Substation operation safety protection monitoring method, device and equipment and storage medium

Abstract

The invention discloses a substation operation safety protection monitoring method, device and equipment and a storage medium, and the method comprises the steps: loading work ticket data through a safety protection monitoring robot, determining a target operator from the work ticket data, following the target operator and collecting video data in the operation process of the target operator in a substation, and storing the video data in the substation; and identifying the video data based on the work ticket data to determine whether the target operating personnel has violation behaviors, and if yes, generating violation alarm information and giving an alarm. According to the invention, the video does not need to be sent to a far-end terminal for manual video monitoring, the method is not influenced by human subjective factors, the security monitoring robot at the site of the transformer substation can accurately and rapidly identify the illegal behaviors of the target operating personnel in real time, and can timely and rapidly give an alarm to stop the illegal behaviors, thereby improving the safety of the transformer substation. And the security and protection monitoring robot can follow the target operating personnel, is not limited by blind spots of a fixed camera, and can perform operation monitoring on the target operating personnel in all directions.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid safety protection, and in particular to a substation operation safety protection monitoring method, device, equipment and storage medium. Background Art

[0002] Due to the large variety of equipment and complex layout in the substation, when operators perform related operations in the substation, they need to be monitored for safety protection.

[0003] In the prior art, cameras are installed in substations to collect work videos of operators through the cameras and transmit the videos to remote monitoring terminals. Monitoring personnel supervise operators through work videos and maintain communication with operators. When operators are found to have violated regulations through work videos, they are reminded through communication calls. However, when using manual videos for safety protection monitoring, when multiple operations are carried out in parallel, a large number of monitoring personnel are required to watch the videos in real time to detect violations, which consumes a lot of manpower and is affected by human subjectivity, making it difficult to detect violations in a timely manner. Summary of the invention

[0004] The present invention provides a substation operation safety protection monitoring method, device, equipment and storage medium to solve the problem that a camera is set in the substation to collect the operation site video and send it to a remote terminal, manual video monitoring at the remote terminal requires a lot of manpower, and it is difficult to detect and stop illegal behaviors in time due to human subjective influence.

[0005] In a first aspect, the present invention provides a substation operation safety protection monitoring method, comprising:

[0006] Applied to security monitoring robots, including:

[0007] Load work ticket data;

[0008] Determining a target operator from the work ticket data;

[0009] During the operation of the target operator in the substation, following the target operator and collecting video data;

[0010] Identify the video data based on the work ticket data to determine whether the target operator has violated the regulations;

[0011] If so, generate violation warning information and issue an alarm.

[0012] Optionally, the work ticket data includes a target operator identification, and determining the target operator from the work ticket data includes:

[0013] Reading a target operator identification from the work ticket data;

[0014] A standard facial image of the target operator is acquired based on the target operator identification.

[0015] Optionally, during the process of the target operator working in the substation, following and collecting video data of the target operator includes:

[0016] Collecting video data while the target operator is working in the substation, and identifying the standard face image from the video data;

[0017] The security monitoring robot is controlled to follow the standard face image to collect video data.

[0018] Optionally, the security monitoring robot includes a positioning module, which identifies the video data based on the work ticket data to determine whether the target operator has violated the regulations, including:

[0019] Acquire a first position of the security monitoring robot, and determine a second position of the target operator based on the first position;

[0020] When the second position meets the preset condition, determining the working area of ​​the target operator;

[0021] Determining whether the operation area is the target operation area in the work ticket data;

[0022] If not, an alarm message of wrong working location is generated and an alarm is issued;

[0023] If yes, identifying first security measures arrangement data of the operation area from the video data;

[0024] determining whether the security measures of the operation area meet preset conditions according to the first security measures arrangement data and the second security measures arrangement data in the work ticket data;

[0025] If not, an alarm message is generated indicating that security measures are improperly arranged;

[0026] If so, inputting the video data into a violation recognition model to obtain a behavior recognition result;

[0027] Determine whether the behavior recognition result contains any preset violation behavior;

[0028] If so, execute the steps of generating violation alarm information and issuing an alarm.

