The DOI matches its Crossref record; 25 of the 25 references it cites were found in a registry or an index; none of the 4 sources its claims cite is checked for support yet.
Research on the characteristics of electro-hydraulic position servo system of RBF neural network under fuzzy rules
Open accessAbstract
A radial basis function neural network PID controller under fuzzy rules (FUZZY-RBF-PID) was designed for the electro-hydraulic position servo system under the influence of uncertain factors such as load mutation, and load stiffness change. Firstly, the mathematical model of the system is established, and the frequency domain and time domain analysis of the system are carried out. Secondly, based on the analysis results, a radial basis function (RBF) neural network PID controller is designed, and fuzzy rules are innovatively used to adjust the learning rate of PID parameters in the RBF neural network learning algorithm in real time. Thirdly, the simulation results show that under the action of the FUZZY-RBF-PID controller, the unit step response of the system has high steady-state accuracy, fast response speed, and under the condition of large load stiffness, the system can recover to the steady-state value faster after being disturbed. At the same time, when the input signal is the sinusoidal signal of 10 HZ, the system under the action of the FUZZY-RBF-PID controller has no obvious phase lag phenomenon, and the tracking error is minimal. The proposed method can effectively improve the comprehensive performance of the electro-hydraulic position servo system under the influence of uncertain factors.
Overview
CoChat Summary
## TL;DR
The paper proposes a FUZZY-RBF-PID controller for an electro-hydraulic position servo system to improve tracking accuracy, disturbance rejection, and steady-state performance under uncertain parameters. In simulation, it outperformed conventional PID and RBF-PID, especially in eliminating steady-state error and reducing adjustment time.
## Key findings
- In the no-load simulation, FUZZY-RBF-PID reached steady state in 0.0131 s, with no overshoot and the steady-state error effectively eliminated.
- Under external load disturbance, FUZZY-RBF-PID had an amplitude fluctuation of 9.177% and an adjustment time of 0.0195 s, compared with PID (8.982%, 0.0375 s) and RBF-PID (9.174%, 0.625 s).
- Under large load stiffness (9 × 10^10 N/m), FUZZY-RBF-PID had 12.6% overshoot, eliminated steady-state error, and reduced adjustment time to 0.0394 s; the paper reports PID and RBF-PID adjustment times of 0.072 s and 0.0744 s under disturbance in this case.
- At a sinusoidal input frequency of 10 Hz, the proposed method showed no obvious phase lag, while RBF-PID exhibited phase lag; the paper concludes FUZZY-RBF-PID had better tracking accuracy and anti-interference ability.
## Methods
- The authors derived a mathematical model of a four-way valve-controlled hydraulic cylinder and analyzed the open-loop system and PID-controlled system characteristics using Bode plots and time-domain simulations.
- They designed an RBF neural network PID controller that updates PID parameters online via gradient descent, then added fuzzy rules to adapt the PID learning rates \(\alpha_P, \alpha_I, \alpha_D\) based on error and error change rate.
- Evaluation was done in Matlab/Simulink using step and sinusoidal signals, comparing PID, RBF-PID, and FUZZY-RBF-PID under no-load, load disturbance, and large load stiffness conditions.
## Limitations
- The paper states a limitation of traditional RBF-PID: the PID learning rates are fixed and cannot adapt intelligently to disturbance magnitude, which can cause slow adjustment or overshoot; this is the motivation for the fuzzy rule layer.
- The evidence in the paper is entirely simulation-based; no physical experiments or hardware validation are reported.
- The paper does not report a dataset, statistical testing, or repeated-trial variability, so the generality of the reported performance is not established (evident from the text).
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures














Verification
Claims the paper makes
0 Valid · 0 Not valid · 3 Not checked · 76 Own results and interpretations
A result the paper states — it cites no source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The low-frequency starting point of the bode diagram of the system’s open loop is 30, and the asymptote slope is 0 dB/Oct.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The crossing Angle frequency of the system is 16.4 rad/s and the phase margin is 91.7°”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The system is stable, the zeros and poles are distributed to the left of the imaginary axis or at the origin, which is a minimum phase Angle system.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“At a frequency of 3080 rad/s, the gain margin is 39.2 dB.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The crossing Angle frequency of the system is 16.4 rad/s and the phase margin is 91.7°”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
58 more claims
Create a free account to see all 79 claims and to verify the 4 references still open.
- The quote only partly states this claim. 8
- It may state two separate claims as one. 8
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“However, in practice, the magnitude and direction of the load force on the equipment vary with the working conditions 16 – 18 .”
