# Heat Rate Prediction of Combined Cycle Power Plant Using an Artificial Neural Network (ANN) Method

^{1}

^{2}

^{3}

^{*}

## Abstract

**:**

_{2}percentage (P2), and power output (P3) as input parameters. Approximately 4322 actual operation data are generated from the digital control system (DCS) in a year. These data were used for ANN training and prediction. Seven parameter variations were developed to find the best parameter variation to predict heat rate. The model with one input parameter predicted heat rate with regression R

^{2}values of 0.925, 0.005, and 0.995 for P1, P2, and P3. Combining two parameters as inputs increased accuracy with regression R

^{2}values of 0.970, 0.994, and 0.984 for P1 + P2, P1 + P3, and P2 + P3, respectively. The ANN model that utilized three parameters as input data had the best prediction heat rate data with a regression R

^{2}value of 0.995.

## 1. Introduction

_{2}percentage, even though those two parameters are usually used in the gas purchase agreement between the gas suppliers and power plant operator. Furthermore, the power plant operator usually has a plant efficiency written in their contract with the regulator. Omar et al. [17] showed that decreasing power generation leads to higher specific fuel consumption.

_{2}) percentage contain in the fuel gas and generated power in megawatts (MW) as input parameters. Some studies above showed that ANN is effective in predicting gas turbine performance. Therefore, an ANN was used as a machine learning tool to predict the power plant heat rate.

## 2. Materials and Methods

_{2}percentage and power generated in MW. Total generated power of the CCPP, from a GT and steam turbine, recorded by a distributed control system (DCS) was used as an input parameter in this paper. Since the DCS did not provide a fuel gas heating unit in MMBTUs and CO

_{2}percentage, the gas supplier’s hourly data were used. The gas provided by the supplier went to the combustion chamber and was used as a fuel for the GT. The exhaust gas from the process was used to feed the HRSG. Since the total heat from these two processes is equal to the gas supplied, the gas data from supplier was used. Equation (1) was used to calculate the plant heat rate [20].

^{3}/h); HHV = High Heating Value (BTU/SCF); P = power output (MW).

## 3. Results

#### 3.1. One Input Parameter

^{2}for all data of 0.925 and 0.954, respectively. P2 only resulted in R

^{2}0.048. With low R

^{2}results from these ANN models, we could see that with only one parameter, the ANN did not meet the expectation of predicting the heat rate. Moreover, with only CO

_{2}percentage as an input parameter, it could not predict the power plant heat rate.

#### 3.2. Two Input Parameters

^{2}were 0.970, 0.994, and 0.984, respectively. It was shown that utilized fuel gas input and power output could predict the power plant heat rate more accurately than fuel gas input with CO

_{2}percentage or CO

_{2}percentage with power output.

#### 3.3. Three Input Parameters

^{2}for model g was 0.995, which was the highest number among all models. Based on these results, utilizing fuel gas input, CO

_{2}percentage and power output together as input parameters in ANN could lead to more accurate power plant heat rate prediction.

## 4. Discussion

^{2}regression was only 0.984, and the validation check was 17. Combining three input parameters, P1 + P2 + P3, could produce better accuracy. Table 6 shows that P1 + P2 + P3 led to the highest regression R

^{2}value. It also had a zero validation check. A validation check refers to the number of errors from the dataset. Lower validation checks could lead to higher accuracy from the model to predict the desired data. The experiment data showed that adding CO

_{2}percentage as an input parameter could lead to higher accuracy in predicting CCPP heat rate value. All the variation had average error data lower than 2%. This indicates that the NN could predict heat rate accurately, and the P1 + P2 + P3 with the lowest error data could be the best variation to predict heat rate.

## 5. Conclusions

- Utilizing one parameter as an input could not bring an accurate heat rate prediction. The ANN regression R
^{2}value for fuel gas energy (MMBTU), CO_{2}percentage (%), and power output (MW) were 0.925, 0.005, and 0.954, respectively. - The regression R
^{2}values for two input parameters, where fuel gas energy (MMBTU) + CO_{2}percentage (%), fuel gas energy (MMBTU) + Power (MW), and CO_{2}percentage (%) + Power (MW), were 0.970, 0.994, and 0.984, respectively. - The combination of all three parameters showed the best result of the ANN model. The regression R
^{2}value was 0.995 with zero validation check and the lowest average error data. - The three parameter combination resulted in the lowest average error in experimental data with 0.19%
- Utilizing fuel gas energy (MMBTU), CO
_{2}percentage (%), and power output (MW) as inputs can lead to an accurate CCPP heat rate prediction.

