CN115984076A - Power enterprise safety production management system and method - Google Patents

Abstract

The application discloses electric power enterprise safety production management system and method, wherein, the system includes: the system comprises a data acquisition module, a model construction module, a route identification module, a behavior identification module and an alarm module; the data acquisition module comprises a worker and vehicle information acquisition module, a worker route image acquisition submodule and a behavior data acquisition submodule; the model building module comprises a route safety model building submodule and a behavior insecurity model building submodule; the route identification module is used for monitoring whether the current worker walking route and the vehicle running route break rules or not; the behavior identification module is used for monitoring whether the current behavior of the worker violates rules or not; the alarm module comprises a walking route alarm submodule and a behavior non-standard alarm submodule. The method and the system can effectively control unsafe behaviors of people, effectively stop safe production accidents, timely block the unsafe behaviors of people, and improve the capabilities of safety management and safety supervision.

Description

Power enterprise safety production management system and method

Technical Field

The application relates to the field of production safety, in particular to a system and a method for managing safe production of an electric power enterprise.

Background

Through analyzing the current situation of the current power production management, pain points and defects existing in safety management are obtained:

1. the supervision and management are difficult: the method has the advantages that the method is wide in operation area, complex in personnel, difficult in effective overall management and control due to outdoor operation, complex in safety regulation and less in supervision personnel, and mainly depends on manual supervision and subjective compliance of the operation personnel;

2. the safety supervision means is weak: the protection measures depend on safety measures, intelligent prompt and real-time supervision are lacked, the safety management means and mode are more traditional, and advanced technical means are lacked;

3. the monitoring blind area is big: monitoring personnel are responsible for dozens to hundreds of cameras, real-time monitoring for 24 hours cannot be realized, more monitoring blind areas exist, the functions of playback and retrieval after accidents can be achieved, and the functions of early warning, tracking and warning reminding are not provided;

4. the outsourcing personnel are difficult to manage: outsourcing team has high mobility, personnel safety consciousness is uneven, the problems that safety protection articles for entry personnel are not completely worn, the quality is poor, safety training personnel are not on duty and the like exist, and the management and control difficulty is high.

Disclosure of Invention

The application discloses a system and a method for managing the safety production of an electric power enterprise, which realize the safety production and management of the electric power enterprise by monitoring a walking route and monitoring working behaviors.

In order to achieve the above purpose, the present application provides the following solutions:

an electric power enterprise safety production management system, the system comprising: the system comprises a data acquisition module, a model construction module, a route identification module, a behavior identification module and an alarm module;

the data acquisition module is used for acquiring worker and vehicle information, worker route images and behavior data;

the model construction modeling is used for constructing a route safety model and a behavior unsafe model;

the route identification module is used for monitoring whether the current worker walking route and the vehicle running route violate rules or not;

the behavior identification module is used for monitoring whether the current behavior of the worker violates rules or not;

the alarm module is used for alarming violation phenomena.

Optionally, the data acquisition module further includes:

the data acquisition module comprises a worker and vehicle information acquisition submodule, a worker route image acquisition submodule and a behavior data acquisition submodule;

the worker and vehicle information acquisition submodule is used for acquiring worker basic information and factory vehicle basic information;

the worker route image acquisition submodule is used for extracting a safe walking route of a worker;

the behavior data acquisition submodule is used for acquiring data of the behaviors of workers.

Optionally, the model building module further includes: a route safety model construction submodule and a behavior insecurity model construction submodule;

the worker route image acquisition submodule extracts a safe walking route of a worker; the behavior insecurity model construction submodule is used for constructing an original image of an insecurity behavior; and constructing a behavior unsafe model.

