Research on the Prediction of Wax Deposition Thickness on Pipe Walls Based on the Optimal Weighted Combination Model
0
Citation
25
Reference
10
Related Paper
Abstract:
Wax deposition seriously affects the safe and economic operation of pipelines. Mastering the variation laws of wax deposition thickness is the premise of formulating reasonable pigging schemes. Although the GM (1,1) model (a kind of gray model) is an effective method for predicting wax deposition thickness on pipe walls, its prediction accuracy is easily affected by the smoothness of the original sequence. The improved GM (1,1) was established by introducing the idea of translation transformation, and an optimal weighted combination model based on the traditional gray model and a logarithmic function model was proposed. The differences in the predicted results of the established models were compared and analyzed through indoor wax deposition experimental data. The research results indicate that the optimal weighted combination model has the highest fitting accuracy, followed by the logarithmic function model and the improved GM (1,1), while the fitting accuracy of the traditional gray model is poor. When the number of modeling samples is five, the average relative error and root mean square error of the prediction results of the optimal weighted combination model are 1.313% and 0.021, respectively, which shows the highest prediction accuracy. When the number of modeling samples is six, the average relative error and root mean square error of the optimal weighted combination model are 2.143% and 0.031, respectively, and its prediction accuracy is still the highest. Overall, the optimal weighted combination model has the advantages of high accuracy and easy implementation, and has strong promotion and application value.为确定适合太湖水体叶绿素的反演算法,为同类卫星数据的建模和应用提供参考,本文根据太湖2007年11月、2009年4月和2011年8月实测水质参数以及同步光谱数据,结合水色遥感传感器MODIS、MERIS、GOCI及我国自主发射的HJ-1号卫星CCD传感器波段参数,基于差值模型、比值模型、三波段模型及APPEL模型,分别建立太湖水体叶绿素浓度反演模型,并分析模型的适宜性.结果显示,基于不同传感器数据APPEL模型的决定系数为0.7308~0.8107,模型相对误差为15%~24%,均方根误差为21%~32%;三波段模型基于不同传感器数据拟合的决定系数为0.6014~0.7610,相对误差为28%~36%,相对均方根误差为39%~46%;差值模型决定系数为0.4954~0.7244,相对误差为39%~53%,相对均方根误差为51%~72%;比值模型决定系数为0.4918~0.7098,相对误差为41%~55%,相对均方根误差为56%~75%.相比较而言,APPEL模型的稳定性较强,适合于不同传感器数据的太湖水体叶绿素浓度的反演.此外,相应不同传感器波段位置、波段宽度对模型反演的精度和稳定性的影响也不同,当波段位置接近叶绿素特征波长时,较窄的波宽有利于模型精度的提高,波段位置和叶绿素浓度特征波长相差较大时,合理增加波谱范围有利于叶绿素特征信息的获取.;In order to determine the most suitable retrieval model for estimating chlorophyll concentration in Lake Taihu and provide a reference for the application of the satellite data, the difference model, the ratio model, the three-band model and APPEL model were built to estimate chlorophyll concentration based on the data of MODIS, MERIS, GOCI and HJ-1 CCD sensor. The dataset included the measured water quality parameters and the synchronous spectra data in November 2007, April 2009 and August 2011. The results of the analysis showed that the decision coefficient of the APPEL model was between 0.7308 and 0.8107 for the different satellite data, the relative error was between 15% and 24%, and the root mean square error was between 21% and 32%; The decision coefficient of the three-band model was between 0.6014 and 0.7610, the relative error was between 28% and 36%, and the root mean square error was between 39% and 46%; The decision coefficient of different models was between 0.4954 and 0.7244, the relative error was between 39% and 53%, and the root mean square error was between 51% and 72%; The decision coefficient of the ratio model was between 0.4918 and 0.7098, the relative error was between 41% and 55%, and the root mean square error was between 56% and 75%.To sum up, the APPEL model showed a strong stability and was suitable for the chlorophyll concentration retrieval of Lake Taihu for different sensor data. In addition, different band widths and band positions had different influences on the retrieval model for estimating chlorophyll concentration.When the band position was close to the characteristic wavelength of chlorophyll, narrow band width was beneficial for the accuracy of the model; while when the band position was far away from the position of the characteristic wavelength, the band width should be increased reasonably.
