scholarly journals Fuzzy-Neural Cost Estimation for Engine Tests

2011 ◽  
pp. 178-204
Author(s):  
Edit J. Kaminsky ◽  
Holly Danker-McDermot ◽  
Freddie Douglas

This chapter discusses artificial computational intelligence methods as applied to cost prediction. We present the development of a suite of hybrid fuzzy-neural systems for predicting the cost of performing engine tests at NASA’s Stennis Space Center testing facilities. The system is composed of several adaptive network-based fuzzy inference systems (ANFIS), with or without neural subsystems. The output produced by each system in the suite is a rough order of magnitude (ROM) cost estimate for performing the engine test. Basic systems predict cost based solely on raw test data, whereas others use preprocessing of these data, such as principal components and locally linear embedding (LLE), before entering the fuzzy engines. Backpropagation neural networks and radial basis functions networks (RBFNs) are also used to aid in the cost prediction by merging the costs estimated by several ANFIS into a final cost estimate.

2009 ◽  
Vol 13 (2) ◽  
Author(s):  
Richard C. Hicks ◽  
Keith Wright

Implementations of inference engine systems invoke many costs, including the cost of the inference engine itself, the cost of integrating the inference engine, and the cost of specialized personnel needed to create and maintain the system. These costs make a very high return on investment a criterion for incorporating these systems into the corporate portfolio of applications and technologies. Recently, the No Inference Engine Theory (NIET) [8] has been developed for creating procedural propositional logic rule-based systems. The NIET systems are implemented in traditional procedural languages such as C++ and do not need an inference engine or proprietary languages, thus eliminating the cost of the inference engine, the cost of integrating the system, and the cost for knowledge of a proprietary language. In addition, these procedural systems are an order of magnitude faster [8] than inference systems and maintain linear performance. For problems using propositional logic, the procedural systems described in this paper offer dramatically lower costs, higher performance, and ease of integration. Lowering the external costs and eliminating the need for specialized skills should make NIET systems more profitable and lead to the wider use of propositional logic systems in business.


2019 ◽  
Vol 258 ◽  
pp. 02027
Author(s):  
Hirijanto ◽  
I Wayan Mundra ◽  
Addy Utomo

Project’s cost is one of important components in project achievement. Because of the uniqueness of construction projects, cost estimation always differs from project to project. The rate of cost components always change over time make difficult to forecast the cost for the upcoming project. The cost component consists of many influencing variables where there is interrelationship each other affecting to the total project cost. This paper objective is to develop a cost prediction model to assist the project planners in cost estimation for future projects. System dynamic is one of the appropriate methods to analyse system behaviour with interrelationship referring to the historic data, so it is able to predict the future project. Developing the model, primary and secondary data are collected from previous studies, interview with the government planner and survey in Malang Regency. The model simulation is Brick work unit with its components. Data from last thirteen years are used to verify and validate the developed model by causal loop diagram as a basic method in system dynamic. The finding showed that the model is closed to real condition through the validation mechanism. The developed system is useful in decision making of budget planning based on work quantity.


2011 ◽  
Vol 332-334 ◽  
pp. 1505-1510
Author(s):  
Xiao Bo Yang

In this paper, a new method of subtractive clustering adaptive network fuzzy inference systems is proposed to assess degree of wrinkle in the fabric. The clustering center can be gotten through subtractive clustering algorithm, which is the base to set up adaptive network inference systems. Firstly, subtractive clustering algorithm is used to confirm the structure of fuzzy neural network, then, fuzzy inference system is used to process pattern recognition. Finally, four kinds of fabric wrinkle feature parameters are used to verify the results on real fabric. The results show the applicability of the proposed method to real data.


2019 ◽  
Vol 8 (4) ◽  
pp. 7824-7828

Cost estimation analysis for the software system project is the foremost difficult tasks in software organizations. In this paper, a comparison between an estimate and actual effort was done by applying the grey wolf’s algorithm to predict the effort and time of this software system for a given archive. The intermediate semi-detached COCOMO model was used with the grey wolf’s algorithm by taking the KLOC of the dataset as input, additionally to fifteen cost drivers and giving effort and time as output. The recommended model of the cost estimation helps the project manager by offering a fast and truly estimates the hassle and time of software system project which is nearer to the actual cost.


