沥青混合料拌和过程实时监控

为控制道路施工过程中沥青混合料的拌和质量与拌和状态, 提出一种以非介入方式利用模板匹配识别算法实时提取骨料、粉料、沥青质量数据、拌和时间及温度等沥青混合料主成分数据信息的方法, 根据识别到的沥青混合料数据信息建立了数据采集与传输的时序逻辑关系; 在WEB监控中心下可视化显示了沥青混合料配合比误差、级配误差、拌和时间和温度等关键信息, 并利用这些多模态信息融合策略评价了沥青混合料的拌和质量; 根据施工过程中沥青混合料类型的先验知识分析了混合料数据的动态变化, 在无人工干预的情况下自动识别了实时生产的沥青混合料类型; 建立了骨料数据的模型分布, 并结合拌和时间判断拌和设备的运行和筛分状态; 存储实时接收到的数据, 实现了沥青混合料历史数据跨时间查询和成本评判。研究结果表明: 利用模板匹配识别算法采集沥青混合料字符数据时间为4.9 ms, 识别准确率达100%, 满足了施工中沥青混合料拌和数据采集时间间隔小于0.02 s的要求, 实现了施工过程中沥青混合料数据的连续检测、自动识别、实时跟踪和可视化监控; 当沥青混合料质量不合格或拌和设备出现故障时可实时预警, 为综合评价沥青混合料拌和过程与实时掌控沥青混合料拌和质量提供了依据。 

Real-time monitoring of asphalt mixture mixing process

To control the mixing quality and mixing state of asphalt mixture during the road construction process, a method based on the template matching recognition algorithm in a non-intrusive manner was proposed to extract the asphalt mixture principal component data, such as aggregate, powder, asphalt quality data, mixing time, and temperature in real-time. Based on the identified asphalt mixture data information, the time sequence logic relationship between data acquisition and transmission was established. The WEB monitoring center visually displayed the key information such as the asphalt mixture ratio error, gradation error, mixing time, and temperature. The multimodal information fusion strategy was used to evaluate the asphalt mixture's mixing quality. Based on the prior knowledge of asphalt mixture type during the construction process, the dynamic change of mixture data was analyzed, and the type of asphalt mixture produced in real-time was automatically identified without the manual intervention. The running and screening statuses of mixing equipment were determined by the established model distribution of aggregate data and the mixing time. The historical data were queried across time and the construction cost was assessed according to the stored real-time received data. Research result shows that the time for collecting the character data of asphalt mixture is 4.9 ms by using the template matching recognition algorithm, and the recognition accuracy rate is up to 100%. It meets the time interval requirement that the mixing data collection of asphalt mixture during the construction is less than 0.02 s. The continuous detection, automatic identification, real-time tracking and visual monitoring on asphalt mixture data during the construction process are realized. The real-time warning is realized when the quality of asphalt mixture is unqualified or the mixing equipment fails. It provides a basis for the comprehensive evaluation of mixing process and the real-time control of mixing quality for asphalt mixture.