CoChat
Sign Up
Cited by 1Geomechanics and Mining EngineeringGeoscience and Mining TechnologyMulti-Criteria Decision Making

Intelligent evaluation of coal mine solid filling effect using fuzzy logic and improved D-S evidence theory

Open access
Zhang, Zihang, Yang, Shangqing, Liu, Yang·2025·Scientific Reports
DOI 10.1038/s41598-025-88913-5PMC PMC11833116
Open this paper in CoChat — free accountOpen PDF

Abstract

Addressing the inherent fuzziness and uncertainty in filling outcomes, this paper proposes a novel method for evaluating the effectiveness of solid filling operations in coal mines by integrating Interval Type-2 Fuzzy Logic Systems (IT2FLS) with an improved Dempster-Shafer (D-S) evidence theory. Initially, local data fusion is conducted using IT2FLS-Adam, where interval type-2 fuzzy sets are employed to fuzzify input features, and the Adam optimizer is utilized for parameter optimization. This allows for preliminary judgments on filling effects from various perspectives based on local features. To overcome the limitations of local fusion, an improved D-S evidence theory is adopted, which effectively handles conflicting evidence by incorporating the Wasserstein distance and Deng entropy to combine the judgments from local features, achieving global data fusion. Experimental results demonstrate that the proposed method attains a remarkable accuracy of 92.9% in global fusion tasks, surpassing traditional methods. This study provides a data fusion framework for filling workfaces, integrating multi-sensor data and addressing the complexities and uncertainties associated with filling processes, thereby making a significant contribution to the intelligent monitoring and management of coal mine filling operations.

AI snapshot

Written from the paper’s full text.

TL;DR

The paper proposes a coal mine solid filling effect evaluation method combining Interval Type-2 Fuzzy Logic Systems with Adam optimization for local fusion and an improved D-S evidence theory using Wasserstein distance and Deng entropy for global fusion. It reports 92.9% global fusion accuracy, outperforming several traditional fuzzy logic and D-S variants.

Key findings

  • The proposed method achieved 92.90% accuracy, 92.91% precision, 92.90% recall, and 92.88% F1 score in global fusion tasks.
  • Local fuzzy logic subsystems alone reached lower accuracies: 77% for filling material, 74% for equipment attitude, and 79% for filling action.
  • Comparative methods scored lower: T1TFLS-D-S 86.41%, T1FLS-improved D-S 87.18%, T2FLS(C0)-D-S 87.75%, and T2FLS(C0)-improved D-S 89.31%.
  • In a conflicting-evidence example, traditional D-S produced an average filling effect with \(m(\theta_2)=0.7615\), while the improved method produced \([0.59953338, 0.39749423, 0.00297239]\), indicating a good filling effect.

Methods

  • Data were collected at an experimental filling work face in a mine in Hebei Province, yielding 500 datasets after excluding outliers and missing values, with nine features and labels of good, average, or poor filling effectiveness encoded as one-hot vectors; data were split 50% training, 30% testing, and 20% validation.
  • Three independent IT2FLS-Adam subsystems handled local fusion for filling material state, equipment spatial position, and pushing mechanism state, using Gaussian interval type-2 membership functions, product t-norm, EIASC reduction, cross-entropy loss, and Adam optimization with \(\beta_1=0.9\), \(\beta_2=0.999\), \(\epsilon=10^{-8}\), 8 fuzzy rules, 1500 max iterations, batch size 64, and early stopping patience 50.
  • Global fusion used improved D-S evidence theory, weighting basic probability assignments by Wasserstein-distance-based credibility and Deng-entropy-based information content before combination; performance was evaluated with accuracy, precision, recall, F1 score, and confusion matrices.

