Prediction of effluent concentration in a wastewater treatment plant using machine learning models

Of growing amount of food waste, the integrated food waste and waste water treatment was regarded as one of the efficient modeling method. However, the load of food waste to the conventional waste treatment process might lead to the high concentration of total nitrogen (T-N) impact on the effluent water quality. The objective of this study is to establish two machine learning models—artificial neural networks (ANNs) and support vector machines (SVMs), in order to predict 1-day interval T-N concentration of effluent from a wastewater treatment plant in Ulsan, Korea. Daily water quality data and meteorological data were used and the performance of both models was evaluated in terms of the coefficient of determination (R²), Nash–Sutcliff efficiency (NSE), relative efficiency criteria (d_rel). Additionally, Latin-Hypercube one-factor-at-a-time (LH-OAT) and a pattern search algorithm were applied to sensitivity analysis and model parameter optimization, respectively. Results showed that both models could be effectively applied to the 1-day interval prediction of T-N concentration of effluent. SVM model showed a higher prediction accuracy in the training stage and similar result in the validation stage. However, the sensitivity analysis demonstrated that the ANN model was a superior model for 1-day interval T-N concentration prediction in terms of the cause-and-effect relationship between T-N concentration and modeling input values to integrated food waste and waste water treatment. This study suggested the efficient and robust nonlinear time-series modeling method for an early prediction of the water quality of integrated food waste and waste water treatment process.     

Modelling of pitting corrosion in marine and offshore steel structures – A technical review

Corrosion is a major cause of structural deterioration in marine and offshore structures. It affects the life of process equipment and pipelines, and can result in structural failure, leakage, product loss, environmental pollution and the loss of life. Pitting corrosion is regarded as one of the most hazardous forms of corrosion for marine and offshore structures. The total loss of the structure might be very small, but local rate of attack can be very large and can lead to early catastrophic failure. Pitting corrosion is a localized accelerated dissolution of metal that occurs as a result of a breakdown in the protective passive film on the metal surface. It has been studied for many years; however, the structural failure due to pit characteristics is still not fully understood. Accurate pit depth measurements, precise strength assessment techniques, risk analysis due to pitting, and the mathematical relationship of the environmental factors that causes pitting failure are also factors, which need further understanding. Hence this paper focuses on these issues. It reviews and analyses the current understanding of the pitting corrosion mechanism and investigates all possible factors that can cause pitting corrosion. Furthermore, different techniques employed by scientists and researchers to identify and model the pitting corrosion are also reviewed and analysed. Future work should involve an in-depth scientific study of the corrosion mechanism and an engineering predictive model is recommended in order to assess failure, and thereby attempt to increase the remaining life of offshore assets.     

Model based grouping of species across environmental gradients

We present a novel approach to the statistical analysis and prediction of multispecies data. The approach allows the simultaneous grouping and quantification of multiple species’ responses to environmental gradients. The underlying statistical model is a finite mixture model, where mixing is performed over the individual species’ responses to environmental gradients. Species with similar responses are grouped with minimal information loss. We term these groups species archetypes. Each species archetype has an associated GLM that can be used to predict distributions with appropriate measures of uncertainty. Initially, we illustrate the concept and method using artificial data and then with application to real data comprising 200 species from the Great Barrier Reef (GBR) lagoon on 13 oceanographic and geological gradients from 12°S to 24°S. The 200 species from the GBR are well represented by 15 species archetypes. The model is interpreted through maps of the probability of presence for a fine scale set of locations throughout the study area. Maps of uncertainty are also produced to provide statistical context. The presence of each species archetype was strongly influenced by oceanographic gradients, principally temperature, oxygen and salinity. The number of species in each group ranged from 4 to 34. The method has potential application to the analysis of multispecies distribution patterns and for multispecies management.     