Root mean square
Cite
Citations (4)
In this paper, we propose an efficient algorithm to piecewise linear approximation of logarithm for the possible application to graphics physics simulation. Compared to the traditional approximation of logarithm methods, our algorithm produce a maximum relative error flatten distribution in all intervals, the maximum relative error can be set according to our difference accuracy needs. Simulations of our methods have been conducted in Matlab to verify correctness. Besides, we further present the hardware implement. Comparison simulation showed that our algorithm is superior to state-of-art logarithm conversion for stimulation accuracy.
Cite
Citations (1)
In this paper, a novel approximation that allows exploitation of the full potential of logarithmic multiplication is proposed. More specifically, the proposed approximation is quantified in terms of mean square error (MSE) and compared to a competitive recent publication. Subsequently, an LSTM network is used as an illustrative test case and the proposed approximation is validated in terms of the accuracy of the netowrk. It has been shown that for short data wordlengths, the proposed approximation can achieve small loss values, for the particular LSTM network. Finally, the circuit implementation of the logarithmic multiplier is synthesized in a 28 nm standard-cell library. Results show reduced hardware complexity for similar loss values on the specific LSTM network.
Approximation Theory
Square (algebra)
Cite
Citations (0)
This article presents a novel solar radiation prediction approach using artificial neural networks. The developed model predicts three meteorological variables using sunshine ratio, day number, and location coordinates. These meteorological variables are solar energy, ambient temperature, and relative humidity. However, three statistical values are used to evaluate the proposed model. These statistical values are mean absolute percentage error, mean bias error, and root mean square error. Based on the results, the developed model predicts accurately the three meteorological variables. The mean absolute percentage error, root mean square error, and mean bias error in predicting solar radiation are 1.3%, 5.8 (1.8%), and 0.9 (0.3%), respectively. While the mean absolute percentage error, root mean square error, and mean bias error values for ambient temperature prediction are 1.3%, 0.4 (1.7%), and 0.1 (0.4%). In addition, the mean absolute percentage error, root mean square error, and mean bias error values in relative humidity prediction are 3.2%, 3.2, and 0.2.
Mean absolute error
Root mean square
Sunshine duration
Cite
Citations (12)
The existing conditions of the Saguling Reservoir are reported to have suffered severe heavy metal pollution due to the presence of wastewater inputs from various types of industries flowing into Citarum River and then accumulating in the Saguling Reservoir. From the results of calibration tests of heavy metal models on water using the Root Mean Square Error (RMSE) analysis and Relative Error (RE) analysis, obtained dispersion coefficients on Cadmium, Chromium, and Lead metals sequentially 1 m 2 / second (with RMSE 0,00515 and 34% relative error); 1 m 2 / second (with RMSE 0.00595 and relative error 26%); and 2.5 m 2 / second (with RMSE 0.028205 and relative error 41.25%) which shows that the model has good capability to simulate the concentration of heavy metals approaching the actual data both in the dry and wet seasons. From the results of the verification test models of concentration of cadmium, lead and chromium in sediments using the Root Mean Square Error (RMSE) analysis and Relative Error (RE) analysis, obtained sequentially 18.53 and 77%; 10.43 and 47.15%; 2.789 and 33%. Error values in sediment concentrations are quite large because of the difficulty of making assumptions that are close to natural conditions.
Lead (geology)
Cite
Citations (1)
Inversion of phytoplankton chlorophyll-a concentration of inland water body is hotspot and difficult problem in water quality remote sensing.This paper provides a method to resolve this problem.Based on the characteristic spectral analysis of chlorophyll-a,suspended matter,chromatic dissolved inorganic matter and pure water molecule in inland water body,the three-band model was spectrally tuned accord with optical properties of Lake TAIHU to optimize spectral bands combination for accurate chlorophyll-a concentration estimation.Be closely related with the chlorophyll concentration of suspended solids by a yellow substance with a small impact on the optimal band combination model,in which inversion of the spring with the factor [Rrs-1(677)-Rrs-1(696)]×Rrs(754),the coefficient of determination and root mean square error were 0.9885,1.80332 ug/L.Validation of the data model,root mean square error of 5.8646ug / l,mean relative error of 25.5%.In the calculations of autumn three-band model,the band for the removal of inorganic suspended matter and yellow substances effects can not be stable,for which we have calculated the two-band model to add to,obtain two models with the factor [Rrs-1(680)-Rrs-1(710)]×Rrs(770) and R(680)-1×R(770),coefficient of determination and root mean square error of 0.881,11.6322 ug / l,and 0.883,11.52633 ug / l.Validation of the data model,root mean square error and mean relative error 15.456ug / l,20.3%,and 15.684ug/l,21.4%,the two models can achieve good inversion results.Therefore,this method can effectively remove suspended matter and yellow substance effect for different time to obtain a better inversion results.
