A tunneling machine personnel safety protection method and device, electronic equipment and medium

Abstract

The application relates to the technical field of heading machines, and discloses a heading machine personnel safety protection method and device, electronic equipment and a medium. The method preliminarily obtains a first probability of whether personnel exist in the working area of the heading machine through image information and a personnel recognition model. Further, a heat release signal and a positioning signal are collected, and multi-source information fusion judgment is performed in combination with the first probability corresponding to the image information, so that it can be accurately judged whether personnel exist in the dangerous area of the heading machine, the problem that a single detection mode is easily disturbed by the environment and has a high false alarm and missed alarm rate can be effectively avoided, and when the danger is confirmed, an alarm can be immediately triggered and the heading machine can be controlled to stop, so that the risk of personnel casualties and equipment damage is reduced from the source, and the safety of personnel in the heading operation site and the continuity of production are ensured.

Description

Technical Field

[0001] This application relates to the field of tunneling machine technology, such as a method, device, electronic equipment, and medium for personnel safety protection in tunneling machines. Background Technology

[0002] As a crucial piece of equipment in underground coal mine tunneling, tunneling machines not only significantly improve tunneling efficiency but also create substantial dynamic hazard zones within and around the construction area. When workers enter or remain in high-risk restricted areas such as the equipment's operating range or material drop zones due to equipment inspection, troubleshooting, material cleaning, or management negligence, serious mechanical collisions, crushing, entanglement, or object strikes can easily occur.

[0003] However, current safety protection for tunneling machines mainly relies on photographing the working area or requiring personnel to wear positioning devices for identification within the area. This identification method is simplistic and inaccurate, failing to provide adequate personnel protection. Frequent false alarms can also disrupt normal tunneling operations, impacting tunneling efficiency and overall work performance, thus posing safety hazards.

[0004] It should be noted that the information disclosed in the background section above is only used to enhance the understanding of the background of this application, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0005] To provide a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. This summary is not intended as a general commentary, nor is it intended to identify key / important components or describe the scope of protection of these embodiments, but rather as a prelude to the detailed description that follows.

[0006] This application provides a method, device, electronic equipment, and medium for personnel safety protection during tunneling machine operations, in order to improve the safety of tunneling machine operations underground.

[0007] In some embodiments, the method includes the following steps: acquiring pyroelectric signals, positioning signals, and image information within a target area; inputting the image information into a preset personnel recognition model to obtain a first probability that personnel exist within the target area; based on a preset confidence value and the pyroelectric signals, positioning signals, and the first probability, predicting personnel in the target area to obtain a fused alarm probability; comparing the fused alarm probability with a preset threshold; when the fused alarm probability is greater than or equal to the preset threshold, determining that personnel have mistakenly entered a dangerous area, outputting an alarm signal, and controlling an audible and visual alarm and stopping the tunneling machine; when the fused alarm probability is less than the preset threshold, determining that the situation is safe, and controlling the tunneling machine to operate normally.

[0008] Optionally, acquiring image information within the target area includes: calculating the blind zone distance I based on the installation height and longitudinal field of view of the thermal imaging camera; calculating the effective recognition distance S based on the maximum recognition distance L of the thermal imaging camera and the blind zone distance I; and taking a thermal imaging photo when a target object is detected within the effective recognition distance S area to obtain image information.

[0009] Optionally, the image information is input into a preset person recognition model to obtain a first probability that a person exists in the target area, including: ; in, Personnel characteristics Corresponding logit value, image information The logits vector is , For image information The total number of features, j is the feature number of image information Z, j=1,2,3,…,k.

[0010] Optionally, based on a preset confidence level, the pyroelectric signal, the positioning signal, and the first probability, personnel prediction is performed on the target area to obtain a fusion alarm probability. ,include: ; in, The confidence weights for the pyroelectric signal. Confidence weights for UWB positioning signals. The confidence weight for the first probability of thermal imaging; To improve the accuracy of pyroelectric sensors in alarming probability, To improve the accuracy of alarms from UWB positioning modules To determine the accurate alarm probability through thermal imaging identification, and .