## Author Contributions

## Funding

## Conflicts of Interest

## References

- Wood, D.A. Combined cycle gas turbine power output prediction and data mining with optimized data matching algorithm. SN Appl. Sci.
**2020**, 2, 1–21. [Google Scholar] [CrossRef] [Green Version] - Liu, Z.; Karimi, I.A. Gas turbine performance prediction via machine learning. Energy
**2020**, 192, 116627. [Google Scholar] [CrossRef] - Bartolini, C.; Caresana, F.; Comodi, G.; Pelagalli, L.; Renzi, M.; Vagni, S. Application of artificial neural networks to micro gas turbines. Energy Convers. Manag.
**2011**, 52, 781–788. [Google Scholar] [CrossRef] - Anvari, S.; Taghavifar, H.; Saray, R.K.; Khalilarya, S.; Jafarmadar, S. Implementation of ANN on CCHP system to predict trigeneration performance with consideration of various operative factors. Energy Convers. Manag.
**2015**, 101, 503–514. [Google Scholar] [CrossRef] - Fast, M.; Assadi, M.; De, S. Development and multi-utility of an ANN model for an industrial gas turbine. Appl. Energy
**2009**, 86, 9–17. [Google Scholar] [CrossRef] - Rossi, F.; Velázquez, D.; Monedero, I.; Biscarri, F. Artificial neural networks and physical modeling for determination of baseline consumption of CHP plants. Expert Syst. Appl.
**2014**, 41, 4658–4669. [Google Scholar] [CrossRef] - Elfaki, E.A.; Hassan, A.H. Prediction of electrical output power of combined cycle power plant using regression ANN model. J. Power Energy Eng.
**2018**, 6, 17–38. [Google Scholar] [CrossRef] [Green Version] - Tüfekci, P. Prediction of full load electrical power output of a base load operated combined cycle power plant using machine learning methods. Int. J. Electr. Power Energy Syst.
**2014**, 60, 126–140. [Google Scholar] [CrossRef] - Rua Orozco, D.J.; Venturini, O.J.; Escobar Palacio, J.C.; del Olmo, O.A. A new methodology of thermodynamic diagnosis, using the thermoeconomic method together with an artificial neural network (ANN): A case study of an externally fired gas turbine (EFGT). Energy
**2017**, 123, 20–35. [Google Scholar] [CrossRef] - Plis, M.; Rusinowski, H. A mathematical model of an existing gas-steam combined heat and power plant for thermal diagnostic systems. Energy
**2018**, 156, 606–619. [Google Scholar] [CrossRef] - Palme, T.; Breuhaus, P.; Assadi, M.; Klein, A.; Kim, M. New Alstom Monitoring Tools Leveraging Artificial Neural Network Technologies. ASME Turbo Expo
**2011**, 281–292. [Google Scholar] [CrossRef] - Smrekar, J.; Pandit, D.; Fast, M.; Assadi, M.; De, S. Prediction of power output of a coal-fired power plant by artificial neural network. Neural Comput. Appl.
**2009**, 19, 725–740. [Google Scholar] [CrossRef] - Fantozzi, F.; Desideri, U. Simulation of power plant transients with artificial neural networks: Application to an existing combined cycle. Proc. Inst. Mech. Eng.
**1998**, 212, 299–313. [Google Scholar] [CrossRef] - Flynn, D.; Ritchie, J.; Cregan, M. Data Mining Techniques Applied to Power Plant Performance Monitoring. In IFAC Proceedings Volumes; Elsevier: Amsterdam, The Netherlands, 2005; Volume 38, pp. 369–374. [Google Scholar]
- Lu, S.; Hogg, B. Dynamic nonlinear modelling of power plant by physical principles and neural networks. Int. J. Electr. Power Energy Syst.
**2000**, 22, 67–78. [Google Scholar] [CrossRef] - Pan, L.; Flynn, D.; Cregan, M. Statistical Model for Power Plant Performance Monitoring and Analysis. In Proceedings of the 2007 42nd International Universities Power Engineering Conference, Brighton, UK, 4–6 September 2007; pp. 121–126. [Google Scholar]
- Khudair, O.A.; Abass, K.A.; Abed, N.S.; Ali, K.H.; Abdulaziz, S.; Shaboot, A.C. Theoretical Investigation For The Effect of Fuel Quality on Gas Turbine Power Plants. J. Phys. Conf. Ser.
**2018**, 1003, 012022. [Google Scholar] [CrossRef] - Walzcak, S.; Narciso, C. Artificial Neural Network. Available online: https://www.researchgate.net/publication/288156361_Artificial_Neural_Networks (accessed on 2 December 2020).
- Taghavifar, H.; Mardani, A.; Taghavifar, L. A hybridized artificial neural network and imperialist competitive algorithm opti-mization approach for prediction of soil compaction in soil bin facility. Measurement
**2013**, 46, 2288–2299. [Google Scholar] [CrossRef] - ASME. ASME PTC 22—2005 Gas Turbine Performance Test Code. Available online: https://www.twirpx.com/file/866220/ (accessed on 2 December 2020).

