Device data supervision method and system based on big data

Abstract

The invention discloses an equipment data supervision method and system based on big data, which are used for collecting operation data of equipment in real time and realizing self-adaptive prediction compensation operation according to an equipment task in combination with a consumable condition, and relates to the technical field of equipment data supervision. According to the equipment data supervision method and system based on the big data, data collected in real time is classified, then historical data is extracted, and a data supervision model is established in combination with equipment parameters to simulate running operation of the equipment, so that whether abnormity exists or not is analyzed and judged after consumable features are extracted; the self-adaptive prediction compensation operation is realized according to the equipment task in combination with the consumable condition, and the generated instruction compensation time is introduced into the data supervision model for optimization, so that the stability of equipment data supervision is realized, the optimization of the data supervision model is utilized, the self-adaptive compensation after real-time data introduction is completed, and the equipment operation efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of device data supervision, and in particular to a device data supervision method and system based on big data. Background Art

[0002] With the rapid development of information technology, printing equipment is increasingly used in various locations, including businesses, schools, and government agencies. During operation, printing equipment generates a large amount of data, such as print job information, device status information, and consumables usage information. This data is of great significance to enterprises' operational management, cost control, and equipment maintenance.

[0003] The reference patent name is: A device data supervision method and system based on big data (patent publication number: CN118798680A, patent publication date: 2024-10-18). The system includes an equipment data analysis module, a comprehensive fault risk analysis module, an external fault risk analysis module, and an equipment data rationalization analysis module. The comprehensive fault risk analysis module is used to analyze the product manufacturing data of the corresponding links in the manufacturing process of the products to be mass-produced based on the working status of the product quality inspection and early warning device in the factory area to be monitored, and predict the comprehensive failure risk of the finished product in combination with the manufacturing data of the products in the corresponding links. By analyzing the test data of the corresponding products to be mass-produced in the factory area to be monitored, the cause of the failure of the corresponding products to be mass-produced is judged according to the test data of each link, and an early warning signal is generated based on the corresponding cause of the failure, thereby not only improving the maintenance efficiency of the products to be mass-produced, but also effectively tracing the cause of the problem, so that the batch production of the products to be mass-produced is effectively guaranteed.

[0004] Based on the description in the above documents, when existing printing equipment is working, the related material consumption data changes due to changes in production demand data, and the monitoring operation of the material situation fails to predict and implement control in advance, resulting in time-consuming equipment processing and the equipment is also prone to malfunction. For this reason, the present invention provides a device data supervision method and system based on big data. Summary of the Invention

[0005] In response to the shortcomings of the existing technology, the present invention provides a device data supervision method and system based on big data, which solves the problem that when the existing printing equipment is working, the related material consumption data changes due to changes in production demand data, and the monitoring operation of the material situation fails to predict and implement control in advance, resulting in time-consuming equipment processing and the equipment is prone to malfunction.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: a device data supervision method based on big data, specifically comprising the following steps:

[0007] Step 1: Install a data acquisition module on each device to collect the device's operating data in real time, and transmit and store the data;

[0008] Step 2: Classify the real-time collected data and then extract historical data. Combined with the equipment parameters, a data supervision model is established to simulate the equipment's operation. After extracting the consumables' features, an analysis is performed to determine whether there are any anomalies. Adaptive prediction and compensation operations are then implemented based on the equipment's tasks and the consumables' conditions. The resulting instruction compensation time is then introduced into the data supervision model for optimization.

[0009] Step 3: Introduce real-time data into the data supervision model for measurement, implement adaptive supervision operations on the equipment, and display the equipment data through the equipment display.

[0010] Preferably, the operation of classifying the real-time collected data in step 2 is:

[0011] Set data classification templates, including equipment task information templates, equipment status information templates, and consumables usage information templates;

[0012] The row category of the task information template is task parameters, and the column category of the task information template is the number of task items;

[0013] The row category of the device status information template is the status category, and the column category of the device status template is the device name;

[0014] The row category of the consumables usage information template is the remaining parameters, and the column category of the consumables usage information template is the consumable name;

[0015] Match the category names of each classification template with the real-time collected equipment operation data, determine the category names of the row and column categories with the same content, and add the corresponding numerical results to the classification template.