[0011] Optionally, the probability of accurate alarm from the pyroelectric sensor. And the probability of accurate alarm from the positioning module Determined in the following ways: ; ; in, This is the first initial weighting value for the pyroelectric sensor. This is the second initial weighting value for the UWB positioning module. This is the initial alarm value for the pyroelectric sensor. This is the initial alarm value for the UWB positioning module.

[0012] Optionally, the target area includes the tunneling machine's operating range, the material drop zone, and the high-risk restricted area around the equipment.

[0013] In some embodiments, the device includes: an information acquisition module for acquiring pyroelectric signals, positioning signals, and image information within a target area; a first probability acquisition module for inputting the image information into a preset personnel recognition model to acquire a first probability that personnel exist within the target area; a fusion alarm probability acquisition and determination module for predicting personnel in the target area based on a preset confidence value, the pyroelectric signals, the positioning signals, and the first probability to obtain a fusion alarm probability; an alarm module for comparing the fusion alarm probability with a preset threshold, and when the fusion alarm probability is greater than or equal to the preset threshold, determining that personnel have mistakenly entered a dangerous area, outputting an alarm signal, and controlling an audible and visual alarm and stopping the tunneling machine; and a safety status determination module for determining a safe status when the fusion alarm probability is less than the preset threshold and controlling the tunneling machine to operate normally.

[0014] The tunneling machine personnel safety protection method, device, electronic equipment, and medium provided in this application embodiment can achieve the following technical effects: By combining image information and personnel recognition models, the initial probability of whether personnel exist within the working area of ​​the tunneling machine is first obtained. Furthermore, pyroelectric signals and positioning signals are collected, and combined with the initial probability corresponding to the image information, multi-source information fusion judgment is performed. This can accurately identify whether there are any unwitting personnel in the dangerous area of ​​the tunneling machine, effectively avoiding the problems of single detection methods being susceptible to environmental interference and having high false alarm and false alarm rates. When danger is confirmed, an alarm can be triggered immediately and the tunneling machine can be stopped, reducing the risk of personnel injury and equipment damage from the source and ensuring the safety of personnel and the continuity of production at the tunneling operation site.

[0015] The above general description and the description below are exemplary and illustrative only and are not intended to limit this application. Attached Figure Description

[0016] One or more embodiments are illustrated by way of example with reference to the accompanying drawings. These illustrations and drawings do not constitute a limitation on the embodiments. Elements having the same reference numerals in the drawings are shown as similar elements. The drawings are not to be scaled. And wherein: Figure 1 This is a software flowchart of a method for protecting personnel safety on a tunneling machine according to an embodiment of this application; Figure 2 A schematic diagram of the working field of view of a tunneling machine provided in an embodiment of this application; Figure 3 A schematic diagram of a thermal imaging camera provided in an embodiment of this application; Figure 4This application provides a schematic diagram of the structure of a personnel safety protection device for a tunneling machine. Figure 5 This is a schematic diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0017] To provide a more detailed understanding of the features and technical content of the embodiments of this application, the implementation of the embodiments of this application will be described in detail below with reference to the accompanying drawings. The accompanying drawings are for illustrative purposes only and are not intended to limit the embodiments of this application. In the following technical description, for ease of explanation, several details are used to provide a full understanding of the disclosed embodiments. However, one or more embodiments may still be implemented without these details. In other cases, well-known structures and devices may be simplified in their depiction to simplify the drawings.

[0018] The terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate for the embodiments of this application described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion.

[0019] Unless otherwise stated, the term "multiple" means two or more.

[0020] In this embodiment, the character " / " indicates that the objects before and after it are in an "or" relationship. For example, A / B means: A or B.

[0021] The term "and / or" describes an association between objects, indicating that three relationships can exist. For example, A and / or B means: A or B, or A and B.

[0022] As a crucial piece of equipment in underground coal mine tunneling, tunneling machines, while significantly improving tunneling efficiency, also create substantial dynamic hazard zones within and around the work area. When workers enter or remain within the equipment's operating range or in areas prone to material spills due to equipment inspection, troubleshooting, material handling, or management negligence, serious mechanical collisions, crushing, entanglement, or being struck by objects can easily occur. These accidents are often sudden and have severe consequences (often resulting in serious injury or even death), causing irreparable harm to individual lives and families, seriously threatening project progress, corporate reputation, and resulting in substantial economic losses. Therefore, a deep understanding of the inherent risks of human-machine interaction in tunneling machine operations and strict control over personnel entering hazardous work areas are core challenges and paramount priorities that urgently need to be addressed in coal mine tunneling safety management.

