-
摘要: 研究了制动力曲线异常检测方法, 分析了回踩异常特性, 考虑了制动力检测工况和制动力曲线变化趋势, 基于余弦相似度与相对误差, 对制动力数据进行聚类, 建立了制动力曲线分段算法; 将制动力曲线分为阻滞段、上升段、持续段和释放段, 提取出相应的数据子集; 对3家检验机构的9 120条制动力曲线进行人工筛选和分析, 归纳了制动超前、回踩、增长滞后3种异常特征, 给出了相应异常检测算法; 对于较难识别的回踩异常, 根据动态规划思想, 找出上升段最长连续趋势下降子序列, 计算了该子序列占制动力曲线上升段的行程比, 并结合经验值来判定该子序列是否异常。研究结果表明: 对于维度不大于32的低维制动力数据, 通过余弦相似度可聚类制动力曲线的阻滞段、上升段、持续段和释放段; 对于维度大于32的高维数据, 因为维数较高, 行程比较小, 分界点对整个序列相似度影响较小, 在这种情况下, 必须在考虑相似度的情况下, 通过分界点的相对误差进一步约束聚类结果, 可以确定制动力曲线的阻滞段、上升段、持续段和释放段; 由于采集的回踩子序列占制动力曲线的行程比为9.8%, 大于行程比的经验阈值8.2%, 因此, 该制动力曲线具有回踩异常, 判断结果正确, 方法可靠。Abstract: The anomaly detection methods of automobile braking curves were studied.The features of the depressing-releasing-depressing anomaly were analyzed.The detection conditions and changing trends of the braking curves were considered.The braking data were clustered based on the cosine similarity and relative error.The segmentation algorithm of the braking curves was established.The braking curves were divided into blocking segment, rising segment, continuous segment, and releasing segment, and the corresponding data subsets were extracted.9 120 braking force curves from 3 inspection institutions were manually screened and analyzed, the three anomalous features including braking advance, depressing-releasing-depressing and braking growth lag were summarized, and the corresponding anomaly detection algorithms were given. For more difficult to identify the depressing-releasing-depressing anomaly, the subsequence with the longest continuous and descending trend in the ascending segment was searched according to the dynamic programming idea.The distance ratio of the subsequence in theascending segment was calculated, and compared with the corresponding experiential value to determine whether the subsequence was anomalous or not.Research result shows that the lowdimensional braking data can be clustered into blocking segment, rising segment, continuous segment, and releasing segment according to the cosine similarity only when the dimensions are not higher than 32.For the high-dimensional data, because their dimensions are higher than 32, the demarcation point has less influence on the overall sequence similarity.In this case, the relative error of the demarcation point must be combined with the similarity to constrain the clustering result for determining the blocking segment, rising segment, continuous segment, and releasing segment of the braking curve.Since the distance ratio of the depressing-releasingdepressing subsequence in the ascending segment is 9.8% and larger than the empirical value of 8.2%, the braking curve has depressing-releasing-depressing anomaly. This is correct, therefore, the method is reliable.