Author(s):  
Vоlоdуmуr Matyukha

The importance of cost estimation of mineral resources in modern economic theory is noted in the article. It is noted that all currently existing methodical and methodological approaches to the valuation of minerals by their economic nature are in fact an analysis of the economic feasibility of realization of investment projects for the development of deposits, which actually answers the question: is the investment project for the development of the field economically viable. Based on the analysis of literary sources, it is established that at the present stage of development of the world economy, the interest in the economic evaluation of the efficiency of development of mineral resources is not waning. However, methodological approaches are different and there is still no unity in them. Experts point out that the current methods require improvement due to the low accuracy of calculations, since the size of the cost estimate depends on the amount of rental payments for the use of mineral resources in mining and the starting price of the sale of a special permit for the development of deposits at auction. For the first time in the economic theory economics, a graphoanalytic method for the cost estimation of mineral deposits has been proposed. The features of this methodological approach based on integral calculus, including the integration of continuous functions, as well as the method of discounting cash flows with simultaneous consideration of the life cycle scheme of deposits, namely mining and geological conditions of mining are opened. The step-by-step sequence of realization of the proposed method is resulted. It is stated that this approach will allow to obtain a more exact cost estimate of a deposit or subsoil by taking into account the following factors: the life of the deposit, the market conditions of the mineral resources, capital and current expenses connected with extraction of minerals and costs of the subsoil user in the post-mining a period of time related to the closure of mines and quarries and the reclamation of disturbed lands formed during the extraction of minerals.


2011 ◽  
Vol 17 (2) ◽  
pp. 157-167 ◽  
Author(s):  
Yousef Baalousha ◽  
Tahir Çelik

