Industrial equipment monitoring method and device based on industrial internet

Abstract

The invention relates to the technical field of industrial scene monitoring, and particularly discloses an industrial equipment monitoring method and device based on the industrial Internet, and the method comprises the steps: obtaining scene data according to information collection equipment in an industrial scene, carrying out the recognition of the scene data, and determining activated industrial equipment; reversely deducing a product type according to the activated industrial equipment, comparing the product type with a recorded task table, and judging a standard abnormality level; positioning workers in the scene data, acquiring distribution information of the workers, and judging a floating anomaly level according to the distribution information; and feeding back the reference anomaly level and the floating anomaly level in real time. According to the invention, the working state of the industrial equipment is acquired by the sensor, then the equipment needing to be detected is positioned, the running state of the equipment is acquired by the camera, then the working task is deduced reversely, the working task is compared and matched with the current task, the safety condition is judged according to the matching result, and the comprehensiveness is extremely high.

Description

Technical Field

[0001] The present invention relates to the field of industrial scene monitoring technology, and specifically to an industrial equipment monitoring method and device based on the industrial Internet. Background Art

[0002] Industrial Internet refers to connecting industrial equipment, systems and people through Internet technology to collect, transmit, store and analyze data to improve the efficiency, quality and flexibility of industrial production. The core elements of Industrial Internet include: Internet of Things (IoT) devices: sensors, RFID tags, smart devices, etc., used to collect data and achieve interconnection; data analysis and big data technology: by analyzing the collected data, optimizing production processes, predicting equipment failures and improving product quality.

[0003] Based on the working Internet, the production workshop can be monitored in real time to determine the degree of abnormality of the environment. The existing workshop risk level determination process is relatively simple, and most of them are based on sensors built into industrial equipment to detect abnormal signals. When abnormal signals are detected, abnormal information is reported. This can only detect whether there are abnormalities in the operation process of the equipment, which is not comprehensive enough. How to improve the comprehensiveness of risk monitoring is the technical problem that the technical solution of the present invention wants to solve. Summary of the invention

[0004] The purpose of the present invention is to provide an industrial equipment monitoring method and device based on the industrial Internet to solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] An industrial equipment monitoring method and device based on the industrial Internet, the method comprising:

[0007] Obtaining the production lines and production information registered in the industrial Internet; the production line is a sequence of industrial equipment, and the production information includes product types and activated equipment corresponding to the product types;

[0008] Acquire scene data according to information collection equipment in the industrial scene, identify the scene data, and determine the activated industrial equipment; the information collection equipment includes a camera and a sensor installed in the industrial equipment;

[0009] Infer the product type based on the activated industrial equipment, compare the product type with the registered task list, and determine the baseline abnormality level;

[0010] Locate the staff in the scene data, obtain the staff distribution information, and determine the floating abnormality level based on the distribution information;

[0011] Real-time feedback of baseline exception level and floating exception level.

[0012] As a further solution of the present invention: the step of obtaining the production line and its production information recorded in the industrial Internet includes:

[0013] Establish a connection channel with the facility table to obtain the equipment location of the industrial equipment in the industrial scene from the facility table;

[0014] Obtain a floor plan of the industrial scene, and set a device point in the industrial scene according to the device location;

[0015] Display the floor plan containing equipment points, receive the connection information entered by the staff, and obtain the production line;

[0016] Receives input from personnel regarding the types of products that are output from each production line.

[0017] As a further solution of the present invention: the step of acquiring scene data according to the information collection device in the industrial scene, identifying the scene data, and determining the activated industrial equipment includes:

[0018] Establish a connection channel with sensors installed in industrial equipment and receive operating parameters fed back by the sensors;

[0019] preliminarily determining the activated industrial equipment according to the operating parameters;

[0020] Get the location of the activated industrial equipment and select the equipment area in the video captured by the camera based on the location;

[0021] Perform color value recognition and contour recognition on the equipment area to determine the contour of the equipment indicator light;

[0022] Determine whether the industrial equipment is activated based on the color value of the equipment indicator light.

