KR102064712B1 - An equipment safety management system with a wearble device and a body detection module - Google Patents

Abstract

The present invention relates to an equipment safety management system combining a wearable device and human body sensing module for efficiently performing safety management. According to the present invention, the equipment safety management system comprises: a worker checking module obtaining sensing information for worker from at least one sensing module and checking the worker within equipment for work according to the obtained sensing information; and a lock control signal output module outputting a lock control signal to the equipment for work according to at least one of a control signal inputted from a control module of the equipment for work or a worker sensing signal inputted from the worker checking module.

Description

Facility safety management system combining wearable device with human body detection module {AN EQUIPMENT SAFETY MANAGEMENT SYSTEM WITH A WEARBLE DEVICE AND A BODY DETECTION MODULE}

The present invention relates to a facility safety management system, and more particularly, to a safety management system combining a wearable device and a human body detection module.

In the general manufacturing industry, due to the nature of the industry, large and medium-sized equipment is installed, and in a working environment dealing with medium- and large-sized equipment, injuries or accidents often occur due to non-compliance with safety rules while working in the equipment.

In particular, equipment workers may enter and work inside the equipment for reasons such as monitoring of the process or repair such as damage, input of materials, or regular inspections.In principle, when working, stop the operation of the equipment. Should be implemented.

However, there is a possibility that an accident may occur for reasons such as working without stopping the equipment or restarting a fellow worker who does not recognize the operation even if the worker stops operation.

In order to prevent such a safety accident, even though the equipment is equipped with a function of detaching and holding a key so that restarting is impossible basically, or detecting an opening state of an entrance door and automatically stopping driving, safety accidents occur constantly. There is a continuous need for a solution to solve this problem.

Based on the above discussion, the following is to provide a facility safety management system combining the wearable device and the human body detection module.

Technical problems to be achieved in the present invention are not limited to the above technical problems, and other technical problems that are not mentioned will be clearly understood by those skilled in the art from the following description.

The facility safety management system combining the wearable device and the human body sensing module, which is an aspect of the present invention for solving the above-described problems, obtains sensing information about an operator from at least one sensing module, and obtains at least one sensing information. According to at least one of the operator confirmation module and the control signal input from the control module of the operation target facility and the operator detection signal input from the operator identification module to check the worker in the work target facility, the lock to the work target facility ( lock) a control signal output module for outputting a control signal.

Further, the lock control signal output module stops the operation of the work target facility when a lock signal of the work target equipment is input or when the worker is confirmed by the worker check module. Outputting a lock control signal, and when the unlock signal of the target equipment is input among the control signals and the absence of an operator is confirmed in the target equipment, starting the operation of the target equipment; And outputting a lock control signal.

Further, the at least one sensing module includes a wearable device, wherein the wearable device is activated by recognizing the wear of the worker and obtaining a lock code associated with the work target facility from the worker. When the wearable device receives an input, the worker identification module recognizes the absence of an operator in the work target facility only when the worker identification module recognizes an unlock code corresponding to the unique identifier of the wearable device and the lock code. It may be characterized as determining. Furthermore, the at least one sensing module comprises a wearable device survey module consisting of three or more antennas, wherein the wearable device survey module comprises a triangle based on the distance from each of the three or more antennas to the wearable device. According to the survey, it can be characterized in that configured to compare the location of the worker and the area of the work object facility.

Furthermore, the at least one sensing module comprises an image based sensing module, wherein the image based sensing module comprises a data set consisting of predetermined object images in a first image area on a predetermined number or more of consecutive frames. If there is an extracted image whose degree of similarity with the learned image database based on the set) is greater than or equal to a preset level, it may be determined that the worker exists.

Furthermore, the at least one sensing module includes an image based sensing module, wherein the image based sensing module determines that the operator is present when detecting an image different from a predetermined image in the second image area. It can be characterized.

According to an embodiment of the present invention, safety management can be efficiently performed through the facility safety management system combining the wearable device and the human body sensing module.

Effects obtained in the present invention are not limited to the above-mentioned effects, and other effects not mentioned above may be clearly understood by those skilled in the art from the following description. will be.

