以基于图的结构模式识别为理论创新、以新能源为主体的新型电力系统和能源系统数字化智能化为分析对象。围绕“碳达峰”和“碳中和”主题，主持2项国家自然科学基金项目，分别是（1）面上项目：面向可重构电池网络储能系统的动态图学习理论研究，57万；（2）重点项目（总经费254万）子课题：面向能源互联网优化的异构信息网络边缘智能理论与方法，76.2万。近三年，主持10多项电力新基建科技项目。与国网亿力科技联合研发 “基于云边协同的人工智能关键技术研发及产业化”，荣获2020年厦门市科技进步二等奖，个人排名第一。
xing ai，chengyu sun，zhihong zhang(通讯作者), and edwin hancock, two-level graph neural network, ieee transactions on neural networks and learning systems (tnnls),2022.(jcr一区期刊，if：11.683)
zhihong zhang, dongdong chen, jianjia wang, lu bai, and edwin hancock, graph motif entropy for understanding time-evolving networks, ieee transactions on neural networks and learning systems (tnnls),2021.(jcr一区期刊，if：11.683)
zhihong zhang, ruiyang liang, xu chen, xuexin xu, guosehng hu, wangmeng zuo and edwin hancock, semi-supervised face frontalization in the wild, ieee transactions on information forensics & security (tifs),vol.16， pp.909-922,2021. (jcr一区期刊，ccf a类，if：6.211)
zhihong zhang, xu chen, beizhan wang, guosheng hu, wangmeng zuo and edwin hancock, face frontalization using appearance flow based convolutional neural network, ieee transactions on image processing, 28(5): 2187-2199, 2019. (jcr一区期刊，ccf a类期刊，if：6.79)
lu bai, lixin cui, lixiang xu, yue wang, zhihong zhang(通讯作者), and edwin hancock, entropic dynamic time warping kernels for co-evolving financial time series analysis, ieee transactions on neural networks and learning systems (tnnls),2021. (jcr一区期刊，if：11.683)
jinhui chen, zhihong zhang (通讯作者) et al. polar transformation on image features for orientation-invariant representations, ieee transactions on multimedia, 21(2): 300-313,2019. (jcr一区期刊，if：5.452)
dongdong chen, zhihong zhang (通讯作者) et al. thermodynamic motif analysis for directed stock market networks，pattern recognition, 2021. (jcr一区期刊，if：7.74)
jianjia wang, zhihong zhang (通讯作者) et al. statistical mechanical analysis for unweighted and weighted stock market networks，pattern recognition, 2021. (jcr一区期刊，if：7.74)
jinhui chen, zhihong zhang (通讯作者) et al. multimodal fusion for indoor sound source localization，pattern recognition, 2021. (jcr一区期刊，if：7.74)
zhihong zhang, yangbin zeng，lu bai and edwin hancock, spectral bounding: strictly satisfying the 1-lipschitz property for generative adversarial networks, pattern recognition, volume 105:2020. (jcr一区期刊，if：7.74)
zhihong zhang, dongdong chen, zeli wang, lu bai, heng li and edwin hancock, depth-based subgraph convolutional auto-encoder for network representation learning, pattern recognition, 90:363-376,2019. (jcr一区期刊，if：7.74)
zhihong zhang, dongdong chen, jianjia wang, lu bai and edwin hancock, quantum-based subgraph convolutional neural networks, pattern recognition,88:38-49,2019. (jcr一区期刊，if：7.74)
xu chen, zhihong zhang (通讯作者), beizhan wang, guosheng hu and edwin hancock, recovering variations in facial albedo from low resolution images, pattern recognition, 74:373-384,2018. (jcr一区期刊，if：7.74)
zhihong zhang, lu bai, yuanheng liang and edwin hancock, joint hypergraph learning and sparse regression for feature selection, pattern recognition,63: 291-309 2017. (jcr一区期刊，if：7.74)
xu chen, zhihong zhang (通讯作者) et al. a graph-based approach to automated eus image layer segmentation and abnormal region detection, neurocomputing,336:79-91 2019. (jcr二区期刊，if：4.072)
chuanyu xu, zhihong zhang (通讯作者) et al. depth-based subgraph convolutional neural networks, in proceedings icpr 2018. （icpr best scientific paper award）
lu bai, zhihong zhang (通讯作者), c wang, x bai and edwin hancock. a graph kernel based on the jensen-shannon representation alignment. in proceedings of ijcai, 3322-3328, 2015. （ccf a类会议）
lu bai, l rossi, zhihong zhang (通讯作者) and edwin hancock. an aligned subtree kernel for weighted graphs. in proceedings of icml, 30-39, 2015. （ccf a类会议）
xuexin xu, liang shi, jinhui chen, xunquan chen, jie lian, pingyuan lin, zhihong zhang(通讯作者), edwin r. hancock. two-pathway style embedding for arbitrary voice conversion, in proceedings of interspeech 2021.