[0023] As a further solution of the present invention: the step of performing color value recognition and contour recognition on the device area and determining the contour of the device indicator light includes:

[0024] Traverse the device area and calculate the color value difference of adjacent pixels;

[0025] When the color value difference is less than a preset tolerance, the adjacent pixels are marked as pixels of the same type;

[0026] Obtain the labeling results of all images in the video shot within a period of time, and obtain the number of image frames in which each pair of adjacent pixels is labeled as the same type of pixels;

[0027] Calculate the ratio of the number of image frames to the total number of frames in that period of time. When the ratio is greater than a preset threshold, consider the adjacent pixels as pixels within the same contour.

[0028] The process is executed in a loop to obtain contour recognition results, calculate the color value average of each contour, and locate the contour of the device indicator light according to the color value average.

[0029] As a further solution of the present invention: the step of inferring the product type according to the activated industrial equipment, comparing the product type with the registered task list, and determining the benchmark abnormality level includes:

[0030] Connecting the equipment points in the floor plan containing the equipment points according to the activated industrial equipment to obtain at least one connection line;

[0031] Match the connecting line with the production line and read the product type of the matched production line;

[0032] Establish a connection channel with the task table to query the product type of the current production activity;

[0033] If the product type of the matched production line is the same as the product type of the current production activity queried, the baseline abnormality level is reduced by one;

[0034] If the product type of the matched production line is different from the product type of the current production activity queried, the baseline exception level is increased by one.

[0035] As a further solution of the present invention: the steps of locating the staff in the scene data, obtaining the distribution information of the staff, and determining the floating abnormality level according to the distribution information include:

[0036] Read the video captured by the camera and locate the staff in the video;

[0037] Get the minimum and average distances between workers and industrial equipment;

[0038] A floating abnormality level is determined according to the minimum distance and the average distance.

[0039] The technical solution of the present invention also provides an industrial equipment monitoring device based on the industrial Internet, the device comprising:

[0040] A production information query module is used to obtain the production lines and their production information registered in the industrial Internet; the production line is a sequence of industrial equipment, and the production information includes product types and activated equipment corresponding to the product types;

[0041] An industrial equipment activation module, used to obtain scene data according to information collection equipment in the industrial scene, identify the scene data, and determine the activated industrial equipment; the information collection equipment includes a camera and a sensor installed in the industrial equipment;

[0042] The benchmark anomaly determination module is used to reversely infer the product type based on the activated industrial equipment, compare the product type with the registered task list, and determine the benchmark anomaly level;

[0043] The floating anomaly determination module is used to locate the staff in the scene data, obtain the distribution information of the staff, and determine the floating anomaly level according to the distribution information;

[0044] The data feedback module is used to provide real-time feedback on the baseline anomaly level and the floating anomaly level.

[0045] As a further solution of the present invention: the production information query module includes:

[0046] A location acquisition unit, used to establish a connection channel with a facility table, and acquire the device location of the industrial equipment in the industrial scene from the facility table;

[0047] An equipment point insertion unit, used to obtain a floor plan of an industrial scene and set equipment points in the industrial scene according to the equipment location;

[0048] A connection information acquisition unit is used to display a floor plan containing equipment points, receive connection information input by a staff member, and obtain a production line;

[0049] The product type receiving unit is used to receive the product type input by the staff regarding the output of each production line.

[0050] As a further solution of the present invention: the industrial equipment activation module includes:

[0051] An operating parameter receiving unit is used to establish a connection channel with a sensor installed in the industrial equipment and receive operating parameters fed back by the sensor;

[0052] A preliminary determination unit, used for preliminarily determining the activated industrial equipment according to the operating parameters;

[0053] An area selection unit is used to obtain the location of the activated industrial equipment and select the equipment area in the video captured by the camera according to the location;

[0054] The area recognition unit is used to perform color value recognition and contour recognition on the device area and determine the contour of the device indicator light;

[0055] The color value verification unit is used to determine whether the industrial equipment is activated according to the color value of the equipment indicator light.