[0029] Optionally, after determining the operating area of ​​the target operator, the method further includes:

[0030] Recognizing a facial image from the video data;

[0031] When the facial image is an image of a person other than the target operator, a warning message is generated that an illegal person has entered the work area.

[0032] Optionally, after generating the violation alarm information and issuing the alarm, the following is also included:

[0033] If the identification results all indicate that there are violations within the preset time period, violation alarm information is sent to the remote monitoring terminal, and the remote monitoring terminal switches to the manual monitoring mode after receiving the violation alarm information.

[0034] Optionally, after determining that the security measures of the work area meet preset conditions according to the first security measures arrangement data and the second security measures arrangement data in the work ticket data, the method further includes:

[0035] capturing a pre-operation image of the operation area from the video data;

[0036] After receiving the operation end instruction, capturing a post-operation image of the operation area from the video data;

[0037] Determine a job result according to the pre-job image and the post-job image;

[0038] Determine whether the operation result is qualified;

[0039] If not, an alarm message indicating that the result is unqualified is generated.

[0040] In a second aspect, the present invention provides a substation operation safety protection monitoring device, which is applied to a security monitoring robot, comprising:

[0041] Work ticket loading module, used to load work ticket data;

[0042] A target operator determination module, used to determine the target operator from the work ticket data;

[0043] A video data acquisition module, used for collecting video data of the target operator during the operation of the target operator in the substation;

[0044] A violation identification module is used to identify the video data based on the work ticket data to determine whether the target operator has violated the regulations. If so, the violation alarm module is executed; if not, the video data acquisition module is executed;

[0045] The violation alarm module is used to generate violation alarm information and issue an alarm.

[0046] In a third aspect, the present invention provides an electronic device, the electronic device comprising:

[0047] at least one processor; and

[0048] a memory communicatively connected to the at least one processor; wherein,

[0049] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the substation operation safety protection monitoring method described in any one of the first aspects of the present invention.

[0050] In a fourth aspect, the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the substation operation safety protection monitoring method described in any one of the first aspects of the present invention when executed.

[0051] The embodiment of the present invention configures a security monitoring robot in the substation, and determines the target operator after loading the work ticket data on the security monitoring robot. The security monitoring robot follows the target operator during the operation of the target operator to collect video data, and identifies whether the target operator has violated the regulations based on the video data. If so, a violation alarm information alarm is generated. There is no need to send the video to a remote terminal for manual video monitoring, and it is not affected by human subjective factors. The security monitoring robot at the substation site can identify the violation of the target operator in real time, accurately and quickly, and can promptly and quickly issue an alarm to stop the violation. Moreover, the security monitoring robot can follow the target operator, is not limited by the blind spots of fixed cameras, and can monitor the operation of the target operator in all directions.

[0052] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0054] Figure 1 This is a flow chart of a substation operation safety protection monitoring method provided by Embodiment 1 of the present invention;

[0055] Figure 2 This is a flow chart of a substation operation safety protection monitoring method provided by Embodiment 2 of the present invention;

[0056] Figure 3 The present invention is a flowchart of an example of a method for monitoring the safety protection of substation operations;

[0057] Figure 4 It is a structural schematic diagram of a substation operation safety protection monitoring device provided by Embodiment 3 of the present invention;

[0058] Figure 5 It is a schematic diagram of the structure of an electronic device provided in Embodiment 4 of the present invention. DETAILED DESCRIPTION

[0059] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0060] Embodiment 1

[0061] Figure 1 This is a flowchart of a substation operation safety protection monitoring method provided in the first embodiment of the present invention. This embodiment can be applied to the situation where the safety protection monitoring of the operating personnel is performed during the substation operation. The method can be executed by a substation operation safety protection monitoring device. The substation operation safety protection monitoring device can be implemented in the form of hardware and / or software, and can be configured in an electronic device, such as in the controller of a security monitoring robot. Figure 1 As shown, the substation operation safety protection monitoring method includes:

[0062] S101, load work ticket data.

[0063] The substation of this embodiment can be equipped with at least one security monitoring robot, which can move within the substation and is equipped with a camera (which can be a single camera or a dual camera). After the operator arrives at the substation, he can first load the work ticket data on the security monitoring robot. In one example, the operator can place the paper work ticket on the scanning device of the security monitoring robot, and the security monitoring robot scans the paper work ticket to obtain the work ticket data. In another example, the operator can enter the work ticket number on the security monitoring robot, and the security monitoring robot can load the work ticket data from the remote server according to the work ticket number.