[0023] However, current safety protection for tunneling machines mainly relies on individual pyroelectric sensors, UWB personnel positioning, or thermal imaging AI identification. However, individual pyroelectric sensors have high false alarm and false negative rates, failing to provide adequate personnel protection. Frequent false alarms also disrupt normal tunneling operations, impacting efficiency. Individual UWB personnel positioning is significantly affected by underground signal interference, and issues such as personnel not wearing positioning cards or damaged cards leading to undetected personnel entering the mine pose safety risks. Individual thermal imaging AI identification is limited by camera angles and the complex underground environment, resulting in false alarms and false negatives, creating safety hazards. Relying on a single method for personnel entry safety protection is limited by its inherent limitations, leading to false alarms and false negatives, failing to accurately identify personnel entering the mine, impacting operational efficiency, and posing safety risks.

[0024] Based on this, the embodiments of this application aim to improve the safety of tunneling machine operation by using multi-sensor signal fusion for personnel identification. Figure 1 As shown in the figure, a method for personnel safety protection in tunneling machines is provided in an embodiment of this application. The method includes the following steps: S101: Acquire pyroelectric signals, positioning signals, and image information within the target area; Pyroelectric signals refer to the electrical signals generated by pyroelectric infrared sensors (PIR) detecting changes in infrared radiation emitted by heat-generating objects such as humans and animals within a target area. These changes are converted by the sensor and used to preliminarily determine the presence of a living heat source in the area. In practice, pyroelectric infrared sensors can be deployed around the hazardous area of ​​the tunneling machine. The sensors continuously detect changes in infrared radiation, and when a human heat source is detected, they output a high-level pulse signal, which is transmitted to the controller. To enhance the signal strength of the pyroelectric signal, an array of pyroelectric sensors can be used to acquire the location and intensity information of heat sources within the area, outputting analog or digital pyroelectric signals.

[0025] Positioning signals refer to the data such as the personnel's position coordinates, distance, and signal strength output by a UWB positioning module, Bluetooth AoA positioning module, or ultrasonic positioning module after measuring the distance / angle of the personnel wearing positioning tags. This data is used to determine whether the personnel have entered a dangerous area.

[0026] Image information refers to two-dimensional image data and heat map data acquired by thermal imaging cameras from the target area, which are used by AI models to identify features such as human contours, postures, and positions.

[0027] S102: Input the image information into a preset personnel recognition model to obtain the first probability that a person exists in the target area; Specifically, image information can be input into a neural network model trained on samples. The model extracts and analyzes human contours, limb features, and temperature distribution features in the image, and outputs a confidence score, i.e., the first probability, indicating the presence of a person within the target area. In this embodiment, the preset person recognition model can employ, but is not limited to, existing convolutional neural networks, YOLO models, Faster R-CNN models, MobileNet lightweight models, or ResNet classification networks, as well as models obtained by improving the structure or parameters of the aforementioned models.

[0028] S103: Based on the preset confidence value, the pyroelectric signal, the positioning signal, and the first probability, perform personnel prediction on the target area to obtain the fusion alarm probability; This step uses preset confidence levels to weight and fuse the first probability of the presence of personnel obtained from pyroelectric signals, positioning signals, and image recognition. By combining the information from the three detection sources, a joint judgment is made on whether personnel exist in the target area. This eliminates the problem of single detection methods being susceptible to environmental interference and having a high probability of misjudgment. Finally, a fused alarm probability that comprehensively reflects the likelihood of a person accidentally entering a dangerous area is calculated, providing a unified basis for subsequent judgment on whether to trigger an alarm and shut down the system.

[0029] S104: Compare the fusion alarm probability with a preset threshold. When the fusion alarm probability is greater than or equal to the preset threshold, determine that personnel have mistakenly entered a dangerous area, output an alarm signal, and control the audible and visual alarm and the tunneling machine to stop. S105: When the probability of the fusion alarm is less than the preset threshold, it is determined to be a safe state, and the tunneling machine is controlled to operate normally.