Optionally, the route safety model building submodule specifically includes:

the route safety model construction sub-module is provided with a plurality of target points in the marked open area and stores the target points, the distances between the target points are uniform, and the target points gradually extend to a distance along the open area;

according to the position of a video tracking worker, generating a walking route of the worker in a factory, wherein when the worker passes through the target point, the target point value is 1, otherwise, the target point value is 0;

collecting a connecting line of a target point with a value of 1 for safe passing of workers in an open area, and constructing a road risk relation according to basic road information of the open area;

calculating the comprehensive road risk of each connecting line according to the connecting line of the target point with the safe passing value of 1 of the worker in the open area;

preferentially selecting a route with low comprehensive road risk as a safe walking route;

and training the safe walking route as a training set to construct a route safety model.

Optionally, the behavioral insecure model building submodule specifically includes:

acquiring a large number of original images of unsafe behaviors of workers; marking the type and the position of unsafe behavior on each image, and establishing an unsafe behavior label image; and constructing a behavior unsafe model.

Optionally, the worker unsafe behavior includes:

the safety belt is not used for high-altitude operation, and the safety belt for high-altitude operation is not hung on a firm component;

the safety helmet is not worn during high-altitude operation;

the construction method is characterized in that the construction method is carried out on light and simple-structure roofs of asbestos tiles, linoleum, reed foils and the like;

the welder does not use a fireproof safety belt;

climbing scaffolds, vertical derricks and the like along ropes and scaffold rods;

resting or leaning on the railing on a high platform, the edge of the hole and the safety net;

taking a cargo-carrying suspension cage;

performing high-altitude operation when thunderstorm, rainstorm, dense fog and wind power are more than or equal to five levels;

entering the site without wearing safety helmets;

working or walking under the hoisted object or under the hoisting arm;

the wearing of the safety helmet is not standard;

passing through the security alert area without authorization;

the walking path is not walked, and the walking path spans or stands on the belt;

a steel rope crossing running equipment such as a coal conveyor and a winch;

when the transport machinery is not stopped stably or moved, the personnel transfer the objects up and down;

machine for sitting, standing and walking on protective cover of rotating and driving part of machine or operating by touching with hand

Transporting personnel with a crane, gripper or other cargo carrying equipment;

manually cleaning the sticky coal on the belt roller or performing other cleaning work on the equipment during operation;

smoking in the first and second stage fire regions;

welding containers and pipelines with pressure, electrification and oil filling;

carrying out electric welding and gas welding in a closed container;

various motor vehicles which are not approved enter the inflammable and explosive area;

the welder does not use a fireproof safety belt;

flammable and explosive materials and dangerous chemicals are discharged on site.

Optionally, the route identifying module specifically includes:

and detecting the walking route of each worker by using the constructed route safety model, judging that the walking route is wrong if the walking route of the worker exceeds the route safety model or is too close to the left and right boundaries, and alarming the walking route.

A power enterprise safety production management method is characterized by comprising the following steps:

s1, collecting worker and vehicle information, worker route images and behavior data;

s2, constructing a route safety model and a behavior unsafe model;

s3, monitoring whether the current worker walking route and the vehicle running route break rules or not;

s4, monitoring whether the current behavior of the worker violates rules or not;

and S5, alarming the violation phenomenon.

The beneficial effect of this application does:

the method and the system can effectively control unsafe behaviors of people, effectively stop safety production accidents, timely block unsafe behaviors of people, improve safety management and safety supervision capabilities, improve safety management and safety supervision, realize a safety policy of 'cherishing life by people' in a real sense, and can be popularized and applied in high-risk industries such as electric power and the like or high-risk operation scenes.

Drawings

In order to more clearly illustrate the technical solution of the present application, the drawings needed to be used in the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for a person skilled in the art to obtain other drawings without any inventive exercise.

Fig. 1 is a system flowchart of a safety production management system of an electric power enterprise according to an embodiment of the present application;

fig. 2 is a method step diagram of a power enterprise safety production management method according to a second embodiment of the present application.

The specific implementation mode is as follows:

the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present application without making any creative effort belong to the protection scope of the present application.

In order to make the aforementioned objects, features and advantages of the present application more comprehensible, the present application is described in further detail with reference to the accompanying drawings and the detailed description.

