A wearable battery furnace foreman behavior recognition system

Abstract

The present application relates to the technical field of behavior recognition, and is a wearable coke oven front worker behavior recognition system, comprising: a wearable collection unit for collecting working process images and behavior acceleration and angular velocity data of the front worker; a control unit for receiving the working process images and acceleration and angular velocity data acquired by the wearable collection unit, and identifying and capturing the features of abnormal events in behavior, posture and timing through a data fusion algorithm model based on vision and high-precision acceleration sensors and gyroscopes, and analyzing whether the behavior of the front worker is abnormal; and a sending unit for sending a shutdown signal to a device-side receiving unit when it is detected that the behavior of the front worker is abnormal. The present application extracts the behavior and posture features of the front worker by acquiring picture information and acceleration and angular velocity data, comprehensively recognizes and determines the behavior and posture changes of the human body, and thus infers the safety behavior of the front worker in the production operation process, so as to realize a method for accurately protecting the coke oven front worker.

Description

Technical Field

[0001] This invention relates to the field of behavior recognition technology, and in particular to a wearable coke oven worker behavior recognition system. Background Technology

[0002] To ensure coking production cycles and capacity, the coking industry has a bad habit of having coking oven machinery, door removal, and head and tail coke handling mechanisms operate in conjunction with furnace operators. However, current equipment monitors have blind spots and lack safety identification and protection technologies for furnace operators. As a result, equipment operation frequently causes injuries and fatalities to furnace operators, making coking oven operation a high-risk industry. Accurate identification and control of coking oven operators' safety has always been a difficult problem for the coking industry.

[0003] In the past, coke oven machinery, as a mobile unit assembly of multiple mechanisms, had some unit areas protected by means of grating, but the moving operation areas of the equipment traveling, door retrieval, and head and tail coke handling mechanisms overlapped with the furnace front operation area responsible for cleaning coke waste and treating flue dust. It was impossible to achieve hard isolation through grating. Currently, the protection of personnel during operations in this area is mostly based on fixed visual cameras on the side of the equipment or alarm sounds during operation. However, due to blind spots in visual monitoring or personnel not hearing the warning sounds, there are often no technical means to quickly stop the equipment in emergency situations such as collisions between the mechanism and personnel or sudden falls. This fails to meet the requirements of safe production and avoid accidents that could cause personal injury to personnel.

[0004] Therefore, there is a need to provide a method for detecting and identifying the behavior of furnace workers through wearable devices, combining the identification results to determine the behavioral characteristics and posture changes of the target human body, thereby inferring the safety of furnace workers during production operations, and feeding back the triggered danger alarm shutdown signal to the equipment-side control system in real time, so as to achieve precise protection for coke oven furnace workers. Summary of the Invention

[0005] To address the aforementioned technical problems, a wearable coke oven worker behavior recognition system is provided. This invention uses a wearable camera to collect image information, extracts the worker's posture changes, and then integrates acceleration and angular velocity data extracted by a wearable inertial measurement unit (IMU) to comprehensively identify and determine the worker's behavioral characteristics and posture changes. This allows for the inference of the worker's safe behavior during production operations, and the triggered hazard alarm results are fed back to the equipment control system in real time, achieving precise protection for coke oven workers.

[0006] The technical means employed in this invention are as follows:

[0007] A wearable coke oven worker behavior recognition system includes: a wearable acquisition unit, a wearable control unit, a wearable stop button, a wearable transmitting unit, and an equipment-side receiving unit. The wearable acquisition unit includes a camera and a wearable IMU (Inertial Measurement Unit) for acquiring image information and acceleration and angular velocity data of the worker's work process, and transmitting this data to the wearable control unit for anomaly identification. The wearable control unit receives the image information and acceleration and angular velocity data acquired by the acquisition unit, and uses a data fusion algorithm based on vision, acceleration sensors, and gyroscopes to identify and capture the behavioral, posture, and temporal characteristics of abnormal events, analyze and determine whether the worker's behavior is abnormal, and issue an anomaly signal. The wearable stop button manually sends a stop signal to the transmitting unit. The transmitting unit receives the abnormal worker behavior signal from the control unit and sends a stop signal to the receiving unit. The receiving unit receives the stop signal from the transmitting unit and triggers the cessation of actions of equipment mechanisms that could harm the worker.

[0008] Furthermore, the wearable control unit includes an edge controller and interface accessories.

[0009] Furthermore, the wearable IMU inertial measurement unit is used to collect the acceleration and angular velocity of the furnace worker in real time, and send the measured data to the edge controller. The edge controller converts the data into directly usable linear acceleration and body posture angle as the basis for judging continuous multi-dimensional abnormal behavior characteristics of the algorithm model.