[0064] The work ticket data may include the identification of the operator (such as the operator's work number), the work location (the coordinates of the work equipment), and may also include work data such as security measures, tool lists, and operation items.

[0065] S102. Determine the target operator from the work ticket data.

[0066] In one embodiment, the target operator identification may be read from the work ticket data, and the standard facial image of the target operator may be acquired based on the target operator identification.

[0067] S103. When the target operator is working in the substation, follow the target operator and collect video data.

[0068] Specifically, video data can be collected while the target operator is working in the substation, and a standard face image can be identified from the video data, and the security monitoring robot can be further controlled to follow the person with the standard face image and collect video data, so that the security monitoring robot can follow the target operator and collect video data for the target operator. It should be noted that sensors such as laser radar and ultrasonic waves can be installed on the security monitoring robot to achieve intelligent obstacle avoidance and path planning, wherein personnel following, obstacle avoidance and path planning can refer to existing robot walking control related algorithms, and the embodiments of the present invention will not be described in detail here.

[0069] S104. Identify the video data based on the work ticket data to determine whether the target operator has violated the regulations.

[0070] The violations in this embodiment vary depending on the work items in the work ticket. In one embodiment, the violations may include mistakenly entering an interval, illegal entry of personnel into the work area, not wearing a safety belt during high-altitude work, entering a high-voltage field or GIS room without wearing a safety helmet, failure to properly arrange safety measures, failure to operate according to the operation ticket, etc.

[0071] Specifically, various violation behavior recognition models can be pre-trained, and video data can be input into the violation behavior recognition model to obtain behavior recognition results, which may include violations. Then, it is determined whether the violations in the behavior recognition results are violations preset in the work tasks of this work ticket. If so, it is determined that the target operator has violated the regulations, and S105 can be executed. If not, it can return to execute S103 to continue collecting video data for monitoring.

[0072] S105: Generate violation warning information and issue an alarm.

[0073] When it is identified that the target staff member has violated the regulations during the operation, the security monitoring robot can generate violation alarm information and issue sound and light alarms, such as through warning indicator lights and playing information describing the violation, to stop the target staff member from continuing to perform the violation.

[0074] The embodiment of the present invention configures a security monitoring robot in the substation, and determines the target operator after loading the work ticket data on the security monitoring robot. The security monitoring robot follows the target operator during the operation of the target operator to collect video data, and identifies whether the target operator has violated the regulations based on the video data. If so, a violation alarm information alarm is generated. There is no need to send the video to a remote terminal for manual video monitoring, and it is not affected by human subjective factors. The security monitoring robot at the substation site can identify the violation of the target operator in real time, accurately and quickly, and can promptly and quickly issue an alarm to stop the violation. Moreover, the security monitoring robot can follow the target operator, is not limited by the blind spots of fixed cameras, and can monitor the operation of the target operator in all directions.

[0075] Embodiment 2

[0076] Figure 2 A flowchart of a substation operation safety protection monitoring method provided in the second embodiment of the present invention is provided. The embodiment of the present invention is optimized on the basis of the above-mentioned first embodiment. Figure 2 As shown, the substation operation safety protection monitoring method includes:

[0077] S201, load work ticket data.

[0078] S202. Determine the target operator from the work ticket data.

[0079] S203. When the target operator is working in the substation, follow the target operator and collect video data.

[0080] The above S201-S203 may refer to S101-S103 in the first embodiment, and will not be described in detail here.

[0081] S204: Acquire a first position of the security monitoring robot, and determine a second position of the target operator based on the first position.

[0082] In this embodiment, a positioning sensor can be provided on the security monitoring robot. The positioning sensor can be used to position the security monitoring robot, obtain the first position of the security monitoring robot, and obtain the second position of the target operator based on the imaging principle of the camera on the security monitoring robot. Exemplarily, the camera can be a dual camera, and the dual camera can be used to determine the distance and direction of the target operator relative to the security monitoring robot, and the second position of the target operator can be calculated in combination with the first position of the security monitoring robot. The second position can be the world coordinates of the target operator or the coordinates of the target operator in the substation coordinate system.