Example one

In the first embodiment, as shown in fig. 1, a system and a method for managing safety production of an electric power enterprise specifically include: the system comprises a data acquisition module, a model construction module, a route identification module, a behavior identification module and an alarm module.

The data acquisition module comprises a worker and vehicle information acquisition module, a worker route image acquisition submodule and a behavior data acquisition submodule;

the worker and vehicle information acquisition module is used for acquiring worker basic information and factory vehicle basic information. The clothes of each worker are provided with the work number of the worker, the facial information, the height, the name, the sex and the basic information of the work number of the worker are collected, and a worker information comparison library is created. The plant vehicle basic information includes: the method comprises the following steps of (1) establishing a vehicle information comparison library by using a vehicle license plate number, a vehicle department, a vehicle appearance and a vehicle color; the worker route image acquisition submodule extracts the safe walking route of the worker, and specifically comprises: extracting a video or a two-dimensional image of the whole factory, extracting an obstacle area and marking the obstacle area, and extracting an open area and marking a walkable area; the behavior data acquisition submodule is used for acquiring behavior images of a large number of different workers.

The model building module comprises a route safety model building submodule and a behavior insecurity model building submodule;

the route safety model construction sub-module is used for setting a plurality of target points in the marked open area and storing the target points, and the target points are uniformly spaced and gradually extend to a distance along the open area; according to the position of a video tracking worker, generating a walking route of the worker and a vehicle in a factory, when the worker and the vehicle pass through the target point, the target point value is 1, otherwise, the target point value is 0, collecting a connecting line of the target point with the safe passing value of 1 of the worker and the vehicle in an open area, and constructing a road risk relation according to basic road information of the open area, wherein the basic road information comprises the position of a road, including the starting position of the road, the ending position of the road, the boundary position of the road and the position of a reference line of the road, the reference line of the road can be a center line of the road, and the starting position and the ending position of the curved road can be preset, so that a target road area is determined according to the basic road information. The road risk relationship may be constructed based on different coordinate systems, the coordinate origin may be the current target position or the starting position of the center line of the target road, and the like, which is not limited herein specifically, and the following cartesian coordinate system is introduced as an example. The calculation method of the road risk field is as follows:

wherein k is _l ，k _r The intensity values of the left boundary risk field and the right boundary risk field of the road respectively represent risk assessment values of the road boundary, the larger the value is, the higher the risk is when the value is close to the road boundary, the value can be determined by simulation experience debugging, and the specific value is not limited here.

Y _bi (s), i ∈ {1, r } respectively represent road left and right boundary values, and:

wherein D is the road width, f _cx And f _cy The Cartesian coordinates of the center line of the road are a function of the length s of the corresponding center line, which means that if the position is closer to the left and right boundaries of the road, the corresponding risk value is larger and larger, and the purpose of restricting workers and vehicles from walking within the range of the safe road is achieved. The subscript i may take the value of l or r, representing the left boundary Y _bl And the right boundary Y _br 。

And calculating the comprehensive road risk of each connecting line according to the connecting line of the target point with the value of 1, which is safely passed by workers and vehicles in the open area. And selecting the route with low comprehensive road risk preferentially as a safe walking route. And training the safe walking route as a training set to construct a route safety model.

The behavior insecurity model construction submodule comprises: acquiring a large number of original images of unsafe behaviors of workers; marking the type and the position of unsafe behavior on each image, and establishing an unsafe behavior label image; and constructing a behavior unsafe model, wherein the behavior unsafe model is a Zeiler and Fergus convolutional neural network model, and the deep learning algorithm is FasterR-CNN. Dividing the label images into a training set and a verification set, inputting the training set into a target detection model for training, judging whether a loss function meets the limit, if so, verifying an input behavior unsafe model of the verification set, judging whether the number of times of training is reached or is smaller than a limit error, judging whether the type and the position of unsafe behavior are accurately detected, accurately finishing the training, and if not, returning to retraining; if the limit is not met, retraining is carried out, the splitting ratio of the training set to the verification set is 1, and the loss function is as follows:

comparison loss function:

specifically, unsafe behavior of the worker includes the following situations:

(1) The safety belt is not used for high-altitude operation, and is not hung on a firm component;

(2) The safety helmet is not worn during high-altitude operation;

(3) The construction method is characterized in that the construction method is carried out on light and simple-structure roofs of asbestos tiles, linoleum, reed foils and the like;

(4) The welder does not use a fireproof safety belt;

(5) Climbing scaffolds, vertical derricks and the like along ropes and scaffold rods;

(6) Resting or leaning on the railing on a high platform, the edge of the hole and the safety net;

(7) Taking a cargo-carrying cage;

(8) The ladder is erected on an unstable support to work;

(9) Performing high-altitude operation when thunderstorm, rainstorm, dense fog and wind power are more than or equal to five levels;

(10) The safety helmet is not worn when the vehicle enters the site;

(11) Working or walking under the hoisted object or under the hoisting arm;

(12) The wearing of the safety helmet is not standard;

(13) Passing through the security alert area without authorization;

(14) The walking path is not walked, and the walking path crosses or stands on the belt;

(15) A steel rope crossing running equipment such as a coal conveyor and a winch;

(16) When the transport machinery is not stopped stably or moved, the personnel transfer the objects up and down;

(17) Machine for sitting, standing and walking on protective cover of rotating and driving parts of machinery or operating by touching with hands

(18) Transporting personnel with a crane, gripper or other cargo carrying equipment;

(19) During operation, the sticky coal on the belt roller is manually cleaned or other cleaning work is carried out on the equipment;

(20) Smoking in the first and second stage fire regions;

(21) Welding a container and a pipeline with pressure, electrification and oil filling;

(22) Carrying out electric welding and gas welding in a closed container;

(23) Various motor vehicles which are not approved enter the inflammable and explosive area;

(24) The welder does not use a fireproof safety belt;

(25) Flammable and explosive materials and dangerous chemicals are discharged on site.

The route identification module detects the walking route of each worker by using the constructed route safety model, judges that the walking route is wrong if the walking route of the worker exceeds the route safety model or is too close to the left boundary and the right boundary, and sends out a walking route alarm. Of course, the embodiment can identify and not only can identify the walking route of the worker, but also can create a vehicle route safety model to monitor the walking route of the vehicle.

The behavior identification module identifies and monitors the behaviors of all workers by using the behavior unsafe model, wherein if the worker is monitored not to use a safety belt based on high-altitude operation, the high-altitude operation safety belt is not hung on a firm component; then alarming is carried out; if the worker is monitored not to wear the safety helmet in the high-altitude operation, an alarm is given; if monitoring that a worker stands on a light and simple structure roof such as asbestos tiles, linoleum, reed foils and the like for construction, alarming; if the condition that the worker does not use the fireproof safety belt is monitored, an alarm is given; if monitoring that workers climb scaffolds, vertical derricks and the like along ropes and scaffold rods, alarming is carried out; if the monitoring shows that the worker has a rest or leans on the handrail on a high platform, the edge of the hole and the safety net, an alarm is given; if monitoring that the worker takes the cargo-carrying cage, alarming; if the condition that the worker ladder is erected on an unstable support to work is monitored, alarming is carried out; if monitoring that the worker performs high-altitude operation when thunderstorm, rainstorm, dense fog and wind power are more than or equal to five levels, alarming; if the condition that the worker enters the site and does not wear a safety helmet is monitored, an alarm is given; if the worker is monitored to operate or walk under the hoisted object or the hoisting arm, an alarm is given; if the situation that the wearing of the safety helmet of the worker is not standard is monitored, an alarm is given; if the condition that the worker passes through the safety warning area without permission is monitored, an alarm is given; if the condition that the worker does not walk on the traffic lane, cross over the belt or stand on the belt is monitored, an alarm is given; if the steel ropes of the operating equipment such as a coal conveyor and a winch are monitored to be crossed by a worker, alarming is carried out; if the condition that the worker transport machinery is not stably stopped or moved is monitored, the worker transfers objects up and down, and then an alarm is given; if monitoring that the worker sits, stands and walks on the protective cover of the rotation and transmission part of the machine or touches the machine in operation with a hand, alarming is carried out; if monitoring that the worker transports the personnel by a hanging head, a grabbing head or other cargo carrying equipment, alarming; if monitoring that workers manually clean the sticky coal on the belt roller or perform other cleaning work on the equipment in the running process, alarming; if the condition that the worker smokes in the first-stage and second-stage fire areas is monitored, an alarm is given; if the condition that workers weld the pressure, electrified and oil-filled container and pipeline is monitored, alarming; if monitoring that the workers simultaneously carry out electric welding and gas welding in the closed container, alarming; if various motor vehicles which are not approved by workers are monitored to enter the inflammable and explosive area, alarming is carried out; if the condition that the worker does not use the fireproof safety belt is monitored, an alarm is given; and if monitoring that the workers discharge flammable and explosive materials and dangerous chemicals on site, alarming.