灰场包气带环境影响预测方法研究——以新疆某电厂灰场为例

灰场在防渗不当或事故工况下,淋滤液的渗漏可能会对灰场包气带产生影响。以新疆某火电厂灰场的淋滤液渗漏情景为例,介绍了淋滤液渗漏对包气带影响的3种预测方法并进行对比分析。结果表明,两类解析法计算误差较大且存在各自适用条件,应优先采用数值法进行定量化预测。     

Minimum ignition energy theoretical model for flammable gas based on flame propagation layer by layer

To achieve the rapid prediction of minimum ignition energy (MIE) for premixed gases with wide-span equivalence ratios, a theoretical model is developed based on the proposed idea of flame propagation layer by layer. The validity and high accuracy of this model in predicting MIE have been corroborated against experimental data (from literature) and traditional models. In comparison, this model is mainly applicable to uniform premixed flammable mixtures, and the ignition source needs to be regarded as a punctiform energy source. Nevertheless, this model can exhibit higher accuracy (up to 90%) than traditional models when applied to premixed gases with wide-span equivalence ratios, such as C₃H₈-air mixtures with 0.7–1.5 equivalence ratios, CH₄-air mixtures with 0.7–1.25 equivalence ratios, H₂-air mixtures with 0.6–3.15 equivalence ratios et al. Further, the model parameters have been pre-determined using a 20 L spherical closed explosion setup with a high-speed camera, and then the MIE of common flammable gases (CH₄, C₂H₆, C₃H₈, C₄H₁₀, C₂H₄, C₃H₆, C₂H₂, C₃H₄, C₂H₆O, CO and H₂) under stoichiometric or wide-span equivalence ratios has been calculated. Eventually, the influences of model parameters on MIE have been discussed. Results show that MIE is the sum of the energy required for flame propagation during ignition. The increase in exothermic and heat transfer efficiency for fuel molecules can reduce MIE, whereas prolonging the flame induction period can increase MIE.     

火电行业环境空气预测评价的研究

以2003年～2011年辽宁省境内新、扩改建火力发电厂和供热机组建设为研究对象,采用案例分析,结合国家有关大气环境影响预测评价的有关规定,就环境影响预测评价中存在的问题进行讨论,提出只有在SO2、NOx、PM10环境现状监测值为标准值的90%、30%、5%以上情况下才进行预测,否则,环境空气预测可以减免。     

On several issues regarding efforts toward a sustainable society

Environmental issues and the future sustainability of society are among the greatest concerns facing society today. How to formulate a pathway toward a sustainable society is a critical question. Several issues associated with this question are presented and discussed. First, a structuring of the issues is presented. The environment can be said to consist of three systems—the natural, social, and human—and their interactions; environmental problems may therefore be defined in terms of perturbations of the interactions among the three systems. A sustainable society can be realized by restoring these interactions. Next, the characteristics of the issues are discussed. Because environmental issues relate to the future, forecasts of the future are essential. Because it is impossible to predict the future with complete accuracy, however, we should develop a method of using information about the future with allowance for error. It should be noted that error characteristics differ according to their time-scale. Third, the relationship between environmental issues and society is discussed. To take collective action on these issues we need society-wide consensus, which requires a reliable and objective platform. Here, more attention must be paid to the distribution of knowledge across society, because scientific knowledge in a modern society tends to be monopolized by research organizations. The role of the media is therefore important. Another important factor is the commitment of the general public; user-friendly ways of galvanizing such commitment should be developed.

基于人工神经网络的松花江朱顺屯断面的水质预测

利用BP神经网络进行短期水质预报并进行水质预测后再评价对环境管理和规划有重要意义。本文建立了朱顺屯断面5个目标水质参数NH3-N、DO、高锰酸盐指数、TN和TP的BPANN水质预测模型,并对实例进行了验证,结果表明建立的推进式ANN可以应用于此类时间序列的环境预测,网络泛化性能好,能够满足实际应用。     

安全标准化系统发展模型及其理论研究

根据安全工程学、人机工程学的理论和原则，结合金川公司的生产实际，对安全标准化班组、车间、工厂建设模型及预测模型进行了探讨。提出了金川公司的安全标准化系统发展模型并升华为实用的理论。     

工业噪声预测模式辨析

分析了国家环保局颁发的《环境影响评价技术导则—声环境》标准所推荐的工业噪声预测模式,发现其不论在应用范围还是在可操作性方面均存在某些缺陷,提出了改进建议。