检索结果-南通市图书馆

维普期刊数据库

基于机器学习的L-赖氨酸发酵过程软测量建模和模型预测控制方法研究

在线全文

学校读者我要写书评

暂无评论

基于机器学习的L-赖氨酸发酵过程软测量建模和模型预测控制方法研...

作者： muhammad shahzad khan 江苏大学

学位级别：硕士

L-赖氨酸发酵过程是一个复杂非线性、强耦合、大时变系统,为最大限度提升L-赖氨酸的生产效率和产品品质,迫切需要利用先进控制技术对L-赖氨酸发酵过程进行动态调控和实时优化,将其控制在最佳工艺条件下进行生产。然而由于涉及菌种的生... 详细信息

L-赖氨酸发酵过程是一个复杂非线性、强耦合、大时变系统,为最大限度提升L-赖氨酸的生产效率和产品品质,迫切需要利用先进控制技术对L-赖氨酸发酵过程进行动态调控和实时优化,将其控制在最佳工艺条件下进行生产。然而由于涉及菌种的生长繁殖、代谢过程,L-赖氨酸发酵过程存在的复杂特性造成了优化运行控制的困难:(1)L-赖氨酸发酵过程内部机理十分复杂,动力学模型呈高度的非线性,难以建立能够准确描述其菌种生长、代谢过程动力学特征的数学模型;(2)发酵过程的动力学特征参数随反应时间或批次的变化而变化,传统的、以动力学为基础的控制方法已难以满足控制性能要求;(3)反映L-赖氨酸发酵过程品质的菌体浓度、基质浓度、产物浓度等关键参量目前还缺乏有效的在线测量手段,成为制约优化运行控制的瓶颈问题。目前对这些关键参量的检测主要采用离线采样分析的方法,存在较大的测量延时,难以实施实时控制,同时取样过程中发酵液易受杂菌污染,严重影响L-赖氨酸的生产过程。L-赖氨酸发酵过程的优化运行控制主要通过对一些环境参量(如溶氧浓度、p H、温度等)的检测,凭借工人经验和感官进行手动操作,自动化水平低,技术落后,无法满足L-赖氨酸发酵过程优化运行控制的要求,且生产过程中错误和故障不易及时发现,造成原材料的浪费和设备的空转,严重制约着L-赖氨酸产业的规模化、集约化进程,因此,如何克服以上问题带来的缺陷成为L-赖氨酸产业界亟需解决的问题之一。针对L-赖氨酸发酵过程中非线性、多变量、强耦合以及关键参量难以在线检测等特点,本文在国家自然科学基金(41376175)、江苏高校优势学科建设工程项目(PAPD)、镇江市重点研发计划-社会发展项目(SH2020005)的资助下,围绕L-赖氨酸发酵过程关键参量软测量、非线性模型预测控制方法等问题,开展L-赖氨酸发酵过程优化运行控制的研究,本论文的具体研究内容如下:论文提出ICS-MLSSVM混合型多输出软传感器建模方法,并将其应用在L-赖氨酸发酵过程的关键参量软测量中,实现对L-赖氨酸发酵过程关键生化变量(菌体浓度、基质浓度、产物浓度)的在线实时检测。首先,根据L-赖氨酸发酵过程的多输入、多输出特点,构建多输出最小二乘支持向量机回归器(MLSSVM)模型。然后,利用改进的布谷鸟搜索(ICS)优化算法对MLSSVM模型的重要参数(γ,λ,σ)进行优化。最后,利用优化后的模型参数值建立了ICSS-MLSSVM软传感器混合模型,在线实现了L-赖氨酸发酵过程的关键生化变量。仿真结果证实,所提出的回归模型能够准确预测关键生化变量。此外,混合ICS-MLSSVM软传感器模型在预测精度和适应性上均优于基于标准CS(CS-MLSSVM)、粒子群优化算法(PSO-MLSSVM)和遗传算法(GA-MLSSVM)的MLSSVM软传感器模型。本部分提出的软测量模型将应用于第四章模型预测控制系统中。针对L-赖氨酸发酵过程中流加速率难以实时控制的问题,提出了一种非线性模型预测控制(NMPC)方法。首先,基于机器学习算法(最小二乘支持向量机-LSSVM)建立了L-赖氨酸发酵过程非线性模型预测控制模型,将其用于非线性模型预测控制中作为过程模型预测产品浓度,然后,采用灰狼优化(GWO)算法优化LSSVM预测模型的关键参数(惩罚因子和核宽)以提高其预测精度,同时,GWO还解决了非线性模型预测控制中的非凸优化问题(GWO-NMPC),用于计算未来最优输入。最后,结合关键参量软测量模型,将基于GWO的LSSVM预测模型(GWO-LSSVM)和非线性模型预测控制(GWO-NMPC)方法与基于粒子群优化(PSO)的预测模型(PSO-LSSVM)和非线性模型预测控制(PSO-NMPC)方法进行比较,验证其有效性。比较结果表明,与基于P S O的预测控制相比,基于G WO的预测控制的预测精度、适应性、实时跟踪能力、总体误差和控制精度都较好。