The alarm module comprises a walking route alarm submodule and a behavior non-standard alarm submodule.

When the walking route alarm information is received, if the walking route of a worker is not standard, the human face is recognized through machine vision, searching and inquiring are carried out according to the human face recognition and the worker information comparison base, after the worker is locked, the illegal image of the worker is projected to a factory large screen, and the work number and the name of the worker are broadcasted. And after the staff returns to the safe route, the large-screen image is cancelled, and the broadcasting is stopped. If the vehicle running route is not standard, the license plate number is identified according to machine vision, comparison and search are carried out on the license plate number and a vehicle comparison library, the illegal vehicle is projected to a large screen, the license plate number of the vehicle is broadcasted, after the vehicle returns to a safe route, the large screen image is cancelled, and broadcasting is stopped.

When receiving the behavior non-standard alarm information, the method comprises the following steps: the face is identified through machine vision, searching and inquiring are carried out according to the face identification and worker information comparison library, after a person is locked, an illegal image of the person is projected to a factory large screen, and the job number and the name of the person are broadcasted. And after the staff returns to the safe route, the large-screen image is cancelled, and the broadcasting is stopped.

Example two

A method for managing safety production of an electric power enterprise, as shown in fig. 2, includes:

s1, an acquisition module is used for acquiring information of workers and vehicles, images of worker routes and behavior data;

s2, constructing a route safety model and a behavior unsafe model;

s3, monitoring whether the current worker walking route and the vehicle running route are illegal or not;

s4, monitoring whether the current behavior of the worker violates rules or not;

and S5, alarming the violation phenomenon.

The above-described embodiments are merely illustrative of the preferred embodiments of the present application, and do not limit the scope of the present application, and various modifications and improvements made to the technical solutions of the present application by those skilled in the art without departing from the spirit of the present application should fall within the protection scope defined by the claims of the present application.

Claims (8)

1. An electric power enterprise safety production management system, characterized in that, the system includes: the system comprises a data acquisition module, a model construction module, a route identification module, a behavior identification module and an alarm module;

the data acquisition module is used for acquiring worker and vehicle information, worker route images and behavior data;

the model construction module is used for constructing a route safety model and a behavior insecurity model based on the collected worker route images and the behavior data;

the route identification module is used for monitoring whether the current worker walking route and the vehicle running route violate rules or not according to the route safety model;

the behavior identification module is used for monitoring whether the current worker behavior violates rules or not according to the behavior insecurity model;

the alarm module is used for alarming violation phenomena.

2. The system for managing the safety production of the power enterprise as claimed in claim 1, wherein the data collection module further comprises:

the data acquisition module comprises a worker and vehicle information acquisition submodule, a worker route image acquisition submodule and a behavior data acquisition submodule;

the worker and vehicle information acquisition submodule is used for acquiring worker basic information and factory vehicle basic information;

the worker route image acquisition submodule is used for extracting a safe walking route of a worker;

the behavior data acquisition submodule is used for acquiring data of the behaviors of workers.