-
表 1 阻滞段聚类过程中的相似度和相对误差
Table 1. Similarities and relative errors of blocking data in clustering process
下载: 导出CSV
-
[1] 赵英勋. 滚筒反力式制动试验台制动力检测分析[J]. 中国测试, 2015, 41 (4): 10-13. https://www.cnki.com.cn/Article/CJFDTOTAL-SYCS201504003.htmZHAO Ying-xun. Detection and analysis of brake force based on roller opposite-force brake tester[J]. China Measurement and Test, 2015, 41 (4): 10-13. (in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-SYCS201504003.htm [2] 马文耀, 吴兆麟, 李伟峰. 船舶异常行为的一致性检测算法[J]. 交通运输工程学报, 2017, 17 (5): 149-158. doi: 10.3969/j.issn.1671-1637.2017.05.014MA Wen-yao, WU Zhao-lin, LI Wei-feng. Conformal detection algorithm of anomalous behaviors of vessel[J]. Journal of Traffic and Transportation Engineering, 2017, 17 (5): 149-158. (in Chinese). doi: 10.3969/j.issn.1671-1637.2017.05.014 [3] 周东华, 魏慕恒, 司小胜. 工业过程异常检测、寿命预测与维修决策的研究进展[J]. 自动化学报, 2013, 39 (6): 711-722. https://www.cnki.com.cn/Article/CJFDTOTAL-MOTO201306005.htmZHOU Dong-hua, WEI Mu-heng, SI Xiao-sheng. A survey on anomaly detection, life prediction and maintenance decision for industrial processes[J]. Acta Automatica Sinica, 2013, 39 (6): 711-722. (in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-MOTO201306005.htm [4] 姚欣歆, 刘英博, 赵炯, 等. 面向设备群体的工况数据异常检测方法[J]. 计算机集成制造系统, 2013, 19 (12): 2993-3001. https://www.cnki.com.cn/Article/CJFDTOTAL-JSJJ201312010.htmYAO Xin-xin, LIU Ying-bo, ZHAO Jiong, et al. Device group-oriented method for abnormal floor data detecting[J]. Computer Integrated Manufacturing Systems, 2013, 19 (12): 2993-3001. (in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-JSJJ201312010.htm [5] 严英杰, 盛戈皞, 陈玉峰, 等. 基于大数据分析的输变电设备状态数据异常检测方法[J]. 中国电机工程学报, 2015, 35 (1): 52-59. https://www.cnki.com.cn/Article/CJFDTOTAL-ZGDC201501008.htmYAN Ying-jie, SHENG Ge-hao, CHEN Yu-feng, et al. An method for anomaly detection of state information of power equipment based on big data analysis[J]. Proceedings of the CSEE, 2015, 35 (1): 52-59. (in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-ZGDC201501008.htm [6] 陶涛, 周喜, 马博, 等. 基于双向LSTM的Seq2Seq模型在加油站时序数据异常检测中的应用[J]. 计算机应用, 2018: 1-7, DOI: 10.11772/j.issn.1001-9081.2018081681.TA.O Tao, ZHOU Xi, MA Bo, et al. Detecting abnormal time series data of gas station utilizing Seq2Seq model based on bi-LSTM[J]. Journal of Computer Applications, 2018: 1-7, DOI: 10.11772/j.issn.1001-9081.2018081681.(in Chinese). [7] 史斌, 姜继平, 王鹏. 基于高频在线水质数据异常的突发污染预警[J]. 中国环境科学, 2017, 37 (11): 4394-4400. doi: 10.3969/j.issn.1000-6923.2017.11.046SHI Bin, JIANG Ji-ping, WANG Peng. Early warning of water pollution incidents based on abnormal change of water quality data from high frequency online monitoring[J]. China Environmental Science, 2017, 37 (11): 4394-4400. (in Chinese). doi: 10.3969/j.issn.1000-6923.2017.11.046 [8] BAO Yue-quan, TANG Zhi-yi, LI Hui, et al. Computer vision and deep learning-based data anomaly detection method for structural health monitoring[J]. Structural Health Monitoring, 2018: 1-21, DOI: 10.1177/1475921718757405. [9] 尚文利, 张盛山, 万明, 等. 基于PSO-SVM的Modbus TCP通讯的异常检测方法[J]. 