To address the poor wear resistance of working components in agricultural machinery (such as plowshares and rotary blades), high-vanadium high-speed steel powder materials with different compositions were designed, and surface strengthening of 60Si2Mn steel plowshare and rotary blade components was performed using laser cladding technology. The influence of the quenching-tempering process on the microstructure and properties of the cladding layer was investigated. The results indicate that the quenched microstructures of cladding layer metals with different compositions all consist of martensite+undissolved carbides (VC, M7C3, M23C6, and M6C)+retained austenite; with the increase in tempering temperature, the microhardness of the cladding layer shows a gradually decreasing trend caused by microstructural evolutions such as retained austenite transformation, secondary carbide precipitation, and tempered martensite decomposition. The microhardness distribution characteristics of the cladding layer are mainly influenced by the size, shape, and location of carbide particles. Based on the random forest algorithm, a microhardness prediction model for the cladding layer metal considering the influence of chemical composition is established.
高钒高速钢是一种以V为主要合金元素,辅以Cr,Mo,W等多种合金元素的高速钢,通过形成大量高硬度的VC颗粒实现对金属材料耐磨性能的增强.合金材料的力学性能主要取决于其微观组织特征,而微观组织又与合金元素的组成密切相关.为建立熔覆层金属的硬度预测模型,除考虑C和V含量对合金硬度的影响外,还需兼顾Cr,Mo,W等其他合金元素的强化作用.机器学习作为人工智能的关键技术,其本质是通过对现有数据、知识和经验的分析来构建计算模型,从而揭示数据内在规律.近年来,数据驱动的机器学习方法因其在处理复杂非线性问题上的卓越表现而备受瞩目.这种方法通过建立输入与输出之间的映射关系,在材料科学领域取得了显著成效,特别是在新材料研发、小样本数据优化和材料机理研究等方面表现尤为突出.根据数据标注情况,机器学习通常可分为监督学习、半监督学习和无监督学习三大类.由于材料科学实验数据通常带有明确标签,因此该领域主要采用监督学习方法进行研究和应用[26].如图10所示,随机森林算法是建立在分类与回归树(classification and regression tree,CART)基础上的.对于普通决策树而言,在节点上的所有p个样本特征中选取一个最优特征,用于划分左右子树;而通过随机选择节点上一部分样本特征,假设为k(且k<p),然后在这k个随机选取的样本特征中,再选择一个最优特征来进行左右子树的划分.这两个随机性使得基本模型之间的相关性显著降低,方差下降,从而进一步增强了模型的泛化能力[27].
YaoKe-yan, LiuChuan-jun, XueZhou. Agricultural equipment innovation from the perspective of new quality productive forces: logical framework, challenges and promotion strategy [J]. Journal of Huazhong Agricultural University (Social Sciences Edition), 2024(6): 61-73.
HuoYue. Policy dividends transformed into innovative driving force for comprehensive upgrading of agricultural machinery and equipment [N]. China Industry News, 2025-04-14(10).
SongYue-peng, WangWei, GaoDong-sheng, et al. Research status of agricultural machine cutting tools treated by surface engineering technology [J]. Journal of Chinese Agricultural Mechanization, 2018, 39(1): 27-31.
[7]
GuanC S, FuJ J, CuiZ C, et al. Evaluation of the tribological and anti-adhesive properties of different materials coated rotary tillage blades [J]. Soil and Tillage Research, 2021, 209: 104933.
JiaHong-lei, WangWan-peng, ChenZhi, et al. Research status and prospect of soil-engaging components optimization for agricultural machinery [J]. Transactions of the Chinese Society for Agricultural Machinery, 2017, 48(7): 1-13.
[11]
ZhangS, YuH X, LiS, et al. Laser cladding strengthening test on the surface of flatness rollers [J]. ISIJ International, 2023, 63(1): 120-127.
[12]
TarasiukW, NapiórkowskiJ, LigierK, et al. Comparison of the wear resistance of Hardox 500 steel and 20MnCr5 [J].Tribologia,2018,273(3): 165-170.