[0083] S205: When the preset conditions are met at the second position, determine the working area of ​​the target operator.

[0084] In one embodiment, the target operator needs to walk to the area specified on the work ticket in the substation to perform the work. For example, the work ticket records the target interval of the work. When the target operator walks, the second position of the target operator can be calculated in real time. If the second position changes within a small range, it means that the target operator has stopped walking and the work area is determined within a small range. The preset condition can be set so that the multiple second positions collected are positions within a preset range. If the multiple second positions collected within a preset time period change within the preset range, it can be determined that the target operator stops walking forward. The target operator may determine whether to reach the target work area within a small range. A work area can be determined based on the second position, such as determining the area within the preset range of the current second position as a work area.

[0085] S206: Determine whether the operation area is the target operation area in the work ticket data.

[0086] Exemplarily, the center of the current working area can be compared with the center of the target working area in the work ticket data. If the distance between the center of the current working area and the center of the target working area is less than a preset value, it means that the current working area is the target working area, and S208 can be executed. If the distance between the center of the current working area and the center of the target working area is greater than or equal to the preset value, it means that the currently determined working area is not the target working area. For example, the target operating personnel may have mistakenly entered the interval, and S207 can be executed.

[0087] S207: Generate alarm information of wrong working location and issue an alarm.

[0088] When the work area determined after the target operator stops walking is not the target work area, the security monitoring robot can generate an alarm message of an incorrect work location and broadcast the alarm message to remind the target operator that the area where he currently stops walking is not the target work area.

[0089] S208: Identify first security measures deployment data of the operation area from the video data.

[0090] In this embodiment, the security measures arrangement data may be information describing the security measures arranged by the target operator in the operation area. In this embodiment, the security measures arrangement recognition model may be pre-trained, and the training may be specifically performed through the following steps:

[0091] S1. Acquire a sample image including security measures, where the sample image is annotated with security measures arrangement data;

[0092] S2. Input the sample image into the security measures layout recognition model, identify the security measures tools (such as identification signs, red cloth, isolation fences, grounding wires, etc.) in the security measures layout recognition model, and output the predicted security measures layout data to describe the current safety measures taken by the target operator;

[0093] S3. Calculate the loss rate, such as mean square error loss, by using the predicted security measure arrangement data and the marked security measure arrangement data. Specifically, the mean square error loss or the cross entropy loss may be calculated by determining whether the security measure object and the location of the security measure object are identified.

[0094] S4, determine whether the training stop condition is met, such as whether the loss rate is less than a preset value or whether the number of iterative training times reaches a preset number; if so, execute S5, if not, execute S6;

[0095] S5. Determine that the security measures arrangement recognition model has completed training;

[0096] S6. Perform gradient descent on the model parameters of the security measures layout recognition model according to the loss rate to adjust the model parameters, such as stochastic gradient descent, batch gradient descent, etc., and return to S2 to continue training.

[0097] After the security measures arrangement recognition model is trained, the video data may be input into the security measures arrangement recognition model to obtain the first security measures arrangement data.

[0098] S209: Determine whether the security measures of the work area meet preset conditions according to the first security measures arrangement data and the second security measures arrangement data in the work ticket data.

[0099] Exemplarily, the second security measure layout data in the work ticket can be: hang "Working Here" signs in front and behind the 110kV bypass 1030 measurement and control device of the 80P 110kV bypass 1030 and busbar 1012 measurement and control panels in the main control room, and hang red cloth isolation in front and behind adjacent operating panels and other operating devices on the same screen. After inputting the video data into the security measures layout recognition model, the first security measures layout data is obtained, and the first security measures layout data and the second security measures layout data are compared to determine whether all security measures are in place, that is, by comparing the first security measures layout data and the second security measures layout data, it is determined whether there are signboards for the 80P 110kV bypass 1030 and the busbar 1012 measurement and control panel cabinet, and the device name and the pressure plate name are identified to determine whether the 110kV busbar 1012 measurement and control panel cabinet and its pressure plate have been enclosed by red cloth. If not enclosed by red cloth or no signboard is hung, the operating personnel are warned to correctly perform the layout of the safety measures listed in the work ticket, and the alarm is continued until the safety measures are correctly arranged.