Limitations

  • The paper does not explicitly state limitations of the proposed method; it discusses limitations of traditional fuzzy logic systems and traditional D-S evidence theory.
  • Evident from the text: validation relies on 500 datasets from a single experimental filling work face in Hebei Province, with labels assigned by field engineers into good, average, or poor categories, so generalization to other mines, geological conditions, or label subjectivity is not addressed.
  • Evident from the text: no external or cross-site validation is reported, and comparative experiments are limited to fuzzy logic and D-S variants on the same dataset.

Model-written summary. Check it against the paper before relying on it.

Integrity signals

Registry

Crossref · 10.1038/s41598-025-88913-5

Cites

23 of 23 references verified0 citation errors · 0 not checkable

Statistics

Nothing to recompute.

Claims the paper makes

0 of 12 cited sources checked · 0 supported · 0 flagged

  • Findingreasoning

    The three fuzzy logic subsystems struggle to correctly assess cases where the filling effect is average.

    “and they struggle to correctly assess cases where the filling effect is average.”
    Quote in the paperSubstantial claim
  • Findingown data

    The proposed method surpasses traditional methods in global fusion tasks.

    “Experimental results demonstrate that the proposed method attains a remarkable accuracy of 92.9% in global fusion tasks, surpassing traditional methods.”
    Quote in the paperSubstantial claim
    • Rests on an assumption: Field engineers’ classifications of filling effectiveness into good, average, and poor are reliable ground-truth labels for training and evaluating the fuzzy logic system.
    • The authors state this as an assumption: The judgments from the three local fuzzy subsystems are independent evidence sources for D-S combination.
    • Rests on an assumption: The training data labels reflect actual operational outcomes.
    • The authors state this as an assumption: Filling effectiveness assessment can be treated as a classification problem with three categories.
  • Findingown data

    The local fusion accuracies of the three fuzzy logic subsystems were 77%, 74%, and 79%, respectively.

    “Due to the inputs of the subsystems only including certain operational information from the filling working face, the accuracy of the filling operation assessments is relatively low, at 77%, 74%, and 79%, respectively”
    Quote in the paperSubstantial claim
  • Findingown data

    After global data fusion using the improved D-S evidence combination theory, the overall accuracy of filling effect assessment was 92.9%.

    “By further combining the judgment results of each subsystem using the improved D-S evidence combination theory, the accuracy of the filling effect assessment was significantly improved, achieving an overall accuracy of 92.9%.”
    Quote in the paperSubstantial claim
  • Findingown data

    The proposed method attains an accuracy of 92.9% in global fusion tasks.

    “Experimental results demonstrate that the proposed method attains a remarkable accuracy of 92.9% in global fusion tasks, surpassing traditional methods.”
    Quote in the paperSubstantial claim
    • Rests on an assumption: Field engineers’ classifications of filling effectiveness into good, average, and poor are reliable ground-truth labels for training and evaluating the fuzzy logic system.
    • The authors state this as an assumption: The judgments from the three local fuzzy subsystems are independent evidence sources for D-S combination.
    • Rests on an assumption: The training data labels reflect actual operational outcomes.
    • The authors state this as an assumption: Filling effectiveness assessment can be treated as a classification problem with three categories.
  • May combine two claims. 18
  • The quote only partly states this claim. 1
  • Classified as probably not a substantial claim. 7

  • May combine two claims.

    Findingreasoning

    The improved method reduces the time complexity of evidence combination to a polynomial level and achieves higher computational efficiency than the traditional D-S combination rule in common application scenarios.

    “The complexity is significantly reduced to a polynomial level, achieving higher computational efficiency in common application scenarios.”
    Quote in the paperSubstantial claim

  • May combine two claims.

    Findingown data

    For the specific evidence set in Table 3, the improved D-S evidence combination method yields final BPA values [0.59953338, 0.39749423, 0.00297239], with the highest credibility corresponding to a good filling effect.

    “Step 3-3: Perform evidence combination on the weighted evidence twice, yielding the final result {[0.59953338, 0.39749423, 0.00297239]}, indicating that the highest credibility corresponds to a good filling effect.”
    Quote in the paperSubstantial claim

  • May combine two claims.

