阅读说明：本技术 一种皮带设备运行全生命周期监控系统与方法 (System and method for monitoring full life cycle of operation of belt equipment ) 是由 王紫千 纪彭 陈文� 程福友 张滇豫 方哲通 王雅慧 于 2020-06-02 设计创作，主要内容包括：本发明公开了一种皮带设备运行全生命周期监控系统与方法,包括设备监控单元,还包括：视频监控单元,设置于皮带设备上方,视频拍摄范围涵盖皮带设备以及警戒区域；照明灯组,由若干固定角度的照明灯组成,设置于皮带设备所在区域的上部空间；行为警示单元,运行识别模型,识别视频中人员面部,分析人员运动轨迹,结合设备监控单元的数据确定风险等级；云服务器,对原始视频数据进行存储,定期性使用云端数据对识别模型进行训练,并将新的模型更新到行为警示单元；预警单元,根据行为警示单元报告的风险等级进行声光预警。通过对设备运行状态以及人员的运动轨迹的共同监控,实现对皮带设备的全方位、全生命周期立体监控,显著提高预警能力。(The invention discloses a system and a method for monitoring the whole life cycle of belt equipment operation, which comprises an equipment monitoring unit and further comprises the following steps: the video monitoring unit is arranged above the belt equipment, and a video shooting range covers the belt equipment and the warning area; the lighting lamp group consists of a plurality of lighting lamps with fixed angles and is arranged in the upper space of the area where the belt equipment is located; the behavior warning unit operates the recognition model, recognizes the face of a person in the video, analyzes the movement track of the person, and determines the risk level by combining the data of the equipment monitoring unit; the cloud server stores original video data, trains the recognition model by periodically using cloud data, and updates a new model to the behavior warning unit; and the early warning unit carries out acousto-optic early warning according to the risk level reported by the behavior warning unit. Through the common monitoring to the running state of the equipment and the movement track of personnel, the comprehensive and full-life-cycle three-dimensional monitoring to the belt equipment is realized, and the early warning capability is obviously improved.)

1. The utility model provides a full life cycle monitored control system of belt equipment operation, includes equipment monitoring unit, its characterized in that still includes:

the video monitoring unit is arranged above the belt equipment, and a video shooting range covers the belt equipment and the warning area;

the lighting lamp group consists of a plurality of lighting lamps with fixed angles and is arranged in the upper space of the area where the belt equipment is located;

the behavior warning unit operates the recognition model, recognizes the face of the person in the video, analyzes the movement track of the person, and determines the risk level by combining the data of the equipment monitoring unit;

the cloud server stores original video data, trains the recognition model by periodically using cloud data, and updates a new model to the behavior warning unit;

and the early warning unit carries out acousto-optic early warning according to the risk level reported by the behavior warning unit.

2. The system for monitoring the full life cycle of the operation of the belt equipment as claimed in claim 1, wherein the video monitoring unit comprises an equipment camera, a peripheral camera and a convex reflector, the convex reflector is arranged above the belt equipment and forms an included angle with the ground, the equipment camera is arranged on one side of the belt equipment with the feeding hole, the equipment camera shoots the images of the feeding hole in the convex reflector and the belt, and the peripheral camera is arranged above the area where the belt equipment is located and shoots the ground.

3. A belt plant operation full lifecycle monitoring system as claimed in claim 1 or 2, characterized in that the plant monitoring unit comprises a deviation sensor, a slip sensor, a tear sensor and a temperature sensor.

4. The belt equipment operation full-life cycle monitoring system according to claim 1 or 2, wherein the behavior warning unit comprises a face recognition module and a motion track analysis module, the face recognition module recognizes faces of people, the motion track analysis module stores motion tracks of shadows of the people who patrol the belt equipment when the people patrol the belt equipment normally and manually, and risk levels are generated when any one of the real-time operation condition of the belt equipment and the behavior condition of the people is abnormal, wherein the real-time operation condition of the belt equipment is judged according to the data of the equipment monitoring unit.

5. A method for monitoring the operation of a belt apparatus through a life cycle, which is used in the system for monitoring the operation of a belt apparatus according to claim 1, comprising the steps of:

s01: acquiring real-time operation parameter data of belt equipment and video data of the periphery of the belt equipment;

s02: judging the running state of the equipment according to the comparison of historical running parameter data and real-time data, and simultaneously judging whether the personnel is in normal behavior or abnormal behavior according to the face recognition result and the shadow motion track in the video, if the equipment and the personnel are judged to be normal, not setting a risk level and continuing the real-time judgment, and if at least one of the equipment and the personnel is judged to be abnormal, carrying out the next step;

S03: if the personnel is judged to be abnormal, whether the equipment state is normal or not, adjusting the corresponding risk level according to the abnormal behavior of the personnel, and if the personnel is judged to be normal, but the equipment is judged to be abnormal, adjusting the risk level according to the abnormality of the equipment;

s04: and carrying out corresponding acousto-optic early warning according to the risk level, and if the current risk level is not available, no action is carried out.