BRIEF DESCRIPTION OF THE DRAWINGS The accompanying drawings, which are included as part of the detailed description to help understand the present invention, provide examples of the present invention and together with the description, describe the technical idea of the present invention.
1 is a block diagram of a facility safety management system according to an embodiment of the present invention.
2 is a reference diagram for explaining a signal processing aspect of a facility safety management system according to an embodiment of the present invention.
3 is a reference diagram for explaining an operation of a facility safety management system using a wearable device according to an embodiment of the present invention.
4 is a reference diagram for describing an operation of an image sensing module according to an embodiment of the present invention.

It is apparent that the present invention is not limited to the description of the embodiments described below, and various modifications may be made without departing from the technical gist of the present invention. In describing the embodiments, descriptions of technical contents that are widely known in the art to which the present invention pertains and are not directly related to the technical gist of the present invention will be omitted.

On the other hand, the same components in the accompanying drawings are represented by the same reference numerals.

In the accompanying drawings, some components may be exaggerated, omitted, or schematically illustrated. This is to clarify the gist of the present invention by omitting unnecessary description that is not related to the gist of the present invention.

1 is a block diagram of a facility safety management system according to an embodiment of the present invention.

Facility safety management system according to the present invention, the operator confirmation control device 110 and the operator confirmation control device to which the present invention is applied may be composed of the work target facility 130 is combined / inserted.

According to the present invention, the operator confirmation control device 110 is configured to include an operator confirmation module 111 and a lock control signal output module 113.

The worker identification module 111 recognizes whether the worker is wearing or not wearing or displays the work contents to the worker, so that the wearable device and the wearable device capable of receiving the confirmation of the work contents can be recognized, the camera and the CCTV. Image-based detection module that can receive the image from the image capture module and the image capture module, etc. to detect the presence of the operator, and the operator who exists in the working radius of the target equipment from the various modules such as the detection sensor module using infrared light It is possible to obtain sensing information about. That is, when acquiring the sensing information from the at least one sensing module, the operator confirmation module may check or determine whether the operator exists in the work target facility.

Furthermore, the sensing module connected to the operator identification module may be activated with priority, for example, only when the wearable device is activated, or when the wearable device recognition module is activated or when the image-based sensing module is activated. Activation of the device may be stopped. On the contrary, in an situation in which an image-based detection module or the like causes an error in worker recognition, the wearable device or the human body sensor may be activated. That is, even if a plurality of sensing modules are used, the worker identification module may instruct activation / deactivation of some sensing modules in consideration of a state of a sensor, a state of a worker, battery consumption, and the like.

The lock control signal output module 113 is a work target based on a control signal input from an existing control module 131 controlling the work target facility 130 or an operator detection signal input from the operator confirmation module 111. A lock / unlock signal can be output to the lock target device 133 in the facility.

In particular, the lock control signal output module in the present invention is included in the work target facility from the control module 131 included in the work target facility or external to the work target facility (for example, a central control server, etc.). The control signal transmitted to the lock target device 133 is received in the middle, and the lock signal is controlled among the received control signals. During maintenance of the work, the operator may be able to send a test signal to the work facility to check whether the work facility is properly maintained. Thus, intercepting all signals transmitted from the control module in the middle can reduce the efficiency of the operator's inspection of the target equipment and cause a problem of delaying the work.

Accordingly, the lock control signal output module 113 according to the present invention selectively checks whether the control signal received from the control module is a lock / unlock signal of the work target facility, and then selectively receives the control signal. It may be determined whether to transmit to the facility to be operated or to output a lock control signal instructing to lock / unlock to the facility to be worked on.

In addition, the lock control signal output module 113 according to the present invention checks whether the operator is identified by determining the operator detection signal of the operator identification module 111 as well as the control signal input from the control module for the work target facility. And output the lock control signal. Accordingly, the lock control signal output module 113 may separately determine a case of locking the work target facility and a case of unlocking the equipment.

The lock control signal output module 113 may stop the operation of the target equipment even when the lock signal of the target equipment is input among the control signals or when the operator is confirmed by the operator identification module. Can be. This is to prevent an unexpected accident by an operator by preventing a malfunction of a work target facility.

However, in the case of unlocking the target equipment, it is preferable to start the operation of the target equipment after confirming all the detection signals and the control signals. This is to prevent an accident that may occur by inputting a lock release signal in a situation in which it is not possible to check whether an operator exists in a facility to be operated from the outside.