关键词： L-赖氨酸发酵机器学习模型预测控制软测量灰狼优化算法最小二乘支持向量机布谷鸟搜索优化

Design and Implementation of a State-feedback Controller Using LQR Technique

同方学位论文库评论

在线全文

同方学位论文库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2022年第11期73卷 2897-2911页

作者： Aamir shahzad Shadi Munshi Sufyan Azam muhammad Nasir khan Mechanical Engineering Department The University of LahoreLahorePakistan Mechanical Engineering Department Umm Al-Qura UniversityMakkahSaudi Arabia Electrical Engineering Department The University of LahoreLahorePakistan

The main objective of this research is to design a state-feedback controller for the rotary inverted pendulum module utilizing the linear quadratic regulator(LQR)*** controller maintains the pendulum in the inverted(upright)position and is robust enough to reject external disturbance to maintain its *** research work involves three major contributions:mathematical modeling,simulation,and real-time *** design a controller,mathematical modeling has been done by employing the NewtonEuler,Lagrange *** resulting model was nonlinear so linearization was required,which has been done around a working *** the estimation of the controller parameters,MATLAB LQR function has been *** has been performed for the designed controller and it also has been implemented and tested over the real inverted *** the results,it is vivid that the designed controller keeps the inverted pendulum in an upright position and rejects the disturbances and falling under gravitational force by adjusting the rotation of the horizontal link.

关键词： Mathematical modeling linearization linear quadratic regulator(LQR) nonlinear system rotary inverted pendulum

Computing and Implementation of a Controlled Telepresence Robot

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Intelligent Automation & Soft Computing 2023年第8期37卷 1569-1585页

作者： Ali A.Altalbe Aamir shahzad muhammad Nasir khan Prince Sattam Bin Abdulaziz University Al-Kharj11942Saudi Arabia Faculty of Computing and Information Technology King Abdulaziz UniversityJeddah21589Saudi Arabia Department of Mechanical Engineering The University of LahoreLahore54000Pakistan Department of Electrical Engineering GC University LahoreLahore54000Pakistan

The development of human-robot interaction has been continu-ously increasing for the last *** this development,it has become simpler and safe interactions using a remotely controlled telepresence robot in an insecure and hazardous *** audio-video communication connection or data transmission stability has already been well handled by fast-growing technologies such as 5G and ***,the design of the phys-ical parameters,e.g.,maneuverability,controllability,and stability,still needs ***,the paper aims to present a systematic,controlled design and implementation of a telepresence mobile *** primary focus of this paper is to perform the computational analysis and experimental implementa-tion design with sophisticated position control,which autonomously controls the robot’s position and speed when reaching an obstacle.A system model and a position controller design are developed with root locus *** design robot results are verified experimentally,showing the robot’s agreement and control in the desired *** robot was tested by considering various parameters:driving straight ahead,right turn,self-localization and complex *** results prove that the proposed approach is flexible and adaptable and gives a better *** experimental results show that the proposed method significantly minimizes the obstacle hits.

