New methods based on a genetic algorithm back propagation (GABP) neural network and general regression neural network (GRNN) for predicting the occurrence of trihalomethanes in tap water

Liu, Kangle; Lin, Tao; Zhong, Tingting; Ge, Xinran; Jiang, Fuchun; Zhang, Xue

doi:10.1016/j.scitotenv.2023.161976

Cited by 15 publications

(5 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This method utilizes the global search capability of GA to optimize the initial weights and thresholds, thereby overcoming these limitations. The flowchart depicting the GA-BP algorithm is presented in Figure 5 The specific steps are as follows [36]:…”

Section: Ga-bp Algorithm Modelmentioning

confidence: 99%

A Single-Stack Output Power Prediction Method for High-Power, Multi-Stack SOFC System Requirements

Zhang,

Hu,

Zhao

et al. 2023

Inorganics

View full text Add to dashboard Cite

The prediction of stack output power in solid oxide fuel cell (SOFC) systems is a key technology that urgently needs improvement, which will promote SOFC systems towards high-power multi-stack applications. The accuracy of power prediction directly determines the control effect and working condition recognition accuracy of the SOFC system controller. In order to achieve this goal, a genetic algorithm back propagation (GA-BP) neural network is constructed to predict output power in the SOFC system. By testing 40 sets of sample data collected from the experimental platform, it is found that the GA-BP method overcomes the limitation of the traditional back propagation (BP) method—falling into local optima. Further analysis shows that the average relative error of GA-BP has decreased to 1%. The reduction of the relative error improves the accuracy of the prediction results and the average prediction accuracy. Compared with the long short-term memory (LSTM) and BP algorithm, the GA-BP prediction model significantly reduces the relative error of power output prediction, which provides a solid foundation for multi-stack SOFC systems.

show abstract

Section: Ga-bp Algorithm Modelmentioning

confidence: 99%

A Single-Stack Output Power Prediction Method for High-Power, Multi-Stack SOFC System Requirements

Zhang,

Hu,

Zhao

et al. 2023

Inorganics

View full text Add to dashboard Cite

show abstract

“…With a faster learning speed, fault tolerance, and robustness, GRNN is well-suited to address nonlinear problems. Moreover, it demonstrates effectiveness in predicting unstable data and remains reliable even with limited sample data [33]. Consequently, GRNN is employed to construct the AWV data forecasting model.…”

Section: Generalized Regression Neural Network Forecasting Modelmentioning

confidence: 99%

Time–Frequency Characteristics and SARIMA Forecasting of Atmospheric Water Vapor in East Asia

et al. 2023

View full text Add to dashboard Cite

Given the increasing impact of extreme rainfall and flooding on human life, studying and predicting changes in atmospheric water vapor (AWV) becomes particularly important. This paper analyzes the moderate-resolution imaging spectroradiometer (MODIS) data of the East Asian region from January 2003 to February 2023. The AWV data are examined in the time and frequency domain using methods such as empirical orthogonal function (EOF), Mann–Kendall (MK) analysis, and others. Additionally, four prediction models are applied to forecast the monthly average AWV data for the next year. The accuracy of these models is evaluated using metrics such as mean square error (MSE), mean absolute error (MAE), root mean square error (RMSE), and coefficient of determination (R2). The findings reveal several key insights: (1) The East Asian region exhibits highly variable seasonal variability in AWV, with identified mutation points after the MK test. (2) Spatial analysis shows high AWV data in the southern coastal areas of China, Thailand, Myanmar, Nansha Islands, and other regions during winter, while the Qinghai-Tibet Plateau region experiences low AWV during summer. (3) The first mode obtained through EOF decomposition contributes over 60% of the variance. Analysis of this mode reveals an increasing trend in AWV data for regions such as the Indian peninsula, Mongolia, and central and northeastern China over the past nine years. Conversely, the Bay of Bengal, Spratly Islands, eastern coast, and certain areas display a decreasing trend. (4) Employing the ensemble empirical mode decomposition (EEMD), the study identifies AWV data as a non-stationary series with an overall decreasing trend from 2003 to 2022. The filtered AWV series undergoes fast Fourier transform (FFT), uncovering periodicities of 2.6 years, 5 years, and 19 years. (5) Among the four forecasting models compared, the seasonal autoregressive integrated moving average model (SARIMA) demonstrates superior performance with the smallest MSE of 0.00782, MAE of 0.06977, RMSE of 0.08843, and the largest R2 value of 0.98454. These results clearly indicate that the SARIMA model provides the best fit. Therefore, the SARIMA forecasting model can be effectively utilized for forecasting AWV data, offering valuable insights for studying weather variability.

show abstract

“…Some machine learning algorithms have been developed to monitor these levels, and by extension, the free chlorine levels, to ensure they are within the recommended range. [34][35][36] One such use of ANNs was in measuring trihalomethanes in the Han River drinking water treatment plant in Seoul City, South Korea, where researchers measured free chlorine concentrations before, during, and after chlorination to ensure free chlorine levels were within a safe range. [37] ANNs were also used to maintain free chlorine concentrations in another water plant in Sao Paulo, Brazil.…”

Section: Introductionmentioning

confidence: 99%

Modeling Biodegradable Free Chlorine Sensor Performance Using Artificial Neural Networks

Siddiqui,

Deen

2023

Adv Materials Technologies

View full text Add to dashboard Cite

Electrochemical sensors are used to measure target analytes in water, meat, fruits, or vegetables, to ensure their safety, security, and integrity for human use. In this paper, a solution‐based fabrication process is presented for a biodegradable electrochemical free chlorine sensor using asparagine that is functionalized onto graphene oxide (GO). An ink solution of the GO functionalized with asparagine is synthesized, and then deposited onto a screen‐printed carbon electrode (SPCE) using a spin coater. The sensor shows high a sensitivity of 0.30 µA ppm−1 over a linear range of 0–8 ppm with a hysteresis‐limited resolution of 0.2 ppm after achieving a steady state at 50 s. From the development and testing of the free chlorine sensor, over 9000 datapoints are collected and used for training an artificial neural network (ANN) model to quantify and characterize the factors affecting the free chlorine sensor's performance, and model its degradation characteristics. The model reports a low mean absolute error (MAE) of 0.1603 and a high model accuracy with a Pearson correlation coefficient (PCC) of 0.9950, demonstrating that these degradation characteristics can be modeled and be used to compensate the degraded performance characteristics of the free chlorine sensors.

show abstract

New methods based on a genetic algorithm back propagation (GABP) neural network and general regression neural network (GRNN) for predicting the occurrence of trihalomethanes in tap water

Cited by 15 publications

References 59 publications

A Single-Stack Output Power Prediction Method for High-Power, Multi-Stack SOFC System Requirements

A Single-Stack Output Power Prediction Method for High-Power, Multi-Stack SOFC System Requirements

Time–Frequency Characteristics and SARIMA Forecasting of Atmospheric Water Vapor in East Asia

Modeling Biodegradable Free Chlorine Sensor Performance Using Artificial Neural Networks

Contact Info

Product

Resources

About