Application of data fusion method to fault diagnosis of nuclear power plant

The work condition of nuclear power plant (NPP) is very bad, which makes it has faults easily. In order to diagnose the faults real time, the fusion diagnosis system is built. The data fusion fault diagnosis system adopts data fusion method and divides the fault diagnosis into three levels, which are data fusion level, feature level and decision level. The feature level uses three parallel neural networks whose structures are the same. The purpose of using neural networks is mainly to get basic probability assignment (BPA) of D-S evidence theory, and the neural networks in feature level are used for local diagnosis, D-S evidence theory is adopted to integrate the local diagnosis results in decision level. The reactor coolant system is the study object and we choose 2# steam generator Utubes break of the reactor coolant system as a diagnostic example, The experiments prove that the fusion diagnosis system can satisfy the fault diagnosis requirement of complicated system, and verify that the fusion fault diagnosis system can realize the fault diagnosis of NPP on line timely.     

Experimental research on dynamic responses characteristics and influence laws of gear transmission-propulsion system under gear excitation北大核心CSCD

［Objective］In order to study the dynamic response characteristics and influence laws of a marine gear transmission-propulsion system, a series of bench tests is carried out.［Methods］First, a biaxial gear transmission-propulsion system test bench including a cross connection gear is built. Experiments to test the acceleration response of the gearbox body and propulsion shaft system are then carried out, and the influence of speed, driving mode, axial static thrust, axial dynamic excitation force from the propeller and other factors on the dynamic response characteristics of the system are compared and analyzed. ［Results］The experimental results show that the transmission law of the vibration acceleration response of the gear transmission-propulsion system is mainly at the meshing frequency and its multipliers, as well as peaks in the low frequency band of 30–80 Hz under certain working conditions. ［Conclusion］This study can provide technical support for the vibration and noise reduction design of gear transmission-propulsion systems. © 2022 Journal of Clinical Hepatology. All rights reserved.     

Application of fuzzy neural network to the nuclear power plant in process fault diagnosis

The fuzzy logic and neural networks are combined in this paper, setting up the fuzzy neural network (FNN) ; meanwhile, the distinct differences and connections between the fuzzy logic and neural network are compared. Furthermore, the algorithm and structure of the FNN are introduced. In order to diagnose the faults of nuclear power plant, the FNN is applied to the nuclear power plant, and the intelligence fault diagnostic system of the nuclear power plant is built based on the FNN . The fault symptoms and the possibility of the inverted U-tube break accident of steam generator are discussed. In order to test the system‘ s validity, the inverted U-tube break accident of steam generator is used as an example and many simulation experiments are performed. The test result shows that the FNN can identify the fault.     

船用柴油机系统的完整建模（英文）

This paper presents a simulator model of a marine diesel engine based on physical, semi-physical, mathematical and thermodynamic equations, which allows fast predictive simulations. The whole engine system is divided into several functional blocks: cooling, lubrication, air, injection, combustion and emissions. The sub-models and dynamic characteristics of individual blocks are established according to engine working principles equations and experimental data collected from a marine diesel engine test bench for SIMB Company under the reference 6M26SRP1. The overall engine system dynamics is expressed as a set of simultaneous algebraic and differential equations using sub-blocks and S-Functions of Matlab/Simulink. The simulation of this model, implemented on Matlab/Simulink has been validated and can be used to obtain engine performance, pressure, temperature, efficiency, heat release, crank angle, fuel rate, emissions at different sub-blocks. The simulator will be used, in future work, to study the engine performance in faulty conditions, and can be used to assist marine engineers in fault diagnosis and estimation(FDI) as well as designers to predict the behavior of the cooling system, lubrication system, injection system, combustion, emissions, in order to optimize the dimensions of different components. This program is a platform for fault simulator, to investigate the impact on sub-blocks engine’s output of changing values for faults parameters such as: faulty fuel injector, leaky cylinder, worn fuel pump, broken piston rings, a dirty turbocharger, dirty air filter, dirty air cooler, air leakage, water leakage, oil leakage and contamination, fouling of heat exchanger, pumps wear, failure of injectors(and many others).     

Fault Diagnosing System of Steam Generator for Nuclear Power Plant Based on Fuzzy Neural Networks

All kinds of reasons are analysed in theory and a fault repository combined with local expert experiences is establishedaccording to the structure and the operation characteristic of steam generator in this paper. At the same time, Kohonen algo-rithm is used for fault diagnoses system based on fuzzy neural networks. Fuzzy arithmetic is inducted into neural networks tosolve uncertain diagnosis induced by uncertain knowledge. According to its self-association in the course of default diagnosis. thesystem is provided with non-supervise, self-organizing, self-learning, and has strong cluster ability and fast cluster velocity.     