[0056] As a further solution of the present invention: the reference abnormality determination module includes:

[0057] A connection line prediction unit, used to connect the equipment points in the floor plan containing the equipment points according to the activated industrial equipment to obtain at least one connection line;

[0058] A comparison and matching unit, used to match the connection line with the production line and read the product type of the matched production line;

[0059] The type reading unit is used to establish a connection channel with the task table and query the product type of the current production activity;

[0060] A self-decrementing unit, used to reduce the base abnormality level by one if the product type of the matched production line is the same as the product type of the current production activity queried;

[0061] The self-increment unit is used to increase the baseline abnormality level by one if the product type of the matched production line is different from the product type of the current production activity queried.

[0062] Compared with the prior art, the beneficial effects of the present invention are as follows: the present invention obtains the working status of industrial equipment by sensors, and then locates the equipment that needs to be detected, obtains the operating status of the equipment by cameras, and then reversely infers the work task, compares and matches the work task with the current task, and determines the safety situation based on the matching result; at the same time, the distance between the staff and the equipment is analyzed to supplement the safety situation, and the comprehensiveness is extremely high. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention.

[0064] Figure 1 This is a flowchart of the industrial equipment monitoring method based on the Industrial Internet.

[0065] Figure 2 This is the first sub-process flowchart of the industrial equipment monitoring method based on the Industrial Internet.

[0066] Figure 3 This is the second sub-process flowchart of the industrial equipment monitoring method based on the Industrial Internet.

[0067] Figure 4 This is the third sub-process flowchart of the industrial equipment monitoring method based on the Industrial Internet.

[0068] Figure 5 This is the fourth sub-process flowchart of the industrial equipment monitoring method based on the Industrial Internet.

[0069] Figure 6 This is a structural block diagram of the industrial equipment monitoring device based on the Industrial Internet. DETAILED DESCRIPTION

[0070] In order to make the technical problems, technical solutions and beneficial effects to be solved by the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0071] Figure 1 The flowchart of the industrial equipment monitoring method based on the industrial Internet is as follows. In an embodiment of the present invention, a method and device for monitoring industrial equipment based on the industrial Internet are provided. The method includes:

[0072] Step S100: Acquire the production line and its production information registered in the industrial Internet; the production line is a sequence of industrial equipment, and the production information includes product type and activated equipment corresponding to the product type;

[0073] The industrial Internet is applied to smart workshops, where a variety of industrial equipment are installed. These industrial equipment have built-in sensors, and cameras are deployed in the smart workshops. These sensors and cameras can obtain the production process in the smart workshops in real time, allowing managers to monitor the smart workshops in real time.

[0074] A smart workshop is first of all a workshop, which is used to provide a venue for production activities. Production activities are limited. There are only a limited number of production lines in a workshop, and the products it produces are also limited. The production lines and their production information registered in the Industrial Internet are obtained. The production line is a sequence of industrial equipment, that is, which industrial equipment is obtained in which order; the production information includes product types and activation devices corresponding to the product types, that is, which product needs to be processed by which industrial equipment.

[0075] Step S200: acquiring scene data according to an information collection device in the industrial scene, identifying the scene data, and determining activated industrial equipment; the information collection device includes a camera and a sensor installed in the industrial equipment;

[0076] Scene data is obtained based on information collection devices in industrial scenes. Information collection devices include cameras and sensors installed in industrial equipment. Scene data is a high-level concept used to characterize data generated during production activities in smart workshops. For sensors, it is data generated during equipment operation; for cameras, it is surveillance video in the workshop during production activities.

[0077] By identifying the scene data, it is possible to determine which devices are in an activated state.

[0078] Step S300: infer the product type according to the activated industrial equipment, compare the product type with the registered task list, and determine the benchmark abnormality level;

[0079] Based on the identified activated industrial equipment, it is possible to predict which production lines are running in the current production activities, and then infer the product types, read the registered task list of the current smart factory (which tasks are currently being performed), compare the inferred product types with the product types in the registered task list, and then determine the baseline abnormality level. If the inferred product types are the same as the product types in the registered task list, it means that the current production activities are the same as the task list, and the baseline abnormality level is very low, indicating that there are no abnormalities; on the contrary, if the inferred product types are different from the product types in the registered task list, the baseline abnormality level will be higher, indicating that there are abnormalities.