[0100] It should be noted that the coding features can be obtained by encoding the first security measure arrangement data and the second security measure arrangement data, and the similarity of the two coding features can be calculated. If the similarity is greater than a threshold, it is determined that the preset conditions are met and S211 can be executed. If not, it is determined that the security measures are improperly arranged and S210 can be executed.

[0101] S210: Generate alarm information about improper arrangement of security measures.

[0102] If it is determined based on the first security measures deployment data and the second security measures deployment data in the work ticket data that the security measures in the work area do not meet the preset conditions, it means that the target operator has not correctly or completely deployed the corresponding security measures required on the work ticket. An alarm message of improper security measures deployment can be generated and played to remind the target operator to deploy security measures.

[0103] S211, input the video data into the violation recognition model to obtain the behavior recognition result.

[0104] In this embodiment, the violation recognition model can be pre-trained, and the training can be specifically performed through the following steps:

[0105] S1. Obtain sample images including violations, and annotate the first violation data in the sample images. For example, obtain images including violations such as not wearing a safety belt when working at height, not wearing a safety helmet when entering a high-voltage field or GIS room, no one on the ladder when climbing a ladder, and blocking a camera as sample images, and annotate the violation category as the first violation data;

[0106] S2, inputting the sample image into the violation recognition model, identifying the behavior of the person in the violation recognition model, and outputting the predicted second violation behavior data;

[0107] S3. Calculate the loss rate using the second violation data and the marked first violation data, such as mean square error loss. Specifically, the loss rate may be calculated by calculating whether there is a violation and the difference in the category of the violation between the second violation data and the first violation data;

[0108] S4, determine whether the training stop condition is met, such as whether the loss rate is less than a preset value or whether the number of iterative training times reaches a preset number; if so, execute S5, if not, execute S6;

[0109] S5. Determine that the violation recognition model has completed training;

[0110] S6. Perform gradient descent on the model parameters of the violation recognition model according to the loss rate to adjust the model parameters, such as stochastic gradient descent, batch gradient descent, etc., and return to S2 to continue training.

[0111] After the target operator has arranged the safety measures, the target operator usually starts to perform related operations. The collected video data can be input into a pre-trained violation recognition model to obtain a behavior recognition result, which includes whether there is a violation and the category of the violation.

[0112] S212: Determine whether the behavior recognition result contains any preset violation behavior.

[0113] This embodiment can pre-configure the violations prohibited by the work tasks of this work ticket, and then compare the violations identified in the recognition results with the pre-configured violations. If the preset violations exist in the recognition results, S213 can be executed. If not, return to S211 and continue to collect video data to identify violations.

[0114] S213: Generate violation warning information and issue an alarm.

[0115] When the target operator is identified to have violated the rules, the security monitoring robot can generate a violation alarm message and broadcast the violation alarm message to stop the target operator from continuing to perform the violation. It should be noted that when generating the alarm message, the video clips including the violation can be intercepted as evidence, and a record and a violation list can be generated. The violation list can include the time, location, work ticket number and violation clauses of the illegal operation. The following is an example of a violation list:

[0116]

[0117]

[0118] like Figure 3The flowchart of an example of substation operation safety protection monitoring is shown as follows: Figure 3 As shown, the specific process is as follows:

[0119] S1, work ticket scanning;

[0120] S2. Determine the work location;

[0121] S3. Follow the operators and identify the safety measures layout;

[0122] S4, determine whether the safety measures are properly arranged, if not, execute S5, if yes, execute S6;

[0123] S5, generating an alarm message to remind that the safety measures are improperly arranged, and returning to S3;

[0124] S6, determine whether the safety measures have been deployed, if so, execute S7, if not, execute S5;

[0125] S7, work permit;

[0126] S8, collecting pre-operation images;

[0127] S9, collecting video data during the operation;

[0128] S10, identifying whether there is any violation through video data, if yes, executing S11; if no, executing S17;

[0129] S11, violation warning;

[0130] S12, identify whether the violation is ongoing, if so, execute S13, if not, execute S9;

[0131] S13, remote alarm, save violation records;

[0132] S14: Has the remote monitoring personnel taken over? If so, execute S15; if not, continue to alarm and return to S12;

[0133] S15, the remote monitoring personnel will take over;

[0134] S17. Safety measures are restored during the operation;

[0135] S18, collecting images after operation;

[0136] S19: Check whether the images before and after the operation are consistent. If yes, the work is finished and the operation is completed. If not, execute S20;

[0137] S20, generate a voice alarm, and return to S18.

