作者: Tarek M. Zayed , Daniel W. Halpin , Ismail M. Basha
DOI: 10.1080/01446190500184451
关键词: Delivery cost 、 Engineering 、 Productivity 、 Artificial neural network 、 Operations research 、 Robustness (computer science) 、 Truck 、 Process (computing) 、 Chart 、 Cycle time 、 Industrial and Manufacturing Engineering 、 Management information systems 、 Building and Construction
摘要: Current research focuses on assessing productivity, cost, and delays for concrete batch plant (CBP) operations using Artificial Neural Network (ANN) methodology. Data were collected to assess cycle time, delays, cost of delivery, price/m3 the CBP. Two ANN models designated represent CBP process considering many variables. Input variables include delivery distance, type, truck mixer's load. Output assessment price/m3. The outputs have been validated show ANN's robustness in output average validity percent is 96.25%. A Time‐Quantity (TQ) chart developed time required both mixers produce a specified quantity concrete. Charts predict time/truck, delays/truck, delivery/m3,