No | Fuel Gas Heat Input (MMBTU) ^{1} | CO_{2} Percentage (%) | Power Output (MW) | Heat Rate (kcal/kWh) |
---|---|---|---|---|

1 | 2197.821 | 3.678 | 302.52 | 1878.26 |

2 | 2197.821 | 3.678 | 302.52 | 1878.26 |

3 | 2197.821 | 3.678 | 302.88 | 1876.03 |

4 | 2197.821 | 3.678 | 303.21 | 1873.99 |

5 | 2196.798 | 3.636 | 303.09 | 1874.17 |

6 | 2196.798 | 3.636 | 302.34 | 1878.82 |

7 | 2197.423 | 3.563 | 302.73 | 1876.23 |

8 | 2197.423 | 3.563 | 303 | 1874.56 |

9 | 2200.318 | 3.614 | 303.03 | 1876.92 |

10 | 2202.682 | 3.577 | 303.12 | 1876.68 |

… | … | … | … | … |

4313 | 2165.601 | 3.719 | 305.01 | 1816.48 |

4314 | 2165.601 | 3.7190 | 303.66 | 1824.56 |

4315 | 2165.601 | 3.7190 | 304.17 | 1821.5 |

4316 | 2165.601 | 3.7190 | 304.68 | 1818.45 |

4317 | 2157.497 | 3.595 | 303.87 | 1816.67 |

4318 | 2155.63 | 3.716 | 302.85 | 1820.62 |

4319 | 2155.63 | 3.716 | 303.3 | 1817.92 |

4320 | 2151.122 | 3.901 | 302.07 | 1823.05 |

4321 | 2150.759 | 3.804 | 301.86 | 1823.44 |

4322 | 2150.759 | 3.804 | 302.28 | 1820.91 |

^{1}Milion British Thermal Unit.

Group | Variation | Parameter Description | Output Parameter |
---|---|---|---|

One input Parameter | P1 | Fuel gas energy (MMBTU) | heat rate |

P2 | CO_{2} percentage (%) | heat rate | |

P3 | Power (MW) | heat rate | |

Two input Parameters | P1 + P2 | Fuel gas energy (MMBTU) & CO_{2} percentage (%) | heat rate |

P1 + P3 | Fuel gas energy (MMBTU) & Power (MW) | heat rate | |

P2 + P3 | CO_{2} percentage (%) & Power (MW) | heat rate | |

Three input parameters | P1 + P2 + P3 | Power (MW) & Fuel gas energy (MMBTU) | heat rate |

No | Actual | P1 | Error | P2 | Error | P3 | Error | P1 + P2 | Error |
---|---|---|---|---|---|---|---|---|---|

1 | 1930.12 | 1961.38 | 1.62% | 1858.55 | 3.71% | 1962.81 | 1.69% | 1928.67 | 0.08% |

2 | 1943.56 | 1961.38 | 0.92% | 1858.55 | 4.37% | 1965.96 | 1.15% | 1928.67 | 0.77% |