From Multiple quadrants displacement tracking control of independent metering electro-hydraulic system (2024) · cites this paper as [18]
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
“16 c ji ( t ) = c ji ( t - 1 ) + α ( y ( t ) - y m ( t ) ) w j x i - c ji b j 2 + β ( c ji ( t - 1 ) - c ji ( t - 2 ) )”
“13 h j = exp - x - c j 2 2 b j 2 Output layer: w j is the weight from the hidden layer unit to the output node, y m ( t ) is the RBF network identification output, and the expression of the weighted sum of hidden layer node output as follows: 14 y m = h 1 w 1 + h 2 w 2 + ⋯ h j w j”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
“30 d 3 ( x d - x ) dt = - a 2 x ¨ - a 3 x ˙ - a 4 x + a 1 U - x ⃛ = a 2 x ¨ + a 3 x ˙ + a 4 x - a 1 U”
“28 x ⃛ = - a 2 x ¨ - a 3 x ˙ - a 4 x + a 1 U Y = x”
Citations
Cites
1 retracted
A Summary of PID Control Algorithms Based on AI-Enabled Embedded Systems
Zhou, Y. (2022) · Security and Communication Networks · doi:10.1155/2022/7156713 · Cited by 26 · cited 1×
“Therefore, because of the above limitations of PID control, the combination of radial basis function (RBF) neural network and PID controller can realize the online regulation of PID parameters and improve the performance of the control system 33 .”
MethodRetractedTrajectory control of electro-hydraulic position servo system using improved PSO-PID controller
Feng, H., Ma, W., Yin, C., & Cao, D. (2021) · Automation in Construction · doi:10.1016/j.autcon.2021.103722 · Cited by 190 · cited 1×
“…can not meet the growing needs, so the combination of intelligent control can make the control effect further, the particle swarm optimization algorithm and other optimization algorithms combined with PID controller 15 , in the system with little change in working conditions have a good play.”
MethodHelian, B., Chen, Z., & Yao, B. (2019) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2019.2947803 · Cited by 118
Wrat, G., Bhola, M., Ranjan, P., Mishra, S. K., & Das, J. (2020) · ISA Transactions · doi:10.1016/j.isatra.2020.01.003 · Cited by 105 · cited 1×
“Therefore, fuzzy rules can be combined with neural networks 31,32 .”
BackgroundGuo, Q., Yin, J., Tian, Y., & Jiang, D. (2017) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2017.2694352 · Cited by 99
Yin, X., Zhang, W., Jiang, Z., & Pan, L. (2019) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2018.09.026 · Cited by 93
An extended state observer-based control design for electro-hydraulic position servomechanism
Shen, W., & Shen, C. (2021) · Control Engineering Practice · doi:10.1016/j.conengprac.2021.104730 · Cited by 60
A New Approach for Transformation-Based Fuzzy Rule Interpolation
Chen, T., Shang, C., Yang, J., Li, F., & Shen, Q. (2019) · IEEE Transactions on Fuzzy Systems · doi:10.1109/tfuzz.2019.2949767 · Cited by 53 · cited 1×
“Then the set is interpreted by the fuzzy rule knowledge base to obtain a certain output value, and the defuzzification process is completed 34 .”
MethodCheng, C., Liu, S., & Wu, H. (2020) · Proceedings of the Institution of Mechanical Engineers Part C Journal of Mechanical Engineering Science · doi:10.1177/0954406220903337 · Cited by 44
Output feedback control of electro-hydraulic asymmetric cylinder system with disturbances rejection
Wang, Y., Zhao, J., Ding, H., & Zhang, H. (2020) · Journal of the Franklin Institute · doi:10.1016/j.jfranklin.2020.12.023 · Cited by 42
Research works printed but not linked: 10
- Wan, Z. & Fu, Y. Integral nonsingular terminal sliding mode control of hydraulic servo actuator based on extended state observer. Shock Vib. 2021, 1–12 (2021).
- Feng, H., Ma, W., Yin, C. & Cao, D. Trajectory control of electro-hydraulic position servo system using improved PSO-PID controller. Automat. Constr. 127, 103722 (2021). · DOI · Paper page
- Li, J. W., Zhang, L. A., Huang, X. M., Zhang, Q. Q. & Wang, G. H. Cascade PID control algorithm for wind turbine blade mold temperature based on improved RBF neural network. Acta Energ. Solar. Sin. 43(03), 330–335. https://doi.org/10.19912/j.0254-0096.tynxb.2020-0640 (2022). · doi:10.19912/j.0254-0096.tynxb.2020-0640
- Dong, Y. & Wei, W. P. Optimization of train ATO system based on RBF neural network PID control. J. Electron. Measurement Instrum. 35(01), 103–109. https://doi.org/10.13382/j.jemi.B2003249 (2021). · doi:10.13382/j.jemi.b2003249
- Xiong, Z. G., Liu, Z., Wang, H. Y. & Cui, J. B. Design of automatic steering control system based on RBF neural network incremental PID. J. Agric. Mech. Res. 43(04), 27–32. https://doi.org/10.13427/j.cnki.njyi.2021.04.004 (2021). · doi:10.13427/j.cnki.njyi.2021.04.004
- Liu, C. L., Wang, M. & Zhang, J. ESO based RBF neural network PID controller for quadrotor aircrafts. Electron. Opt. Control. 28(9), 84–88. https://doi.org/10.3969/j.issn.167-637X.2021.0.018 (2021). · doi:10.3969/j.issn.167-637x.2021.0.018
- Zhao, Y., Zhou, Q. Y., Shao, N. F., Lu, R. R. & Hu, X. Z. Electro-hydraulic servo system based on RBF neural network fuzzy PID control. J. Mech. Electr. Eng. 39(2), 244–249. https://doi.org/10.3969/j.issn.1001-4551.2022.02.015 (2022). · doi:10.3969/j.issn.1001-4551.2022.02.015
- Fei, C. G. & Wu, T. N. Application of improved neural network PID in controlling temperature of air conditioner. J. Civil Aviat. Univ. China 40(01), 34–39 (2022).