关键词： Computing telepresence healthcare system position controller mobile robot

Radionuclide concentrations in sand samples from riverbanks of Muzaffarabad,Azad Kashmir

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Nuclear Science and Techniques 2018年第7期29卷 103-115页

作者： Abdul Razzaq khan muhammad Rafique Abdul Jabbar Saeed Ur Rahman muhammad Ikram shahzad muhammad Ejaiz khan Mulaika Yasin Department of Physics University of Azad Jammu andKashmir MuzaffarbadAzad Kashmir 13100Pakistan Health Physics Division Pakistan Institute of NuclearScience and Engineering(PINSTECH)NiloreIslamabad 45650Pakistan Department of Medical Physics Nuclear MedicineOncologyand Radiotherapy InstituteIslamabadPakistan Physics Division Directorate of SciencePINSTECHP.O.NiloreIslamabad 45650Pakistan

This paper presents the results of a radiological risk assessment arising from the presence of naturally occurring radionuclides in sand samples from three riverbanks in *** mean values obtained for 232 Th,226 Ra,and 40 K were found to be 44.58 ± 3.34,48.25 ± 1.77,and 239.92 ± 22.73 Bq kg^(-1),*** assess the uniformity of exposure,the radium equivalent activity(Raeq) was calculated and was found to be130.47 ± 8.29 Bqkg^(-1).The current reported value for Raeqis lower than the maximum permissible value,that is,370 Bq kg^(-1),and equivalent to a gamma dose of1.5 m Svy^(-1).To investigate the possible contribution to health risks of alpha particle exposure,the radon exhalation rate(RER) from the sand samples was *** mean RER for all the samples was found to be335 m Bq m-^(2) h^(-1).About 43% of the samples were found to have an indoor excess lifetime cancer risk value slightly higher than recommended safety limit of 1,as proposed by the ICRP.A normalized parameter,the equivalent multiplicative factor,was defined and used to compare the current results with the findings of studies performed in other *** findings are relevant to both human health and future environmental radiation monitoring.

关键词：放射性核种样品克什米尔河岸风险评价调查结果 226Ra gamma

维普期刊数据库

Data Fusion Architecture Empowered with Deep Learning for Breast Cancer Classification

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2023年第12期77卷 2813-2831页

作者： Sahar Arooj muhammad Farhan khan Tariq shahzad muhammad Adnan khan muhammad Umar Nasir muhammad Zubair Atta-ur-Rahman Khmaies Ouahada Faculty of Computing Riphah International UniversityIslamabad45000Pakistan Department of Forensic Sciences University of Health SciencesLahore54000Pakistan Department of Electrical and Electronic Engineering Science University of JohannesburgP.O.Box 524Johannesburg2006South Africa School of Computing Skyline University CollegeUniversity City SharjahSharjah1797United Arab Emirates Riphah School of Computing and Innovation Faculty of ComputingRiphah International UniversityLahore CampusLahore54000Pakistan Department of Software Faculty of Artificial Intelligence&SoftwareGachon UniversitySeongnamGyeonggido13120Korea Department of Computer Science Bahria UniversityLahore CampusLahore54000Pakistan Department of Computer Science College of Computer Science and Information Technology(CCSIT)Imam Abdulrahman Bin Faisal University(IAU)P.O.Box 1982Dammam31441Saudi Arabia