[0030] The embodiments provided in this application first obtain the initial probability of whether there are personnel in the working area of ​​the tunneling machine through image information and personnel recognition model. Then, pyroelectric signals and positioning signals are collected and combined with the initial probability corresponding to the image information to perform multi-source information fusion judgment. This can accurately identify whether there are personnel who have mistakenly entered the dangerous area of ​​the tunneling machine, effectively avoiding the problems of single detection methods being easily affected by environmental interference and having a high false alarm and false alarm rate. When danger is confirmed, an alarm can be triggered immediately and the tunneling machine can be stopped, reducing the risk of personnel injury and equipment damage from the source and ensuring the safety of personnel and the continuity of production at the tunneling operation site.

[0031] Optionally, in step S101 of the above method, obtaining image information within the target area includes: calculating the blind spot distance I based on the installation height of the thermal imaging camera and the longitudinal field of view; calculating the effective recognition distance S based on the maximum recognition distance L of the thermal imaging camera and the blind spot distance I; and taking a thermal imaging photo when a target object is detected within the effective recognition distance S area to obtain image information.

[0032] Specifically, edge computing units can be installed on-site to receive various signals, such as pyroelectric signals, positioning signals, and image information. For example... Figure 2 The diagram shown is a schematic representation of the imaging field of view of thermal imaging camera 1. The video images received by the edge computing unit from thermal imaging camera 1 are related to the installation location of thermal imaging camera 1.

[0033] The longitudinal field of view of thermal imaging camera 1 is α, the farthest recognition distance allowed by the resolution is L, and the installation position of thermal imaging camera 1 is h. Then the blind zone distance I is: ; The effective recognition range distance S is: ; When a person is within the effective recognition range distance S, the edge computing unit can receive an effective image of the person captured by the thermal imaging camera, such as... Figure 3 As shown, Figure 3 This includes personnel 2 and interference objects 3.

[0034] In this way, by calculating the blind zone distance and effective recognition distance through the installation parameters of the thermal imaging camera, interference from invalid areas can be eliminated, and image information can be collected only within the effective recognition range. This improves the targeting and accuracy of image acquisition, reduces the system resource consumption caused by invalid data processing, and improves the response speed and reliability of personnel identification.

[0035] Optionally, in the above method, inputting image information into a preset person recognition model to obtain the first probability that a person exists in the target area includes: ; in, Personnel characteristics Corresponding logit value, image information The logits vector is , For image information The total number of features, j is the feature number of image information Z, j=1,2,3,…,k.

[0036] By employing a pre-defined personnel identification model and calculating the probability of personnel presence using standardized formulas, quantitative identification of personnel within the target area is achieved, improving the accuracy and stability of personnel detection and providing reliable data support for subsequent fusion judgment.

[0037] Optionally, in the above method, based on a preset confidence value, the pyroelectric signal, the positioning signal, and the first probability, personnel prediction is performed on the target area to obtain a fusion alarm probability. ,include: ; in, The confidence weights for the pyroelectric signal. Confidence weights for UWB positioning signals. The confidence weight for the first probability of thermal imaging; To improve the accuracy of pyroelectric sensors in alarming probability, To improve the accuracy of alarms from UWB positioning modules To determine the accurate alarm probability through thermal imaging identification, and .

[0038] The above embodiments, by assigning weights to pyroelectric signals, UWB positioning signals, and thermal imaging AI recognition and performing weighted fusion calculations, achieve complementary advantages of multi-source detection data, significantly reduce the probability of false alarms and false negatives, and improve the reliability and accuracy of personnel identification in dangerous areas.

[0039] The above-mentioned pyroelectric sensor has an accurate alarm probability. And the probability of accurate alarm from the positioning module Determined in the following ways: ; ; in, This is the first initial weighting value for the pyroelectric sensor. This is the second initial weighting value for the UWB positioning module. This is the initial alarm value for the pyroelectric sensor. This is the initial alarm value for the UWB positioning module.