[0138] This embodiment determines the second position of the target operator through the first position of the security monitoring robot, further determines the work area through the second position, and judges whether the work area is the target work area specified in the work ticket. If not, an alarm message of incorrect work location is generated and an alarm is issued. If so, video data is used to identify whether the target operator has correctly arranged safety measures. If not, an alarm message of improper security measures arrangement is generated. If so, video data is used to identify whether the target operator has violated regulations. If so, violation alarm information is generated and an alarm is issued. This realizes the determination of the target operator's work location, whether the safety measures are arranged correctly, and whether there are any violations through video data, and can issue real-time on-site alarms without sending the video to a remote terminal for manual video monitoring, and is not affected by human subjective factors. The security monitoring robot at the substation site can identify the target operator's work location, security measures and violations in real time, accurately and quickly, and can promptly and quickly issue an alarm to stop violations. The security monitoring robot can follow the target operator, is not limited by the blind spots of fixed cameras, and can monitor the target operator's operations in all directions.

[0139] In an optional embodiment, if the identification results within a preset time period are all violations, a violation alarm message is sent to a remote monitoring terminal, which switches to a manual monitoring mode after receiving the violation alarm message. For example, after the target operator is initially identified as performing a violation, if the target operator continues to perform a violation within a preset time period, a violation alarm message is sent to the remote monitoring terminal, which switches to a manual monitoring mode after receiving the violation alarm message. A background monitoring person contacts the target operator to stop the violation, thereby achieving a situation where the on-site security monitoring robot reminds the target operator that it cannot stop the violation and the violation is stopped manually.

[0140] In one embodiment, for the target work area where the target operator is located, after collecting video data, facial images can be identified from the video data. When the facial image is an image of a person other than the target operator, an alarm message is generated that an illegal person has entered the work area, thereby realizing the identification through video data whether there are persons other than the target operator specified in the work ticket. If so, it is determined that an illegal person has entered the target work area. The security monitoring robot can generate an alarm message that an illegal person has entered, and play the alarm message to remind the illegal person to leave the target work area.

[0141] In addition, after identifying the facial image of the target operator, the target operator's safety regulations test, skill qualification certificate, special operation certificate (such as high altitude climbing) and other data can be read through the target operator's facial image to determine whether the target operator is qualified to perform the task of the work ticket. If not, an insufficient qualification alarm message is generated to remind the target staff that they are insufficiently qualified.

[0142] In another embodiment, a pre-job image of the operation area (for example, after security measures are arranged) can be captured from the video data. After receiving the operation end instruction, a post-job image of the operation area can be captured from the video data. The operation result is determined based on the pre-job image and the post-job image to determine whether the operation result is qualified. If not, an alarm message indicating that the result is unqualified is generated to issue an alarm. The operation result is determined based on the pre-job image and the post-job image. The pre-job image and the post-job image can be input into an image comparison model to obtain the difference between the pre-job image and the post-job image. The difference can be used to determine the equipment status before and after the operation and the operation area comparison, so as to automatically identify whether the equipment status before and after the operation is consistent, so as to automatically determine whether there is any unsafe behavior such as missed recovery of the equipment and whether the tools are left on site, and record the work locations where the operators have worked during the operation, and determine whether there are any work locations that have been missed during the operation recovery process.

[0143] Embodiment 3

[0144] Figure 4 This is a schematic diagram of the structure of a substation operation safety protection monitoring device provided by the third embodiment of the present invention. Figure 4 As shown, the substation operation safety protection monitoring device includes:

[0145] A work ticket loading module 401 is used to load work ticket data;

[0146] A target operator determination module 402 is used to determine the target operator from the work ticket data;

[0147] The video data acquisition module 403 is used to collect video data of the target operator during the operation of the target operator in the substation;

[0148] A violation identification module 404 is used to identify the video data based on the work ticket data to determine whether the target operator has violated the regulations. If so, the violation alarm module 405 is executed; if not, the video data acquisition module 403 is executed;

[0149] The violation warning module 405 is used to generate violation warning information and issue an alarm.

