ارزیابی هزینه مورد انتظار کیفیت (COQ) در پروژه های ساخت و ساز در مصر با استفاده از مدل شبکه عصبی مصنوعی

Many definitions for quality were provided by experts. Among these definitions are: quality is the fitness for use [14], conformance to requirements [4], quality is a predictable degree of uniformity and dependability, at low cost and suited to the market [6]. Cost of quality is an essential element of the total cost of any construction project. Consequently, the accurate assessment of such cost of quality can materially affect the reliability of the estimated cost of any construction project. Stated differently, the accurate and reliable cost estimating for any construction projects is not really possible without the deep investigation for the expected cost of quality of this project. Cost of quality is generally affected by many factors. Any attempt to assess the cost of quality of any project should take the different cost of quality factors into consideration. The main objective of this paper is to establish a neural network model that will enable the construction firms to assess cost of quality for any future building project. This will improve the company’s performance and its ability to compete with other companies through the improvement of bids accuracy. The “Neural Connection 2.0 Professional” was chosen to generate the proposed model. The main factors affecting the expected cost of quality were clearly identified. The different sequences of the model development will be deeply investigated. Moreover, the validity of the proposed model will be evaluated using a number of case study applications.

COQ is usually understood as the sum of conformance plus non-conformance costs, where cost of conformance is the price paid for prevention of poor quality, and cost of non-conformance is the cost of poor quality caused by product and service failure. These COQ can be also broken down into the three categories: • Prevention cost: the cost of any action taken to investigate, prevent or reduce the risk of nonconformity. • Appraisal cost: the cost of evaluating the achievement of quality requirements. • Internal failure cost: the costs arising within an organization due to nonconformities or defects at any stage of the quality loop. • External failure cost: the cost arising after delivery to a customer/user due to nonconformities or defects which may include the cost of claims against warranty, replacement and consequential losses and evaluation of penalties incurred. Cost of quality is an essential element of the total cost of any construction project. Cost of quality is generally affected by many factors, such as planned COQ for the project, awareness of quality for project team, supervision team experience, labor skills, suppliers, design errors, defected material, plan of improving quality, external factors, accident, equipment down time and project duration. The objective of this study is to identify the most important factors affecting cost of quality and to develop an Artificial Neural Network model that can help cost estimator to arrive at a more reliable assessment for the expected cost of quality of any building construction project. Literature review COQ models were classified into five groups of generic models. These are: P-A-F model, Crosby’s model, opportunity cost models, process cost models and ABC (Activity Based Costing) models. Porter and Rayner [19] make a more comprehensive survey of the published literature and present a detailed review of quality cost models, focusing again mainly on the P-A-F category and its limitations. The following is a summary for the main literature concerning the cost of quality topic: 1. Vernon et al. (1985) [23] Increases in construction planning during design and co-ordination across the design-construction interface are shown to have very strong effects on reducing construction time and increases in the former variable, which also included aspects of value analysis, reduce the cost of the building [21]. 2. Tesfai (1987) [22] Developed a good quality culture. Owners, designers and contractors will take quality seriously, preventive disciplines will be widely used and camaraderie’s will be observed throughout the industry [20]. 3. Davis et al. (1989) [5] A quality performance tracking system (QPTS) has been developed to provide for the quantitative analysis of certain quality-related aspects of projects, by systematically collecting and classifying costs of quality. By defining quality as “conformance to requirements,” the cost of quality becomes measurable. It consists of two main parts, the cost of quality management efforts and the cost of correcting deviations [6]. 4. Abdul-Rahman (1995) Stated that poor quality resulting from non-conformance during construction leads to extra cost and time to all members of the project team. The costs of rectifying non-conformance can be high and they can affect a firm’s profit margin and its competitiveness. Construction-related firms can identify non-conformance information by employing a quality cost matrix as illustrated in a case study as a basis for improvement [1]. 5. Abdul-Rahman (1996) Described the use of the quality cost matrix to capture the cost of non-conformance during a construction project and limited the Quality Performance Tracking System (QPTS) and developed a Quality Cost Matrix (QCM), which took into account the effect of a failure on time, particularly, the costing of accelerating work and specific causes of a non-conformance [2]. 6. Abdul-Rahman (1997) Investigated the importance of client role in determining the quality of the end product; the usefulness of information on non-conformances in preventing failures and improving a process; problems with ground conditions; how most failure costs can be eliminated; how the contractor’s role should include anticipating of problems; and how information on the cost of failures can be an indicator of weaknesses and assist in preventing the same failure in the future [3]. 7. Low et al (1998) [16] Stated that there are three components that make up quality costs: prevention, appraisal and failure costs. Proper design and implementation of these work procedures would lead to reduced wastage as more work would be done right the first time [13]. 8. Love (1999) [15] Determining the causal structure of rework influences in construction, contributes to study of quality in construction by capturing the complexity and dynamism of those factors that influence rework and project performance in a holistic manner. Rework is caused by errors made during the design process. These errors appear downstream in the procurement process and therefore have a negative impact on a project’s performance [12]. 9. Mwamila et al. (1999) [17] Stated that construction speed is impacted by the number and productivity of workers and can be increased by reliable equipment and early planning and design that maximize use of limited available resources. Building quality is dependent on standardization, product suitability evaluation, defect identification, and thorough planning. Labor costs are generally a small portion of total construction costs; however, labor is a key cost factor because it affects both quality and speed [14]. 10. Heng Li et al. (2000) [12] Analyzed the causes and costs of rework projects and discussed. The findings reveal that the cost of rework for the case study projects was 3.15–2.40% of their project contract value. Changes initiated by the client and end-user together with errors and omissions in contract documentation were found to be the primary causes of rework [10]. 11. Ofori et al. (2000) [18] Assessed the perceptions and expectations of contractors concerning ISO 9000 certification and the costs and benefits in practice. Contractors’ expectations of ISO 14000 certification were also ascertained, together with their environmental awareness, policies and current practices, and their views on measures which could promote its widespread adoption [15]. 12. Firuzan (2002) [10] Proposed a radical change in industry practice that will improve the quality of the construction process and the levels of customer satisfaction derived from it by evaluating the quality performance of the contractor. An alternative theory is developed of what constitutes quality, client satisfaction, performance, and their interrelationships in the context of the construction industry [7]. 13. Irani et al. (2003) [13] Developed the prototype Project Management Quality Cost System (PROMQACS) to determine quality costs in construction projects. The system was used to determine the cost and causes of rework that occurred in the projects. It is suggested that project participants can use the information in PROMQACS to identify shortcomings in their project-related activities and therefore take the appropriate action to improve their management practices in future projects [11]. 14. Dikmen et al. (2005) [8] Examined the applicability of QFD (Quality Function Deployment) as a strategic decision-making tool after the construction stage of a housing project to determine the best marketing strategy, to make a comparison between the performances of different competitors and to transfer the experience gained from the current project to the forthcoming projects (5). 15. Samadony et al. (2006) [21] Revealed that the mean expenditure on quality in the Egyptian construction firms is about 26% of total cost, and the internal failure cost is about 10% from total project cost. The key to continuing success in quality management is the ability to collect poor quality information to improve the performance of the construction process. This information should then be incorporated into the design and management of the new projects. This information can also be used to measure the performance of construction firms so that continuous improvement is based on measurement of performance can be effectively implemented [18]. 16. Rosenfeld (2009) [20] Compare cost of quality versus cost of non-quality in construction. The methodology is based on quantifying the four types of quality-related costs in residential construction, and relates them to each other by expressing them all as percentages of the relevant total construction revenues [17].