[0010] Furthermore, the wearable edge controller can also receive image information of the furnace worker's work process, and through a data fusion algorithm model based on vision, acceleration sensors, and gyroscopes, identify and capture the characteristics of abnormal events in terms of behavior, posture, and timing, and analyze and determine whether the furnace worker's behavior is in an abnormal state. Furthermore, the wearable stop button is redundantly configured. In addition to using a data fusion algorithm model to identify abnormal patterns, the system also has a wearable manual stop button configured in parallel to quickly send a stop signal to the transmitting unit, thereby effectively protecting personal safety.

[0011] Compared with the prior art, the present invention has the following advantages: The wearable coke oven worker behavior recognition system provided by this invention is based on data acquisition from images, high-precision accelerometers, and gyroscopes. Through a data fusion algorithm model strategy based on vision and high-precision accelerometers and gyroscopes, it identifies and captures the behavioral, posture, and temporal characteristics of abnormal events, analyzes and determines whether the worker's behavior is in an abnormal state. It has the advantage of successfully identifying abnormal states from the daily work of workers in complex industrial scenarios with high precision. This advances personnel protection from simple video surveillance to more intelligent technological means, greatly enhancing the ability to identify abnormal behavior. Simultaneously, it moves the safety management checkpoint forward, realizing a transformation from passive response to proactive early warning, and from manual inspection to intelligent monitoring, constructing a solid technological protective wall. Ultimately, it achieves the goal of intelligently protecting the personal safety of coke oven workers and effectively overcomes the technical challenges of personal safety protection in the coking industry. Attached Figure Description

[0012] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 This is a flowchart of the wearable coke oven front-end worker behavior recognition system of the present invention.

[0014] Figure 2 This is an architecture diagram of the wearable coke oven front-end worker behavior recognition system in an embodiment of the present invention. Detailed Implementation

[0015] It should be noted that, unless otherwise specified, the embodiments and features described in the present invention can be combined with each other. The present invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0016] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The following description of at least one exemplary embodiment is merely illustrative and is in no way intended to limit the present invention or its application or use. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0017] It should be noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of exemplary embodiments according to the invention. As used herein, the singular form is intended to include the plural form as well, unless the context clearly indicates otherwise. Furthermore, it should be understood that when the terms "comprising" and / or "including" are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof.

[0018] Unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of the components and steps described in these embodiments do not limit the scope of the invention. It should also be understood that, for ease of description, the dimensions of the various parts shown in the drawings are not drawn to actual scale. Techniques, methods, and devices known to those skilled in the art may not be discussed in detail, but where appropriate, such techniques, methods, and devices should be considered part of the specification. In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not as limitations. Therefore, other examples of exemplary embodiments may have different values. It should be noted that similar reference numerals and letters in the following figures denote similar items; therefore, once an item is defined in one figure, it need not be further discussed in subsequent figures.

[0019] like Figure 1 As shown, this invention provides a wearable coke oven worker behavior recognition system, comprising: a wearable acquisition unit, a wearable control unit, a wearable transmitting unit, and an equipment-side receiving unit. The wearable acquisition unit includes a camera and a wearable IMU (Inertial Measurement Unit) for acquiring image information and acceleration and angular velocity data of the worker's work process, and transmitting this information to the wearable control unit for anomaly identification. The wearable control unit receives the image information and acceleration and angular velocity data acquired by the acquisition unit, and uses a data fusion algorithm model based on vision, acceleration sensors, and gyroscopes to identify and capture the behavioral, posture, and temporal characteristics of abnormal events, analyze and determine whether the worker's behavior is abnormal, and issue an anomaly signal. A wearable stop button is used to manually send a stop signal to the transmitting unit. The transmitting unit receives the abnormal worker behavior signal from the control unit and sends a stop signal to the receiving unit. The receiving unit receives the stop signal from the transmitting unit and triggers the cessation of actions of equipment mechanisms that could harm the worker.

[0020] During implementation, a head-mounted camera can be used to capture full-body images of the furnace worker.

[0021] In a specific implementation, as a preferred embodiment of the present invention, the wearable control unit includes an edge controller and interface accessories.

[0022] In a specific implementation, as a preferred embodiment of the present invention, the wearable IMU inertial measurement instrument is used to collect the acceleration and angular velocity of the furnace worker in real time, and send the measured data to the edge controller. The edge controller converts the data into linear acceleration and body posture angle that can be used directly, as the basis for judging the continuous multi-dimensional abnormal behavior of the algorithm model.

[0023] In a specific implementation, as a preferred embodiment of the present invention, the wearable edge controller can also receive image information of the furnace worker's work process, and through a data fusion algorithm model based on vision, acceleration sensors, and gyroscopes, identify and capture the characteristics of abnormal events in terms of behavior, posture, and timing, and analyze and lock whether the furnace worker's behavior is in an abnormal state. In a specific implementation, as a preferred embodiment of the present invention, the wearable stop button is redundantly configured. In addition to using a data fusion algorithm model to identify abnormal modes, the system also has a wearable manual stop button configured in parallel to quickly send a stop signal to the sending unit, so as to effectively protect personal safety.