[0040] Specifically, let's take a pyroelectric sensor as an example to explain the initial alarm value. The initial alarm value for a pyroelectric sensor can be set to 1 if the pyroelectric signal emitted by the sensor indicates the presence of people in the target area; otherwise, it's set to 0. Since the detection accuracy of pyroelectric sensors is limited, false alarms can occur. Therefore, to avoid false alarms, pyroelectric signals can be collected at preset time intervals. The probability of people being present in the target area from multiple collected signals is used as the initial alarm value for the pyroelectric sensor. For example, if 7 out of 10 detections indicate people are present, the initial alarm value for the pyroelectric sensor is set to 0.7. The method for determining the initial alarm value of the pyroelectric sensor also applies to determining the initial alarm value of the positioning module, and will not be elaborated further here. In this way, by setting initial weighting values ​​to weight the initial alarm values ​​of the pyroelectric sensor and the UWB positioning module, accurate quantification of both types of sensor signals is achieved, avoiding the influence of misjudgment from a single sensor signal on the final alarm result. This makes the basic detection data more closely match the actual operating scenario and improves the rationality of the calculated fusion alarm probability.

[0041] Optionally, the target area includes the tunneling machine's operating range, the material drop zone, and the high-risk restricted area around the equipment.

[0042] Another method for personnel safety protection in tunneling machines provided in this application includes the following steps: S401: Calculate the blind zone distance I based on the installation height of the thermal imaging camera and the longitudinal field of view; S402: Calculate the effective recognition distance S based on the maximum recognition distance L of the thermal imaging camera and the blind spot distance I; S403: When a target object is detected within the effective identification distance S area, thermal imaging is performed to obtain image information, and pyroelectric signals and UWB positioning signals within the target area are acquired simultaneously.

[0043] S404: Input the image information into the preset personnel recognition model, and calculate the first probability that there are personnel in the target area through the formula.

[0044] S405: The pyroelectric signal and the UWB positioning signal are weighted separately. The probability of accurate alarm of the pyroelectric sensor is calculated using the first initial weighting value, and the probability of accurate alarm of the UWB positioning module is calculated using the second initial weighting value.

[0045] S406: Based on preset confidence weights, the fusion alarm probability is obtained by weighted fusion calculation combining the accurate alarm probability of the pyroelectric sensor, the accurate alarm probability of the UWB positioning module, and the first probability of thermal imaging recognition. The sum of the confidence weights of the pyroelectric signal, the UWB positioning signal, and the first probability confidence weight of thermal imaging is 1.

[0046] S407: Compare the fusion alarm probability with a preset threshold. When the fusion alarm probability is greater than or equal to the preset threshold, it is determined that personnel have mistakenly entered a dangerous area, an alarm signal is output, and the audible and visual alarms and the tunneling machine are controlled to stop are controlled. When the fusion alarm probability is less than the preset threshold, it is determined to be a safe state, and the tunneling machine operates normally.

[0047] This embodiment integrates multi-source information acquisition, effective identification range screening, AI personnel identification, sensor signal weighted processing, multi-data fusion judgment, and alarm shutdown control. First, it eliminates blind spot interference through thermal imaging camera parameter calculation. Then, it accurately quantifies the probability of personnel presence through an AI model. Simultaneously, it performs weighted optimization of pyroelectric and UWB positioning signals. Finally, it completes multi-signal fusion calculation according to confidence weights, comprehensively improving the accuracy, reliability, and anti-interference capability of personnel detection. A complete closed loop is formed from data acquisition, processing, judgment to execution control, significantly reducing the false alarm and missed alarm rates. When personnel accidentally enter a dangerous area, it can quickly respond and achieve dual protection of alarm and shutdown, significantly improving the safety protection level of the tunneling machine operation site and ensuring the life safety of operators and stable operation of equipment.