Therefore, the lock control signal output module receives an unlock signal of the target equipment among the control signals received from the control module, and the operator does not exist in the target equipment through the operator identification module (that is, Member), the lock control signal for starting the operation of the work target facility can be output.

Furthermore, in addition to the operation of outputting the lock control signal, the lock control signal output module 113 according to the present invention is opened even when the work target equipment is in an abnormal state (for example, the work target equipment is normally closed at the door). The emergency stop of the equipment and at the same time, the alarm module can be used to sound the warning lights installed on the outside of the equipment, or to perform an operation for sharing the emergency situation between workers through the wearable device. That is, the notification module may allow a worker who has a specific code to display a notification consisting of tactile, auditory, and visual effects in which the locked state of the manufacturing apparatus may be recognized. For example, the notification module may notify that an operator is present in the work target facility or that the work target facility is in an abnormal state through at least one of a light emitting body, a lamp, a display unit, a speaker, and a wearable device associated with the manufacturing equipment.

In the present invention, the sensing module that can be connected to the operator identification module and can transmit a worker sensing signal may have various forms. Hereinafter, for convenience of description, the wearable device, the wearable device measurement module, the image-based detection module, and the human body sensor have been described based on the sensor, but the IoT sensor that can transmit a detection signal indicating the presence of the operator to the operator identification module The present invention may also be applied to additional devices such as the present invention. In the present invention, the wearable device 121 may be connected to the operator confirmation control device 110 to transmit an operator detection signal to the operator confirmation module 111.

For example, when a worker is recognized through a wearable device (eg, a smart band, a work helmet, a wireless earphone, etc.) having a unique identifier, the wearable device may be used to determine whether the worker works on the lockable device. I can recognize it.

In this case, the wearable device 121 may be set to have respective unique identifiers, and the individual unique identifiers may be set to match specific workers. Accordingly, the information of the scheduled work contents, work target equipment, etc. may be displayed to a specific worker, or information of work activity, work time, work target equipment, etc. of a specific worker may be grasped by the manager. Unusual situations where workers who are not involved in accessing the equipment to be worked on can be identified.

The wearable device 121 according to the present invention may be activated by recognizing a wear of a specific worker. When the worker is recognized through the activated wearable device, the wearable device 121 may be locked only by checking a unique identifier of the activated wearable device. It may be configured to release.

This is because the worker confirmation module can reliably determine that the work of the target facility is in progress when the work target facility is locked by the specific worker. For example, when a wearable device receives a lock code associated with a work facility from an operator, the operator identification module only checks an unlock code corresponding to a unique identifier and a lock code of the wearable device. In this case, it can be determined that no worker exists in the facility to be operated. Here, the lock code may be simply a code for locking / unlocking, but a code related to a specific target equipment, a code based on a specific maintenance scheduling, and a code related to a worker group to which a specific worker belongs. The lock / unlock code may be shared by multiple workers.

For example, when the worker wears the wearable device 121 and the wearable device is activated, if the worker knows the start of the maintenance work of the equipment to be worked on, the operator identification device identifies the unique identifier of the wearable device that informed the start of the maintenance work. It can be operated to unlock the target equipment only when the end of the maintenance work of the target equipment through the wearable device matching the corresponding unique identifier is stored. By using the wearable device, the operator can simply stop the equipment just before starting work, and only the party who stops driving can be restarted, thereby preventing safety accidents caused by unexpected external workers. .

In addition, locking / unlocking of the lockable device 133 in the present invention is possible only through a specific wearable device, so that the worker who started the work does not release the lock so that the operation of the lockable device is unnecessarily stopped. In order to periodically notify the worker wearing the wearable device. For example, by alerting the worker periodically that the lockable device is in a locked state through vibration or a notification sound through the wearable device, the worker's psychological stability is promoted, and even though work on the target device is inadvertently terminated. It is possible to prevent the equipment to be stopped from working. Further, when the worker notifies the operator confirmation control device of the start of the work on the work target facility through the wearable device, the start of work may be transmitted to a fellow worker related to the maintenance of the work target facility. If the human body sensor / image capturing module (camera) associated with the lock target device is activated, the wearable device may not be activated. This is because, as described above, when one sensing module normally recognizes an operator, it is not necessary to repeatedly recognize the operator in another sensing module, and this is to reduce the battery consumption of the wearable device. However, even in such a case, when the operator confirmation module recognizes the start of the work by the wearable device, it is preferable to unlock the lock target facility only when the wearable device is activated to instruct the end of the work.