3 | 1918.19 | 1962.03 | 2.29% | 1858.32 | 3.12% | 1960.44 | 2.20% | 1929.10 | 0.57% |

4 | 1930.22 | 1962.03 | 1.65% | 1858.32 | 3.72% | 1963.29 | 1.71% | 1929.10 | 0.06% |

5 | 1927.70 | 1962.03 | 1.78% | 1858.32 | 3.60% | 1962.69 | 1.82% | 1929.10 | 0.07% |

6 | 1929.72 | 1962.03 | 1.67% | 1858.32 | 3.70% | 1963.17 | 1.73% | 1929.10 | 0.03% |

7 | 1933.59 | 1962.41 | 1.49% | 1858.15 | 3.90% | 1964.12 | 1.58% | 1929.30 | 0.22% |

8 | 1928.04 | 1962.41 | 1.78% | 1858.15 | 3.63% | 1962.81 | 1.80% | 1929.30 | 0.07% |

9 | 1936.64 | 1962.41 | 1.33% | 1858.15 | 4.05% | 1964.83 | 1.46% | 1929.30 | 0.38% |

10 | 1927.54 | 1962.41 | 1.81% | 1858.15 | 3.60% | 1962.69 | 1.82% | 1929.30 | 0.09% |

1072 | 1816.48 | 1811.50 | 0.27% | 1860.87 | 2.44% | 1814.07 | 0.13% | 1821.54 | 0.28% |

1073 | 1824.56 | 1811.50 | 0.72% | 1860.87 | 1.99% | 1816.74 | 0.43% | 1821.54 | 0.17% |

1074 | 1821.50 | 1811.50 | 0.55% | 1860.87 | 2.16% | 1815.73 | 0.32% | 1821.54 | 0.00% |

1075 | 1818.45 | 1811.50 | 0.38% | 1860.87 | 2.33% | 1814.72 | 0.21% | 1821.54 | 0.17% |

1076 | 1816.67 | 1814.29 | 0.13% | 1860.40 | 2.41% | 1816.32 | 0.02% | 1822.70 | 0.33% |

1077 | 1820.62 | 1814.93 | 0.31% | 1860.86 | 2.21% | 1818.34 | 0.13% | 1822.98 | 0.13% |

1078 | 1817.92 | 1814.93 | 0.16% | 1860.86 | 2.36% | 1817.45 | 0.03% | 1822.98 | 0.28% |

1079 | 1823.05 | 1816.47 | 0.36% | 1861.58 | 2.11% | 1819.88 | 0.17% | 1823.71 | 0.04% |

1080 | 1823.44 | 1816.60 | 0.38% | 1861.20 | 2.07% | 1820.30 | 0.17% | 1823.74 | 0.02% |

1081 | 1820.91 | 1816.60 | 0.24% | 1861.20 | 2.21% | 1819.47 | 0.08% | 1823.74 | 0.16% |

No | Actual | P1 + P3 | Error | P2 + P3 | Error | P1 + P2 + P3 | Error | |
---|---|---|---|---|---|---|---|---|