[0150] Optionally, the work ticket data includes a target operator identification, and the target operator determination module 402 includes:

[0151] A personnel identification reading unit, used for reading the target operating personnel identification from the work ticket data;

[0152] The standard face image acquisition unit is used to acquire the standard face image of the target operator based on the target operator identification.

[0153] Optionally, the video data acquisition module 403 includes:

[0154] A target operator identification unit, used to collect video data during the operation of the target operator in the substation, and identify the standard face image from the video data;

[0155] The video following acquisition unit is used to control the security monitoring robot to follow the standard face image to acquire video data.

[0156] Optionally, the security monitoring robot includes a positioning module, and the violation identification module 404 includes:

[0157] a target operator position determination unit, configured to obtain a first position of the security monitoring robot and determine a second position of the target operator based on the first position;

[0158] A working area determining unit, configured to determine a working area of ​​the target operator when the second position meets a preset condition;

[0159] An operation area determination unit, used to determine whether the operation area is the target operation area in the work ticket data, and if so, execute the security measures arrangement data identification unit, and if not, execute the work location error alarm unit;

[0160] A work location error alarm unit, used to generate work location error alarm information and issue an alarm;

[0161] a security measure arrangement data identification unit, configured to identify first security measure arrangement data of the operation area from the video data;

[0162] A security measure judgment unit, used to determine whether the security measures of the operation area meet the preset conditions according to the first security measure arrangement data and the second security measure arrangement data in the work ticket data. If yes, the behavior recognition unit is executed; if no, the security measure alarm unit is executed;

[0163] A security measures alarm unit, used to generate alarm information of improper security measures deployment;

[0164] A behavior recognition unit, used for inputting the video data into a violation recognition model to obtain a behavior recognition result;

[0165] The recognition result judgment unit is used to judge whether the behavior recognition result contains preset illegal behaviors, and if so, execute the illegal warning module 405.

[0166] Optionally, the violation identification module 404 further includes:

[0167] A face recognition unit, used to recognize a face image from the video data;

[0168] The illegal person intrusion alarm unit is used to generate alarm information that an illegal person enters the working area when the face image is an image of a person other than the target operating person.

[0169] Optionally, also include:

[0170] The remote alarm module is used to send violation alarm information to the remote monitoring terminal if the identification results are all violations within a preset time period. The remote monitoring terminal switches to the manual monitoring mode after receiving the violation alarm information.

[0171] Optionally, the violation identification module 404 further includes:

[0172] A pre-operation image acquisition unit, used for capturing a pre-operation image of the operation area from the video data;

[0173] A post-operation image acquisition unit, configured to capture a post-operation image of the operation area from the video data after receiving a job end instruction;

[0174] A job result determination unit, configured to determine a job result according to the pre-job image and the post-job image;

[0175] The operation result judging unit is used to judge whether the operation result is qualified, and if not, execute the unqualified alarm unit;

[0176] The unqualified alarm unit is used to generate alarm information of unqualified results for alarm.

[0177] The substation operation safety protection monitoring device provided in the embodiment of the present invention can execute the substation operation safety protection monitoring method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0178] Embodiment 4

[0179] Figure 5A schematic diagram of the structure of an electronic device 40 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0180] like Figure 5 As shown, the electronic device 40 includes at least one processor 41, and a memory connected to the at least one processor 41, such as a read-only memory (ROM) 42, a random access memory (RAM) 43, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 41 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 42 or the computer program loaded from the storage unit 48 to the random access memory (RAM) 43. In the RAM 43, various programs and data required for the operation of the electronic device 40 can also be stored. The processor 41, the ROM 42, and the RAM 43 are connected to each other through a bus 44. An input / output (I / O) interface 45 is also connected to the bus 44.