Breast cancer(BC)is the most widespread tumor in females worldwide and is a severe public health *** is the leading reason of death affecting females between the ages of 20 to 59 around the *** detection and therapy can help women receive effective treatment and,as a result,decrease the rate of breast cancer *** cancer tumor develops when cells grow improperly and attack the healthy tissue in the human *** are classified as benign or malignant,and the absence of cancer in the breast is considered *** learning,machine learning,and transfer learning models are applied to detect and identify cancerous tissue like *** research assists in the identification and classification of *** implemented the pre-trained model AlexNet and proposed model Breast cancer identification and classification(BCIC),which are machine learning-based models,by evaluating them in the form of comparative *** used 3 datasets,A,B,and *** fuzzed these datasets and got 2 datasets,A2C and *** A2C is the fusion of A,B,and C with 2 classes categorized as benign and *** B3C is the fusion of datasets A,B,and C with 3 classes classified as benign,malignant,and *** used customized AlexNet according to our datasets and BCIC in our proposed *** achieved an accuracy of 86.5%on Dataset B3C and 76.8%on Dataset A2C by using AlexNet,and we achieved the optimum accuracy of 94.5%on Dataset B3C and 94.9%on Dataset A2C by using proposed model BCIC at 40 epochs with 0.00008 learning *** proposed fuzzed dataset model using transfer *** fuzzed three datasets to get more accurate results and the proposed model achieved the highest prediction accuracy using fuzzed dataset transfer learning technique.

关键词： Breast cancer classification deep learning machine learning transfer learning learning rate

A PHEMT Based Wideband LNA for Wireless Applications

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

China Communications 2015年第10期12卷 108-116页

作者： muhammad Saad khan ZHANG Hongxin HE Pengfei Sulman shahzad Rahat Ullah School of Electronic Engineering Beijing University of Posts and Telecommunications(BUPT) Electrical Engineering Department University College of Engineering & TechnologyBahauddin Zakariya University Institute of Science and Technology for Opto-electronic Information Yantai University State Key Laboratory of Information Photonics and Optical Communications Beijing University of Posts and Telecommunications

This work is about the development of a super low noise amplifier with minimum power consumption and high gain for several wireless *** amplifier operates at frequency bands of 0.9-2.4 GHz and can be used in many applications like Wireless local area network(WLAN),WiFi,Bluetooth,ZigBee and Global System for mobile communications(GSM).This new design can be employed for the IEEE 802.15.4 standard in industrial,scientific and medical(ISM) *** enhancement mode pseudomorphic high electron mobility transistor PHEMT is used here due to its high linearity,better performance and less noisy *** common source inductive degeneration method is employed here to enhance the gain of *** amplifier produces a gain of more than 17 dB and noise figure of about 0.5 *** lower values of S11 and S22 reflect the accuracy of impedance matching network placed at the input and output sides of *** Advance Design System(ADS) is used for the design and simulation *** the layout of design is developed on the FR4 substrate.

关键词： low noise amplifier phemt advanced design system wireless local area network global positioning system

维普期刊数据库

Proximate composition and elemental analysis in soft tissues of freshwater mussels （Anodonta anatina） from the Chashma Lake, River Indus Pakistan

在线全文

学校读者我要写书评

暂无评论

Frontiers in Biology 2016年第4期11卷 331-337页

作者： muhammad Sohail muhammad Naeem khan Abdul Shakoor Chaudhry Khurram shahzad Department of Zoology University of the Punjab Lahore Pakistan School of Agriculture_Food and Rural development Newcastle University UK

BACKGROUND： Aquatic invertebrates are playing an important role in assessment of the water contaminants and also serve as a major component of food chain. Freshwater mussels are considered to be the good bioindicator species of aquatic environment and widely used to determine the metals load. METHODS： Proximate composition and elemental analysis were carried out in edible （foot, mantle） and non-edible portion （gills） of freshwater mussels （Anodonta anatina） harvested from various site of Chashma Lake, River Indus Pakistan. RESULTS： The nutritional components were varied among the studied portion and muscular foot found to be the best part for consumption. Protein and fat contents were significantly higher in foot （15.90±0.88%, 1.19 ±0.26%） as compared to mantle （10.78±2.24%, 0.27±0.09%） and gills （6.44± 1.22%, 0.53 4-0.15%） respectively. For the macro minerals mantle had high concentration of Ca （46838±984 mg/kg）, Na （2706±343 mg/kg）, P （6921± 1063 mg/kg） and Mn （7207± 1046 mg/kg） as compared to foot. CONCLUSIONS： Heavy metals （Cd, Cu, Cr） concentration in edible portions were lower than the permissible limit by WHO whereas the concentration of Pb was slightly higher than the recommended value that might be the risk for the consumers. Being filter feeder gills accumulated the high concentration of all the metals and found to be the key portion for biomonitoring studies. Freshwater mussels of Chashma Lake Indus River are the rich source of protein and all the other micro and macro minerals therefore could be used as an excellent source of food.