- Hong, C. S., Huang, J., Guan, Y. Y. & Ma, X. Q. Combustion control of power station boiler by coupling BP/RBF neural network and fuzzy rules. J. Eng. Therm. Energy Power 36(4), 142–148. https://doi.org/10.16146/j.cnki.rndlgc.2021.04.021 (2021). · doi:10.16146/j.cnki.rndlgc.2021.04.021
- Lv, X. D. & Wu, C. N. Design and simulation of improved fuzzy neural network PID controller. J. Data Acquis. Process. 36(02), 365–373. https://doi.org/10.16337/j.1004-9037.2021.02.018 (2021). · doi:10.16337/j.1004-9037.2021.02.018
Cited by
Hao, X., Xin, Z., Huang, W., Wan, S., Qiu, G., Wang, T., & Wang, Z. (2025) · Scientific Reports · doi:10.1038/s41598-025-05904-2 · Cited by 25
Zhang, W., Wang, B., Wu, Z., Zhang, F., Zhang, J., Zhang, S., Zhang, J., Zhang, J., Sun, H., Waters, K. E., et al. (2025) · Precision Engineering · doi:10.1016/j.precisioneng.2025.07.011 · Cited by 17
An Adaptive Estimation Model for the States and Loads in Electro-Hydraulic Actuation Systems
Dichev, D., Georgiev, B., Zhelezarov, I., Karadzhov, T., & Hristov, H. (2025) · Actuators · doi:10.3390/act14090447 · Cited by 12
“Artificial intelligence algorithms—neural networks and fuzzy logic—are increasingly used to model and control systems with nonlinearities and uncertainties [26,27].”
Geng, J., Deng, J., Bai, Z., Wen, X., Lu, J., Yan, Q., & Yang, X. (2025) · Results in Engineering · doi:10.1016/j.rineng.2025.106687 · Cited by 13
Dong, Z., Song, H., Liao, Y., Wang, H., Song, M., Jiang, J., & Chen, G. (2025) · Actuators · doi:10.3390/act14060261 · Cited by 6
“This approach has the disadvantages of low energy e ffi ciency, large heat generation, and cumbersome troubleshooting [3,4].”
Metadata
- Authors
- Li, J., Li, W., & Du, X.
- Affiliations
- Harbin University of Science and Technology (CN)
- Corresponding author
- Li, Jianying
- Venue
- Scientific Reports
- Published
- 2024-07-03
- Volume
- 14
- Issue
- 1
- Pages
- 15332-15332
- ISSN
- 2045-2322 (ISSN-L)
- PMC
- PMC11222530
- OpenAlex
- W4400278449
- Cited by
- 25
- References
- 25
- Citations by year
- 2026: 12 · 2025: 11 · 2024: 2
- FWCI
- 3.35
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- cc-by
- creativecommons.org/licenses/by/4.0 (tdm)
- creativecommons.org/licenses/by/4.0 (vor)
- Locations
- Scientific Reports (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Topics
- Physical Sciences › Engineering › Mechanical Engineering › Hydraulic and Pneumatic Systems
- Physical Sciences › Engineering › Control and Systems Engineering › Advanced Algorithms and Applications
- Physical Sciences › Engineering › Control and Systems Engineering › Industrial Technology and Control Systems
- Keywords
- electro-hydraulic position servo system, radial basis function neural network, PID controller, fuzzy rules, adaptive learning rate, load disturbance, tracking error, disturbance rejection
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
A language model drew the claims from the paper on 2026-10-11, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-11 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Research on the characteristics of electro-hydraulic position servo system of RBF neural network under fuzzy rules. https://app.cochat.ai/papers/10.1038/s41598-024-64262-7
- The paper
- Li, J., Li, W., & Du, X. (2024). Research on the characteristics of electro-hydraulic position servo system of RBF neural network under fuzzy rules. Scientific Reports. https://doi.org/10.1038/s41598-024-64262-7
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.