Prediction of Hot Deformation Behavior of 7Mo Super Austenitic Stainless Steel Based on Back Propagation Neural Network

The hot compression tests of 7Mo super austenitic stainless(SASS)were conducted to obtain flow curves at the temperature of 1000-1200℃and strain rate of 0.001 s^(-1)to 1 s^(-1).To predict the non-linear hot deformation behaviors of the steel,back propagation-artificial neural network(BP-ANN)with 16×8×8 hidden layer neurons was proposed.The predictability of the ANN model is evaluated according to the distribution of mean absolute error(MAE)and relative error.The relative error of 85%data for the BP-ANN model is among±5%while only 42.5%data predicted by the Arrhenius constitutive equation is in this range.Especially,at high strain rate and low temperature,the MAE of the ANN model is 2.49%,which has decreases for 18.78%,compared with conventional Arrhenius constitutive equation.

可食性膜在食品保鲜中的应用现状及研究进展

在食品保鲜领域,可食用天然抗菌保鲜膜是一种重要的可生物降解膜,具有易降解、成本低、来源广等特点。介绍了多糖膜、蛋白膜和脂质膜3种可食性涂膜在食品保鲜中的应用现状,综述了复合成膜技术、纳米颗粒制备技术及添加植物精油在制备可食性涂膜中的研究进展,以期为可食性包装材料在保鲜领域中的进一步研究提供参考借鉴。

Development of the artificial seabed technology and implementation pretrial well in the South China Sea

This paper introduces the recent highly significant activity of China Oilfield Services Ltd. （COSL） in the South China Sea, where COSL conducted pretrial drilling in June of 2008. The paper discusses some key research and new practices which led to the fabrication of related equipment which was evaluated in the trial. The market for deepwater drilling in the world has grown over the past 10 years but there are few drilling vessels or platforms suitable for drilling in deepwater or super deepwater. China needs equipment capable of deepwater drilling operations. COSL has some semisubmersible platforms, but they are only considered suitable for operations in water depths less than 475 m. An enabling technology, referred to as an artificial seabed, has been under development by COSL since 2004, and it applies the research results and experiences of many experts in deepwater drilling. COSL hopes this technology will allow drilling to depths of approximately 1 000-1 500m with its current platforms. The paper presents research progress and improvements in fabrication and necessary upgrades to equipment for extending deepwater drilling. The pretrial well was executed at a water depth of nearly 500m. COSL will drill the trial well around 2009 at the same location in the South China Sea.

Design of Constructed Wetland for Treatment of Tailwater from Wastewater Treatment Plant

In this study, the project of constructed wetland for treatment of tailwater from the wastewater treatment plant in Wudang Mountain was taken as an example, and the technological processes, pollution load, wetland bed structure, bed filler, selection of plants and hydraulic conditions of the subsurface flow constructed wetland were discussed. A subsurface flow constructed wetland, which covered an area of 7 227 m^2 was finally designed. It could treat 7 000 m^3 of tailwater from the wastewater treatment plant a day. In addition, the system could reduce the emission of COD, BODs, TN, TP and NH3-N by 25.55, 25.55, 12.78, 1.28 and 17.89 t respectively a day. The outlet water was proved to reach the Standard A of the first class in Discharge Standard of Pollutants for Municipal Wastewater Treatment Plant （GB 18918-2002）.

Hot deformation behavior and processing maps of Mg-Zn-Cu-Zr magnesium alloy

The deformation behaviors of a new quaternary Mg-6Zn-1.5Cu-0.5Zr alloy at temperatures of 523-673 K and strain rates of 0.001-1 s-1 were studied by compressive tests using a Gleeble 3800 thermal-simulator.The results show that the flow stress increases as the deformation temperature decreases or as the strain rate increases.A strain-dependent constitutive equation and a feed-forward back-propagation artificial neural network were used to predict flow stress,which showed good agreement with experimental data.The processing map suggests that the domains of 643-673 K and 0.001-0.01 s-1 are corresponded to optimum conditions for hot working of the T4-treated Mg-6Zn-1.5Cu-0.5Zr alloy.

