云梯系统电梯高负载分析数据

依据告警数据，评估电梯的运行状态和安全性能，及时在轿厢内提醒乘客安全乘梯，设备抓图便于在发生突发状况时，快速了解现场状况，定位电梯及乘客所在位置，对梯内乘客的安全起到实际保障作用；定期对告警数据设备抓图所反映的现场情况进行分析，方便物业制定对电梯的维护保养计划；根据一段时间内告警的数据规模、现场图片、时间等，帮助电梯生产销售企业了解该地的乘梯情况，选择销售合适的电梯类型；公开报道一段时间内电梯高负载告警数据，可以提高公众对乘梯安全的重视程度。
1.通过基于传感器的实时电梯门开关状态检测算法检出处于运行状态的电梯； 2.开启电梯内摄像头抓图服务(抓图频率1FPS),并将图片上传到华为云obs。云端算法服务器从华为云obs拉取到图片后，通过基于深度学习神经网络训练的目标检测算法进行图片检测，输出图片相关属性；3.输出的图片属性包含：目标类型category、目标坐标框box、目标结果置信度score、目标匹配groupid； 4.对输出的目标类型进行识别，category所代表的含义分别为：0-人体，1-人头，groupid为人头和其他类别的匹配数量，当算法根据检出的人数计算出当前负载超过电梯荷载后将触发电梯高负载告警，告警时间为时间戳，更加精准。

This dataset evaluates the operating status and safety performance of elevators based on alarm data. It timely reminds passengers in elevator cars to ride safely, captures device images to quickly understand the on-site situation, locate the elevator and the passengers' positions during emergencies, and effectively guarantees the safety of passengers in the elevator. Regular analysis of the on-site conditions reflected by alarm data and captured device images enables property management to formulate elevator maintenance plans. Based on the scale of alarm data, on-site images, time and other information over a period of time, it helps elevator manufacturing and sales enterprises understand the local elevator-riding situation and select appropriate elevator types for sales. Publishing high-load alarm data of elevators over a period of time can also enhance the public's awareness of elevator riding safety.
1. Detect elevators in operation using a sensor-based real-time elevator door switch state detection algorithm;
2. Enable the in-elevator camera image capture service with a capture frequency of 1 FPS, and upload the captured images to Huawei Cloud OBS. After the cloud algorithm server pulls the images from Huawei Cloud OBS, it performs image detection via an object detection algorithm trained on deep learning neural networks, and outputs relevant attributes of the images;
3. The output image attributes include: target category, target bounding box, target confidence score, and target matching group ID;
4. Identify the output target categories, where the meanings of the category values are: 0 - human body, 1 - human head. The group ID represents the number of matches between human heads and other categories. When the algorithm calculates that the current load exceeds the elevator's rated load based on the detected number of people, an elevator high-load alarm will be triggered, with the alarm time recorded as a timestamp for higher accuracy.

搜集汇总

数据集介绍

特点

该数据集为浙江新再灵科技股份有限公司登记的云梯系统电梯高负载分析数据，包含2251条电梯高负载告警记录，用于评估电梯运行状态和安全性能，并通过算法检测电梯内人数以触发电梯高负载告警。