6. The method for monitoring the full life cycle of the operation of the belt equipment as claimed in claim 5, wherein when the shadow motion trail is judged, the shadow and the real object are distinguished according to the color brightness in the image, and then the shadow of the person and the shadow of other objects are distinguished according to the length-width ratio of the shadow.

Technical Field

The invention relates to the field of fault monitoring of conveying equipment, in particular to a system and a method for monitoring the whole life cycle of belt equipment operation.

Background

The belt conveyor is key equipment for conveying raw material ores, and is a blood vessel for connecting all sections of processes and supplying supplementary raw materials. The belt conveying device is widely used in the processes of ore excavation, production, transportation and processing, and has the working characteristics of large conveying capacity, complex working environment, strong bearing capacity, long conveying distance and the like. The occurrence of accidents of slipping, deviation and breakage of the conveying belt can cause a great deal of loss to the production and cost of enterprises. Minor negligence in the preparation and repair process can pose a serious threat to the safety of the operating personnel. In addition, the belt conveyor can be influenced when the feeding hoppers on the upper and lower positions of the belt conveyor are blocked and the like, and abnormal halt can be caused when the belt conveyor is seriously stopped.

However, in the prior art, monitoring is focused on the belt conveyor, monitoring of nearby workers is lacked, and evaluation of the relationship between the behavior and the risk of the workers is also lacked, so that the safety is poor, and for example, the invention with the authorization notice number CN104670840B discloses a monitoring device for the operation of a bulk material conveying belt. The controller is internally provided with central software which transmits an operation information program to the monitoring controller, angle signals generated by the monitoring device are compared with standard values respectively to form angle signals I, II and III, the angle signals are transmitted to the monitoring controller, a stop signal is generated through intelligent judgment and comparison, and the stop signal is transmitted to a PLC (programmable logic controller) of a belt conveyor control system through the monitoring controller to drive the belt conveyor to stop operating. The device can monitor the operation condition of each conveyer to the wireless networking of conveyer data of installation monitoring devices. The faults of the conveyer belt are monitored, and property loss is reduced.

Therefore, in addition to monitoring the safety risk of the belt body operation, the monitoring system needs to incorporate the personnel behavior safety and the associated equipment operation safety in the belt machine working space into a risk control closed loop. So as to realize the omnibearing full-life-cycle three-dimensional monitoring of the belt equipment.

Disclosure of Invention

Aiming at the problem that the prior art can not monitor by combining equipment and personnel conditions, the invention provides a system and a method for monitoring the whole life cycle of belt equipment operation.

The technical scheme of the invention is as follows.

The utility model provides a full life cycle monitored control system of belt equipment operation, includes equipment monitoring unit, still includes: the video monitoring unit is arranged above the belt equipment, and a video shooting range covers the belt equipment and the warning area; the lighting lamp group consists of a plurality of lighting lamps with fixed angles and is arranged in the upper space of the area where the belt equipment is located; the behavior warning unit operates the recognition model, recognizes the face of the person in the video, analyzes the movement track of the person, and determines the risk level by combining the data of the equipment monitoring unit; the cloud server stores original video data, trains the recognition model by periodically using cloud data, and updates a new model to the behavior warning unit; and the early warning unit carries out acousto-optic early warning according to the risk level reported by the behavior warning unit. By means of equipment monitoring, video monitoring, image processing and the like, various abnormal scenes such as belt abnormality, personnel identity abnormality, personnel behavior abnormality, safety perimeter intrusion, funnel material blockage and the like are identified by means of machine vision. The risk recognition capability of the monitoring system is improved by expanding the level and the range of risk perception of the monitoring system.

Preferably, the video monitoring unit comprises an equipment camera, a peripheral camera and a convex reflector, the convex reflector is arranged above the belt equipment and forms a certain included angle with the ground, the equipment camera is arranged on one side of the belt equipment with a feed port, the equipment camera shoots images of the feed port and the belt in the convex reflector, and the peripheral camera is arranged above the area where the belt equipment is located and shoots the ground. The equipment camera is matched with the convex reflector, so that more equipment parts can be shot by the equipment camera in a smaller visual field range, and the arrangement of the camera is reduced.