Uncertainty analysis of propulsion shafting vibration北大核心CSCD

［Objective］In view of the insufficient safety and reliability of the traditional deterministic vibration analysis of ship propulsion shafting system, the vibration response analysis of the shafting system under uncertain excitation conditions is carried out. ［Methods］Using non-random vibration analysis based on non-probabilistic convex model process, the uncertain excitation and vibration response are described in the form of the upper and lower bounds of the interval to reduce dependence on a large amount of excitation sample data. Compared with the calculation results in the relevant literature, the validity of the program for solving the response bound of the two-degrees-of-freedom (2-DOFs) system is verified, and the uncertain vibration problem of the shafting system is then explored on this basis. ［Results］The results show that when the shafting system is excited by [−30 N, 30 N] propeller laterally, a displacement response of the magnitude of about 10−6 m is generated at the bearing. It is also indicate that the shafting system is excited in a certain interval, so a certain interval response must be produced. ［Conclusions］Applying the non-probabilistic convex model process and non-random vibration analysis to the field of the uncertain vibration analysis of ship propulsion shafting system, the vibration displacement response bound of the shafting under uncertain excitation conditions can be obtained with fewer excitation samples, thereby providing useful references for improving the robustness of the dynamic response prediction of ship propulsion shafting systems. © 2023 Chinese Journal of Ship Research. All rights reserved.     

采用蒸汽再加热的船用蒸汽推进装置冷凝加热系统的热力学分析（英文）

The thermodynamic(energy and exergy) analysis of a condensate heating system, its segments, and components from a marine steam propulsion plant with steam reheating is performed in this paper. It is found that energy analysis of any condensate heating system should be avoided because it is highly influenced by the measuring equipment accuracy and precision. All the components from the observed marine condensate heating system have energy destructions lower than 3 kW, while the energy efficiencies of this system are higher than 99%. The exergy efficiency of closed condensate heaters continuously increases from the lowest to the highest steam pressures(from 70.10% to 92.29%). The ambient temperature variation between 5 °C and 45 °C notably influences the exergy efficiency change of both low pressure heaters and the low pressure segment equal to 31.61%,12.37%, and 18.35%, respectively.     

A new marine propulsion system

A new marine propulsion system is proposed . A small liquid sodium cooled reactor acts as prime mover; alkali-metal thermal-to-electric conversion (AMTEC) cells are employed to convert the heat energy to electricity; superconducting magneto-hydrodynamic thruster combined with spray-water thruster works as propulsion. The configuration and characteristics of this system are described. Such a nuclear-powered propulsion system is not only free of noise, but also has high reliability and efficiency. It would be a preferable propulsion system for ships in the future。     

Experimental research on dynamic vibration absorber with negative stiffness for longitudinal vibration control of propulsion shafting system北大核心CSCD

［Objectives］In order to control the first longitudinal vibration mode of propulsion shafting systems, a dynamic vibration absorber with disc spring negative stiffness is proposed and its experimental verification carried out. ［Methods］A test bench is established for the propulsion shafting system containing a dynamic vibration absorber with negative stiffness. According to the first longitudinal vibration mode of the shafting, a dynamic vibration absorber with negative stiffness integrated into the thrust bearing is developed. Vibration transmission tests under different rotational speeds, static thrusts and negative stiffness are then carried out, and acceleration response data on the thrust bearing foundation and shafting is obtained. ［Results ］ The results show that the developed dynamic vibration absorber with negative stiffness can achieve vibration suppression of 7.8 dB for the thrust bearing foundation in the first longitudinal mode of the propulsion shafting with a mass ratio of 1.6%, and the vibration control effect of the negative stiffness dynamic vibration absorber is maintained at 3.3 dB when the natural frequency changes by 5% and the thrust changes by 40%. The vibration response on the thrust bearing foundation and shafting do not deteriorate even at non-optimal negative stiffness. ［Conclusions］This study shows that a dynamic vibration absorber with negative stiffness can effectively suppress vibration transmission at the first longitudinal mode of a shafting under different rotational speeds. © 2023 Authors. All rights reserved.     

Research on pattern recognition for marine steam turbine rotor axis orbit

The structure ,function and recognition method of an axis orbit auto-recognizing system are presented in this paper. In order to make the best use of information of format and dynamic characteristics of marine steam turbine axis orbit, the structure and functions or neural network are applied to this system,which can be used to auto-recognize axis orbit of the system turbine rotor using BP neural network     

带有偏差单元的递归神经网络诊断方法在齿轮箱故障诊断中的应用

提出了带有偏差单元的递归神经网络方法,并将其应用到齿轮箱的故障诊断中．通过对齿轮箱的基本零件齿轮故障的设置,研究TBP神经网络的改进算法与带有偏单元的递归神经网络用于齿轮箱故障诊断的有效性。研究表明,带有偏单元的递归神经网络方法比BP网络训练速度快,精度要高,节省时间,能够精确实现故障定位。     

基于多体动力学仿真的柴油机传动齿轮故障机理与监测方法研究

针对现有船用柴油机热工参数无法有效监测报警传动齿轮故障的问题,基于柴油机普遍缺失振动监测数据,难以有效提取故障特征的现状,采用多体动力学仿真技术研究柴油机齿轮载荷与曲轴止推轴承磨损之间的内在关联,基于仿真结果提取传动齿轮故障条件下的振动信号特征;采用实际故障案例振动数据,提取传动齿轮箱振动信号的时域、频域特征,实际特征变化规律与仿真结果一致,检验了本文仿真研究成果的正确性。     