[0080] Step S400: Locate the staff in the scene data, obtain the distribution information of the staff, and determine the floating abnormality level according to the distribution information;

[0081] Based on the above content, the staff is identified and located in the captured video of the camera in the scene data, and the distribution information of the staff is obtained. The floating abnormality level can be determined based on the distribution information. Generally speaking, the closer the staff is to the equipment, the higher the floating abnormality level, which means it is more dangerous.

[0082] Step S500: Feedback the baseline abnormality level and the floating abnormality level in real time;

[0083] Finally, the baseline exception level and floating exception level are fed back, and the feedback data format is the baseline exception level plus or minus the floating exception level.

[0084] Figure 2 The first sub-process flowchart of the industrial equipment monitoring method based on the industrial Internet is as follows:

[0085] Step S101: establishing a connection channel with a facility table, and obtaining the device location of industrial equipment in the industrial scene from the facility table;

[0086] Step S102: obtaining a floor plan of an industrial scene, and setting a device point in the industrial scene according to the device location;

[0087] Step S103: Display the floor plan containing the equipment points, receive the connection information input by the staff, and obtain the production line;

[0088] Step S104: receiving the product type output by each production line input by the staff.

[0089] The above content provides a specific process for obtaining production line and production information, establishing a connection channel with the facility table, obtaining the equipment location of industrial equipment in the industrial scene in the facility table, and then obtaining the floor plan of the industrial scene, inserting the equipment location into the floor plan according to a preset scale, and obtaining the equipment point; displaying the floor plan containing the equipment point, receiving the connection information entered by the staff, and obtaining the production line. During the connection process, the connection order of each equipment point is retained. Finally, the product type input by the staff regarding the output of each production line is received.

[0090] Figure 3 The second sub-flow chart of the industrial equipment monitoring method based on the industrial Internet, wherein the steps of acquiring scene data according to the information acquisition device in the industrial scene, identifying the scene data, and determining the activated industrial equipment include:

[0091] Step S201: establishing a connection channel with a sensor installed in an industrial device, and receiving operating parameters fed back by the sensor;

[0092] Step S202: preliminarily determining activated industrial equipment according to the operating parameters;

[0093] Step S203: obtaining the location of the activated industrial equipment, and selecting the equipment area in the video captured by the camera according to the location;

[0094] Step S204: performing color value recognition and contour recognition on the device area to determine the contour of the device indicator light;

[0095] Step S205: judging whether the industrial equipment is activated according to the color value of the equipment indicator light.

[0096] In an example of the technical solution of the present invention, a specific solution for querying activated industrial equipment is provided, a connection channel with a sensor installed in the industrial equipment is established, and operating parameters fed back by the sensor can be received based on the connection channel. If the operating parameter is not the value in the preset closed state, it is determined to be activated. Conversely, if the operating parameter is the value in the preset closed state, it is determined to be inactivated.

[0097] The above process is a preliminary determination process. The location of the activated industrial equipment is obtained. The equipment area is selected in the video captured by the camera according to the location. The contour and color value of the equipment area are recognized. The indicator lights of each industrial equipment can be located, which is called the indicator light contour.

[0098] Specifically, the step of performing color value recognition and contour recognition on the device area to determine the contour of the device indicator light includes:

[0099] Traverse the device area and calculate the color value difference of adjacent pixels;

[0100] When the color value difference is less than a preset tolerance, the adjacent pixels are marked as pixels of the same type;

[0101] Obtain the labeling results of all images in the video shot within a period of time, and obtain the number of image frames in which each pair of adjacent pixels is labeled as the same type of pixels;

[0102] Calculate the ratio of the number of image frames to the total number of frames in that period of time. When the ratio is greater than a preset threshold, consider the adjacent pixels as pixels within the same contour.

[0103] The process is executed in a loop to obtain contour recognition results, calculate the color value average of each contour, and locate the contour of the device indicator light according to the color value average.

[0104] The above content describes the contour recognition process and the color value recognition process in detail. For each device area, each pixel in the device area is traversed, and the color value difference between adjacent pixels is calculated. When the color value difference is less than the preset tolerance, the adjacent pixels are marked as similar pixels. The video is composed of multiple images, and each device corresponds to a device area in the multiple images. Therefore, multiple marking results can be obtained. If adjacent pixels are marked as similar pixels enough times within a period of time, it can be determined that they belong to the same contour, thereby obtaining the most stable and accurate contour recognition result.