ChenDeng-hua, YuHong-hai, LiuHai-ding, et al. Microstructure and properties of hard-phase reinforced wear-resistant layer on 60Si2Mn steel for soil-engaging component deposited by laser cladding [J]. Heat Treatment of Metals, 2023, 48(12): 213-221.
[15]
JankauskasV, AntonovM, VarnauskasV, et al. Effect of WC grain size and content on low stress abrasive wear of manual arc welded hardfacings with low-carbon or stainless steel matrix [J]. Wear, 2015, 328/329: 378-390.
ShiYun, DuXiao-dong, ZhuangPeng-cheng, et al. Research and development trend of plasma cladding technology [J]. Surface Technology, 2019, 48(12): 23-33.
[20]
Van AckerK, VanhoyweghenD, PersoonsR, et al. Influence of tungsten carbide particle size and distribution on the wear resistance of laser clad WC/Ni coatings [J]. Wear, 2005, 258(1/2/3/4): 194-202.
YuanQing-long, FengXu-dong, CaoJing-jing, et al. Research on microstructure of Ni-based alloy coating by laser cladding [J]. Chinese Journal of Lasers, 2010, 37(8): 2116-2120.
[23]
ChenK Y, YangX F, LiW Y, et al. Study on the wear and corrosion resistance of Fe-Mo coatings on 65Mn steel ploughshares by laser cladding [J]. Applied Physics A, 2022, 128(9): 795.
YanYong, WangHong-li. Study on laser cladding strengthening technology for surface [J]. Journal of Heilongjiang Bayi Agricultural University, 2020, 32(1): 78-82,108.
WuZhao-kun, QiuBin-lin, ZhouYu-chong, et al. Microstructure and hardness analysis of 316L stainless steel layer by laser cladding [J]. Journal of Shanghai University of Engineering Science, 2014, 28(2): 106-110.
[28]
XuL J, XingJ D, WeiS Z, et al. Optimisation of chemical composition of high speed steel with high vanadium content for abrasive wear using an artificial neural network [J]. Materials & Design, 2007, 28(3): 1031-1037.
[29]
XuL J, XingJ D, WeiS Z, et al. Study on relative wear resistance and wear stability of high-speed steel with high vanadium content [J]. Wear, 2007, 262(3/4): 253-261.
WeiShi-zhong, XuLiu-jie, ZhuJin-hua, et al. Effect of carbon and vanadium content on microstructure and mechanical properties of high vanadium high speed steel [J]. Journal of Iron and Steel Research, 2005, 17(5): 66-71.
[32]
WeiS Z, ZhuJ H, XuL J. Effects of vanadium and carbon on microstructures and abrasive wear resistance of high speed steel [J]. Tribology International, 2006, 39(7): 641-648.
[33]
LiuJ L, ShiG Q, DingP D. Study of residual austenite in the surface layer of (M2) high speed steel hardened by laser [J]. Lasers in Engineering, 1999, 9: 77-83.
[34]
XuL J, XingJ D, WeiS Z, et al. Artificial neural network prediction of retained austenite content and impact toughness of high-vanadium high-speed steel (HVHSS) [J]. Materials Science and Engineering: A, 2006, 433(1/2): 251-256.
[35]
YuanW Y, LiR F, ChenZ H, et al. A comparative study on microstructure and properties of traditional laser cladding and high-speed laser cladding of Ni45 alloy coatings [J]. Surface and Coatings Technology, 2021, 405: 126582.
[36]
XuL J, WeiS Z, XiaoF N, et al. Effects of carbides on abrasive wear properties and failure behaviours of high speed steels with different alloy element content [J]. Wear, 2017, 376/377: 968-974.
[37]
Huang X Y, Jin C, Zhang C, et al. Machine learning assisted modelling and design of solid solution hardened high entropy alloys [J]. Materials & Design, 2021, 211: 110177.
[38]
Yuan M. Data mining and machine learning: WEKA application technology and practice [M].Beijing:Tsinghua University Press, 2016.
Liu Yuan. Property prediction based on machine learning and database platform of Cr-V wear-resistant steel [D]. Luoyang: Henan University of Science and Technology, 2023.