A5071040769- Corrosion Behavior and Inhibition
- Non-Destructive Testing Techniques
- Concrete Corrosion and Durability
- Hydrogen embrittlement and corrosion behaviors in metals
- Grey System Theory Applications
- Bayesian Modeling and Causal Inference
- Domain Adaptation and Few-Shot Learning
- Biomedical Text Mining and Ontologies
- Multimodal Machine Learning Applications
- Thermal Radiation and Cooling Technologies
- Advanced Thermoelectric Materials and Devices
- Structural Integrity and Reliability Analysis
- Rough Sets and Fuzzy Logic
- Energy Load and Power Forecasting
- Smart Materials for Construction
- Data Quality and Management
- Mineral Processing and Grinding
- Multi-Criteria Decision Making
- Petroleum Processing and Analysis
- Advanced Thermodynamics and Statistical Mechanics
- Electronic Health Records Systems
Northwestern Polytechnical University
2020-2021
University of Science and Technology Beijing
2015-2020
Beijing Haidian Hospital
2018
Nanjing Institute of Technology
2018
The atmospheric corrosion of carbon steel was monitored by a Fe/Cu type galvanic sensor for 34 days. Using random forest (RF)-based machine learning approach, the impacts relative humidity, temperature and rainfall were identified to be higher than those airborne particles, sulfur dioxide, nitrogen monoxide ozone on initial corrosion. RF model demonstrated accuracy artificial neural network (ANN) support vector regression (SVR) models in predicting instantaneous can further improved after...
The objective of this paper is to develop an approach forecast the outdoor atmospheric corrosion rate low alloy steels and do corrosion-knowledge mining by using a Random Forests algorithm as tool. We collected data 17 under 6 test stations in China over 16 years experimental datasets. Based on datasets, model established implement purpose prediction data-mining. results showed that random forests can achieve best generalization compared commonly used machine learning methods such artificial...
Purpose This study aims to achieve long-term prediction on a specific monotonic data series of atmospheric corrosion rate vs time. Design/methodology/approach paper presents new method, used the collected carbon steel provided by China Gateway Corrosion and Protection, that combines non-linear gray Bernoulli model (NGBM(1,1) with genetic algorithm attain purpose this study. Findings Results experiments showed present study’s method is more accurate than other algorithms. In particular, mean...
Purpose The purpose of this paper is to present a new model which combines the non-equidistant GM(1,1) with GCHM_WBO (generalized contra-harmonic mean (GCHM); weakening buffer operator (WBO)). authors use solve deadlock that for large number corrosion rate, it difficult establish reasonable prediction and improve accuracy. Design/methodology/approach This research consists three parts: model, operator, optimization morphing parameter (contained in GCHM, control intensity operator)....
According to Standard ISO9223, the level of atmospheric corrosion is determined by three factors including chloride ion, SO2 and time wetness. In practice, missing one or more these data very common, increasing difficulty in accurate determination level. order overcome such problem, we used Cerebellar Model Articulation Controller (CMAC) for partial Bayesian network all occasion. By obtaining relationship between parts other attributes data, correlation model was established complement data....
Distribution mismatch can be easily found in multi-sensor systems, which may caused by different shoot angles, weather conditions and so on. Domain adaptation aims to build robust classifiers using the knowledge from a well-labeled source domain, while applied on related but target domain. Pseudo labeling is prevalent technique for class-wise distribution alignment. Therefore, numerous efforts have been spent alleviating issue of mislabeling. In this paper, unlike existing selective hard...
GM(1,1) model is widely used in the field of corrosion rate prediction. In this paper, we present a new model, which combines non-equidistant with GCHM_WBO (GCHM, Generalized Contra-Harmonic Mean; WBO, Weakening Buffer Operator), to solve deadlock that large number difficult establish reasonable prediction and improve accuracy. It contains morphing parameter, so as effectively control intensity weakening operator. The paper proposes an algorithm calculate parameter based on given sample....
<sec> <title>BACKGROUND</title> Electronic health record information systems' continuous application has accumulated enormous medical data with potential value. Semantic interoperability is the premise of mining and realizing these values by sharing reusing vast scattered, heterogeneous, multi-source clinical data. Several initiatives have been developing models to realize improve semantic interoperability, among which openEHR model one outstanding models. Reusing archetypes from Clinical...