    Findingown data

    The proposed method achieved accuracy 92.90%, precision 92.91%, recall 92.90%, and F1 score 92.88% in global fusion tasks.

    “| Proposed method | 92.90% | 92.91% | 92.90% | 92.88% |”
    Quote in the paperSubstantial claim

  • May combine two claims.

    Findingown data

    The proposed method achieved an accuracy of 93% in global fusion tasks within the filling working face, demonstrating superior performance compared to traditional methods.

    “Experimental results indicate that the proposed method achieved an accuracy of 93% in global fusion tasks within the filling working face, demonstrating superior performance compared to traditional methods.”
    Quote in the paperSubstantial claim

  • May combine two claims.

    Findingown data

    When x increases from 0 to 0.5, the difference between the two probability distributions decreases and the Wasserstein distance is lower; when x increases from 0.5 to 1, the difference increases and the Wasserstein distance is higher.

    “When x increases from 0 to 0.5, the difference between the two probability distributions decreases, and the degree of conflict diminishes, resulting in a lower Wasserstein distance. Conversely, when x increases from 0.5 to 1, the difference between the two basic probability distributions increases again, leading to a higher degree of conflict and an increase in Wasserstein distance.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Findingown data

    The proposed method's precision, recall, and F1 score surpassed those of the other compared methods.

    “Additionally, the precision, recall, and F1 score for the proposed method surpassed those of the other methods.”
    Quote in the paperSubstantial claim

  • May combine two claims.

    Findingown data

    For the specific evidence set in Table 3, traditional D-S evidence theory yields a final fusion result of average filling effect (m(theta2)=0.7615), which contradicts intuition and the actual situation.

    “Thus, according to traditional D-S evidence theory, the final fusion result suggests an average filling effect, which contradicts intuition and the actual situation.”
    Quote in the paperSubstantial claim
    • Rests on an assumption: In the illustrative example, the actual filling effect is not average (i.e., it is good).

  • The quote only partly states this claim.

    Findingown data

    The proposed method outperformed the T1TFLS-D-S, T1FLS-improved D-S, T2FLS(C0)-D-S, T2FLS(C0)-improved D-S, and IT2FLS-D-S methods in global fusion accuracy.

    “| Proposed method | 92.90% | 92.91% | 92.90% | 92.88% |”
    Quote in the paperSubstantial claim

  • May combine two claims.

    Interpretationown data

    The global fusion method based on the improved D-S evidence combination theory can effectively handle conflicts in local evidence and make accurate judgments regarding the filling effect.

    “This demonstrates that the global fusion method based on the improved D-S evidence combination theory can effectively handle conflicts in local evidence and make accurate judgments regarding the filling effect.”
    Quote in the paperSubstantial claim

  • May combine two claims.

    Interpretationreasoning

    The improved D-S evidence theory can more accurately allocate evidence weights by integrating Wasserstein distance and Deng entropy, thereby enhancing the accuracy and reliability of the final global fusion results.

    “Building on this foundation, the improved D-S evidence theory can more accurately allocate evidence weights by integrating Wasserstein distance and Deng entropy, thereby enhancing the accuracy and reliability of the final global fusion results.”
    Quote in the paperSubstantial claim

  • May combine two claims.

    Premisecitation

    The degree of insufficient contact with the roof and the density of the fill determine whether the fill can effectively support the roof under stress, thereby influencing the extent to which subsidence of the roof and surface can be limited.

    “The degree of insufficient contact with the roof and the density of the fill determine whether the fill can effectively support the roof under stress, thereby influencing the extent to which subsidence of the roof and surface can be limited38.”
    Quote in the paperSubstantial claim0 of 1 sources checked
    • cites [38] Qiu, J.-P., Yang, L., Xing, J. & Sun, X.-G. Analytical solution for determining the required strength of mine backfill based on its damage constitutive model. Soil Mechanics and Foundation Engineering 54, 371–376 (2018). source

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Premisecitation

    D-S evidence theory does not require prior knowledge.