[0048] like Figure 4 As shown, a personnel safety protection device 500 for a tunneling machine is provided in an embodiment of this application. The device includes: The information acquisition module 501 is used to acquire pyroelectric signals, positioning signals and image information within the target area; The first probability acquisition module 502 is used to input image information into a preset personnel recognition model to obtain the first probability that a person exists in the target area; The fusion alarm probability acquisition and determination module 503 is used to predict personnel in the target area based on a preset confidence value, the pyroelectric signal, the positioning signal and the first probability, and obtain the fusion alarm probability. Alarm module 504 is used to compare the fusion alarm probability with a preset threshold. When the fusion alarm probability is greater than or equal to the preset threshold, it is determined that personnel have mistakenly entered a dangerous area, an alarm signal is output, and the sound and light alarm and the tunneling machine are stopped are controlled. The safety status determination module 505 is used to determine a safe status when the probability of the fusion alarm is less than a preset threshold, and to control the tunneling machine to operate normally.

[0049] The embodiments provided in this application first obtain a preliminary probability through image information and personnel recognition models. Then, pyroelectric signals and positioning signals are collected, and combined with image information, these three types of data are used to perform multi-source information fusion judgment. This can accurately identify whether there are any personnel who have mistakenly entered the dangerous area of ​​the tunneling machine. It effectively avoids the problems of single detection methods being easily affected by environmental interference and having a high false alarm and false alarm rate. When danger is confirmed, an alarm can be triggered immediately and the tunneling machine can be stopped. This reduces the risk of personnel injury and equipment damage from the source and ensures the safety of personnel and the continuity of production at the tunneling operation site.

[0050] Combination Figure 5 As shown, this application provides an electronic device 600, including a processor 100 and a memory 101. Optionally, the device may further include a communication interface 102 and a bus 103. The processor 100, communication interface 102, and memory 101 can communicate with each other via the bus 103. The communication interface 102 can be used for information transmission. The processor 100 can call logical instructions in the memory 101 to execute the tunneling machine personnel safety protection method described in any of the above embodiments.

[0051] Furthermore, the logic instructions in the aforementioned memory 101 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium.

[0052] The memory 101, as a computer-readable storage medium, can be used to store software programs and computer-executable programs, such as program instructions / modules corresponding to the methods in the embodiments of this application. The processor 100 executes functional applications and data processing by running the program instructions / modules stored in the memory 101, thereby implementing the tunneling machine personnel safety protection method of the above embodiments.

[0053] The memory 101 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the terminal device. Furthermore, the memory 101 may include high-speed random access memory and may also include non-volatile memory.

[0054] This application provides a computer-readable storage medium storing computer-executable instructions, which are configured to execute the tunneling machine personnel safety protection method described in the above embodiments.

[0055] This application provides a computer program product, which includes a computer program stored on a computer-readable storage medium. The computer program includes program instructions, which, when executed by a computer, cause the computer to perform the tunneling machine personnel safety protection method described above.

[0056] The aforementioned computer-readable storage medium may be a transient computer-readable storage medium or a non-transitory computer-readable storage medium.

[0057] The technical solutions of this application embodiment can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes one or more instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in this application embodiment. The aforementioned storage medium can be a non-transitory storage medium, including: USB flash drive, portable hard drive, read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk, and other media capable of storing program code; it can also be a transient storage medium.

[0058] The foregoing description and accompanying drawings fully illustrate embodiments of this application to enable those skilled in the art to practice them. Other embodiments may include structural, logical, electrical, procedural, and other changes. The embodiments represent only possible variations. Individual components and functions are optional unless explicitly required, and the order of operation may vary. Parts and features of some embodiments may be included in or replace parts and features of other embodiments. Moreover, the terminology used in this application is for describing embodiments only and is not intended to limit the claims. As used in the description of embodiments and claims, the singular forms “a,” “an,” and “the” are intended to equally include the plural forms unless the context clearly indicates otherwise. Similarly, the term “and / or” as used in this application means including one or more of the associated listed items and all possible combinations thereof. Additionally, when used in this application, the term "comprise" and its variations "comprises" and / or "comprising" refer to the presence of stated features, integrals, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components, and / or groups thereof. Without further limitations, an element defined by the phrase "comprises a..." does not exclude the presence of other identical elements in the process, method, or apparatus that includes said element. In this document, each embodiment may focus on the differences from other embodiments, and similar or identical parts between embodiments can be referred to mutually. For methods, products, etc., disclosed in the embodiments, if they correspond to the method section disclosed in the embodiments, the relevant parts can be referred to the description of the method section.