Preferably, the device monitoring unit comprises a deviation sensor, a slip sensor, a tear sensor and a temperature sensor. The method is used for realizing the conventional fault detection of the belt.

Preferably, the behavior warning unit comprises a face recognition module and a motion trail analysis module, the face recognition module recognizes the face of a person, the motion trail analysis module stores the motion trail of a person shadow during normal manual inspection, a risk grade is generated when any aspect of the real-time running state of the belt equipment and the behavior state of the person is abnormal, and the real-time running state of the belt equipment is judged according to the data of the equipment monitoring unit. The behavior warning unit identifies and analyzes according to the identification model, independent networking is achieved in the edge calculation mode, the network safety problem is avoided, meanwhile, data are transmitted to the cloud end to be trained, and adaptability is improved.

Because people's clothing is different, and the discernment degree of difficulty is big, and direct discernment personnel's body can occupy a large amount of computation space, and when the illumination angle was fixed, the shadow possesses human profile characteristic but does not have complicated colour, and belt equipment operation place is different from the warehouse simultaneously, and personnel can not cause the shadow to lose the attitude because of carrying the article often, therefore the shadow is very ideal discernment target. Under normal conditions, if the equipment data is normal and the personnel track is normal, the risk level is not generated, and if at least one party is abnormal, the risk level is generated; if the equipment parameter is obtained by mistake, the display is normal, but the emergency response is carried out after the worker finds the abnormality, or the equipment is abnormal but the worker does not find, or the equipment is abnormal and the worker finds the abnormality and carries out the emergency response at the same time, the risk grade is generated. Measures for emergency response, risk level and the like are determined by self according to specific standards, and implementation of the technical scheme is not influenced. Wherein the motion trail of the shadow is used as the basis for judging the moving process of the personnel.

The invention also provides a method for monitoring the whole life cycle of the operation of the belt equipment, which is used for the system for monitoring the whole life cycle of the operation of the belt equipment and comprises the following steps: s01: acquiring real-time operation parameter data of belt equipment and video data of the periphery of the belt equipment; s02: judging the running state of the equipment according to the comparison of historical running parameter data and real-time data, and simultaneously judging whether the personnel is in normal behavior or abnormal behavior according to the face recognition result and the shadow motion track in the video, if the equipment and the personnel are judged to be normal, not setting a risk level and continuing the real-time judgment, and if at least one of the equipment and the personnel is judged to be abnormal, carrying out the next step; s03: if the personnel is judged to be abnormal, whether the equipment state is normal or not, adjusting the corresponding risk level according to the abnormal behavior of the personnel, and if the personnel is judged to be normal, but the equipment is judged to be abnormal, adjusting the risk level according to the abnormality of the equipment; s04: and carrying out corresponding acousto-optic early warning according to the risk level, and if the current risk level is not available, no action is carried out.

Preferably, when the shadow motion trajectory is determined, the shadow and the real object are distinguished according to color brightness in the image, and then the shadow of the person and the shadow of another object are distinguished according to the aspect ratio of the shadow. The shadow will not be pure black due to the light reflecting effect of the substance, and thus is set according to the brightness of the actual location, while the aspect ratio of the shadow is determined according to the angle of the lighting device. Do not affect the implementation of the scheme.

The substantial effects of the invention include: by adopting a computer vision technology to process the field video signal, safety events and risk factors which are difficult to discover based on the traditional method of field instrument measurement can be discovered; due to the fact that the operation amount is small, the equipment for image processing can be independently networked, potential network and information safety hazards caused by operation of an equipment monitoring system can be eliminated essentially, massive original data can be stored through the cloud, and hardware and labor input is effectively reduced.

Drawings

FIG. 1 is a schematic illustration of a belt installation in accordance with an embodiment of the present invention;

FIG. 2 is a schematic diagram of an identification scenario in accordance with an embodiment of the present invention;

the figure includes: 1-belt equipment, 2-equipment camera, 3-convex reflector, 4-lighting lamp and 5-shadow.

Detailed Description

The technical solution of the present application will be described with reference to the following examples. In addition, numerous specific details are set forth below in order to provide a better understanding of the present invention. It will be understood by those skilled in the art that the present invention may be practiced without some of these specific details. In some instances, methods, means, elements and circuits that are well known to those skilled in the art have not been described in detail so as not to obscure the present invention.