On-line Estimation in Fed-batch Fermentation Process Using State Space Model and Unscented Kalman Filter

On-line estimation of unmeasurable biological variables is important in fermentation processes,directly influencing the optimal control performance of the fermentation system as well as the quality and yield of the targeted product.In this study,a novel strategy for state estimation of fed-batch fermentation process is proposed.By combining a simple and reliable mechanistic dynamic model with the sample-based regressive measurement model,a state space model is developed.An improved algorithm,swarm energy conservation particle swarm optimization(SECPSO) ,is presented for the parameter identification in the mechanistic model,and the support vector machines(SVM) method is adopted to establish the nonlinear measurement model.The unscented Kalman filter(UKF) is designed for the state space model to reduce the disturbances of the noises in the fermentation process.The proposed on-line estimation method is demonstrated by the simulation experiments of a penicillin fed-batch fermentation process.

A Study on Comprehensive Modeling for Errors in on-line Measuring System of Machining Center

Based on the theory of multi-body system (MBS), bine’s and huston’s methods are applied to an on-line measuring system of machining center in this paper. Through the study on modeling technique, the comprehensive model for errors calculation in an on-line measuring System of machining center have been built for the first time. Using this model, the errors can be compensated by soft.ware and the measuring accuracy can be enhanced without any more inveSt. This model can be used in all kinds of machining center.

Modeling of Microstructure Evolution and Mechanical Properties of Steel Plates Produced by Thermo-Mechanical Control Process and Its On-line Application

An integrated metallurgical model was developed to predict microstructure evolution and mechanical properties of low-carbon steel plates produced by TMCP. The metallurgical phenomena occurring during TMCP and mechanical properties were predicted for different process parameters. In the later passes full recrystallization becomes difficult to occur and higher residual strain remains in austenite after rolling. For the reasonable temperature and cooling schedule, yield strength of 30 mm plain carbon steel plate can reach 310 MPa. The first on-line application of prediction and control of microstructure and properties (PCMP) in the medium plate production was achieved. The predictions of the system are in good agreement with measurements.

On-Line Structural Breaks Estimation for Non-stationary Time Series Models

Non-stationary time series could be divided into piecewise stationary stochastic signal. However, the number and locations of breakpoints, as well as the approximation function of the respective segment signal are unknown. To solve this problem, a novel on-line structural breaks estimation algorithm based on piecewise autoregressive processes is proposed. In order to find the "best" combination of the number, lengths, and orders of the piecewise autoregressive (AR) processes, the Akaikes Information Criterion (AIC) and Yule-Walker equations are applied to estimate an AR model fit to the data. Numerical results demonstrate that the proposed estimation algorithm is suitable for different data series. Furthermore, the algorithm is used in a clinical study of electroencephalogram (EEG) with satisfactory results, and the ability to deal with real-time data is the most outstanding characteristic of on-line structural breaks estimation algorithm proposed.

Dynamic Fault Model for On-Line Evaluation of Yarn End Breakage during Ring Spinning

In this paper, a dynamic fault model is proposed to predict yarn end breakage in the spinning procedure through investigation of fault characteristics. In view of the principle that uniformity bad in raw material causes iustable yarn formation, the investigation focuses on the fault characteristic existing in the dynamic tension. Analyzing the dynamic spinning system, the phenomenon of over random shock in a spinning triangle is discovered to be the main physical event prior to yarn end breakage. The fault characteristic is further confirmed by dynamic tests and signal processing, and can be used to make an approach to predicting yarn end breakage. A relative energy feature is defined for evaluating the tendency of yarn end breakage, and its effectiveness is verified by on.line monitoring tests in the laboratory. The research results show that the proposed dynamic fault model has not only an advantage in indicating the presence of fault characteristics, but also great potentials in quantitating fault in online spinning monitoring.

Research on Business Model Optimization of Artificial Intelligence Garbage Classification

In recent years,garbage classification and environmental protection are gradually becoming an important step in the construction of ecological civilization in China.However,the popularity and commercial value of the application of artificial intelligence trash cans in Beijing are not high at present.This article analyzes these problems one by one and propose solutions,hoping that the commercial value of artificial intelligence trash cans can be optimized and improved and to make the city greener.This paper uses the questionnaire method and the literature method to research and analyze the optimization of the business model of artificial intelligence in garbage classification.