3. The system according to claim 2, wherein the model building module further comprises: a route safety model construction submodule and a behavior insecurity model construction submodule;

the worker route image acquisition submodule extracts a safe walking route of a worker; the behavior insecurity model construction submodule is used for constructing an original image according to insecurity behaviors; and constructing a behavior unsafe model.

4. The electric power enterprise safety production management system according to claim 3, wherein the route safety model building submodule specifically comprises:

the route safety model construction sub-module is provided with a plurality of target points in the marked open area and stores the target points, and the target points are uniformly spaced and gradually extend to a distance along the open area;

according to the position of a video tracking worker, generating a walking route of the worker in a factory, wherein when the worker passes through the target point, the target point value is 1, otherwise, the target point value is 0;

collecting a connecting line of a target point with a value of 1 for safe passing of workers in an open area, and constructing a road risk relation according to basic road information of the open area;

calculating the comprehensive road risk of each connecting line according to the connecting line of the target point with the safe passing value of 1 of the worker in the open area;

selecting a route with low comprehensive road risk preferentially as a safe walking route;

and training the safe walking route as a training set to construct a route safety model.

5. The power enterprise safety production management system according to claim 3, wherein the behavior insecure model building submodule specifically comprises:

acquiring an original image of unsafe behaviors of workers; marking the type and the position of unsafe behavior on each image, and establishing an unsafe behavior label image; and constructing a behavior unsafe model.

6. The power enterprise safety production management system of claim 5, wherein the worker unsafe behavior comprises:

the safety belt is not used for high-altitude operation, and is not hung on a firm component;

the safety helmet is not worn during high-altitude operation;

the construction method is characterized in that the construction method is carried out on light and simple-structure roofs of asbestos tiles, linoleum, reed foils and the like;

the welder does not use a fireproof safety belt;

climbing scaffolds, vertical derricks and the like along ropes and scaffold rods;

resting or leaning on the railing on a high platform, the edge of the hole and the safety net;

taking a cargo-carrying suspension cage;

performing high-altitude operation when thunderstorm, rainstorm, dense fog and wind power are more than or equal to five levels;

the safety helmet is not worn when the vehicle enters the site;

working or walking under the hoisted object or under the hoisting arm;

the wearing of the safety helmet is not standard;

passing through the security alert area without authorization;

the walking path is not walked, and the walking path spans or stands on the belt;

a steel rope crossing running equipment such as a coal conveyor and a winch;

when the transport machinery is not stopped stably or moved, the personnel transfer the objects up and down;

machine for sitting, standing and walking on protective cover of rotating and driving part of machine or operating by touching with hand

Transporting personnel with a crane, gripper or other cargo carrying equipment;

manually cleaning the sticky coal on the belt roller or performing other cleaning work on the equipment during operation;

smoking in the first and second stage fire regions;

welding containers and pipelines with pressure, electrification and oil filling;

carrying out electric welding and gas welding in a closed container;

various motor vehicles which are not approved enter the inflammable and explosive area;

the welder does not use a fireproof safety belt;

flammable and explosive materials and dangerous chemicals are discharged on site.

7. The system for managing the safety production of the power enterprise as claimed in claim 1, wherein the route identification module specifically comprises:

and detecting the walking route of each worker by using the constructed route safety model, judging that the walking route is wrong if the walking route of the worker exceeds the route safety model or is too close to the left and right boundaries, and alarming the walking route.

8. A power enterprise safety production management method is characterized by comprising the following steps:

s1, collecting worker and vehicle information, worker route images and behavior data;

s2, constructing a route safety model and a behavior unsafe model;

s3, monitoring whether the current worker walking route and the vehicle running route are illegal or not;

s4, monitoring whether the current behavior of the worker violates rules or not;

and S5, alarming the violation phenomenon.

Images