1 | 1930.12 | 1930.85 | 0.04% | 1935.11 | 0.26% | 1932.78 | 0.14% | |

2 | 1943.56 | 1938.25 | 0.27% | 1939.50 | 0.21% | 1943.22 | 0.02% | |

3 | 1918.19 | 1924.42 | 0.32% | 1932.04 | 0.72% | 1923.87 | 0.30% | |

4 | 1930.22 | 1931.08 | 0.04% | 1935.93 | 0.30% | 1933.33 | 0.16% | |

5 | 1927.70 | 1929.69 | 0.10% | 1935.12 | 0.38% | 1931.35 | 0.19% | |

6 | 1929.72 | 1930.80 | 0.06% | 1935.77 | 0.31% | 1932.94 | 0.17% | |

7 | 1933.59 | 1932.52 | 0.06% | 1937.24 | 0.19% | 1935.61 | 0.10% | |

8 | 1928.04 | 1929.45 | 0.07% | 1935.46 | 0.38% | 1931.22 | 0.16% | |

9 | 1936.64 | 1934.19 | 0.13% | 1938.21 | 0.08% | 1938.01 | 0.07% | |

10 | 1927.54 | 1929.17 | 0.08% | 1935.29 | 0.40% | 1930.82 | 0.17% | |

1072 | 1816.48 | 1821.28 | 0.26% | 1820.62 | 0.23% | 1820.14 | 0.20% | |

1073 | 1824.56 | 1827.36 | 0.15% | 1822.06 | 0.14% | 1826.51 | 0.11% | |

1074 | 1821.50 | 1825.09 | 0.20% | 1821.52 | 0.00% | 1824.12 | 0.14% | |

1075 | 1818.45 | 1822.79 | 0.24% | 1820.98 | 0.14% | 1821.71 | 0.18% | |

1076 | 1816.67 | 1821.52 | 0.27% | 1822.22 | 0.31% | 1820.36 | 0.20% | |

1077 | 1820.62 | 1825.02 | 0.24% | 1822.91 | 0.13% | 1824.36 | 0.21% | |

1078 | 1817.92 | 1822.98 | 0.28% | 1822.44 | 0.25% | 1822.22 | 0.24% | |

1079 | 1823.05 | 1825.82 | 0.15% | 1823.51 | 0.02% | 1825.79 | 0.15% | |

1080 | 1823.44 | 1826.54 | 0.17% | 1823.79 | 0.02% | 1826.29 | 0.16% | |

1081 | 1820.91 | 1824.65 | 0.21% | 1823.35 | 0.13% | 1824.34 | 0.19% |

Input Parameter | Max Error | Average Error |
---|---|---|

P1 | 7.84% | 0.73% |

P2 | 4.81% | 1.84% |

P3 | 5.42% | 0.58% |

P1 + P2 | 5.80% | 0.49% |

P1 + P3 | 2.10% | 0.23% |

P2 + P3 | 5.14% | 0.41% |

P1 + P2 + P3 | 1.47% | 0.19% |

No | Actual | Prediction | Error |
---|---|---|---|

1 | 2462.34 | 2404.59 | 2.35% |

2 | 2429.13 | 2436.05 | 0.28% |

3 | 2461.90 | 2433.80 | 1.14% |

4 | 2446.28 | 2431.91 | 0.59% |

5 | 2443.30 | 2414.70 | 1.17% |

6 | 2433.57 | 2431.62 | 0.08% |

7 | 2460.70 | 2434.82 | 1.05% |

8 | 2462.24 | 2438.58 | 0.96% |

9 | 2436.63 | 2451.69 | 0.62% |

10 | 2447.93 | 2437.34 | 0.43% |

1019 | 2447.89 | 2447.84 | 0.00 |

1020 | 2451.29 | 2430.37 | 0.01 |

1021 | 2445.20 | 2444.25 | 0.00 |

1022 | 2439.77 | 2394.99 | 0.02 |

1023 | 2420.73 | 2431.86 | 0.00 |

1024 | 2453.71 | 2437.44 | 0.01 |

1025 | 2423.18 | 2422.99 | 0.00 |

1026 | 2409.58 | 2432.12 | 0.01 |

1027 | 2439.65 | 2412.53 | 0.01 |

1028 | 2431.93 | 2421.86 | 0.00 |

Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |

© 2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).

## Share and Cite

**MDPI and ACS Style**

Arferiandi, Y.D.; Caesarendra, W.; Nugraha, H.
Heat Rate Prediction of Combined Cycle Power Plant Using an Artificial Neural Network (ANN) Method. *Sensors* **2021**, *21*, 1022.
https://doi.org/10.3390/s21041022

**AMA Style**

Arferiandi YD, Caesarendra W, Nugraha H.
Heat Rate Prediction of Combined Cycle Power Plant Using an Artificial Neural Network (ANN) Method. *Sensors*. 2021; 21(4):1022.
https://doi.org/10.3390/s21041022

**Chicago/Turabian Style**

Arferiandi, Yondha Dwika, Wahyu Caesarendra, and Herry Nugraha.
2021. "Heat Rate Prediction of Combined Cycle Power Plant Using an Artificial Neural Network (ANN) Method" *Sensors* 21, no. 4: 1022.
https://doi.org/10.3390/s21041022