Furthermore, in the present invention, when the wearable device 121 is set to be connected to the operator confirmation control apparatus 110, the wearable device measurement module 123 may be additionally activated in order to determine the correct position of the worker.

Wearable device measurement module 123 in the present invention may be configured to survey the position of the worker through at least one antenna. That is, by measuring the distance between the antenna and the wearable device from the individual antenna constituting the wearable device measurement module, and using a plurality of antennas to confirm the position of the wearable device through triangulation, the operator is present in the lock target equipment You can check whether or not. A detailed description thereof will be described in more detail with reference to FIG. 3.

In the present invention, as one of the sensing modules connected to the operator identification module, the image-based sensing module 125 may be used. The image-based detection module 125 may analyze the extracted image in the specific image area and determine that the operator exists when the image is similar to the predetermined image, and when a different image other than the predetermined image is detected in the specific image area. It is also possible to stop the operation of the lock target device by determining that an abnormal situation has occurred. A detailed description thereof will be described in detail with reference to FIG. 4.

In addition, in the present invention, it is possible to check the entry of the worker through the human body sensor module installed inside / outside of the lock target equipment. The human body detection sensor may be a variety of sensors such as an infrared sensor, an ultrasonic sensor, an ultraviolet sensor, a motion recognition sensor, and the like, and by configuring an IoT-based network, it is possible to transmit a worker detection signal to the worker identification module. Furthermore, in the present invention, since the operator is recognized using a plurality of sensing modules, priority can be set for the efficiency of the work sensor. For example, the human body sensing sensor may deactivate the wearable device and process the image of the image sensing module. May be set to be activated only when is difficult. Therefore, if a specific sensing module becomes abnormal, it will try to activate it by talking to another sensing module connected to the worker identification module, and if it is deactivated, unlock it from the control module of the target equipment. Although the signal is transmitted and the operator confirmation module indicates that the operator is unconfirmed, the lock control signal for stopping the operation of the operation target facility may be output to the operation target facility. This is to prevent the operator identification module from making an incorrect judgment due to an error of the detection module.

Therefore, according to the present invention, workers can be guaranteed a safe environment in which the equipment is not operated until the required work is completed while minimizing downtime (ie, downtime) of the target equipment, and the manager or fellow workers can The driving status and work history of the system can be shared in real time, and the effect on the site can be easily identified.

2 is a reference diagram for explaining signal processing aspects of signal processing of a wearable device and a facility safety management system according to an exemplary embodiment of the present invention. In the description related to FIG. 2, for convenience of explanation, the description will be made using a name of a transceiver.

When the worker transceiver 220 (for example, a wearable device) is activated through an operation such as worn by a worker, the worker transceiver may transmit a signal regarding equipment entry / release to a control module, an operator confirmation control device, and the like. In addition, event information related to the lock target device (for example, start / end of another worker's work, status of the lock target device) may be received. However, for example, in the case of a wearable device, a signal may be weakened when entering the inside of a facility to be worked, or a signal strength may not be relatively strong due to a problem such as a battery. Alternatively, a problem may occur in which reception of event information is difficult.

Therefore, the facility safety management system according to the present invention may further include a repeater 220. The repeater 220 may amplify the signal received from the operator's transceiver and transmit it to the equipment transceiver, or may transmit the amplified signal from the equipment transceiver to the worker transceiver. That is, each of the repeaters is a device for a signal transceiver for a wearable device, a sensor constituting an IoT network, and equipment for a work target facility, using a preset protocol for each repeater, and amplifying a signal transmitted to the repeater for receiving sensitivity. And by increasing the distance, it is possible to transmit and receive signals to a worker transceiver, a work target facility or another repeater.

The equipment transceiver 230 may convert a signal received from the repeater 220 and transmit the signal to the lock control signal output module or convert the signal received from the lock control signal output module and transmit the signal to the repeater / worker transceiver. The transceiver for the equipment may be included in the operator identification module, and in the case of a transceiver (for example, a wearable device) worn by an operator, various wireless communication protocols may be used, and a lock control signal output module may be used for the wireless communication protocol. This needs to be converted into a recognizable signal. Therefore, according to the present invention, as the equipment transceiver is used, the wearable device may use various protocols such as LTE, WIFI, BLE, and LORA, and communication methods are not limited. Furthermore, only by performing a hardware / software update of the transceiver for the worker, signal transmission from the equipment using various communication protocols to the lock control signal output module 240 can be stably performed.