The survey results illustrated that cost of quality are greatly affected by many aspects. Among these aspects come project duration, planned cost of quality, supervision team experience, project size project location. All of these factors make the detailed estimation of such cost of quality a more difficult task. Hence, it is expected that an ANN’s model would be a suitable tool for assessment of cost of quality in construction projects in Egypt. The following conclusions may be deduced from this study: • All the way through the literature review, potential factors that control the percentage of cost of quality for building construction projects were recognized. Thirteen factors were identified. • The analysis of the composed data gathered from a questionnaire survey among the Egyptian construction experts illustrated that project’s duration, planned cost of quality, supervision team experience, project size, project location, Awareness of quality for the project team, class of contractor, client type, labor skills and project type are the top 10 factors affecting the percentage of cost of quality for building construction projects in Egypt. • A satisfactory neural network model was obtained through one hundred and six (106) experiments for predicting the percentage of cost of quality for building construction projects in Egypt for the future projects. This model consists of one input layer with 10 neurons (nodes), one hidden layer having eight hidden nodes with a tangent transfer function and one output layer. The learning rate of this model is set automatically by the N-Connection (version 2.0) while the training and testing tolerance are set to 0.1. • The results of testing for the best model indicated a testing root mean square error (RMS) value of 0.259. • Testing the validity of the proposed model was carried out on five (5) facts that were still unseen by the network. The results of the testing indicated an accuracy of (80%). As the model wrongly predicted the percentage of cost of quality for only one project (20%) of the testing sample.