Coal Bottom Ash (CBA) is a by-product from the generation of electricity using pulverized coal; Tanjung Bin power plant in Malaysia is a coal-based power plant that generates tonnes of bottom ash daily without known economic value that ends up in the ash pond. Due to the problems associated with the disposal ash pond in terms of cost and environmental impact, attention has now been focused on how best to utilize this waste. This paper present the recent development achieved on the utilization of bottom ash from Tanjung Bin power plant Malaysia in concrete development; physical and chemical properties, workability and fresh concrete properties as well as the strength development of Tanjung Bin bottom ash.

In this study, a neural network based model available in Weka Algorithms, was utilized to test the predictive capacity of compressive strength in high strength concrete (HSC) with steel fiber addition. Fiber addition levels ranged from 0.19 – 2.0% were utilized obtained from literature with a total of 192 instances (datasets) and 10 attributes. To test the performance of the algorithm, a 10 – fold cross-validation method was used to assess the effectiveness which was later compared with full training sets. Also, seven learning schemes were utilized to determine the optimum using percentage split. Results generated from the model include correlation coefficient, mean absolute error, root mean squared error, and relative absolute error. It was observed a good correlation coefficient was obtained which was close to unity at 70-30 and 80-20% of training to testing, and significant reduction in the associated errors were observed. Results for coefficient of determination are also presented and follow the same trend observed in the percentage split results. Time taken to generate the model was much shorter an indication of efficiency.

Compressive strength, fc of concrete is affected by a number of factors such as type and percentage of cement, water content, size and amount of additives and aggregates, mixing procedures, and compaction as well as curing process [1], [2]. In concrete with fiber addition, it has been reported that this addition sometimes exert influence on the strength of the resulting concrete. The work of [3], reported that fc of concrete with steel fiber addition increased with fiber content for lower aspect ratio, while in higher aspect ratio, the increase was up to 1% before it fluctuates. This corresponds to what has been reported in the literature that it can either increase, decrease, or show no trend at all [4], [5]. This trend in concrete with steel fiber addition present a challenge especially when prediction of strength is the ultimate goal, when using machine learning applications. This is because the program has to be trained to be conversant with the dataset to be able to make accurate predictions.

No abstract