[0016] Preferably, the operation of establishing the data supervision model in combination with the parameters of the device in step 2 is:

[0017] According to the model parameters of the actual equipment and the position relationship in the three-dimensional space, a data supervision model is established to realize simulation operation;

[0018] Then, the operation relationship and linkage data between each device are introduced into the data supervision model to realize the linkage operation of the devices after the task information is filled in.

[0019] Preferably, the operation of analyzing and judging whether there is an abnormality after extracting the consumables features in step 2 is:

[0020] Extract the consumables information data from the consumables usage information template and extract the image data to perform consumables feature analysis.

[0021] After extracting the image data, the origin is set based on the position corresponding to the center of the crosshair cursor of the acquisition camera. Then, with the origin as the starting point, the X-axis and Y-axis are established respectively along the extension direction of the crosshair cursor.

[0022] A reference point A and a reference point B are set on the same boundary of the image data and in the positive direction of the X / Y coordinate system, and whether the consumable feature is offset is determined based on the reference point A and the reference point B;

[0023] And determine whether there is any abnormality on the top surface of the consumables. After determining that there is an abnormality, determine whether the side consumables features are abnormal.

[0024] Preferably, the operation of determining whether the feature is offset based on reference point A and reference point B is:

[0025] Based on the distance measurement on the image, the coordinates of reference point A are determined to be (x1, y1), and the coordinates of reference point B are determined to be (x2, y2);

[0026] Determining whether a boundary where a reference point of the current image data is located is a vertical boundary or a horizontal boundary;

[0027] When the boundary is a vertical boundary, compare whether x1 is equal to x2. If x1 is not equal to x2, there is a deviation in the consumable characteristics;

[0028] When the boundary is a horizontal boundary, compare whether y1 is equal to y2. If y1 is not equal to y2, there is a deviation in the consumable characteristics.

[0029] Preferably, the operation of determining whether there is an abnormality on the top surface of the consumables and determining whether there is an abnormality and then determining whether the side consumables feature is abnormal is as follows:

[0030] Grayscale processing is performed on the image data of the top surface with consumable features, and the shadow area in the image data is partially enlarged. Then, pixel points are set at equal intervals in the horizontal direction from the enlarged area, and the grayscale values of the pixel points are calculated;

[0031] Determine whether the grayscale value of the current magnified area feature changes, and if so, determine it as an abnormal situation;

[0032] Then, the corresponding side image data of the top surface image data of the current consumable feature is extracted, and the side image data is analyzed to determine the boundary of the paper to be processed, and to determine whether the boundary feature has a bending or folding characteristic curve. If so, the current consumable feature needs to be repaired.

[0033] Preferably, the adaptive prediction compensation operation in step 2 is implemented according to the equipment task and the consumables situation as follows:

[0034] Based on the equipment tasks in the historical data, the corresponding consumables status is extracted, and the consumables replenishment instructions are transmitted after the consumables are completely consumed;

[0035] And according to the working rate change of the corresponding equipment task, the corresponding toner consumption and paper consumption are extracted, and the remaining nodes of the consumables when compensation is required are calculated;

[0036] Then, the remaining nodes of consumables are marked according to the real-time task requirements, thereby realizing adaptive compensation operations.

[0037] Preferably, the node operation of calculating the remaining amount of consumables required for compensation according to the toner consumption is:

[0038] By extracting the toner situation inside the ink cartridge, the height of the ink cartridge is set to H1. The distance between the top surface of the toner located directly above the discharge port and the sensor mirror is h1, and the sensor mirror is flush with the top surface of the ink cartridge cavity. The length and width of the bottom surface of the ink cartridge are L1 and L2 respectively.