INTEGRATION OF HUMAN FACTORS ENGINEERING AND QUALITY MANAGEMENT

Human factors engineering and quality management are different research branches in the field of industrial engineering.A basis for interaction based on the concepts and techniques of human factors engineering and quality management with some practical examples of cooperative effect is defined in this paper.The specific challenges about the quality management in manufacturing and service are presented to demonstrate that the human factors analysis of quality problems leads to new tends for integrated development.

COOPERATIVE DESIGN UNDER CONCURRENT ENGINEERING ENVIRONMENT

This paper outlines a concurrent engineering environment that supports interaction between members of a geographically dispersed multidisciplinary team who is engaged in engineering design activities. Some ideas of engineering design, especially conceptual design are reviewed. A deeper scientific analysis of intelligent design is discussed. A new problem solving strategy and methodologies to implement cooperative design are proposed. Finally, a conceptual model of a blackboard system for accomplishing conceptual design automation is presented. Its fundamental principles, system organization and key implementation techniques are investigated in detail.

BACKGROUND KNOWLEDGE AND SECONDARY KNOWLEDGE BASES IN LEARNINGS YSTEMS

This paper presents the differences and relations between background knowledge and domain theories in learning systems. The roles they play during learning procedures are discussed. It is emphasized that background knowledge plays an important role in enhancing the ability of a learning system. An explanation based learning system with domain theory in primary knowledge base and background knowledge in secondary knowledge base is introduced as an example. It shows how background knowledge can be used to solve some of the problems caused by incomplete domain theory in an explanation based learning system. The system can accomplish knowledge level learning through purely deductive approach. At last the acquisition of background knowledge is briefly discussed.

Ship motion extreme short time prediction of ship pitch based on diagonal recurrent neural network

A DRNN (diagonal recurrent neural network) and its RPE (recurrent prediction error) learning algorithm are proposed in this paper .Using of the simple structure of DRNN can reduce the capacity of calculation. The principle of RPE learning algorithm is to adjust weights along the direction of Gauss-Newton. Meanwhile, it is unnecessary to calculate the second local derivative and the inverse matrixes, whose unbiasedness is proved. With application to the extremely short time prediction of large ship pitch, satisfactory results are obtained. Prediction effect of this algorithm is compared with that of auto-regression and periodical diagram method, and comparison results show that the proposed algorithm is feasible.

Application of gray correlation analysis and artificial neural network in rock mass blasting

Studied forecasting and controlling the blasting fragmentation by using artifi- cial neural network for multi-ingredients. At the same time, according to the characteris- tic of multi-parameters input to network model, the gray correlation theory was employed to find out key factors, which can not only save time of computation and parameters in- put, but improve the stability of the model.

Flow behavior of Al-6.2Zn-0.70Mg-0.30Mn-0.17Zr alloy during hot compressive deformation based on Arrhenius and ANN models

The hot deformation behavior of Al?6.2Zn?0.70Mg?0.30Mn?0.17Zr alloy was investigated by isothermal compressiontest on a Gleeble?3500machine in the deformation temperature range between623and773K and the strain rate range between0.01and20s?1.The results show that the flow stress decreases with decreasing strain rate and increasing deformation temperature.Basedon the experimental results,Arrhenius constitutive equations and artificial neural network(ANN)model were established toinvestigate the flow behavior of the alloy.The calculated results show that the influence of strain on material constants can berepresented by a6th-order polynomial function.The ANN model with16neurons in hidden layer possesses perfect performanceprediction of the flow stress.The predictabilities of the two established models are different.The errors of results calculated by ANNmodel were more centralized and the mean absolute error corresponding to Arrhenius constitutive equations and ANN model are3.49%and1.03%,respectively.In predicting the flow stress of experimental aluminum alloy,the ANN model has a betterpredictability and greater efficiency than Arrhenius constitutive equations.