The lock control signal output module 240 may transmit a start / stop command to a work target facility based on at least one of a signal transmitted through a control module and a transceiver for a worker. Can be sent to the transceiver. Furthermore, the control module for the entry / release of the work target equipment of the worker, the state of the work equipment (operation state, door opening, failure, etc.) based on the signal recognized or transmitted through the equipment transceiver 230 This can help managers identify information related to the plant they are working on.

At this time, the lock control signal output module 240 according to the present invention transmits a signal to a work target facility by using power line communication (PLC), in the case of manufacturing equipment there is a case where the size is larger than the signal radius of the wireless communication Since the signal strength may be weakened or interference may occur depending on the mechanical structure of the manufacturing equipment, the control command may be stably transmitted to the work target facility by configuring the work target facility using power line communication.

The control module 260 is an operator confirmation control device including a lock control signal output module. The control module 260 may receive information such as operation / stop status and operation history of a work target facility, store it in a database, and display the information to an administrator. It can also provide manager functions such as forced restart of target equipment or data initialization.

3 is a reference diagram for explaining an operation of a facility safety management system using a wearable device and a wearable device survey module according to an exemplary embodiment of the present invention.

According to an embodiment of the present invention, the worker may input a lock code through the activated wearable device (S310). If the worker indicated the start of his work through the wearable device when entering the work facility, the work content may be displayed on the wearable devices of other workers who share the same lock code, and if the work facility is running, the work stops. Can be changed to a locked state that cannot be restarted. Further, workers who share a lock code associated with a work facility in a locked state may periodically receive a signal related to the state of the work facility.

Accordingly, the facility safety management system may additionally determine whether the wearable device survey module is activated when the wearable device is activated (S320), and measure the location of the worker using the wearable device survey module when the wearable device survey module is activated. . The wearable device survey module may include at least one antenna. In the wearable device survey module, the form of the surveyed information may vary according to the number of antennas that recognize the wearable device. For example, in the wearable device survey module, when only one antenna is used, only the wearable device may be recognized. When the two antennas are used, the wearable device may be considered in consideration of the distance at which the wearable device is recognized at each antenna. The position candidate of the device can be calculated. In addition, when using three or more antennas, the position of the operator may be measured by triangulation based on the distance from the individual antennas. In particular, in a method of recognizing a location by triangulating the distance of the wearable device through individual antennas, a communication protocol such as a radio frequency, a Bluetooth, or a WIFI may be used.

Hereinafter, a description will be given mainly on the case of measuring the position of the operator using three or more antennas. When the wearable device survey module of the facility safety management system is activated, the position of the worker is measured using three or more antennas (S325).

For example, according to a triangulation based on the distance from each of the three or more antennas to the wearable device, it may be configured to compare the location of the work target facility and the location of the worker recognized from the wearable device. Here, the individual antennas may be installed at a predetermined position by a manager in advance, but may be configured to include a GPS sensor so that the position is automatically detected when coupled to the work target equipment.

The operator identification module of the safety management system may determine whether the operator exists in the work target facility (S330). If the worker does not display the starting state of his work through the wearable device when the worker enters, the human body detection module coupled to the image-based sensing module or the equipment may check whether the worker enters. In this case, when all or part of the human body is detected in the facility to be worked, or when normal worker detection is not possible through an operator detection module (for example, a camera, a CCTV, a human body sensor, etc.) In the case of being obscured, it may be determined that the worker has entered, and then the operation for stopping the operation target equipment may be performed.

In addition, when the position of the wearable device is measured, the control server or the like may map the position of the wearable device on the layout of the work target facility to determine whether the lockable device has been entered into the lock target device and the status of the location of the worker.

In this case, the operator confirmation control device receives a signal from the control module associated with the work target facility in addition to the worker detection module (S340).

In response to the lock signal received from the control module received from the control module or the operator detection signal received from the operator confirmation module, it is possible to output a lock control signal instructing to start or stop the operation of the lock target equipment (S350).

When the lock control signal instructs the lock, the facility safety management system stops the lock target facility that is the target among the work target facilities (S360).

