applies prognostics and health management technologies to compressor system for the first time. Firstly, the meaning of compressor health management system is elaborated. Secondly, the study contents and hierarchical structure of compressor system are expounded. Finally, this paper proposes the concept of compressor integrated health index and give the major steps of calculating compressor integrated health index based on TOPSIS method.

This paper shows how to analyze the overall energy efficiency of two typical equipments of compressed air system: lubricant-injected rotary screw compressors and aftercooler. Firstly, air power, a proposed effective tool of weighing energy, is introduced as the quantitative standard of energy in compressed air. Then, compression process of lubricant-injected rotary screw compressors for air production is analyzed deeply and the state change of compressed air is discussed in detail. Compressed air's air powers in the one-stage compression air system including one- stage compressor, intercooler, and aftercooler are discussed particularly. After discussion on the compressor's adiabatic and isotonic efficiencies, the efficiencies of compressor and aftercooler are defined with air power and their overall energy efficiency is proposed as the final energy- conversion efficiency. The efficiency analysis methods discussed in this study will be greatly helpful to an energy-saving equipment selection and energy assessment for pneumatic system.