Multiobjective extremal optimization with applications to engineering design

In this paper, we extend a novel unconstrained multiobjective optimization algorithm, so-called multiobjective extremal optimization （MOEO）, to solve the constrained multiobjective optimization problems （MOPs）. The proposed approach is validated by three constrained benchmark problems and successfully applied to handling three multiobjective engineering design problems reported in literature. Simulation results indicate that the proposed approach is highly competitive with three state-of-the-art multiobjective evolutionary algorithms, i.e., NSGA-11, SPEA2 and PAES. Thus MOEO can be considered a good alternative to solve constrained multiobjective optimization problems.

APPLICATION OF EXPERT SYSTEM BASED ON NEURAL NETWORK IN MINING THE GENTLE INCLINED THICK SEAM

This paper presents a new method for the correct selection of mining methods and pre-diction of main technological and economic indexes of the face in the gentle inclined thick seams with the application of the artificial neural network theory and the expert system. The theory anal- ysis and calculating results indicate that the method is reliable, practical and precise. This method has strongly capabilities of self-study and non-linear dynamic data process. It is expected to be widely applied in the policy decision and prediction of mining technology in coal mine.

Evaluation of Relationship Between Clothing Pressure of Men's Suit and Comfort

An investigation on relationship between clothing pressure of men's suit and wearing comfort is conducted. With the pressure measurements at different parts of men's suit under normal standing posture and in motion, the objective assessment of the total comfort are related to the subjective ratings of clothing pressure. There is a common strong sensation of pressure on shoulder with normal standing posture, and a strong relationship between total comfort and clothing pressure in back armhole and the front of upper arm with posture in motion.

Optimization of assembly line balancing using genetic algorithm

In a manufacturing industry, mixed model assembly line(MMAL) is preferred in order to meet the variety in product demand. MMAL balancing helps in assembling products with similar characteristics in a random fashion. The objective of this work aims in reducing the number of workstations, work load index between stations and within each station. As manual contribution of workers in final assembly line is more, ergonomics is taken as an additional objective function. Ergonomic risk level of a workstation is evaluated using a parameter called accumulated risk posture(ARP), which is calculated using rapid upper limb assessment(RULA) check sheet. This work is based on the case study of an MMAL problem in Rane(Madras) Ltd.(India), in which a problem based genetic algorithm(GA) has been proposed to minimize the mentioned objectives. The working of the genetic operators such as selection, crossover and mutation has been modified with respect to the addressed MMAL problem. The results show that there is a significant impact over productivity and the process time of the final assembled product, i.e., the rate of production is increased by 39.5% and the assembly time for one particular model is reduced to 13 min from existing 18 min. Also, the space required using the proposed assembly line is only 200 m2 against existing 350 m2. Further, the algorithm helps in reducing workers fatigue(i.e., ergonomic friendly).

Developing a matrix to explore the relationship between partnering and total quality management in construction

Recently, there has been an increasing awareness and implementation of practices associated with Partnering and Total Quality Management (TQM) in the construction industry. Partnering and TQM both seek to enhance construction outcomes, yet rigorous studies of Partnering and TQM have been conducted separately and have not carefully examined common or unique practices associated with these techniques. This paper presents the findings of a theoretical analysis of an integrated approach for the use of Partnering and TQM. A matrix approach has been used to explore the extent to which Partnering may improve TQM implementation in construction. The matrix is based around 3 indexes, namely; the Degree of Partnering, the Degree of TQM and the Project Success Index and enables the relationship between Partnering and TQM to be analysed quantitatively. It also assists in understanding the trends of Partnering and TQM and their relationship to project performance. The results of a case study using this matrix are also presented. It has been concluded that the integrated use of Partnering can facilitate improvements in the way TQM is implemented in construction.

