Mixture ratio modeling of dynamic systems

Any knowledge extraction relies (possibly implicitly) on a hypothesis about the modelled-data dependence. The extracted knowledge ultimately serves to a decision-making (DM). DM always faces uncertainty and this makes probabilistic modelling adequate. The inspected black-box modeling deals with “universal” approximators of the relevant probabilistic model. Finite mixtures with components in the exponential family are often exploited. Their attractiveness stems from their flexibility, the cluster interpretability of components and the existence of algorithms for processing high-dimensional data streams. They are even used in dynamic cases with mutually dependent data records while regression and auto-regression mixture components serve to the dependence modeling. These dynamic models, however, mostly assume data-independent component weights, that is, memoryless transitions between dynamic mixture components. Such mixtures are not universal approximators of dynamic probabilistic models. Formally, this follows from the fact that the set of finite probabilistic mixtures is not closed with respect to the conditioning, which is the key estimation and predictive operation. The paper overcomes this drawback by using ratios of finite mixtures as universally approximating dynamic parametric models. The paper motivates them, elaborates their approximate Bayesian recursive estimation and reveals their application potential.     

Flow state monitoring of gas-water two-phase flow using multi-Gaussian mixture model based on canonical variate analysis

As a highly complex and time-varying process, gas-water two-phase flow is commonly encountered in industries. It has a variety of typical flow states and transition flow states. Accurate identification and monitoring of flow states is not only beneficial to further study of two-phase flow but also helpful for stable operation and economic efficiency of process industry. Combining canonical variate analysis (CVA) and Gaussian mixture model (GMM), a strategy called multi-CVA-GMM is proposed for flow state monitoring in gas-water two-phase flow. CVA is used to extract flow state features from the perspective of correlation between historical data and future data, which solves the cross correlation and temporal correlation of multi-sensor measurement data. GMM calculates the possibility that the current flow state belongs to each typical flow pattern and judges the current flow state by probability indicators. It is conducive to follow-up use of Bayesian inference probability and Mahalanobis distance-based (BID) indicator for flow state monitoring, which avoids repeated traversal of multiple CVA-GMM models and improves the efficiency of the monitoring process. The probability indicators can also be used to analyze transition flow states. The method combining the probabilistic idea of GMM with the deterministic idea of multimodal modeling can accurately identify the current flow state and effectively monitor the evolution of flow state. The multi-CVA-GMM method is validated by using the measured data of the horizontal flow loop of gas-water two-phase flow experimental facility, and its effectiveness is proved.     

Computational modelling of water flow inside laboratory Knelson concentrator bowl

Enhanced gravity concentrators such as Knelson concentrator (KC) are extensively used in the mineral processing industry. The complexities of KC bowl geometry and variation of feed characteristics have forced process engineers to design empirically new units using laboratory and pilot-scale Knelson concentrators. However, numerical modelling methods such as computational fluid dynamics (CFD) and discrete element method (DEM) provide a better insight of flow behaviour of fluid and particulate solid phases inside these processing units. This article reports findings of CFD simulations for single-phase water flow inside the laboratory KC. An available standard 7.5-cm laboratory KC bowl was numerically simulated using realisable k-ε turbulence model to resolve the turbulence dispersion of existing transitional flow regime. The effects of relative centrifugal force (RCF) intensity and bed fluidisation water flow rate on the water velocity and pressure distributions were studied. Simulations confirmed the swirling flow pattern governing inside the bowl. The results revealed that the impact of RCF intensity on the water field values is greater than that of bed fluidisation water flow rate. Both velocity and pressure variations inside the bowl rings followed a linear trend.     

Integration of imitation learning using GAIL and reinforcement learning using task-achievement rewards via probabilistic graphical model

The integration of reinforcement learning (RL) and imitation learning (IL) is an important problem that has long been studied in the field of intelligent robotics. RL optimizes policies to maximize the cumulative reward, whereas IL attempts to extract general knowledge about the trajectories demonstrated by experts, i.e, demonstrators. Because each has its own drawbacks, many methods combining them and compensating for each set of drawbacks have been explored thus far. However, many of these methods are heuristic and do not have a solid theoretical basis. This paper presents a new theory for integrating RL and IL by extending the probabilistic graphical model (PGM) framework for RL, control as inference. We develop a new PGM for RL with multiple types of rewards, called probabilistic graphical model for Markov decision processes with multiple optimality emissions (pMDP-MO). Furthermore, we demonstrate that the integrated learning method of RL and IL can be formulated as a probabilistic inference of policies on pMDP-MO by considering the discriminator in generative adversarial imitation learning (GAIL) as an additional optimality emission. We adapt the GAIL and task-achievement reward to our proposed framework, achieving significantly better performance than policies trained with baseline methods.     

