CN112907105B

CN112907105B - Early warning method and device based on service scene

Info

Publication number: CN112907105B
Application number: CN202110266586.6A
Authority: CN
Inventors: 陈彩娜; 潘岐深; 陈慧坤; 张壮领; 李华; 李斌; 郑松源
Original assignee: Guangdong Power Grid Co Ltd
Current assignee: Guangdong Power Grid Co Ltd
Priority date: 2021-03-10
Filing date: 2021-03-10
Publication date: 2023-01-20
Anticipated expiration: 2041-03-10
Also published as: CN112907105A

Abstract

The invention discloses an early warning method and device based on a service scene, wherein the early warning method comprises the following steps: constructing a model by using the collected information of the business scene, and storing the model to a cloud; acquiring field information of a current service scene in real time by using an AR device, transmitting the field information to a cloud, and identifying a target in the current service scene according to the model; and judging whether the safety state of the target meets preset regulations or not, and if not, outputting early warning information to the AR equipment in real time. According to the method, the wearable AR equipment is used, the image recognition and space positioning technology is combined to perform real-time early warning on the dangerous situation in the current service scene, and the personal safety of service personnel is effectively guaranteed.

Description

Early warning method and device based on service scene

Technical Field

The invention relates to the technical field of data processing, in particular to an early warning method and device based on a service scene.

Background

The transformer in the transformer area is important equipment in a distribution network, and plays an important role in distributing and transmitting electric energy to users in the transformer area, the life and production of the users in the transformer area, such as residents, schools, enterprises and the like are directly influenced by the transformer in the transformer area due to faults of the transformer in the transformer area, and the transformer in the transformer area is important to guarantee the safety of the transformer in the emergency repair process because the transformer in the transformer area relates to high-risk operation.

At present, the existing maintenance early warning method mainly monitors equipment and operators in a fixed scene in real time through various sensors, so as to judge danger information in the working process. However, the scene, equipment and personnel organization of the emergency repair of the power equipment are not fixed, and the existing early warning method cannot be applied to the emergency repair scene with dynamic change, so that real-time early warning prompt cannot be provided.

Disclosure of Invention

In order to solve the technical problems, the invention provides an early warning method and device based on a service scene, which achieve early warning of dangerous conditions in the scene by acquiring and analyzing service scene information through an AR device.

The invention provides a service scene-based early warning method, which comprises the following steps:

constructing a model by using the collected information of the business scene, and storing the model to a cloud;

acquiring field information of a current service scene in real time by using an AR device, transmitting the field information to a cloud end, and identifying a target in the current service scene according to the model;

and judging whether the safety state of the target meets preset regulations or not, and if not, outputting early warning information to the AR equipment in real time.

Optionally, after identifying the target in the current service scenario according to the model, the method further includes: and transmitting the target to the AR equipment, and marking the target in the current service scene acquired by the AR equipment in real time.

Optionally, the model comprises a Fast-RNN model.

Optionally, the method further includes: and emitting rays to the target area from the center of the AR equipment, and obtaining the field distance between the target and the AR equipment according to the intersection point of the rays and the target.

Optionally, if multiple AR devices exist in the field of the current service scene, the early warning information is synchronously output to the multiple AR devices.

The invention also provides a warning device based on the service scene, which comprises:

the model building module is used for building a model by utilizing the collected information of the business scene and storing the model to the cloud;

the target identification model is used for acquiring the field information of the current business scene in real time by utilizing the AR equipment, transmitting the field information to the cloud end and identifying a target in the current business scene according to the model;

and the real-time early warning module is used for judging whether the safety state of the target meets preset regulations or not, and if not, outputting early warning information to the AR equipment in real time.

Optionally, the apparatus further comprises: and if a plurality of AR devices exist on the site of the current service scene, synchronously outputting the early warning information to the plurality of AR devices.

Optionally, after identifying the target in the current service scene according to the model, the method further includes: and transmitting the target to the AR equipment, and marking the target in the current service scene acquired by the AR equipment in real time.

Optionally, the apparatus further comprises: and emitting rays to the target area from the center of the AR equipment, and obtaining the field distance between the target and the AR equipment according to the intersection point of the rays and the target.

The present invention also provides a computer-readable storage medium, on which a computer program is stored, which, when executed by a processor, implements the service scenario-based warning method as described in any of the above.

Compared with the prior art, the invention has the beneficial effects that:

the early warning method and the early warning device based on the service scene utilize AR equipment to acquire and identify the field target of the current service scene, further judge the safety state of the target, send out early warning information according to the judgment result and realize the field real-time monitoring of different emergency repair scenes; meanwhile, the model is used for identifying and analyzing the dangerous state of the on-site target, so that the accuracy and timeliness of danger judgment can be effectively improved, and the personal safety of business personnel can be guaranteed.

Drawings

In order to more clearly illustrate the technical solution of the present invention, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.

Fig. 1 is a schematic flow diagram of an early warning method based on a service scenario according to an embodiment of the present invention;

fig. 2 is a schematic structural diagram of an early warning device based on a service scenario according to an embodiment of the present invention.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

It should be understood that the step numbers used herein are for convenience of description only and are not intended as limitations on the order in which the steps are performed.