Estimating is a fundamental part of construction projects. Accurate cost estimate is the single most important element involved in the series of events that leads to a profitable completion of a contract in construction industry. The success or failure of a project depends on the accuracy of cost estimation. A cost estimate becomes more difficult and more complicated under inflationary medium. An unpredictable inflation rate and long progress payment delay during this period makes the budgeting function very difficult, if not impossible. The cost estimation process uses lots of data. The availability of the appropriate data at the appropriate time is one of the main factors affecting the accuracy of the cost estimation. As the complexity of the estimating task increases computerized system becomes increasingly important. The estimator should develop a good system of estimating forms and procedures that exactly meet the requirements of the pro- ject, and that is understood and accessible by all team members. This system should provide the ability to define material, labor hour and equipment hour quantities required for the project. Material, labor, and equipment unit costs are then applied to the bill of quantities. This paper presents An Integrated Web-Based Data Warehouse and Artificial Neural Net- works Model for Unit Price Analysis with Inflation Adjustment system called “DANUP“. Web facilities and database management capabilities of Microsoft Visual Studio 2005 are applied to create a data warehouse which is mainly aimed to integrate data from multiple heterogeneous databases and other information sources. The System also supports integrated cost index for adjusting the effect of inflation during estimating process. An artificial neural network model for forecast- ing the cost indices in Turkey for the project period has been developed. A construction project takes relatively long time to complete, effective communication among the project participants during the project period is important. A web based system is developed to facilitate the collection of construction cost information and communication. The web based sys- tem focuses on demonstrating the potential of data centric web data bases in enhancing the communication process during project execution. End users can access the database through the internet and perform certain transactions according to their authorization. Santrauka Sąmatos sudarymas – esminė statybos projektų dalis. Tiksli sąnaudų sąmata – vienas svarbiausių elementų, susijusių su įvykiais, kurie statybų sektoriuje leidžia pelningai įvykdyti sutartį. Projekto sėkmė arba žlugimas priklauso nuo to, ar tiksliai įvertintos sąnaudos. Infliacinėje aplinkoje sąnaudas įvertinti sunkiau ir sudėtingiau. Dėl neprognozuojamo infliacijos lygio ir ilgalaikių dalinių mokejimų vėlavimo per tokį laikotarpį biudžetą numatyti itin sunku, o gal net neįmanoma. Vertinant sąnaudas reikia gausybės duomenų. Galimybė reikiamu metu gauti reikiamus duomenis – vienas pagrindinių veiksnių, darančių įtaką sąnaudų sąmatos tikslumui. Kadangi sąmatas sudaryti vis sudėtingiau, vis svarbiau yra naudoti kompiuterizuotas sistemas. Sąmatininkas turi suformuoti gerą sąmatų sudarymo formų ir procedūrų sistemą, tiksliai atitinkančią projekto reikalavimus, suprantamą ir prieinamą visiems komandos nariams. Tokioje sistemoje reikia funkcijos, leidžiančios nurodyti projektui reikalingų medžiagų, darbo valandų ir įrangos naudojimo valandų skaičius. Tuomet medžiagų, darbo ir įrangos vienetų kainos įtraukiamos i sąmatą. Šiame darbe pristatoma integruoto internetinio duomenų saugyklos ir dirbtinių neuroninių tinklų modelio, tinkamo analizuoti vieneto kainą, atsižvelgiant į infliacija, sistema, pavadinta ”DANUP“. Naudojant Microsoft Visual Studio 2005 internetines ir duomenų bazių valdymo funkcijas, sukuriama duomenų saugykla, kurios svarbiausias tikslas – integruoti iš daugybės heterogeninių duomenų bazių ir kitų informacijos šaltinių gautus duomenis. Be to, naudojant sistemą galima sudaryti integruotą sąnaudų indeksą, kuris sudarant sąmatą leidžia įvertinti infliacijos poveikį. Buvo sukurtas dirbtinio neuroninio tinklo modelis, leidžiantis Turkijoje prognozuoti sąnaudų indeksus, kurie galios vykstant projektui. Statybos projektas trunka gana ilgai, taigi vykdant projektą svarbu, kad bendravimas tarp jo dalyvių būtų efektyvus. Buvo sukurta internetinė sistema, padedanti rinkti informaciją apie statybų sąnaudas ir bendrauti tarpusavyje. Pagrindinis internetinės sistemos tikslas – parodyti, kaip, remiantis duomenų kiekiu grindžiamomis internetinėmis duomenų bazėmis, vykdant projektą galima pagerinti komunikaciją. Galutiniai vartotojai duomenų bazę gali pasiekti internetu ir, priklausomai nuo prieigos lygio, atlikti tam tikras operacijas.


2014 ◽  
Vol 989-994 ◽  
pp. 2684-2687
Author(s):  
Wei Zhou ◽  
Xiao Xue Wang

Many machine learning approaches in the field of Artificial Intelligence (AI) have been developed. Most of them rely on using large data sets to build up knowledge. However, the traffic system usually has only few data. In this article, the so-called adaptive neural fuzzy inference systems (ANFIS) is employed to predict the traffic time-series with few data, including flow, speed and occupancy


2013 ◽  
Vol 284-287 ◽  
pp. 2120-2123
Author(s):  
Pi Yun Chen ◽  
Yu Yi Fu ◽  
Kuo Lan Su ◽  
Jin Tsong Jeng

In this paper, the Box–Cox transformation-based annealing robust fuzzy neural networks (ARFNNs) are proposed for identification of the nonlinear Magneto-rheological (MR) damper with outliers and skewness noises. Firstly, utilizing the Box-Cox transformation that its object is usually to make residuals more homogeneous in regression, or transform data to be normally distributed. Consequently, a support vector regression (SVR) method with Gaussian kernel function has the good performance to determine the number of rule in the simplified fuzzy inference systems and initial weights in the fuzzy neural networks. Finally, the annealing robust learning algorithm (ARLA) can be used effectively to adjust the parameters of the Box-Cox transformation-based ARFNNs. Simulation results show the superiority of the proposed method for the nonlinear MR damper systems with outliers and skewness noises.


Sign in / Sign up

Export Citation Format

Share Document