    “One significant advantage of D-S evidence theory in merging independent evidence is that it does not require prior knowledge, but this can also lead to inefficiencies when handling highly conflicting evidence25.”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [25] Zhao, K. et al. A survey: Optimization and applications of evidence fusion algorithm based on dempster-shafer theory. Applied Soft Computing 124, 109075 (2022). source

  • May combine two claims.

    Interpretationown data

    The improved D-S evidence combination theory can address conflicts in judgments from different subsystems, thereby synthesizing various assessments of the filling effect during the global fusion phase and correctly evaluating the outcome of filling operations.

    “The improved D-S evidence combination theory can address conflicts in judgments from different subsystems, thereby synthesizing various assessments of the filling effect during the global fusion phase and correctly evaluating the outcome of filling operations.”
    Quote in the paperSubstantial claim

  • Probably not a substantial claim: may not pass S2 (checkable).

    Interpretationnone given

    Fuzzy logic systems exhibit significant advantages in modeling systems characterized by uncertainty and imprecision, particularly through the integration of Interval Type-2 Fuzzy Logic Systems with Dempster-Shafer evidence theory.

    “In summary, fuzzy logic systems exhibit significant advantages in modeling systems characterized by uncertainty and imprecision, particularly through the innovative integration of Interval Type-2 Fuzzy Logic Systems with Dempster-Shafer evidence theory.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Premisecitation

    IT2FLS outperforms T1FLS in highly uncertain situations.

    “Wu and Mendel conducted an in-depth investigation into the key differences between T1FLS and Interval Type-2 Fuzzy Logic Systems (IT2FLS), establishing that IT2FLS outperforms T1FLS in highly uncertain situations14.”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [14] Wu, D. On the fundamental differences between interval type-2 and type-1 fuzzy logic controllers. IEEE Transactions on Fuzzy Systems 20, 832–848 (2012). source

  • May combine two claims.

    Premisecitation

    Existing fuzzy logic methods are often tailored for single data sources, rendering them ineffective at integrating data from multiple sensors, which limits their applicability in real-time decision-making.

    “Existing methods are often tailored for single data sources, rendering them ineffective at integrating data from multiple sensors, which limits their applicability in real-time decision-making22.”
    • Also stated in: § Introduction · plain
      “Furthermore, these systems are often limited to single data sources and struggle to achieve global integration of multidimensional features in multi-sensor data fusion contexts.”
    Quote in the paperSubstantial claim0 of 1 sources checked
    • cites [22] Coupland, S. & John, R. Geometric type-1 and type-2 fuzzy logic systems. IEEE Transactions on Fuzzy Systems 15, 3–15 (2007). source

  • May combine two claims.

    Premiseown data

    Wasserstein distance effectively captures the differences between different BPAs and reflects these as values between (0,1).

    “Wasserstein distance effectively captures the differences between different BPAs and reflects these as values between (0,1).”
    Quote in the paperSubstantial claim

  • Probably not a substantial claim: may not pass S4 (based).

    Premisenone given

    The conventional Dempster combination rule may yield counterintuitive results when handling highly conflicting evidence, potentially leading to outcomes that deviate from actual scenarios.

    “The conventional Dempster combination rule may yield counterintuitive results when handling highly conflicting evidence, potentially leading to outcomes that deviate from actual scenarios.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Interpretationreasoning

    The state of the filling material, the spatial positioning of filling equipment, and the operational status of the compaction mechanism significantly impact filling effectiveness.

    “Therefore, these three aspects of the filling work face’s operational status significantly impact filling effectiveness.”
    Quote in the paperSubstantial claim
    • Rests on an assumption: The sensor network within the filling work face accurately obtains the specific values of the factors influencing filling effectiveness.

  • May combine two claims.