[0181] A number of components in the electronic device 40 are connected to the I / O interface 45, including: an input unit 46, such as a keyboard, a mouse, etc.; an output unit 47, such as various types of displays, speakers, etc.; a storage unit 48, such as a disk, an optical disk, etc.; and a communication unit 49, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 49 allows the electronic device 40 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0182] The processor 41 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 41 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 41 executes the various methods and processes described above, such as a substation operation safety protection monitoring method.

[0183] In some embodiments, the substation operation safety protection monitoring method can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 48. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 40 via the ROM 42 and / or the communication unit 49. When the computer program is loaded into the RAM 43 and executed by the processor 41, one or more steps of the substation operation safety protection monitoring method described above can be performed. Alternatively, in other embodiments, the processor 41 can be configured to execute the substation operation safety protection monitoring method in any other appropriate manner (for example, by means of firmware).

[0184] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0185] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0186] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, device, or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0187] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0188] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0189] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0190] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0191] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A substation operation safety protection monitoring method, characterized in that: Applied to security monitoring robots, including: Load work ticket data; Determining a target operator from the work ticket data; During the operation of the target operator in the substation, following the target operator and collecting video data; Identify the video data based on the work ticket data to determine whether the target operator has violated the regulations; If so, generate violation warning information and issue an alarm.

2. The method according to claim 1, characterized in that The work ticket data includes a target operator identification, and determining the target operator from the work ticket data includes: Reading a target operator identification from the work ticket data; A standard facial image of the target operator is acquired based on the target operator identification.

3. The method according to claim 2, characterized in that When the target operator is working in the substation, the target operator is followed and video data is collected, including: Collecting video data while the target operator is working in the substation, and identifying the standard face image from the video data; The security monitoring robot is controlled to follow the standard face image to collect video data.

4. The method according to any one of claims 1 to 3, characterized in that: The security monitoring robot includes a positioning module, which identifies the video data based on the work ticket data to determine whether the target operator has violated the regulations, including: Acquire a first position of the security monitoring robot, and determine a second position of the target operator based on the first position; When the second position meets the preset condition, determining the working area of ​​the target operator; Determining whether the operation area is the target operation area in the work ticket data; If not, an alarm message of wrong working location is generated and an alarm is issued; If yes, identifying first security measures arrangement data of the operation area from the video data; determining whether the security measures of the operation area meet preset conditions according to the first security measures arrangement data and the second security measures arrangement data in the work ticket data; If not, an alarm message is generated indicating that security measures are improperly arranged; If so, inputting the video data into a violation recognition model to obtain a behavior recognition result; Determine whether the behavior recognition result contains any preset violation behavior; If so, execute the steps of generating violation alarm information and issuing an alarm.

5. The method according to claim 4, characterized in that After determining the operating area of ​​the target operator, the method further includes: Recognizing a facial image from the video data; When the facial image is an image of a person other than the target operator, a warning message is generated that an illegal person has entered the work area.

6. The method according to claim 4, characterized in that After the violation alarm information is generated and the alarm is issued, it also includes: If the identification results all indicate that there are violations within the preset time period, violation alarm information is sent to the remote monitoring terminal, and the remote monitoring terminal switches to the manual monitoring mode after receiving the violation alarm information.

7. The method according to claim 4, characterized in that After determining that the security measures of the operation area meet the preset conditions according to the first security measures arrangement data and the second security measures arrangement data in the work ticket data, the method further includes: capturing a pre-operation image of the operation area from the video data; After receiving the operation end instruction, capturing a post-operation image of the operation area from the video data; Determine a job result according to the pre-job image and the post-job image; Determine whether the operation result is qualified; If not, an alarm message indicating that the result is unqualified is generated.

8. A substation operation safety protection monitoring device, characterized in that: Applied to security monitoring robots, including: Work ticket loading module, used to load work ticket data; A target operator determination module, used to determine the target operator from the work ticket data; A video data acquisition module, used for collecting video data of the target operator during the operation of the target operator in the substation; A violation identification module is used to identify the video data based on the work ticket data to determine whether the target operator has violated the regulations. If so, the violation alarm module is executed; if not, the video data acquisition module is executed; The violation alarm module is used to generate violation alarm information and issue an alarm.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the substation operation safety protection monitoring method described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the substation operation safety protection monitoring method according to any one of claims 1 to 7 when executed.

Images