电子学报, 2014, 42 (11): 2314-2320. doi: 10.3969/j.issn.0372-2112.2014.11.029SHANG Wen-li, ZHANG Sheng-shan, WAN Ming, et al. Modbus/TCP communication anomaly detection algorithm based on PSO-SVM[J]. Acta Electronica Sinica, 2014, 42 (11): 2314-2320. (in Chinese). doi: 10.3969/j.issn.0372-2112.2014.11.029 [10] 王德文, 杨力平. 智能电网大数据流式处理方法与状态监测异常检测[J]. 电力系统自动化, 2016, 40 (14): 122-128. doi: 10.7500/AEPS20150828001WANG De-wen, YANG Li-ping. Stream processing method and condition monitoring anomaly detection for big data in smart grid[J]. Automation of Electric Power Systems, 2016, 40 (14): 122-128. (in Chinese). doi: 10.7500/AEPS20150828001 [11] 余宇峰, 朱跃龙, 万定生, 等. 基于滑动窗口预测的水文时间序列异常检测[J]. 计算机应用, 2014, 34 (8): 2217-2220, 2226. https://www.cnki.com.cn/Article/CJFDTOTAL-JSJY201408018.htmYU Yu-feng, ZHU Yue-long, WAN Ding-sheng, et al. Time series outlier detection based on sliding window prediction[J]. Journal of Computer Applications, 2014, 34 (8): 2217-2220, 2226. (in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-JSJY201408018.htm [12] 张忠林, 周晓侠. 基于滑动窗口聚类的时序关联规则挖掘方法[J]. 计算机工程与设计, 2014, 35 (4): 1408-1413. doi: 10.3969/j.issn.1000-7024.2014.04.055ZHANG Zhong-lin, ZHOU Xiao-xia. Method of mining sequential association rules based on clustering of sliding window[J]. Computer Engineering and Design, 2014, 35 (4): 1408-1413. (in Chinese). doi: 10.3969/j.issn.1000-7024.2014.04.055 [13] 刘子豪, 李凌, 叶枫. 基于SparkR的水文传感器数据的异常检测方法[J]. 计算机应用, 2018: 1-6, DOI:10.11772/j.issn.1001-9081.2018081782.LIU Zi-hao, LI Ling, YE Feng. Anomaly detection method for hydrologic sensor data based on SparkR[J]. Journal of Computer Applications, 2018: 1-6, DOI:10.11772/j.issn.1001-9081.2018081782.(in Chinese). [14] 李海林, 邬先利. 基于频繁模式发现的时间序列异常检测方法[J]. 计算机应用, 2018, 38 (11): 3204-3210. doi: 10.11772/j.issn.1001-9081.2018041252LI Hai-lin, WU Xian-li. Time series anomaly detection method based on frequent pattern discovery[J]. Journal of Computer Applications, 2018, 38 (11): 3204-3210. (in Chinese). doi: 10.11772/j.issn.1001-9081.2018041252 [15] LI Guang, WANG Jie, LIANG Jing, et al. Application of sliding nest window control chart in data stream anomaly detection[J]. Symmetry, 2018, 10 (4): 1-13. [16] 费欢, 肖甫, 李光辉, 等. 基于多模态数据流的无线传感器网络异常检测方法[J]. 计算机学报, 2017, 40 (8): 1829-1842. https://www.cnki.com.cn/Article/CJFDTOTAL-JSJX201708007.htmFEI Huan, XIAO Fu, LI Guang-hui, et al. An anomaly detection method of wireless sensor network based on multimodals data stream[J]. Chinese Journal of Computers, 2017, 40 (8): 1829-1842. (in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-JSJX201708007.htm [17] DING Zhi-guo, FEI Min-rui. An anomaly detection approach based on isolation forest algorithm for streaming data using sliding window[J]. IFAC Proceedings Volumes, 2013, 46 (20): 12-17. doi: 10.3182/20130902-3-CN-3020.00044 [18] 王桂兰, 周国亮, 赵洪山, 等. 大规模用电数据流的快速聚类和异常检测技术[J]. 