When the worker finishes the work of the work target equipment (S370), it is possible to drive the work target equipment. For example, when there is an attempt to drive externally, if there is no task notification through the wearable device, and it is determined that the human body detection in the equipment is normally safe, the operation of the equipment is possible. In addition, the equipment in the locked state can not be restarted unless the worker releases the work through the wearable device, so if the unlock code is not confirmed through the wearable device, it is periodically locked to the workers. Inform. If the worker's mistake does not indicate the completion of work through the wearable device, the equipment does not change the status in the locked state, which makes it impossible to restart it. It is desirable to inform.

In response, the facility safety management system determines a lock release code corresponding to the unique identifier and lock code of the activated wearable device (S380). In other words, if a worker indicates completion of his / her work through a wearable device at the time of leaving, the work is displayed on wearable devices of other workers who share the same code, and the worker's absence is confirmed in the worker confirmation module of the target equipment. do.

If the operator confirmation module cannot normally detect, it is assumed that the operator exists and the state of the lock target facility is determined to be abnormal, and the lock state is maintained.

If it is determined that the operator does not exist and an unlock signal is input from the control module, the lock control signal output module outputs a lock control signal instructing to release the lock to unlock the work target equipment (S390). That is, when a worker attempts to drive from the outside after leaving, when the work is confirmed through the wearable device, the work completion is indicated to other workers, and after the detection module in the equipment checks the normal situation, It is restarted.

4 is a reference diagram for describing an operation of an image sensing module according to an embodiment of the present invention.

The image-based sensing module according to the present invention stops the operation of the work target facility when the presence of a pre-stored object image is detected on consecutive frames in the image area or when an image detecting a change in the predetermined image is detected. can do. Here, the pre-stored object image may be learned by applying artificial intelligence, and for example, a detection engine for an image-based sensing module may be trained using a deep learning algorithm, a Convolutional Neural Network (CNN).

For example, the dataset that is the training data for body recognition in the present invention not only includes the whole body image of a person, but also includes data of body parts that are mainly used by the worker, thereby extending the worker's hands. Can be learned to detect even if only part of the equipment. In particular, in the image classification method applied in the present invention, when the driving unit (motor, robot, etc.) of the work target equipment is recognized in the image, instead of tracking an object having dynamic movement, the extracted image is stored in advance in the object image ( For example, it is possible to show a high recognition rate for the worker, and to increase the recognition rate by learning the false / non-detect situation data using the CNN. Accordingly, the detection engine learned through deep learning reads the image transmitted through the camera in real time to determine whether a person is present in the target equipment, and according to the angle of view / shooting range of the camera, Even if only a part of the body can be recognized by the image sensing module. That is, the detection engine according to the present invention can classify individual body parts and improve the accuracy of judging that a person has entered by learning about each part of the body such as a human hand, foot, and head.

Accordingly, in the present invention, a real-time image is determined through a detection engine learned through artificial intelligence with respect to the captured image, and when the body is recognized over a predetermined number or more consecutive frames, it is determined that there is an internal entry of a person. Can be. Here, the number of frames that are the basis of the determination for detecting the worker and the level of similarity for determining the extracted image may be preset by the administrator, but may be gradually improved according to the learning data of the detection engine. .

In other words, if the operator's actions (entry, entry and exit) is judged through the camera, there is a problem that structurally increase the possibility of misdetection (classification as entry) and false positives (classification as entry). The image-based sensing module according to the present invention may perform an emergency stop determination as soon as the body is observed, and a specific area of the image photographed using a camera or a CCTV may be set as an area where no operator should be present.

FIG. 4A is a reference diagram for explaining a method for checking whether an operator exists in an image area set to determine similarity based on an extracted image.

In FIG. 4 (a), extraction is performed in a specific image area on a predetermined number of consecutive frames or more, in which the similarity with the learned image database based on a data set composed of predetermined object images is equal to or greater than a predetermined level. If the image exists, it can be determined that the worker exists.