It is to be understood that the terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in the specification of the present invention and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.

The terms "comprises" and "comprising" indicate the presence of the described features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.

The term "and/or" refers to any and all possible combinations of one or more of the associated listed items and includes such combinations.

As shown in fig. 1, an embodiment of the present invention provides a service scenario-based early warning method, which includes the following steps.

S11: and constructing a model by using the collected information of the business scene, and storing the model to a cloud.

For a target service scene, information such as environment and equipment in the scene can be collected firstly, and the image recognition algorithm is utilized to model the partial information to obtain a model for recognizing coordinate values and categories of targets in the service scene.

In this embodiment, the model comprises a Fast-RNN model.

S12: and acquiring the field information of the current service scene in real time by utilizing the AR equipment, transmitting the field information to the cloud, and identifying the target in the current service scene according to the model.

In one embodiment, after identifying the target in the current business scenario according to the model, the method further comprises: and transmitting the target to the AR equipment, and marking the target in the current service scene acquired by the AR equipment in real time.

Specifically, when a certain device is selected as a target, after the target device is identified in the current service scene, the information of the target device may be transmitted to the AR device, and the target device is highlighted in the view of the current service scene of the AR device.

In this embodiment, a ray may be sent from the center of the AR device to the target area, and the on-site distance between the target and the AR device may be obtained according to an intersection of the ray and the target.

The position of the target in the space can be positioned by the method, and the accurate actual distance between the target and the AR equipment is further calculated.

S13: and judging whether the safety state of the target meets preset regulations or not, and if not, outputting early warning information to the AR equipment in real time.

In this embodiment, if a plurality of AR devices exist on the site of the current service scene, the early warning information is synchronously output to the plurality of AR devices, so as to keep information intercommunication and sharing, and ensure the synchronism and real-time performance of the early warning information.

Another embodiment of the invention provides an early warning method based on a service scene, which is applied to emergency repair operation of a transformer in a transformer area as an example.

For each transformer in the transformer area, image acquisition is required to be performed on the surrounding environment and equipment information corresponding to each transformer in the transformer area, a reusable equipment library and a reusable scene library are established, and a model is established for identifying and classifying a target area in a scene of emergency repair of the transformer in the transformer area.

Specifically, the environmental information mainly comprises a transformer of a transformer area, a distribution box, a pole tower, a cross arm, a distribution line, a road or a highway; the equipment information comprises a transformer of a transformer area, high-low voltage grounding wires, a crane, a safety warning board and the like.

Specifically, image information of each angle of equipment to be replaced and rush-repaired of a transformer in a transformer area needs to be acquired, and the equipment comprises the transformer, a rack, a distribution box, an engineering truck, a fence, a drop-out fuse, a power testing rod, a guide chain, a pulley and the like.

After image acquisition is completed, an acquired image information set is divided into three parts which are respectively used for model training, model primary verification and model secondary verification. Firstly, performing model training on an image for training through a Fast R-CNN network structure to obtain a predicted value of a target area in the image and a category to which the target area belongs, judging the accuracy of a classification result by using a cross entropy loss function, enabling the cross entropy loss function result to be as close to 0 as possible by continuously adjusting network structure parameters to obtain a model with higher classification accuracy, and finally storing the model to the cloud.

For the transformer in the transformer area to be rush-repaired, after rush-repair personnel arrive at the site, the AR equipment is used for collecting image information of the site, the collected image information is transmitted to the cloud end, and scene characteristics of the operation site are identified.

The cloud end analyzes the acquired image information by using the trained model, identifies the category and the position of the target in the image, and feeds the category and the position of the target in the image back to the front-end AR equipment.

The front-end AR equipment utilizes the fed-back information to highlight the target in the equipment visual field, and meanwhile, the distance and the relative position between the target and the AR equipment of rush-repair personnel are accurately calculated by utilizing rays emitted by the AR equipment to the target.

Before beginning to salvage the operation, need to discern the potential safety hazard that exists at the scene: the emergency repair personnel carry AR equipment to scan the surrounding environment of the site, and the preset model is used for identifying the target in the scene.

Specifically, when the target is set as a high-voltage fuse, judging whether the high-voltage fuse in the current scene is disconnected or not by using a preset model, if the state of the high-voltage fuse is not disconnected, highlighting the high-voltage fuse in red in the visual field of the AR equipment, and synchronously displaying the output early warning information; when the target is set as a high-voltage and low-voltage grounding wire, whether the high-voltage and low-voltage grounding wire is installed on the site or not is judged by using a preset model, and if the high-voltage and low-voltage grounding wire does not exist in the current scene, corresponding early warning information appears in the field of view of the AR equipment. By using the method, the potential safety hazard of the emergency repair site can be accurately checked in real time, and the working efficiency of emergency repair workers is improved.