[0105] For each contour in the contour recognition result, the mean color value within the contour is calculated, and the indicator light contour can be quickly located. Since the indicator light contour has only a limited number of colors, such as red, green or yellow, the positioning process based on the color value mean is very simple.

[0106] Figure 4 The third sub-flow chart of the industrial equipment monitoring method based on the industrial Internet, wherein the steps of inferring the product type according to the activated industrial equipment, comparing the product type with the registered task list, and determining the benchmark abnormality level include:

[0107] Step S301: Connecting the equipment points in the floor plan containing the equipment points according to the activated industrial equipment to obtain at least one connection line;

[0108] Step S302: Match the connecting line with the production line, and read the product type of the matched production line;

[0109] Step S303: Establish a connection channel with the task table to query the product type of the current production activity;

[0110] Step S304: if the product type of the matched production line is the same as the product type of the queried current production activity, the baseline abnormality level is reduced by one;

[0111] Step S305: If the product type of the matched production line is different from the product type of the queried current production activity, the baseline abnormality level is increased by one.

[0112] According to the activated industrial equipment, the equipment points are connected in the floor plan containing the equipment points. There are many ways to connect the equipment points. Generally, a direction is preset, such as from the entrance to the exit. The number of connection lines obtained is at least one, and generally, there are multiple ones.

[0113] Match the connecting line with the production line, read the product type of the matched production line, and each connecting line can be matched to a production line.

[0114] Establish a connection channel with the task table and query the product type of the current production activity. If the product type of the matched production line is the same as the product type of the current production activity queried, it means that the actual situation is the same as the theoretical situation, and the benchmark abnormality level is reduced by one. If the product type of the matched production line is different from the product type of the current production activity queried, it means that the actual situation is different from the theoretical situation, and the benchmark abnormality level is increased by one.

[0115] Figure 5 This is a fourth sub-process flowchart of an industrial equipment monitoring method based on the industrial Internet. The steps of locating the staff in the scene data, obtaining the distribution information of the staff, and determining the floating abnormality level according to the distribution information include:

[0116] Step S401: reading the video captured by the camera and locating the staff in the video;

[0117] Step S402: obtaining the minimum distance and average distance between the staff and the industrial equipment;

[0118] Step S403: determining the floating abnormality level according to the minimum distance and the average distance.

[0119] Finally, read the video captured by the camera and use the personnel positioning algorithm to locate the staff. If the camera can obtain the temperature, the positioning process will be very simple; obtain the minimum distance and average distance between the staff and the industrial equipment. The smaller the minimum distance, the higher the floating anomaly level, and the smaller the average distance, the higher the floating anomaly level. The weights of the two are different. By adding the minimum distance and the average distance based on different weights, the floating anomaly level can be obtained.

[0120] Figure 6 The following is a structural block diagram of an industrial equipment monitoring device based on the industrial Internet. In an embodiment of the present invention, an industrial equipment monitoring device based on the industrial Internet, the device 10 includes:

[0121] The production information query module 11 is used to obtain the production lines and their production information registered in the industrial Internet; the production line is a sequence of industrial equipment, and the production information includes the product type and the activated equipment corresponding to the product type;

[0122] The industrial equipment activation module 12 is used to obtain scene data according to the information collection device in the industrial scene, identify the scene data, and determine the activated industrial equipment; the information collection device includes a camera and a sensor installed in the industrial equipment;

[0123] The benchmark abnormality determination module 13 is used to reversely infer the product type according to the activated industrial equipment, compare the product type with the registered task table, and determine the benchmark abnormality level;

[0124] The floating abnormality determination module 14 is used to locate the staff in the scene data, obtain the distribution information of the staff, and determine the floating abnormality level according to the distribution information;

[0125] The data feedback module 15 is used to provide real-time feedback of the baseline abnormality level and the floating abnormality level.