舰船动力装置智能诊断方法研究

文章围绕动力装置故障监控诊断的三种常用方法——热参数分析、油液分析、振动分析,归纳和总结了舰船动力装置智能诊断的基于专家系统的方法、人工神经网络方法、模糊逻辑方法和知识发现的方法,从专家系统的发展、混合智能诊断、不确定性人工智能3个方面对现代动力装置诊断技术的发展趋势和有待解决的问题进行分析与探讨,提出了装置故障诊断领域未来的研究方向。     

船舶主机性能故障的主成因分析

介绍了船舶主机２０种典型性能故障的仿真模型计算结果。通过对各故障下热工参数的主成因分析,揭示了热工参数的相关性,提出了性能故障的降维识别方法,并介绍了人工神经网络在船舶主机故障诊断中的具体应用。     

基于引力搜索BP神经网络的柴油机故障诊断

为了提高柴油机故障诊断的精度,将引力搜索算法用于BP神经网络初始权值及阈值优化,提出了一种基于引力搜索算法和BP神经网络相结合的智能故障诊断方法,并将其运用于柴油机磨损故障的振动诊断。结果表明,该方法与BP神经网络相比,对柴油机的磨合、磨损、极限等故障诊断准确,精度提高明显,验证了该方法的有效性。     

船舶推进轴系故障特征信息识取方法比较

为研究不同船舶推进轴系故障特征量提取方法的优缺点,针对船舶推进轴系故障振动信号的瞬态(脉冲)和周期性2个特点,介绍快速傅里叶变换(FFT)、EAF和EEAF3种周期故障特征信息识取方法,并在实船试验中就这3种方法的适用性、准确性和复杂程度等进行比较分析。结果表明:EEAF相比FFT和EAF,能快速、准确地提取船舶推进轴系周期性故障信息的特征频率及其振幅,具有良好的稳定性,可专门用于船舶推进轴系故障分析和诊断。     

齿轮箱弹性隔振时的推进装置模态分析研究

随着推进主机隔振性能的提升,齿轮箱已成为影响船舶声学性能的重要振源,因此需要采取隔振措施以减小其向船体传递的能量。弹性隔振技术可以改善齿轮箱的振动性能,但是挠性传动部件将导致齿轮箱与推进主机隔振系统之间产生振动耦合,从而增大对推进装置进行模态分析的难度。以某船推进装置为研究对象,基于多刚体动力学理论,推导了计及齿轮箱与推进柴油机隔振系统之间振动耦合特性的推进装置整体隔振系统运动微分方程,并进行了模态分析。结果表明,计及隔振系统之间振动耦合的模态分析结果与两个隔振系统单独进行模态分析的结果存在显著差异,证明了齿轮箱弹性隔振时建立推进装置整体隔振系统分析模型的必要性。最后,对该推进装置的设计和使用进行了评估和建议。     

可监测性设计理论在船舶动力机械系统设计中的应用

船舶动力机械系统一旦出现故障直接威胁船舶安全,但是船舶服役后难以增加设备完善动力机械运行状态的监测。为此,提出了可监测性设计理论内涵,在常规船舶设计建造阶段考虑动力机械系统的可监测性,从而构建出可监测性设计理论在船舶动力机械系统设计中的工程应用框架。以远洋救助船动力机械系统为例,分析了可监测性设计理论在机械系统设计中的具体应用。实践证明,可监测性设计理论在船舶动力机械系统中的工程化实施增强了其可监测性,大大提高了自身状态监测和故障诊断能力水平,并且为船舶动力机械创新设计和机械系统的可再制造提供了保障和技术支撑。     

基于BP神经网络的船用柴油机振动状态监测

通过监测柴油机表面振动信号,用时间序列分析方法提取柴油机故障的振动特征参数,以此建立相应的神经网络,用于船用柴油机的状态监测,提高诊断的准确性。试验研究在中速四冲程增压柴油机上进行。文中以柴油机气阀间隙异常的诊断和柴油机负荷状态的识别为例阐述了该方法的实现过程,并给出了振动信号的特征参数与柴油机工作状态之间的关系。研究表明,利用神经网络监测柴油机运行状态的变化是可行的和有效的。     

基于PCA和SVM的柴油发动机冲击故障诊断方法研究

针对柴油发动机振动信号进行故障诊断技术研究,提出了一种基于主成分分析和支持向量机的柴油发动机冲击故障诊断方法。首先利用小波包分解提取出冲击故障的特征;再利用主成分分析技术获得敏感特征参数,进而减小数据处理的复杂程度;最后利用支持向量机对敏感特征参数样本进行训练,获得分类模型,进而实现故障分类。将该方法用于柴油机实际故障分类,诊断准确率较高,证实了本文方法对多种冲击故障诊断的有效性。