智能垃圾分类拾捡机器人抓取角度自动控制研究

角度偏离程度过大会导致机器人抓取行为出现偏差,从而使机器人错误抓取拾捡目标。为解决上述问题,针对智能垃圾分类拾捡机器人抓取角度自动控制展开研究。根据模糊pid控制原则,完成对机器人抓取参数的整定处理,再定义抓取行为动作空间,通过建模抓取过程的方式,确定抓取角度的取值范围,并在此基础上,推导具体的抓取角度控制条件,实现智能垃圾分类机器人抓取角度自动控制。实验结果表明,上述方法的应用,可将抓取角度控制在0°~25°的数值范围之内,不会因角度偏离程度过大而造成机器人偏差抓取的问题,能够保障机器人对拾捡目标的精准抓取。

规制背景下垃圾分类行为的影响因素研究

规制背景下个体的垃圾分类行为是城市垃圾分类效果的微观基础,因此垃圾分类行为的影响因素为人们所关注.依照计划行为理论,对垃圾分类的行为态度、主观规范、感知行为控制会影响垃圾分类行为.针对广州市高校学生的1155份有效调查问卷,利用结构方程模型对其数据进行分析,研究发现行为态度对垃圾分类行为无显著影响;主观规范对行为影响最大,其次是感知行为控制.个体的垃圾分类行为受室友的影响大于受家人的影响,而学校对垃圾分类行为设有奖惩制度对垃圾分类行为的预测作用最大.依据实证分析结果,可从以下方面来促进垃圾分类:首先,环境教育从认知教育转为垃圾分类引导、情景教育;其次,对城市生活垃圾分类可实施“奖惩”并提高规制强度;最后,利用群体对个体的垃圾分类行为规范的影响,可实施以小区、楼栋为单元的垃圾分类管理.

垃圾回收路径优化的经济性分析——以成都市为例

成都市是我国新一线城市,近年来,随着社会经济的快速发展,垃圾产生量大幅度增加。优化垃圾回收路径对于城市的可持续发展至关重要。以成都市为例,结合垃圾分类回收现状,运用灰色模型及反向传播(Back Propagation,BP)神经网络模型预测垃圾产生量,通过最小生成树模型规划最优路径,运用物联网技术提高运输周转效率,实现零库存。随着垃圾回收路径的优化,成都市可以更好地实现资源利用和环境保护的双重红利。

基于单片机的智能垃圾箱设计

针对当前垃圾分类效率低、回收利用率低、污染严重的问题,为了加强垃圾管理,创造优美、舒适的环境,采用STM32单片机作为核心控制器,结合K20图像识别系统、光敏电阻、太阳能发电板、蓄电池和OV5642摄像头等组件,利用MX-YOLOv3平台,设计了一款具有投放、垃圾分类、储电照明功能且可以移动的智慧垃圾箱,可广泛使用于学校、小区、城市街道、景区等多种场所,旨在提高垃圾分类效率,促进资源回收,减少环境污染。

Online model identification of lithium-ion battery for electric vehicles

In order to characterize the voltage behavior of a lithium-ion battery for on-board electric vehicle battery management and control applications,a battery model with a moderate complexity was established.The battery open circuit voltage (OCV) as a function of state of charge (SOC) was depicted by the Nernst equation.An equivalent circuit network was adopted to describe the polarization effect of the lithium-ion battery.A linear identifiable formulation of the battery model was derived by discretizing the frequent-domain description of the battery model.The recursive least square algorithm with forgetting was applied to implement the on-line parameter calibration.The validation results show that the on-line calibrated model can accurately predict the dynamic voltage behavior of the lithium-ion battery.The maximum and mean relative errors are 1.666% and 0.01%,respectively,in a hybrid pulse test,while 1.933% and 0.062%,respectively,in a transient power test.The on-line parameter calibration method thereby can ensure that the model possesses an acceptable robustness to varied battery loading profiles.

Mathematical Model of Dynamic Operation and Optimum Control of Billet Reheating Furnace

This paper provides a mathematical model for the billet reheating process in furnace.A new optimum method is brought up that the objective function is the integral value of enthalpy increasing process of a billet.Different delays are simulated and calculated,some proper delay strategies are ob- tained.The on-line computer control model is de- veloped.The real production conditions simulated, the temperature deviation of drop out billet from the target temperature is kept within±15℃.

城市生活垃圾分类准确率研究:基于环境关心、制度信任和社区归属感的分析

生活垃圾的准确分类投放是垃圾资源化回收利用的重要前提,垃圾分类准确率也是评价政策实施效果的重要指标。根据杭州市微观调研数据,采用多元有序Logistic模型分析环境关心、制度信任以及社区归属感对垃圾分类准确率的影响;运用层次回归将制度信任对“环境关心—垃圾分类准确率”关系的调节效应及社区归属感对“制度信任—垃圾分类准确率”关系的调节效应纳入分析。结果表明:社区归属感、制度信任对公众垃圾分类准确率均存在显著正效应;社区归属感对“制度信任—垃圾分类准确率”存在显著正向调节效应;此外,年龄和家庭年收入也均显著正向影响公众垃圾分类准确率。

城市居民垃圾分类行为干预体系构建——基于行为改变轮理论的实证分析

自2017年国家全面推行垃圾分类以来,一直存在居民参与率不高的问题。为了解决该问题,可基于行为改变轮理论,运用结构方程模型探索城市居民垃圾分类的行为来源,并提出正向干预措施。研究表明:(1)机会和动机能够对分类行为产生正向的直接影响,而能力与行为之间没有显著的直接影响;(2)能力通过动机对行为产生的间接影响要大于机会通过动机而产生的间接影响;(3)对行为的总影响大小依次为机会、动机和能力。依据行为干预措施与行为来源之间的对应关系,为提升居民垃圾分类的机会采取的干预措施包括实现、限制、社会重建和建模。