    Interpretationreasoning

    The proposed method directly treats the BPA as a vector of length N, utilizing Wasserstein distance and Deng entropy to optimize evidence weighting and conflict resolution, thus avoiding enumeration of the power set.

    “In contrast, the proposed method directly treats the BPA as a vector of length N, utilizing the Wasserstein distance and Deng entropy to optimize evidence weighting and conflict resolution, thus avoiding the enumeration of the power set.”
    Quote in the paperSubstantial claim

  • Classified as probably not a substantial claim.

    Premisenone given

    D-S theory lacks effective tools to quantify and balance the uncertainty between pieces of evidence.

    “While the D-S theory is sensitive to evidence uncertainty, it lacks effective tools to quantify and balance the uncertainty between pieces of evidence.”
    Quote in the paperSubstantial claim

  • May combine two claims.

    Interpretationown data

    The improved method can accurately capture the complex operational patterns of filling tasks during the local fusion phase, utilizing fuzzy rules to describe uncertainties and fuzziness within the filling operation system.

    “This indicates that the proposed improved method can accurately capture the complex operational patterns of filling tasks during the local fusion phase, utilizing fuzzy rules to describe the uncertainties and fuzziness within the filling operation system.”
    Quote in the paperSubstantial claim

  • Probably not a substantial claim: may not pass S4 (based). May combine two claims.

    Premisenone given

    In multi-sensor scenarios, the computational complexity of D-S theory grows exponentially, restricting its applicability in real-time systems.

    “In multi-sensor scenarios, the computational complexity of D-S theory grows exponentially, restricting its applicability in real-time systems.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Premisenone given

    Each sensor and the fuzzy logic system can only assess the filling effect from a specific angle, so local information may be incomplete or uncertain.

    “Since each sensor and the fuzzy logic system can only assess the filling effect from a specific angle, there may be instances of incomplete or uncertain local information.”
    Quote in the paperSubstantial claim

  • Probably not a substantial claim: may not pass S4 (based).

    Interpretationreasoning

    Leveraging the Adam optimization algorithm from deep learning frameworks to adaptively adjust fuzzy rule parameters significantly improves the efficiency and adaptability of rule generation.

    “Leveraging the Adam optimization algorithm from deep learning frameworks to adaptively adjust fuzzy rule parameters, significantly improving the efficiency and adaptability of rule generation.”
    Quote in the paperNot a substantial claim
25 of 25

  • The paper relies on this without support.

    Field engineers’ classifications of filling effectiveness into good, average, and poor are reliable ground-truth labels for training and evaluating the fuzzy logic system.

    “Engineers classified the filling effectiveness into three categories: good, average, and poor.”

  • The authors state this as an assumption.

    The judgments from the three local fuzzy subsystems are independent evidence sources for D-S combination.

    “filling material characteristics, filling equipment attitude characteristics and pushing mechanism characteristics are input into three independent fuzzy logic systems.”

  • The paper relies on this without support.

    The training data labels reflect actual operational outcomes.

    “The training data utilized consists of labeled data that reflect actual operational outcomes, allowing for the use of the cross-entropy loss function to measure the accuracy of the fuzzy logic system’s judgment regarding filling operation effects:”

  • The authors state this as an assumption.

    Filling effectiveness assessment can be treated as a classification problem with three categories.

    “Thus, the problem of assessing filling effectiveness can be viewed as a classification problem, where the category with the highest probability constitutes the judgment of the fuzzy logic system.”

  • The paper relies on this without support.

    The sensor network within the filling work face accurately obtains the specific values of the factors influencing filling effectiveness.

    “By employing a sensor network within the filling work face, specific values of these influencing factors can be obtained, allowing for quantitative analysis through mathematical tools such as fuzzy logic, thereby enabling objective and accurate assessments of filling effectiveness.”

  • The paper relies on this without support.

    The experimental filling work face in Hebei Province is representative of coal mine filling operations for evaluating the proposed method.