[0126] Furthermore, the production information query module 11 includes:

[0127] A location acquisition unit, used to establish a connection channel with a facility table, and acquire the device location of the industrial equipment in the industrial scene from the facility table;

[0128] An equipment point insertion unit, used to obtain a floor plan of an industrial scene and set equipment points in the industrial scene according to the equipment location;

[0129] A connection information acquisition unit is used to display a floor plan containing equipment points, receive connection information input by a staff member, and obtain a production line;

[0130] The product type receiving unit is used to receive the product type input by the staff regarding the output of each production line.

[0131] Specifically, the industrial equipment activation module 12 includes:

[0132] An operating parameter receiving unit is used to establish a connection channel with a sensor installed in the industrial equipment and receive operating parameters fed back by the sensor;

[0133] A preliminary determination unit, used for preliminarily determining the activated industrial equipment according to the operating parameters;

[0134] An area selection unit is used to obtain the location of the activated industrial equipment and select the equipment area in the video captured by the camera according to the location;

[0135] The area recognition unit is used to perform color value recognition and contour recognition on the device area and determine the contour of the device indicator light;

[0136] The color value verification unit is used to determine whether the industrial equipment is activated according to the color value of the equipment indicator light.

[0137] In addition, the reference abnormality determination module 13 includes:

[0138] A connection line prediction unit, used to connect the equipment points in the floor plan containing the equipment points according to the activated industrial equipment to obtain at least one connection line;

[0139] A comparison and matching unit, used to match the connection line with the production line and read the product type of the matched production line;

[0140] The type reading unit is used to establish a connection channel with the task table and query the product type of the current production activity;

[0141] A self-decrementing unit, used to reduce the base abnormality level by one if the product type of the matched production line is the same as the product type of the current production activity queried;

[0142] The self-increment unit is used to increase the baseline abnormality level by one if the product type of the matched production line is different from the product type of the current production activity queried.

[0143] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An industrial equipment monitoring method based on the industrial Internet, characterized in that: The method comprises: Obtaining the production lines and production information registered in the industrial Internet; the production line is a sequence of industrial equipment, and the production information includes product types and activated equipment corresponding to the product types; Acquire scene data according to information collection equipment in the industrial scene, identify the scene data, and determine the activated industrial equipment; the information collection equipment includes a camera and a sensor installed in the industrial equipment; Infer the product type based on the activated industrial equipment, compare the product type with the registered task list, and determine the baseline abnormality level; Locate the staff in the scene data, obtain the staff distribution information, and determine the floating abnormality level based on the distribution information; Real-time feedback of baseline exception level and floating exception level.

2. The industrial equipment monitoring method based on the industrial Internet according to claim 1 is characterized in that: The steps of obtaining the production line and its production information recorded in the industrial Internet include: Establish a connection channel with the facility table to obtain the equipment location of the industrial equipment in the industrial scene from the facility table; Obtain a floor plan of the industrial scene, and set a device point in the industrial scene according to the device location; Display the floor plan containing equipment points, receive the connection information entered by the staff, and obtain the production line; Receives input from personnel regarding the types of products that are output from each production line.

3. The industrial equipment monitoring method based on the industrial Internet according to claim 1 is characterized in that: The step of acquiring scene data according to the information collection device in the industrial scene, identifying the scene data, and determining the activated industrial equipment includes: Establish a connection channel with sensors installed in industrial equipment and receive operating parameters fed back by the sensors; preliminarily determining the activated industrial equipment according to the operating parameters; Get the location of the activated industrial equipment and select the equipment area in the video captured by the camera based on the location; Perform color value recognition and contour recognition on the equipment area to determine the contour of the equipment indicator light; Determine whether the industrial equipment is activated based on the color value of the equipment indicator light.

4. The industrial equipment monitoring method based on the industrial Internet according to claim 3 is characterized in that: The step of performing color value recognition and contour recognition on the device area to determine the contour of the device indicator light comprises: Traverse the device area and calculate the color value difference of adjacent pixels; When the color value difference is less than a preset tolerance, the adjacent pixels are marked as pixels of the same type; Obtain the labeling results of all images in the video shot within a period of time, and obtain the number of image frames in which each pair of adjacent pixels is labeled as the same type of pixels; Calculate the ratio of the number of image frames to the total number of frames in that period of time. When the ratio is greater than a preset threshold, consider the adjacent pixels as pixels within the same contour. The process is executed in a loop to obtain contour recognition results, calculate the color value average of each contour, and locate the contour of the device indicator light according to the color value average.