[0059] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the embodiments of this application. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0060] The methods and products (including but not limited to devices and equipment) disclosed in the embodiments herein can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For instance, the division of units may be merely a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, and the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to implement this embodiment according to actual needs. In addition, the functional units in the embodiments of this application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0061] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than that shown in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. In the descriptions corresponding to the flowcharts and block diagrams in the accompanying drawings, the operations or steps corresponding to different blocks may also occur in a different order than disclosed in the description; sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. Each block in a block diagram and / or flowchart, and combinations of blocks in a block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

Claims

1. A method for personnel safety protection in tunneling machines, characterized in that, Includes the following steps: Acquire pyroelectric signals, positioning signals, and image information within the target area; The image information is input into a preset person recognition model to obtain the first probability that a person exists in the target area; Based on a preset confidence level, the pyroelectric signal, the positioning signal, and the first probability, personnel prediction is performed on the target area to obtain a fusion alarm probability. The fusion alarm probability is compared with a preset threshold. When the fusion alarm probability is greater than or equal to the preset threshold, it is determined that personnel have mistakenly entered a dangerous area. An alarm signal is output and the sound and light alarm and the tunneling machine are controlled to stop. When the probability of the fusion alarm is less than a preset threshold, it is determined to be a safe state, and the tunneling machine is controlled to operate normally.

2. The method according to claim 1, characterized in that, Acquire image information within the target area, including: Calculate the blind zone distance I based on the installation height of the thermal imaging camera and the longitudinal field of view. The effective recognition distance S is calculated based on the maximum recognition distance L of the thermal imaging camera and the blind spot distance I. When a target object is detected within the effective identification distance S area, thermal imaging is performed to obtain image information.

3. The method according to claim 1, characterized in that, Inputting image information into a preset person recognition model to obtain the first probability that a person exists in the target area includes: ； in, Personnel characteristics Corresponding logit value, image information The logits vector is , For image information The total number of features, j is the feature number of image information Z, j=1,2,3,…,k.

4. The method according to claim 1, characterized in that, Based on a preset confidence level, the pyroelectric signal, the positioning signal, and the first probability, personnel prediction is performed on the target area to obtain a fused alarm probability. ,include: ； in, Confidence weights for pyroelectric signals Confidence weights for UWB positioning signals. The confidence weight for the first probability of thermal imaging; To improve the accuracy of pyroelectric sensors in alarming probability, To improve the accuracy of alarms from UWB positioning modules To determine the accurate alarm probability through thermal imaging identification, and .

5. The method according to claim 4, characterized in that, The probability of accurate alarm from the pyroelectric sensor And the probability of accurate alarm from the positioning module Determined in the following ways: ； ； in, This is the first initial weighting value for the pyroelectric sensor. This is the second initial weighting value for the UWB positioning module. This is the initial alarm value for the pyroelectric sensor. This is the initial alarm value for the UWB positioning module.

6. The method according to any one of claims 1 to 5, characterized in that, The target area is one or more of the following: the tunneling machine's operating range, the material drop zone, and the high-risk restricted area around the equipment.

7. A personnel safety protection device for a tunneling machine, characterized in that, include: The information acquisition module is used to acquire pyroelectric signals, positioning signals, and image information within the target area; The first probability acquisition module is used to input image information into a preset person recognition model to obtain the first probability that a person exists in the target area; The fusion alarm probability acquisition and determination module is used to predict the number of people in the target area based on a preset confidence value, the pyroelectric signal, the positioning signal and the first probability, and obtain the fusion alarm probability. The alarm module is used to compare the fusion alarm probability with a preset threshold. When the fusion alarm probability is greater than or equal to the preset threshold, it is determined that the personnel have mistakenly entered the dangerous area, and an alarm signal is output to control the audible and visual alarm and the tunneling machine to stop. The safety status determination module is used to determine a safe status when the probability of the fusion alarm is less than a preset threshold, and to control the tunneling machine to operate normally.

8. An electronic device comprising a processor and a memory storing program instructions, characterized in that, The processor is configured to execute the tunneling machine personnel safety protection method as described in any one of claims 1 to 6 when executing the program instructions.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions configured to perform the tunneling machine personnel safety protection method as described in any one of claims 1 to 6.

Images