    “To obtain the dataset necessary for generating fuzzy rules, data collection was conducted at an experimental filling work face in a mine located in Hebei Province, following the sensor arrangement designed in this study.”

  • The paper relies on this without support.

    Traditional D-S evidence theory often produces counterintuitive outcomes when handling conflicting evidence, causing fusion results to deviate from the true situation and affecting decision accuracy.

    “However, it exhibits certain limitations when handling conflicting evidence, often resulting in counterintuitive outcomes, particularly when there is significant conflict among the pieces of evidence.”

  • The paper relies on this without support.

    In the illustrative example, the actual filling effect is not average (i.e., it is good).

    “which contradicts intuition and the actual situation.”

  • The paper relies on this without support.

    The evidence sources (BPAs from the three fuzzy logic subsystems) are independent.

    “By applying Dempster’s combination rule, the BPAs of the filling effect from various sources are fused, synthesizing the support from different information sources to arrive at the final global assessment of the filling effect.”

  • The paper relies on this without support.

    The dataset used for training, testing, and validation is representative of filling working face conditions.

    “To validate the performance of the proposed method for assessing filling effects, a dataset was utilized for testing and verification.”
10 of 10

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.

  • Reported Deng entropies are too large for the three-category BPAs

    Major

    The three BPAs in Table 3 assign mass only to singleton categories. The paper says Deng entropy then equals Shannon entropy, which cannot exceed log2(3) ≈ 1.585 for three categories; all three reported entropies exceed that bound. These values feed into the proposed evidence weights.

  • Figure 3 caption describes a different diagram

    Minor

    The text introduces Figure 3 as a structural diagram of the hydraulic support, but its caption calls it a diagram of the filling body's bearing-support process.

  • Equipment-position subsystem has conflicting input dimensions

    Minor

    The system description specifies three inputs for each fuzzy logic system, but the accuracy-testing section lists only two inputs for the equipment-position system.

  • Reported information contents do not follow the stated entropy formula

    Minor

    Equation 25 defines information content as e raised to minus Deng entropy. Using the reported H2 = 3.29 and H3 = 3.47 gives approximately 0.037 and 0.031, respectively, not the reported 0.37 and 0.24. These quantities are used to weight the evidence.

  • Comparative-results paragraph reverses two table accuracies

    Minor

    The paragraph assigns 87.18% to T1TFLS-D-S and 86.41% to T1FLS-improved D-S, whereas Table 4 assigns them 86.41% and 87.18%, respectively.

  • Proposed method is assigned other methods' accuracies

    Minor

    The paragraph says the proposed method and the IT2FLS (C0) method achieved 87.75% and 89.31%, respectively. Table 4 instead reports 92.90% for the proposed method; 87.75% and 89.31% belong to two T2FLS (C0) variants.