5. The industrial equipment monitoring method based on the industrial Internet according to claim 2 is characterized in that: The steps of inferring the product type according to the activated industrial equipment, comparing the product type with the registered task list, and determining the benchmark abnormality level include: Connecting the equipment points in the floor plan containing the equipment points according to the activated industrial equipment to obtain at least one connection line; Match the connecting line with the production line and read the product type of the matched production line; Establish a connection channel with the task table to query the product type of the current production activity; If the product type of the matched production line is the same as the product type of the current production activity queried, the baseline abnormality level is reduced by one; If the product type of the matched production line is different from the product type of the queried current production activity, the baseline anomaly level is increased by one.

6. The industrial equipment monitoring method based on the industrial Internet according to claim 1 is characterized in that: The steps of locating the staff in the scene data, obtaining the distribution information of the staff, and determining the floating abnormality level according to the distribution information include: Read the video captured by the camera and locate the staff in the video; Get the minimum and average distances between workers and industrial equipment; A floating abnormality level is determined according to the minimum distance and the average distance.

7. An industrial equipment monitoring device based on the industrial Internet, characterized in that: The device comprises: A production information query module is used to obtain the production lines and their production information registered in the industrial Internet; the production line is a sequence of industrial equipment, and the production information includes product types and activated equipment corresponding to the product types; An industrial equipment activation module, used to obtain scene data according to information collection equipment in the industrial scene, identify the scene data, and determine the activated industrial equipment; the information collection equipment includes a camera and a sensor installed in the industrial equipment; The benchmark anomaly determination module is used to reversely infer the product type based on the activated industrial equipment, compare the product type with the registered task list, and determine the benchmark anomaly level; The floating anomaly determination module is used to locate the staff in the scene data, obtain the distribution information of the staff, and determine the floating anomaly level according to the distribution information; The data feedback module is used to provide real-time feedback on the baseline anomaly level and the floating anomaly level.

8. The industrial equipment monitoring device based on the industrial Internet according to claim 7 is characterized in that: The production information query module includes: A location acquisition unit, used to establish a connection channel with the facility table, and obtain the device location of the industrial equipment in the industrial scene from the facility table; An equipment point insertion unit, used to obtain a floor plan of an industrial scene and set equipment points in the industrial scene according to the equipment location; A connection information acquisition unit is used to display a floor plan containing equipment points, receive connection information input by a staff member, and obtain a production line; The product type receiving unit is used to receive the product type input by the staff regarding the output of each production line.

9. The industrial equipment monitoring device based on the industrial Internet according to claim 7 is characterized in that: The industrial equipment activation module includes: An operating parameter receiving unit is used to establish a connection channel with a sensor installed in the industrial equipment and receive operating parameters fed back by the sensor; A preliminary determination unit, used for preliminarily determining the activated industrial equipment according to the operating parameters; An area selection unit is used to obtain the location of the activated industrial equipment and select the equipment area in the video captured by the camera according to the location; The area recognition unit is used to perform color value recognition and contour recognition on the device area and determine the contour of the device indicator light; The color value verification unit is used to determine whether the industrial equipment is activated according to the color value of the equipment indicator light.

10. The industrial equipment monitoring device based on the industrial Internet according to claim 8, characterized in that: The benchmark abnormality determination module comprises: A connection line prediction unit, used to connect the equipment points in the floor plan containing the equipment points according to the activated industrial equipment to obtain at least one connection line; A comparison and matching unit is used to match the connection line with the production line and read the product type of the matched production line; The type reading unit is used to establish a connection channel with the task table and query the product type of the current production activity; A self-decrementing unit, used to reduce the base abnormality level by one if the product type of the matched production line is the same as the product type of the current production activity queried; The self-increment unit is used to increase the baseline abnormality level by one if the product type of the matched production line is different from the product type of the current production activity queried.

Images