The image capturing module (eg, camera, CCTV, etc.) continuously photographs the area where the worker can be located in the target facility in real time and delivers it to the image-based sensing module. Accordingly, the image-based sensing module may cluster data for image classification by extracting a single frame from an image transmitted from the image capturing module. For example, a single frame may be analyzed in the image-based sensing module, and the analyzed result may be output as an image and data, respectively. However, since a frame related to one image is less than 0.1 second in time units, it is not preferable to stop the equipment by looking at the result value of a single frame, and determine whether a real person has entered the equipment by converting it to cumulative data. It is desirable to

Therefore, for example, when analyzing an image of 15 fps (Frame Per Second), the result (image, data) is “Person 1 92%, Person 2 72%, table 100%”. Since “Person 1, Person 2” are two entities classified as bodies on a single frame, the image-based detection module may determine that a person has been detected when the threshold is set by an administrator. . For example, if the threshold is set to 75%, the "Person 1" entity can be judged as a body on a single frame, and the other entity "Person 2" does not show similarity above the threshold and can be analyzed using additional frames. In this case, by applying a high threshold on a single frame to determine the similarity of the object, and applying a method of determining the similarity by applying a relatively low threshold on successive frames, it is more efficient to determine the presence or absence. You may.

That is, the facility safety management system may determine whether the operation target equipment is operable by determining an additional frame when it is determined that the determination data is insufficient or that it is not a human body. If it detects a person coming in, it may send an emergency stop command to the facility to be locked. In addition, in order to improve the performance of the stationary recording of the work target facility and the performance of the image-based sensing module, an image determined to be entered by a person may be separately stored.

FIG. 4B is a reference diagram for explaining a case in which a specific area of the image is set as an area where an operator should not be present. When detecting an image different from a predetermined image within a specific image, it may be determined that an operator exists. For example, even if only the equipment should be present in the image area, if an image different from that of the equipment is detected, the operation may be temporarily stopped to prevent an accident due to an unexpected entry of an operator. In other words, performing the operator detection applying artificial intelligence to all areas on the image may cause a load on the operation of the control server, and in order to detect more efficiently, the target equipment is stopped only by the presence of different images in a specific image area. You can.

In addition, the image-based sensing module can effectively prevent accidents by setting an image extracted for a specific area on one image through a detection engine and determining different images for the remaining areas. Can be.

The embodiments of the present invention disclosed in the specification and the drawings are only specific examples to easily explain the technical contents of the present invention and aid the understanding of the present invention, and are not intended to limit the scope of the present invention. It is apparent to those skilled in the art that other modifications based on the technical idea of the present invention can be carried out in addition to the embodiments disclosed herein.

The facility safety management system combining the wearable device and the human body sensing module as described above can be applied to various industrial fields.

Claims (6)

In the facility safety management system that combines a wearable device and a human body detection module,
An operator identification module for obtaining sensing information about an operator from at least one sensing module including the wearable device, and identifying an operator in a work target facility according to the obtained at least one sensing information; And
And a lock control signal output module configured to output a lock control signal to the work target facility according to at least one of a control signal input from the control module of the work target facility or a worker detection signal input from the worker identification module. ,
The worker confirmation module,
When the wearable device is activated based on the priority of the at least one sensing module and receives a lock code associated with the work target facility,
Only when a unique identifier of the wearable device and an unlock code corresponding to the lock code are recognized, it is determined that the absence of the work is confirmed in the work target facility.
Safety management system. The method of claim 1,
The lock control signal output module,
Outputs a lock control signal for stopping operation of the work target facility when a lock signal of the work target facility is input or when the worker is confirmed by the worker identification module among the control signals;
Outputting a lock control signal for starting the operation of the work target facility only when an unlock signal of the work target facility is input and the absence of an operator is confirmed in the work target facility. Characterized by
Safety management system. The method of claim 1,
The wearable device may be activated by recognizing wear of the worker.
Safety management system. The method of claim 3, wherein
The at least one sensing module
A wearable device survey module consisting of three or more antennas,
The wearable device survey module,
Characterized in that configured to compare the location of the worker and the area of the work target facility according to triangulation based on the distance from each of the three or more antennas to the wearable device,
Safety management system. The method of claim 1,
The at least one sensing module
Includes an image-based detection module,
The image-based detection module,
In the first image area on the predetermined number or more consecutive frames, when there is an extracted image whose degree of similarity with the image database learned based on a data set composed of predetermined object images is higher than or equal to a preset level, Characterized in that the worker exists,
Safety management system. The method of claim 1,
The at least one sensing module
Includes an image-based detection module,
The image-based detection module,
Characterized in that the operator is present in the second image area, when detecting an image different from the predetermined image,
Safety management system.

Images