6 of 6

Cites

Flagged first, then by citations

Research works printed but not linked: 17

  1. Miao, X. Progress of fully mechanized mining with solid backfilling technology. Journal of China Coal Society 37, 1247–1255 (2012).
  2. Liu, J., Wang, H. & Zhao, J. Review and prospect of development of solid backfill technology in coal mine. Coal Science and Technology 48, 27–38 (2020).
  3. Zhang, J. et al. Research progress on intelligent sorting and in-situ filling technology in deep coal mines. Journal of Mining and Safety Engineering 37, 11 (2020).
  4. Miao, X., Ju, F., Huang, Y. & Guo, G. New development and prospect of backfilling mining theory and technology. Journal of China University of Mining and Technology 44, 10 (2015).
  5. Huang, Y., Zhang, J. & Du, J. Time-dependence of backfilling body in fully mechanized backfilling mining face. Journal of China University of Mining and Technology 41, 5 (2012).
  6. Zhang, Z. Design and application of intelligent filling system for fully mechanized working face in extremely thin coal seam. Journal of Mine Automation 47 (2021).
  7. yanli, H., Jixiong, Z., Qiang, Z., Shoujiang, N. & Baifu, A. Strata movement control due to bulk factor of backfilling body in fully mechanized backfilling mining face. Journal of Mining and Safety Engineering 29, 162–167 (2012).
  8. Lingang, J. & Huaxing, Z. Stability of backfill in long wall filling mining. Journal of Mining and Safety Engineering 36, 1234–1239 (2019).
  9. Das, A. K., Gupta, N. & Granados, C. Weighted hesitant bipolar-valued fuzzy soft set in decision-making. Songklanakarin Journal of Science and Technology 45 (2023).
  10. Das, A. K. & Granados, C. A new fuzzy parameterized intuitionistic fuzzy soft multiset theory and group decision-making. Journal of Current Science and Technology 12, 547–567 (2022).
  11. Miao, X. Principle of underground pressure control in fully-mechanized coal mining with solid filling and force analysis of mining support. Journal of China University of Mining and Technology 6, 795–801 (2010).
  12. Zhang, Q., Zhang, J., Ju, F., Li, M. & Geng, D. Backfill body’s compression ratio design and control theory research in solid backfill coal mining. Journal of China Coal Society 39, 64–71 (2014).
  13. Li, M., Zhang, J., Miao, X. & Huang, Y. Strata movement under compaction of solid backfill body. Journal of China University of Mining and Technology 43, 969–973 (2014).
  14. Hao, Y., Jixiong, Z., Sheng, Z., Xiancheng, M. & Junli, C. Macro-micro research on compaction properties of granular backfilling materials. Journal of China Coal Society 42, 8 (2017).
  15. Wenbin, X., Baogui, Y., Shengli, Y. & Peng, D. Experimental study on correlativity between rheological parameters and grain grading of coal gauge backfill slurry. Journal of Central South University(Science and Technology) 47, 8 (2016).
  16. Lixin, L., Meng, L., Qiang, Z. & Yang, T. Experimental study on mechanical properties of solid mixed filling materials in typical mining areas. Journal of Mining and Safety Engineering 36, 9 (2019).
  17. Gengzhan, W. & Yafei, L. Superstatic filling hydraulic support structure. Coal mine machinery 36, 2 (2015).

Cited by

Sorted by citations

Related

Authors
Zhang, Z., Yang, S., & Liu, Y.
Affiliations
China University of Mining and Technology - Beijing (CN)
Corresponding author
Liu, Yang
ORCID
Venue
Scientific Reports
Publisher
Springer Science and Business Media LLC
Published
2025-02-17
Volume
15
Issue
1
Pages
5750-5750
ISSN
2045-2322 (ISSN-L)
DOI
10.1038/s41598-025-88913-5
PMC
PMC11833116
OpenAlex
W4407633790
Semantic Scholar
57939b1e1fc8563d4ebd46b9e332272a670c2d35
Cited by
0
References
23
FWCI
0.00
Type
journal article
Language
en
Open access
Licence
Locations
  • Scientific Reports (publishedVersion, cc-by-nc-nd)
  • PubMed Central (publishedVersion, cc-by-nc-nd)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
Funders
National Natural Science Foundation of Hebei Province (E2020402064)
Topics
  • Physical Sciences › Engineering › Mechanics of Materials › Geomechanics and Mining Engineering
  • Physical Sciences › Engineering › Safety, Risk, Reliability and Quality › Geoscience and Mining Technology
  • Social Sciences › Decision Sciences › Management Science and Operations Research › Multi-Criteria Decision Making
Keywords
interval type-2 fuzzy systems, Dempster-Shafer theory, data fusion, Adam optimizer, Wasserstein distance, Deng entropy, sensor fusion, uncertainty management

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.

Claims read by deepseek-v4.1-flash under definition version 3 (extract-v3) on 2026-10-29.

Classified by jev-1.13-20260917 (gold-guideline-v0.2) on 2026-10-29.

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