Experimental Study on Remaining Useful Life Prediction of Lithium-Ion Batteries Based on Three Regression Models for Electric Vehicle Application
Round 1
Reviewer 1 Report
The paper needs some clarifications. Following are some reviewer's concerns:
-The paper is focused on the techniques used to extrapolate the information about the SOH of LIB starting from measurements. Anyway, the context is not clear. How this information is obtained in practice? For this reason, in the introduction, a brief overview of the hardware systems and their possible applications (the paper is focused on EV, thus wired charging, and wireless charging...) available in the literature that allows performing these measurements should be included, for example:
- G. Lutzemberger et al., "Design of a Wireless Charging System for Online Battery Spectroscopy", Energies, 2021, 14(1):218, https://doi.org/10.3390/en14010218.
- D. Simatupang and S. -Y. Park, "Integration of Battery Impedance Spectroscopy With Reduced Number of Components Into Battery Management Systems," in IEEE Access, vol. 10, pp. 114262-114271, 2022, doi: 10.1109/ACCESS.2022.3217095.
-X. Wang, X. Wei, Q. Chen and H. Dai, "A Novel System for Measuring Alternating Current Impedance Spectra of Series-Connected Lithium-Ion Batteries With a High-Power Dual Active Bridge Converter and Distributed Sampling Units," in IEEE Transactions on Industrial Electronics, vol. 68, no. 8, pp. 7380-7390, Aug. 2021, doi: 10.1109/TIE.2020.3001841.
-Which are the disadvantages of Machine Learning approach for this application?
-Line 108. What I2R is? In (1)-(4) please describe each parameter.
5. Fig. 3: axis labels are missing.
-Is not clear if the temperature has been taken into account for the experiment in Fig. 8 to 16. The temperature highly affects the battery characteristics. Thus, it is possible that the proposed technique fails when the battery operates at a different temperature. Please clarify the conditions for the training and validation.
-What is the difference in terms of information included inside MSE and RMSE? In the abstract. Is it really useful to use six decimal numbers for the RME and MRSE?
Moderate editing of English language required
Author Response
Dear Sir!
I answer some questions below:
Question 1: Sections 2.1 and 2.2 are too long and can be significantly reduced. In section 2.1, the authors assume the condition uk > uj, but this does not appear anywhere else in calculating the mixture of a regression model.
Answer 1: Thank you for submitting your comments. In my paper, only two critical parameters are used for the article predicting the life of Lithium-Ion batteries. Three regression models are used to indicate the energy of Lithium-Ion batteries based on measured parameters such as voltage and temperature.
Question 2: After equation (10), all the other equations are not numbered.
Answer 2: I edited.
Question 3: the probability for a given country h to be in a class k should be the proportion of observations (households) in country h that belong to the income class k. On page 9, the first equation (it would be easier for the reader if the equation is numbered) is not precisely the proportion of people because the authors take the sum of the probability. The interpretation of the equation in not obvious. Normally, after estimating a mixture of regression model we have for each observation its estimated probabilities to be classified into the different classes identified. What is often done is to classify a given observation into the class where its estimated probability is higher. In many software this is also the method used that gives us the proportion of people in each of the classes. The authors should explain the equation on page 9 and how to interpret it. Alternatively, they may use the proportion approach which will make the interpretation easier.
Answer 3: Thank you for submitting your comments.
The formulas in section 4 describe the problem of predicting battery life by the linear regression model. Linear regression is a method to predict the dependent variable (y) based on the value of the independent variable (x). This means that linear regression should have a linear relationship between the independent and non-independent variables, and the effect of a change in the values of the independent variables should further affect the dependent variables. Belong. Some properties of linear regression are that the regression line always passes through the mean of the independent variable (x) and the standard of the dependent variable (y). The regression line minimizes the sum of the "area of errors." The sum of areas measures the response/dependent variable (y) ratio variation.
This linear regression method is calculated through formula 5. The parameters to be calculated such as weight, and neural network regression, are calculated by formulas 6 and 7. The prediction model is estimated with error with the sample model according to formulas 8 and 9.
Author Response File: 
Author Response.docx
Reviewer 2 Report
In this paper , the authors expressed three regression models that predict the lithium-ion battery life for electric cars based on a supervised machine-learning regression algorithm. The Linear Regression, Bagging Regressor, and Random Forest Regressor models will be compared for capacity prediction of lithium-ion batteries based on voltage-dependent per-cell modeling.
This paper has reasonable experiments and sufficient data, the structure of the manuscript is clear and well written. There are some problems, which must be solved before it is considered for publication. If the following issues are well addressed, the author believes that this article will make a certain contribution to the capacity prediction field of lithium-ion batteries.
1. In page 1, ABSTRACT, authors are suggested to start broad in the general background, then narrow in on the relevant topic that will be pursued in the paper. Maybe this part can be improved!
2. The format of the article should be unified, such as the position of the subheadings in the second section, the format of all formulas, etc.
3. All images in the text should be replaced with high-definition images.
4. All references should be consistent in format.
5. CONCLUSIONS needs more in it, as it's more of an afterthought. Perhaps the authors can explain the research work to be carried out in the future.
Quality of English Language needs further improvement.
Author Response
Dear Sir!
I answer some questions below:
Question 1: Sections 2.1 and 2.2 are too long and can be significantly reduced. In section 2.1, the authors assume the condition uk > uj, but this does not appear anywhere else in calculating the mixture of a regression model.
Answer 1: Thank you for submitting your comments. In my paper, only two critical parameters are used for the article predicting the life of Lithium-Ion batteries. Three regression models are used to indicate the energy of Lithium-Ion batteries based on measured parameters such as voltage and temperature.
Question 2: After equation (10), all the other equations are not numbered.
Answer 2: I edited.
Question 3: the probability for a given country h to be in a class k should be the proportion of observations (households) in country h that belong to the income class k. On page 9, the first equation (it would be easier for the reader if the equation is numbered) is not precisely the proportion of people because the authors take the sum of the probability. The interpretation of the equation is not apparent. Typically, after estimating a mixture of regression models, we have estimated probabilities for each observation to be classified into the identified classes. What is often done is to organize a given word into the category where its estimated probability is higher. In many software, this method gives us the proportion of people in each class. The authors should explain the equation on page 9 and how to interpret it. Alternatively, they may use the proportion approach to make the interpretation easier.
Answer 3: Thank you for submitting your comments.
The formulas in section 4 describe the problem of predicting battery life by the linear regression model. Linear regression is a method to predict the dependent variable (y) based on the value of the independent variable (x). This means that linear regression should have a linear relationship between the independent and non-independent variables, and the effect of a change in the values of the independent variables should further affect the dependent variables. Belong. Some properties of linear regression are that the regression line always passes through the mean of the independent variable (x) and the standard of the dependent variable (y). The regression line minimizes the sum of the "area of errors." The sum of areas measures the response/dependent variable (y) ratio variation.
This linear regression method is calculated through formula 5. The parameters to be calculated, such as weight, and neural network regression, are calculated by formulas 6 and 7. The prediction model is estimated with error with the sample model according to formulas 8 and 9.
Author Response File: Author Response.docx
Round 2
Reviewer 1 Report
All the concerns have been addressed.
Minor editing of English language required
Reviewer 2 Report
The authorshave addressed all my concerns well. It can be published as it is.