[0039] Then extract the toner consumption rate under the current task requirement as V n , and the timestamp of the toner being consumed is t1, and the timestamp of the compensation after the instruction transmission is realized is t2;

[0040] Then the margin node after the compensation time is calculated as:

[0041] T1=[(H1-h1)×L1×L2] / V n -(t2-t1);

[0042] And under the current task requirements, the toner inside the ink cartridge reaches the remaining node when the toner is consumed for time T1, and the compensation instruction is transmitted and the consumables filling operation is implemented.

[0043] Preferably, the node operation of calculating the remaining amount of consumables required for compensation according to the paper consumption situation is:

[0044] By extracting the paper situation inside the paper box, the height of the paper storage area is set to H2. The distance between the top surface of the paper pile and the sensor mirror is h2, and the sensor mirror is flush with the top surface of the inner cavity of the paper storage area.

[0045] Then extract the paper loss rate under the current task requirements as V m , and the time stamp of the extracted paper being consumed is t3, and the time stamp of the compensation after the instruction transmission is realized is t4;

[0046] Then the margin node after the compensation time is calculated as:

[0047] T2=(H2-h2) / Vn -(t4-t3);

[0048] And under the current task requirements, the paper inside the paper storage is the surplus node when the consumption time T1, and the compensation instruction is transmitted and the consumables filling operation is realized.

[0049] The present invention also discloses a device data system based on big data, comprising:

[0050] Data acquisition module, which uses sensors to collect equipment operation data;

[0051] The data analysis module analyzes and processes the collected data, uses historical data to establish a data supervision model to simulate the operation of the equipment, and analyzes, judges and predicts the nodes that need compensation to achieve adaptive adjustment and compensation operations;

[0052] The data display module introduces real-time data for measurement and displays the data values through a combination of charts and text.

[0053] The present invention provides a device data monitoring method and system based on big data. Compared with the existing technology, it has the following advantages:

[0054] 1. This big data-based equipment data supervision method and system classifies the real-time collected data and then extracts historical data. It establishes a data supervision model based on the equipment parameters to simulate the equipment's operation, analyzes and determines whether there are abnormalities after the consumables features are extracted, and implements adaptive prediction and compensation operations based on the equipment tasks and consumables conditions. The generated instruction compensation time is introduced into the data supervision model for optimization, thereby achieving stability in equipment data supervision. By utilizing the optimization of the data supervision model, adaptive compensation after the introduction of real-time data is completed, thereby improving the efficiency of equipment operation.

[0055] 2. The big data-based equipment data supervision method and system extracts the consumable information data from the consumable usage information template, and extracts image data to implement the analysis operation of the consumable characteristics, and determines whether there is an abnormality on the top surface of the consumable characteristics. After determining that there is an abnormality, it determines whether the side consumable characteristics are abnormal, thereby determining the abnormality of the consumables, effectively avoiding the problem of paper jams, thereby ensuring the smooth operation of the equipment, and at the same time discovering and solving abnormalities while supervising the equipment data, thereby improving supervision efficiency.

[0056] 3. The big data-based equipment data supervision method and system extracts the corresponding consumables according to the equipment tasks in the historical data, and transmits the consumables replenishment instructions after the consumables are completely consumed. It also extracts the corresponding toner consumption and paper consumption according to the working rate changes of the corresponding equipment tasks, and calculates the remaining nodes of the consumables when each consumable needs to be compensated, so as to adapt to the different task requirements and predict the consumables situation in advance, thereby effectively completing the compensation of consumables and making the equipment operation more stable. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 This is an operational flow chart of the device data monitoring method of the present invention;

[0058] Figure 2 This is a principle block diagram of the device data monitoring system of the present invention. DETAILED DESCRIPTION

[0059] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 making creative efforts are within the scope of protection of the present invention.