A knowledge construction methodology to automate case-based learning using clinical documents

The case-based learning (CBL) approach has gained attention in medical education as an alternative to traditional learning methodology. However, current CBL systems do not facilitate and provide computer-based domain knowledge to medical students for solving real-world clinical cases during CBL practice. To automate CBL, clinical documents are beneficial for constructing domain knowledge. In the literature, most systems and methodologies require a knowledge engineer to construct machine-readable knowledge. Keeping in view these facts, we present a knowledge construction methodology (KCM-CD) to construct domain knowledge ontology (i.e., structured declarative knowledge) from unstructured text in a systematic way using artificial intelligence techniques, with minimum intervention from a knowledge engineer. To utilize the strength of humans and computers, and to realize the KCM-CD methodology, an interactive case-based learning system(iCBLS) was developed. Finally, the developed ontological model was evaluated to evaluate the quality of domain knowledge in terms of coherence measure. The results showed that the overall domain model has positive coherence values, indicating that all words in each branch of the domain ontology are correlated with each other and the quality of the developed model is acceptable.     

350MW机组锅炉SCR脱硝系统优化

准东煤田是我国目前最大的整装煤田,但准东煤在锅炉燃烧过程中易发生结焦问题,一般掺烧高岭土缓解结焦。某燃用准东煤350 MW机组,锅炉燃煤掺烧高岭土后烟气携带灰尘颗粒及灰尘量增大,出现SCR脱硝系统烟道积灰严重和喷氨量明显偏大问题,同时在空气预热器形成硫酸氢氨堵塞,使机组不能长周期稳定运行。通过与国内同类型多台机组锅炉对比后发现,脱硝系统均存在易产生积灰的脱硝转向室、催化剂上方及空气预热器入口斜坡积灰状况等情况。针对存在的问题,通过建立改造前、后的模型计算分析,进行了导流板布置的优化设计、CFD流场分布、优化SCR系统导流板设计、声波与蒸汽吹灰器结合吹灰和氨注射栅格优化升级等工作,应用德图480风速仪实测风速试验,发现脱硝烟道原导流板设计不合理及施工安装偏差;原导流板水平段跨距大,支撑不足,造成导流板压塌变形,影响烟气流场分布;锅炉所烧煤质为高钠煤,为防止锅炉结焦掺烧高岭土后,增加了烟气飞灰颗粒及灰尘量,飞灰具有很大黏性,易沉积在烟道导流板及烟道壁面上。因此,提出对脱硝内部各处导流板进行优化改造,对脱硝系统烟道易产生积灰的部位增加声波吹灰器,对喷氨格栅喷嘴数量及氨空混合器升级,同时开展锅炉SCR脱硝喷氨热态优化调整试验工作。通过开展相关工作,SCR烟气系统的烟气流场相对标准偏差优化5%,相同负荷下液氨消耗量降低45%,彻底解决脱硝系统积灰和空气预热器堵塞问题,实现机组满负荷达标稳定运行。锅炉长期运行半年后停炉检查,发现前期脱硝系统烟道高达1 m的积灰部位彻底解决,催化剂表面干净无杂物,解决了脱硝系统积灰问题,同时配合提高空气预热器冷端综合温度的措施,彻底解决锅炉空气预热器堵塞问题。同时,经济效益显著,每年可以分别节约液氨费用70万元,节约风机电耗费用100万元,节约检修清理积灰及检修费用80万元,节约空气预热器冲洗治理费用20万元,综合节约费用270万元/a,达到预期效果实现机组长周期安全经济稳定运行。     

Development and validation of a micro-fin tubes evaporator model using R134a and R1234yf as working fluids

This paper presents a model of shell and tube evaporator with micro-fin tubes using R1234yf and R134a. The model developed for this evaporator uses the ε-NTU method to predict the evaporating pressure, the refrigerant outlet enthalpy and the outlet temperature of the secondary fluid. The model accuracy is evaluated using different two-phase flow boiling correlations for micro-fin tubes and comparing predicted and experimental data. The experimental tests were carried out for a wide range of operating conditions using R134a and R1234yf as working fluids. The predicted parameter with maximum deviations, between the predicted and experimental data, is the evaporating pressure. The correlation of Akhavan– Behabadi et al. was used to predict flow boiling heat transfer, with an error on cooling capacity prediction below 5%. Simulations, carried out with this validated model, show that the overall heat transfer coefficient of R1234yf has a maximum decrease of 10% compared with R134a.     

Human mobility synthesis using matrix and tensor factorizations

Human mobility prediction is of great advantage in route planning and schedule management. However, mobility data is a high-dimensional dataset in which multi-context prediction is difficult in a single model. Mobility data can usually be expressed as a home event, a work event, a shopping event and a traveling event. Previous works have only been able to learn and predict one type of mobility event and then integrate them. As the tensor model has a strong ability to describe high-dimensional information, we propose an algorithm to predict human mobility in tensors of location context data. Using the tensor decomposition method, we extract human mobility patterns with multiple expressions and then synthesize the future mobility event based on mobility patterns. The experiment is based on real-world location data and the results show that the tensor decomposition method has the highest accuracy in terms of prediction error among the three methods. The results also prove the feasibility of our multi-context prediction model.     

基于虚拟化技术的在线开放课程建设研究--以“常用工具软件”课程为例

随着互联网的迅猛发展,建设在线开放课程成为高职院校信息化教学改革的一个方向。首先通过分析国内外的在线课程现状,发现阻碍在线课程发展的共性问题;然后对"常用工具软件"课程现状进行深入调查、分析和研究,提出将虚拟化技术应用到课程建设中以解决网络教学遇到的问题;最后将研究结论应用到教学实践中,用于提升学生专业能力,提高教学效果。