In the process of carrying out urgent repair operation, the danger hidden danger of urgent repair personnel and equipment needs to be identified: the AR equipment is used for identifying and positioning the position of the rush-repair personnel in the current scene in real time, the actions of the rush-repair personnel are synchronously captured, the distance between the rush-repair personnel and the electrified equipment is dynamically calculated, and if the distance is smaller than a preset safety critical value, early warning information is output to the AR equipment. Meanwhile, a dangerous falling area needs to be dynamically calculated according to the length of the suspension arm of the on-site crane and the lifting range, and if a person steps out of the dangerous falling area of the current crane, early warning information is output to AR equipment in real time, so that the personal safety of emergency repair and operating personnel is ensured.

In addition, need early warning scene still includes: the rush-repair operation site occupies a motor vehicle lane.

For the same first-aid repair operation site, when all personnel log in AR equipment, the same token value (token) is used, so that when everybody is in the same scene, information can be kept intercommunicated and shared.

When one AR device receives the early warning information, the AR devices of all the personnel in the scene can receive the early warning information in real time, and timeliness and synchronism of the early warning information are guaranteed.

As shown in fig. 2, another embodiment of the present invention further provides a warning device based on a service scenario, which includes a model building module 101, a target recognition model 102, and a real-time warning module 103.

The model building module 101 is configured to build a model by using the collected information of the service scenario, and store the model to the cloud.

The target identification model 102 is configured to acquire field information of a current service scene in real time by using an AR device, transmit the field information to a cloud, and identify a target in the current service scene according to the model.

The real-time early warning module 103 is configured to determine whether the safety state of the target meets a preset rule, and if not, output early warning information to the AR device in real time.

Because the content of information interaction, execution process, and the like among the modules in the device is based on the same concept as the method embodiment of the present invention, specific content can be referred to the description in the method embodiment of the present invention, and is not described herein again.

Embodiments of the present invention further provide a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the method according to any one of the above embodiments.

It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above may be implemented by instructing relevant hardware by a computer program, where the computer program may be stored in a computer-readable storage medium, and when executed, the computer program may include the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.

While the foregoing is directed to the preferred embodiment of the present invention, it will be understood by those skilled in the art that various changes and modifications may be made without departing from the spirit and scope of the invention.

Claims

1. An early warning method based on a service scene is characterized by comprising the following steps:

constructing a model by using the collected information of the business scene, and storing the model to a cloud end;

transmitting the target to the AR equipment, and marking the target in a current service scene acquired by the AR equipment in real time;

emitting rays to the target area from the center of the AR equipment, and obtaining the field distance between the target and the AR equipment according to the intersection point of the rays and the target;

judging whether the safety state of the target accords with preset regulations or not, if not, outputting early warning information to the AR equipment in real time, and the method comprises the following steps:

identifying the target by using the model, and judging whether potential safety hazards exist on the site according to the identified target state;

positioning the position of an emergency repair worker in the service scene according to the site distance, synchronously capturing the action of the emergency repair worker by utilizing the AR equipment, dynamically calculating the distance between the emergency repair worker and the identified electrified target by utilizing the model, comparing the distance with a preset safety critical value, and judging whether the emergency repair worker has potential safety hazard;

acquiring the length and the lifting range of a suspension arm of a field crane by using the AR equipment, dynamically calculating a dangerous falling region by using the model, acquiring the position relation between rush-repair personnel and the dangerous falling region according to the positions of the rush-repair personnel in the service scene, and judging whether the rush-repair personnel has potential safety hazards or not according to the position relation;

and outputting early warning information in real time by using the model according to the potential safety hazard, and sending the early warning information to the AR equipment.

2. The traffic scenario-based alert method of claim 1, wherein the model comprises a Fast-RNN model.

3. The service scenario-based early warning method according to claim 1, further comprising:

and if a plurality of AR devices exist on the site of the current service scene, synchronously outputting the early warning information to the plurality of AR devices.

4. An early warning device based on a service scene is characterized by comprising:

the target identification model is used for acquiring the field information of the current business scene in real time by utilizing the AR equipment, transmitting the field information to the cloud end and identifying a target in the current business scene according to the model; transmitting the target to the AR equipment, and marking the target in a current service scene acquired by the AR equipment in real time; emitting rays to the target area from the center of the AR equipment, and obtaining the field distance between the target and the AR equipment according to the intersection point of the rays and the target;

the real-time early warning module is used for judging whether the safety state of the target accords with preset regulations or not, if not, then outputs early warning information to the AR equipment in real time, and comprises:

identifying the target by using the model, and judging whether potential safety hazards exist on the site or not according to the identified target state;

positioning the position of the rush-repair personnel in the service scene according to the field distance, synchronously capturing the actions of the rush-repair personnel by utilizing the AR equipment, dynamically calculating the distance between the rush-repair personnel and the identified electrified target by utilizing the model, comparing a preset safety critical value with the distance, and judging whether the rush-repair personnel has potential safety hazards or not;

and outputting early warning information in real time by using the model according to the potential safety hazard and sending the early warning information to the AR equipment.

5. The warning device based on service scene as claimed in claim 4, further comprising:

6. A computer-readable storage medium, on which a computer program is stored, wherein the computer program, when executed by a processor, implements the service scenario-based alert method according to any one of claims 1 to 3.