关键词： proximate composition minerals metals River Indus freshwater mussel

Neural Machine Translation Models with Attention-Based Dropout Layer

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2023年第5期75卷 2981-3009页

作者： Huma Israr Safdar Abbas khan muhammad Ali Tahir muhammad Khuram shahzad Muneer Ahmad Jasni Mohamad Zain School of Electrical Engineering and Computer Science(SEECS) National University of Science and TechnologyIslamabadPakistan Institute for Big Data Analytics and Artificial Intelligence(IBDAAI) Kompleks Al-KhawarizmiUniversiti Teknologi MARA40450Shah AlamSelangorMalaysia

In bilingual translation,attention-based Neural Machine Translation(NMT)models are used to achieve synchrony between input and output sequences and the notion of *** model has obtained state-of-the-art performance for several language ***,there has been little work exploring useful architectures for Urdu-to-English machine *** conducted extensive Urdu-to-English translation experiments using Long short-term memory(LSTM)/Bidirectional recurrent neural networks(Bi-RNN)/Statistical recurrent unit(SRU)/Gated recurrent unit(GRU)/Convolutional neural network(CNN)and *** results show that Bi-RNN and LSTM with attention mechanism trained iteratively,with a scalable data set,make precise predictions on unseen *** trained models yielded competitive results by achieving 62.6%and 61%accuracy and 49.67 and 47.14 BLEU scores,*** a qualitative perspective,the translation of the test sets was examined manually,and it was observed that trained models tend to produce repetitive output more *** attention score produced by Bi-RNN and LSTM produced clear alignment,while GRU showed incorrect translation for words,poor alignment and lack of a clear ***,we considered refining the attention-based models by defining an additional attention-based dropout *** dropout fixes alignment errors and minimizes translation errors at the word *** empirical demonstration and comparison with their counterparts,we found improvement in the quality of the resulting translation system and a decrease in the perplexity and over-translation *** ability of the proposed model was evaluated using Arabic-English and Persian-English datasets as *** empirically concluded that adding an attention-based dropout layer helps improve GRU,SRU,and Transformer translation and is considerably more efficient in translation quality and speed.

关键词： Natural language processing neural machine translation word embedding attention perplexity selective dropout regularization Urdu Persian Arabic BLEU

Fluoridation and Sintering of Hydroxyapatite Material and Their Mechanical Properties

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Wuhan University of Technology(Materials Science) 2014年第1期29卷 190-196页

作者： muhammad Asif 付正义 WANG Weimin WANG Hao TAN Tiening shahzad Ahmad khan State Key Lab of Advanced Technology for Materials Synthesis and Processing Wuhan University of Technology

In the current work hydroxyapatite Ca10(PO4)6 ·OH2(HA) was sintered with the addition of 3 wt% aluminum isopropoxide(C9H21AlO3) powder and 3 wt % Teflon powder(-C2 F2-). Sample was prepared by following sol-gel technique. Obtained pellets of samples were sintered. For investigation of effects of temperature on microstructures and mechanical properties the samples were sintered at various temperatures. For studying the phase composition, microstructures and elemental analysis the sintered samples were characterized by X-rays diffraction(XRD), scanning electron microscopy(SEM) and energy dispersive X-rays diffraction(EDAX) respectively. After sintering the samples mechanical properties, i e, grains size, apparent density, Vickers hardness, bending strength and compressive strength were found to be 2.14-18.76 μm, 1.523 6-0.752 g/cm3, 3.60-0.600 GPa and bending strength 33.265 8-14.900 MPa, 75-33 MPa, respectively. As a result of sintering fluoridated composite material was obtained.

关键词： fluoridated hydroxyapatite pressureless sintering mechanical properties hydroxyapatite materials