电力系统自动化, 2016, 40 (24): 27-33. doi: 10.7500/AEPS20160123002WANG Gui-lan, ZHOU Guo-liang, ZHAO Hong-shan, et al. Fast clustering and anomaly detection technique for large-scale power data stream[J]. Automation of Electric Power Systems, 2016, 40 (24): 27-33. (in Chinese). doi: 10.7500/AEPS20160123002 [19] AGHABOZORGI S, SHIRKHORSHIDI A S, WAH T Y. Time-series clustering-a decade review[J]. Information Systems, 2015, 53: 16-38. doi: 10.1016/j.is.2015.04.007 [20] FAHAD A, ALSHATRI N, TARI Z, et al. A survey of clustering algorithms for big data: taxonomy and empirical analysis[J]. IEEE Transactions on Emerging Topics in Computing, 2014, 2 (3): 267-279. doi: 10.1109/TETC.2014.2330519 [21] FAROUGHI A, JAVIDAN R. CANF: Clustering and anomaly detection method using nearest and farthest neighbor[J]. Future Generation Computer Systems, 2018, 89: 166-177. doi: 10.1016/j.future.2018.06.031 [22] JAIN B J. The mean partition theorem in consensus clustering[J]. Pattern Recognition, 2018, 79: 427-439. doi: 10.1016/j.patcog.2018.01.030 [23] ISMKHAN H. I-k-means-plus: An iterative clustering algorithm based on an enhanced version of the K-means[J]. Pattern Recognition, 2018, 79: 402-413. doi: 10.1016/j.patcog.2018.02.015 [24] RODRIGUEZ A, LAIO A. Clustering by fast search and find of density peaks[J]. Science, 2014, 344: 1492-1496. doi: 10.1126/science.1242072 [25] 田力, 向敏. 基于密度聚类技术的电力系统用电量异常分析算法[J]. 电力系统自动化, 2017, 41 (5): 64-70. https://www.cnki.com.cn/Article/CJFDTOTAL-DLXT201705010.htmTIAN Li, XIANG Min. Abnormal power consumption analysis based on density-based spatial clustering of applications with noise in power system[J]. Automation of Electric Power Systems, 2017, 41 (5): 64-70. (in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-DLXT201705010.htm [26] 庄池杰, 张斌, 胡军, 等. 基于无监督学习的电力用户异常用电模式检测[J]. 中国电机工程学报, 2016, 36 (2): 379-387. https://www.cnki.com.cn/Article/CJFDTOTAL-ZGDC201602008.htmZHUANG Chi-jie, ZHANG Bin, HU Jun, et al. Anomaly detection for power consumption patterns based on unsupervised learning[J]. Proceedings of the CSEE, 2016, 36 (2): 379-387. (in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-ZGDC201602008.htm [27] PURARJOMANDLANGRUDI A, GHAPANCHI A H, ESMALIFALAK M. A data mining approach for fault diagnosis: an application of anomaly detection algorithm[J]. Measurement, 2014, 55: 343-352. doi: 10.1016/j.measurement.2014.05.029 [28] RANSHOUS S, SHEN S, KOUTRA D, et al. Anomaly detection in dynamic networks: a survey[R]. Hoboken: Wiley Periodicals, Inc., 2015. [29] THEISSLER A. Detecting known and unknown faults in automotive systems using ensemble-based anomaly detection[J]. KnowledgeBased Systems, 2017, 123: 163-173. [30] LI Guang-hui, LU Wen-wei, FENG Hai-lin. Outlier detection methods based on neural network in wireless sensor networks[J]. Computer Science, 2014, 41 (11A): 208-211. [31] PANDEESWARI N, KUMAR G. Anomaly detection system in cloud environment using fuzzy clustering based ANN[J]. Mobile Networks and Applications, 2016, 21: 494-505. [32] WU Jia, ZENG Wei-ru, YAN Fei. Hierarchical temporal memory method for time-series-based anomaly detection[J]. Neurocomputing, 2018, 273: 535-546. -
点击查看大图
图(11) / 表(1)
计量
- 文章访问数: 971
- HTML全文浏览量: 93
- PDF下载量: 736
- 被引次数: 0
