Fault diagnosis for wind turbine based on improved extreme learning machine

A fault diagnosis method based on improved extreme learning machine (IELM) is proposed to solve the weakness (weak generalization ability, low diagnostic rate) of traditional fault diagnosis with feedforward neural network algorithm. This method fuses signal feature vectors, extracts six parameters as the principal component analysis (PCA) variables, and calculates correlation coefficient matrix among the variables. The weight values of control parameters in the extreme learning model are dynamically adjusted according to the test samples’ constantly changing. Consequently, the weight fixed drawback in the original model can be remedied. A fault simulation experiment platform for wind turbine drive system is built, eight kinds of fault modes are diagnosed by the improved extreme learning model, and the result is compared with that of other machine learning methods. The experiment indicates that the method can enhance the accuracy and generalization ability of diagnosis, and increase the computing speed. It is convenient for engineering application.     

Gain and noise figure analysis of Er<Superscript>3+</Superscript>-doped YAG transparent ceramic microchip amplifier

The rate equations and the power evolution equations based on excited state absorption (ESA) and cooperative upconversion (CUC) of high concentration erbium-doped yttrium aluminum garnet (YAG) transparent ceramic waveguide amplifier are set up to analyze the effects of the pump power, active ion concentration and waveguide length on the amplifier gain and noise figure (NF). The numerical analysis predicts that with a pump power of 100mW, an active ion concentration of 1.0×10²⁶ ion/m³ and a waveguide length of 3 cm, a small-signal gain of 30 dB and an NF of 5 dB can be achieved in the micro-chip amplifier.     

Research on probability distribution of port cargo throughput

In order to more accurately examine developing trends in gross cargo throughput, we have modeled the probability distribution of cargo throughput. Gross cargo throughput is determined by the time spent by cargo ships in the port and the operating efficiency of handling equipment. Gross cargo throughput is the sum of all compound variables determining each aspect of cargo throughput for every cargo ship arriving at the port. Probability distribution was determined using the Wald equation. The results show that the variability of gross cargo throughput primarily depends on the different times required by different cargo ships arriving at the port. This model overcomes the shortcoming of previous models： inability to accurately determine the probability of a specific value of future gross cargo throughput. Our proposed model of cargo throughput depends on the relationship between time required by a cargo ship arriving at the port and the operational capacity of handling equipment at the port. At the same time, key factors affecting gross cargo throughput are analyzed. In order to test the efficiency of the model, the cargo volume of a port in Shandong Province was used as an example. In the case study the actual results matched our theoretical analysis.     

Design optimization of a torpedo shell structure

An optimized methodology to design a more robust torpedo shell is proposed. The method has taken into account reliability requirements and controllable and uncontrollable factors such as geometry, load, material properties, manufacturing processes, installation, etc. as well as human and environmental factors. The result is a more realistic shell design. Our reliability optimization design model was developed based on sensitivity analysis. Details of the design model are given in this paper. An example of a torpedo shell design based on this model is given and demonstrates that the method produces designs that are more effective and reliable than traditional torpedo shell designs. This method can be used for other torpedo system designs.     

An investigation of the performance of an electronic in-line pump system for diesel engines

WIT Electronic Fuel System Co., Ltd. has developed a new fuel injector, the Electronic In-line Pump （EIP） system, designed to meet China＇s diesel engine emission and fuel economy regulations. It can be used on marine diesel engines and commercial vehicle engines through different EIP systems. A numerical model of the EIP system was built in the AMESim environment for the purpose of creating a design tool for engine application and system optimization. The model was used to predict key injection characteristics under different operating conditions, such as injection pressure, injection rate, and injection duration. To validate these predictions, experimental tests were conducted under the conditions that were modeled. The results were quite encouraging and in agreement with model predictions. Additional experiments were conducted to study the injection characteristics of the EIP system. These results show that injection pressure and injection quantity are insensitive to injection timing variations, this is due to the design of the constant velocity cam profile. Finally, injection quantity and pressure vs. pulse width at different cam speeds are presented, an important injection characteristic for EIP system calibration.     

Study on J-integral with SENB specimensin a condenser material

A series of tests was performed with three-point single-edge-notched-bend (SENB) specimens in a condenser material (Titanium alloy). Results show that the J-integral values of welded joint and HAZ are obviously smaller than those of the base metal. It signifies that the welding process can result in a reduced toughness of Titanium alloy and the effect of crack orientation on toughness value is not negligible for engineering applications. Besides, the J-integral values of L-T direction specimens are much higher than those of LS ones. The J-integral values of rolled ring are: J_(C-R)>J_(C-L)>J_(L-R).     

Law enforcement in the ocean

The combating of the present great variety of criminal activities occurring at sea mainly involves measures to be taken on land, in particular in ports.However, also actual enforcement at sea will continue to play an essential (complementary) role. This article surveys the rules of international law governing law enforcement measures at sea. These rules are complex, because distinctions have to be made between the various jurisdictional zones at sea and between the positions of the flag state, the coastal state and the port state. Traditionally, ships in the high seas (all sea areas beyond a narrow band of territorial sea) were under the exclusive jurisdiction of the flag state. In an increasing number of situations, the coastal state now has law enforcement authority over foreign ships in expanded areas up to 200 nautical miles offshore. But apart from these situations, flag state jurisdiction still prevails beyond the territorial sea. This makes effective law enforcement difficult. In practice, many obstacles can be overcome by making more effective use of the authority of the port state, and by concluding new international agreements providing for specific enforcement systems.     

Sliding mode robust fault-tolerant control for uncertain systems with time delay

Considering the modeling uncertainties and external disturbance, a kind of sliding mode robust H∞fault-tolerant control method for time delay system with actuator fault is proposed. The upper-bound of the uncertainties is considered as a known constant, while the upper-bound of the actuator fault is unknown. A sufficient condition for the existence of an integral sliding mode dynamics is given in terms of linear matrix inequality(LMI). A novel adaptive law is given to estimate the unknown upper-bound of faults. On this basis, a type of sliding mode robust H∞fault-tolerant control law is designed to guarantee the asymptotic stability and the H_∞ performance index of the system. Finally, the simulation on quad-rotor semi-physical platform demonstrates the reliability and validity of the method.     

Novel electronic braking system design for EVS based on constrained nonlinear hierarchical control

Both environment protection and energy saving have attracted more and more attention in the electric vehicles (EVs) field. In fact, regarding control performance, electric motor has more advantages over conventional internal combustion engine. To decouple the interaction force between vehicle and various coordinating and integrating active control subsystems and estimate the real-time friction force for Advanced Emergency Braking System (AEBS), this paper’s primary intention is uniform distribution of longitudinal tire-road friction force and control strategy for a Novel Anti-lock Braking System (Nov- ABS) which is designed to estimate and track not only any tire-road friction force, but the maximum tire-road friction force, based on the Anti-Lock Braking System (ABS). The longitudinal tire-road friction force is computed through real-time measurement of breaking force and angular acceleration of wheels. The Magic Formula Tire Model can be expressed by the reference model. The evolution of the tire-road friction is described by the constrained active-set SQP algorithm with regard to wheel slip, and as a result, it is feasible to identify the key parameters of the Magic Formula Tire Model. Accordingly, Inverse Quadratic Interpolation method is a proper way to estimate the desired wheel slip in regards to the reference of tireroad friction force from the top layer. Then, this paper adapts the Nonlinear Sliding Mode Control method to construct proposed Nov-ABS. According to the simulation results, the objective control strategy turns out to be feasible and satisfactory.