[0024] Example like Figure 2 As shown, this invention provides a wearable coke oven pre-furnace worker behavior recognition system, the operation process of which is as follows: Before commencing operations, furnace operators must correctly trigger the start button on the wearable behavior recognition device.

[0025] Once the wearable recognition device starts up normally, it begins to continuously collect camera images to the edge controller and enters the intelligent algorithm posture recognition mode. When the algorithm identifies and determines that the furnace front worker's behavior is abnormal, it can trigger the stop button of the wearable recognition device and send a stop signal to the receiving unit on the device side.

[0026] As an IMU (Inertial Measurement Unit) for parallel attitude recognition, after the wearable behavior device enters the working mode, it collects the acceleration and angular velocity of the furnace worker in real time and sends the measured data to the edge controller. The controller converts these raw data into information such as linear acceleration and body posture angle that can be used directly. Once the algorithm determines an abnormal state of behavior posture by analyzing a series of continuous, multi-dimensional features, it can trigger the stop signal of the wearable recognition device and send the stop signal to the receiving unit at the device end.

[0027] In addition, to enhance the protection against injuries to furnace workers, the attitude recognition IMU inertial measurement unit, after the wearable behavior device enters the working mode, collects the behavior acceleration and angular velocity of the furnace workers. In addition to using algorithms to identify abnormal patterns, it also redundantly sets an abnormal output mode with a judgment threshold for quickly sending shutdown signals to effectively protect personal safety.

[0028] Meanwhile, to demonstrate the ease of operation of the wearable behavior recognition device, a wearable stop button is also provided, which can be used to manually and quickly send a stop signal to the transmitting unit for personnel safety protection.

[0029] This invention utilizes a high-quality detection data fusion algorithm model strategy based on vision, high-precision accelerometers, and gyroscopes to define and capture the characteristics of abnormal events in terms of behavior, posture, and timing. Through rigorous multi-stage logical verification, it successfully identifies abnormal states from the daily work of furnace operators in complex industrial operation scenarios with high precision. In particular, the algorithm advances personnel protection from simple threshold judgment to more intelligent technical means, greatly enhancing the ability to identify abnormal behaviors.

[0030] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A wearable coke oven furnace worker behavior recognition system, characterized in that, include: The device includes a wearable data acquisition unit, a wearable control unit, a wearable stop button, a wearable transmitting unit, and a device-side receiving unit, wherein: The wearable acquisition unit includes a camera and a wearable IMU inertial measurement unit, which is used to acquire image information of the furnace worker's working process and acceleration and angular velocity data, and send the image information and acceleration and angular velocity data to the wearable control unit for anomaly identification; The wearable control unit is used to receive the working process image information and acceleration and angular velocity data acquired by the wearable acquisition unit, and through a data fusion algorithm model based on vision and acceleration sensors and gyroscopes, it identifies and captures the characteristics of abnormal events in behavior, posture and timing, analyzes and locks whether the behavior of the furnace front worker is abnormal, and issues an abnormal signal. The wearable stop button is used to manually send a stop signal to the wearable transmitting unit; The wearable transmitting unit is used to receive abnormal furnace operation signals from the wearable control unit and send a shutdown signal to the equipment-side receiving unit. The equipment-side receiving unit is used to receive the shutdown signal sent by the wearable transmitting unit and trigger the equipment mechanism that causes damage to the furnace operator to stop its operation.

2. The wearable coke oven pre-furnace worker behavior recognition system according to claim 1, characterized in that, The wearable control unit includes an edge controller and interface accessories.

3. The wearable coke oven pre-furnace worker behavior recognition system according to claim 1, characterized in that, The wearable IMU (Inertial Measurement Unit) is used to collect the acceleration and angular velocity of the furnace worker in real time. The measured data is sent to the edge controller, which converts the data into directly usable linear acceleration and body posture angles as the basis for judging continuous multi-dimensional abnormal behavior characteristics of the algorithm model.

4. The wearable coke oven pre-furnace worker behavior recognition system according to claim 2, characterized in that, The wearable edge controller can also receive image information of the furnace worker's work process, and through a data fusion algorithm model based on vision, acceleration sensors and gyroscopes, identify and capture the characteristics of abnormal events in behavior, posture and timing, and analyze and lock whether the furnace worker's behavior is in an abnormal state.

5. The wearable coke oven pre-furnace worker behavior recognition system according to claim 1, characterized in that, The wearable stop button is redundant. In addition to using a data fusion algorithm model to identify abnormal patterns, the system also has a wearable manual stop button, which is used to quickly send a stop signal to the transmitting unit to effectively protect personal safety.

Images