Control for Intelligent Manufacturing： A Multiscale Challenge

The Made in China 2025 initiative will require full automation in all sectors, from customers to production. This will result in great challenges to manufacturing systems in all sectors. In the future of manufacturing, all devices and systems should have sensing and basic intelligence capabilities for control and adaptation. In this study, after discussing multiscale dynamics of the modern manufacturing system, a five-layer functional structure is proposed for uncertainties processing. Multiscale dynamics include： multi-time scale, spacetime scale, and multi-level dynamics. Control action will differ at different scales, with more design being required at both fast and slow time scales. More quantitative action is required in low-level operations, while more qualitative action is needed regarding high-level supervision. Intelligent manufacturing systems should have the capabilities of flexibility, adaptability, and intelligence. These capabilities will require the control action to be distributed and integrated with different approaches, including smart sensing, optimal design, and intelligent learning. Finally, a typical jet dispensing system is taken as a real-world example for multiscale modeling and control.

Prediction for asphalt pavement water film thickness based on artificial neural network

In order to study the variation o f the asphalt pavement water film thickness influenced by multi-factors,anew method for predicting water film thickness was developed by the combination o f the artificial neural network(ANN)a d two-dimensional shallow water equations based on hydrodynamic theory.Multi-factors included the rainfall intensity,pavement width,cross slope,longitudinal slope a d pavement roughness coefficient.The two-dimensional hydrodynamic method was validated by a natural rainfall event.Based on the design scheme o f Shen-Sha expressway engineering project,the limited training data obtained by the two-dimensional hydrodynamic simulation model was used to predict water film thickness.Furthermore,the distribution of the water film thickness influenced by multi-factors on the pavement was analyzed.The accuracy o f the ANN model was verified by the18sets o f data with a precision o f0.991.The simulation results indicate that the water film thickness increases from the median strip to the edge o f the pavement.The water film thickness variation is obviously influenced by rainfall intensity.Under the condition that the pavement width is20m and t e rainfall intensity is3m m/h,t e water film thickness is below10mm in the fast lane and20mm in t e lateral lane.Athough there is fluctuation due to the amount oftraining data,compared with the calculation on the basis o f the existing criterion and theory,t e ANN model exhibits a better performance for depicting the macroscopic distribution of the asphalt pavement water film.

Mathematical models and expert system for grate-kiln process of iron ore oxide pellet production(Part Ⅰ):Mathematical models of grate process

Grate process is an important step in grate-kiln pellet production.However,as a relatively closed system,the process on grate is inaccessible to direct detection,therefore,it is hard to control.As a result,mathematical models of temperature distribution,moisture distribution and oxidation degree distribution in pellet bed,with good universality,computation speed and calculation accuracy,are presented based on analysis of heat transfer and physical-chemical reactions during grate process.And real-time visualization of temperature,moisture and oxidation degree distribution in pellet bed during grate process is realized.Model validation is displayed,and the similarity of 91% is proved.The results can reveal real time status on grate,and provide a solid foundation for the subsequent study of artificial intelligence control system of pellet production.

Design of a New Multifunctional Wheelchair-bed

Currently, the aging of the population has become the world＇s social problem. With the increase of aging population and lots of disability, paralysis makes nursing care more difficult. Because of many elderly cannot get timely care, the phenomenon that the elderly have chronic diseases has become more and more serious. It is important to research and develop a new product which can help the elderly and the disabled for improving the quality of their life. This paper suggests a new type of mnltifunctional self-caring wheelchair-bed, which is combined with a wheelchair and a bed. The bed can realize the free conversion among user sitting, leg lifting and lying down, and also can implement the function of turning on sides. Particularly, the wheelchair can be easily separated from the bed and combined, so that patients and the elderly can move freely using it, and even it can be transformed into a standing type to satisfy the patient＇s standing demand, and to a certain extent, carry out the purpose of rehabilitation.