基于机器视觉的垃圾分拣机器人设计与实现

垃圾分类回收是实现资源循环利用至关重要的一环,对此设计了一种基于OpenMV机器视觉的垃圾分拣机器人。针对可回收垃圾、不可回收垃圾、有害垃圾选出特例作为训练集,利用EDGE IMPULSE的在线网站训练出神经网络模型,识别分类成功率可达97%以上。分拣机器人支持在线自动和手机APP控制两种模式,通过传送带传送,由舵机驱动机械臂投放至指定分类的垃圾桶。后由垃圾运输车自动运输垃圾,节省人力。

基于SPMYOLOv3的水面垃圾目标检测

为解决水面垃圾检测中存在目标形状尺度差异大,难以区分背景以及目标偏小的问题,本文提出了一种SPMYOLOv3目标检测算法来实现对水面垃圾的检测.首先,对收集到的水面垃圾数据集进行标注,使用改进的K-means算法对数据集重新聚类,得到与数据集更匹配的先验框.其次,在YOLOv3的主干网络后添加SE-PPM模块,加强目标的特征信息,保证目标尺度不变且保留全局信息.再使用多向金字塔网络对不同尺度的特征图进行融合,获得携带更加丰富的上下文信息的特征图.最后使用在损失函数中使用focal loss计算负样本的置信度损失,抑制了YOLOv3中正负样本不均衡问题.改进后的算法在水面垃圾数据集上的实验结果表明,相比于原YOLOv3算法检测精度提升了3.96%.

垃圾分类背景下上海市生活垃圾产生量的影响因素研究及预测

选取人口因素、经济发展水平、居民消费水平、城市建设情况等方面作为影响上海市生活垃圾产生量的因素,利用2011—2020年生活垃圾产生量及各影响因素的数据,通过灰色关联度分析得出外省市来沪旅游人数、人均可支配收入及人均消费支出是上海市生活垃圾产生量的主要影响因素。建立GM (1,1)模型对上海市生活垃圾产生量进行预测,在考虑垃圾分类的影响下预测出2022年和2023年上海市生活垃圾产生量分别为9.723×10^(6)t和1.012×10^(7)t,为上海市生活垃圾减量及总量控制提供科学指导。

基于多方满意度的户外分类垃圾桶可持续设计评价方法

目的 从可持续设计角度出发,为了更好地平衡用户、企业、环境、资源等多方需求的综合满意度,对户外分类垃圾桶可持续设计评价方法展开研究。方法 通过实地观察和访谈调研收集了多方需求,并利用双因子五阶Likert量问卷采集了初步需求的满意度调查数据;采用Kano模型分析计算需求敏感度并完成需求的筛选;将筛选后的需求和相应的敏感度分别作为评价指标和指标权重,完成了可持续设计评价指标体系的构建;结合灰色关联评价算法,对户外分类垃圾桶设计方案进行了评价实践和验证。结果 以12款户外垃圾桶设计方案作为评价实例,不仅实现了方案的综合得分排序,还通过单指标优势对综合最优方案做了进一步的优化。结论 实践结果表明,基于多方满意度户外分类垃圾桶可持续设计评价方法,能够有效评判户外分类垃圾桶的可持续设计质量,并帮助设计师优化和提升设计方案,具有较强的可操作性。

基于PP-PicoDet技术的智能垃圾分类

目前在垃圾分类目标检测上大多采用YOLOv5系列算法,该算法在相同参数量的情况下,检测精度和检测速度都相对不太高,难以满足实际应用需求;对基于PP-PicoDet技术的垃圾分类目标检测应用进行了研究,并将其与几种常见的垃圾分类目标检测算法进行实验对比分析;结果表明,PP-PicoDet算法能够在使用更少的参数量的情况下,实现较高的检测精度和速度,能够满足移动端部署需求。

基于TPB-VBN整合模型的居民垃圾分类意愿影响因素研究——以合肥市为例

垃圾产生端是垃圾分类的核心节点,因此增强居民垃圾分类意愿具有重要意义。本文选用TPB-VBN整合模型作为基本理论框架,将垃圾分类激励政策作为重要影响因素,对居民垃圾分类意愿进行实证分析。修正后,TPB-VBN整合模型得到结构方程验证。经分析,后果意识和环保意识对责任归属有积极影响,后果意识、责任归属与激励政策对个人规范有积极影响,个人规范与知觉行为控制对居民垃圾分类意愿有积极影响。最后,结合我国社会文化背景,从政府、企业、社区三个角度提出对策,以提高城市居民的垃圾分类意愿。