Root mean square
Cite
Citations (0)
Background: The Air Pollutant Index (API) in Malaysia is determined by calculating sub-indices for the six main pollutants: particulate matter (PM10 and PM2.5), ozone (O3), carbon monoxide (CO), sulphur dioxide (SO2), and nitrogen dioxide (NO2), based on the possible health implications to the public. The study focuses on the UiTM Shah Alam Internet of Things (IoT) monitoring station in Selangor, which is an urban area. Method: Data was retrieved from low-cost IoT sensors, containing datasets from February 2022 to June 2022. The study aims to develop a predictive model using a Machine-Learning approach to predict air pollutant concentrations for the following day. Results: The comparison of the three models reveals that Random Forest had the best predictive models for PM10 concentration, with root-mean-square error (RMSE) values between 10.88 and 18.15, absolute error values between 8.03 and 11.39, and relative error values between 29.67 and 31.51. The RMSE, absolute error, and relative error for SO2 were (0.26-0.39), (0.11-0.26), and (50.11%- 84.64%), respectively. The absolute error (0.003–0.004), relative error (20.83%–24.52%), and RMSE (0.004–0.005) for NO2 were measured. For CO, the relative error (26.01%-42.34%), absolute error (0.147-0.250), and RMSE (0.259-0.468) were all within allowable bounds. The O3 RMSE, absolute, and relative errors were (0.003–0.005), (0.0005-0.00006), and (26.17%–33.10%), respectively. The results of the concentration prediction for PM2.5 were as follows: RMSE: (16.65 - 26.83), absolute error (10.15 - 14.29) and relative error (31.43% - 33.09%). Conclusion: Based on the results, the study shows that PM2.5 is a significant pollutant, representing the API.
Mean absolute error
Nitrogen dioxide
Cite
Citations (1)
This work presents a systematic approach for the implementation of decimal logarithmic converter. In this approach the decimal logarithm is divided into different regions and linear approximation is applied to each of them. The novelty of this algorithm lies in the selection of regions for linear approximation. The regions are selected in such a way that only a minimum number of coefficients is to be stored. All the other coefficients for linear approximation can be generated from the stored coefficients. A 10-region linear approximation method is explained in detail. Simulation results show that this method achieves a maximum positive and negative error of 0.0044 and 0.0015 respectively. It can also be applied to a 20-region approximation, which has a maximum positive and negative error of 0.000811 and 0.000948 respectively.
Decimal
Approximation Theory
Cite
Citations (1)
The problem of obtaining optimal starting values for the calculation of the square root using Newton's method is considered. It has been pointed out elsewhere that if relative error is used as the measure of goodness of fit, optimal results are not obtained when the inital approximation is a best fit. It is shown here that if, instead, the so-called logarithmic error is used, then a best initial fit is optimal for both types of error. Moreover, use of the logarithmic error appears to simplify the problem of determining the optimal initial approximation.
Square root
Root (linguistics)
Square (algebra)
Error Analysis
Cite
Citations (28)
Abstract The main challenge in the lead removal simulation is the behaviour of non-linearity relationships between the process parameters. The conventional modelling technique usually deals with this problem by a linear method. The substitute modelling technique is an artificial neural network (ANN) system, and it is selected to reflect the non-linearity in the interaction among the variables in the function. Herein, synthesized deep eutectic solvents were used as a functionalized agent with carbon nanotubes as adsorbents of Pb2+. Different parameters were used in the adsorption study including pH (2.7 to 7), adsorbent dosage (5 to 20 mg), contact time (3 to 900 min) and Pb2+ initial concentration (3 to 60 mg/l). The number of experimental trials to feed and train the system was 158 runs conveyed in laboratory scale. Two ANN types were designed in this work, the feed-forward back-propagation and layer recurrent; both methods are compared based on their predictive proficiency in terms of the mean square error (MSE), root mean square error, relative root mean square error, mean absolute percentage error and determination coefficient (R2) based on the testing dataset. The ANN model of lead removal was subjected to accuracy determination and the results showed R2 of 0.9956 with MSE of 1.66 × 10−4. The maximum relative error is 14.93% for the feed-forward back-propagation neural network model.
Root mean square
Linearity
Backpropagation
Deep eutectic solvent
Mean absolute error
Cite
Citations (27)