[0060] See also Figure 1-Figure 2 , the present invention provides three technical solutions:

[0061] Embodiment 1: A device data monitoring method based on big data, specifically comprising the following steps:

[0062] Step 1: Install a data acquisition module on each device to collect the device's operating data in real time, and transmit and store the data;

[0063] Step 2: Classify the real-time collected data and then extract historical data. Combined with the equipment parameters, a data supervision model is established to simulate the equipment's operation. After extracting the consumables' features, an analysis is performed to determine whether there are any anomalies. Adaptive prediction and compensation operations are then implemented based on the equipment's tasks and the consumables' conditions. The resulting instruction compensation time is then introduced into the data supervision model for optimization.

[0064] Step 3: Introduce real-time data into the data supervision model for measurement, implement adaptive supervision operations on the equipment, and display the equipment data through the equipment display.

[0065] Among them, by classifying the data collected in real time and then extracting the historical data, the data supervision model is established in combination with the equipment parameters to simulate the operation of the equipment, and the analysis of the consumables characteristics after extraction is realized to determine whether there is an abnormality, and adaptive prediction compensation operations are implemented according to the equipment tasks and consumables conditions. The generated instruction compensation time is introduced into the data supervision model optimization, thereby achieving the stability of equipment data supervision. By utilizing the optimization of the data supervision model, the adaptive compensation after the introduction of real-time data is completed, and the efficiency of equipment operation is improved.

[0066] In the embodiment of the present invention, the operation of classifying the real-time collected data in step 2 is:

[0067] Set data classification templates, including equipment task information templates, equipment status information templates, and consumables usage information templates;

[0068] The row category of the task information template is task parameters, and the column category of the task information template is the number of task items;

[0069] The row category of the device status information template is the status category, and the column category of the device status template is the device name;

[0070] The row category of the consumables usage information template is the remaining parameters, and the column category of the consumables usage information template is the consumable name;

[0071] Match the category names of each classification template with the real-time collected equipment operation data, determine the category names of the row and column categories with the same content, and add the corresponding numerical results to the classification template.

[0072] In the embodiment of the present invention, the operation of establishing the data supervision model in combination with the parameters of the device in step 2 is as follows:

[0073] According to the model parameters of the actual equipment and the position relationship in the three-dimensional space, a data supervision model is established to realize simulation operation;

[0074] Then, the operation relationship and linkage data between each device are introduced into the data supervision model to realize the linkage operation of the devices after the task information is filled in.

[0075] In the embodiment of the present invention, the operation of analyzing and determining whether there is an abnormality after extracting the consumables features in step 2 is:

[0076] Extract the consumables information data from the consumables usage information template and extract the image data to perform consumables feature analysis.

[0077] After extracting the image data, the origin is set based on the position corresponding to the center of the crosshair cursor of the acquisition camera. Then, with the origin as the starting point, the X-axis and Y-axis are established respectively along the extension direction of the crosshair cursor.

[0078] A reference point A and a reference point B are set on the same boundary of the image data and in the positive direction of the X / Y coordinate system, and whether the consumable feature is offset is determined based on the reference point A and the reference point B;

[0079] And determine whether there is any abnormality on the top surface of the consumables. After determining that there is an abnormality, determine whether the side consumables features are abnormal.

[0080] In the embodiment of the present invention, the operation of determining whether a feature is offset based on reference point A and reference point B is as follows:

[0081] Based on the distance measurement on the image, the coordinates of reference point A are determined to be (x1, y1), and the coordinates of reference point B are determined to be (x2, y2);

[0082] Determining whether a boundary where a reference point of the current image data is located is a vertical boundary or a horizontal boundary;

[0083] When the boundary is a vertical boundary, compare whether x1 is equal to x2. If x1 is not equal to x2, there is a deviation in the consumable characteristics;

[0084] When the boundary is a horizontal boundary, compare whether y1 is equal to y2. If y1 is not equal to y2, there is a deviation in the consumable characteristics.

[0085] Among them, by extracting the consumable information data in the consumable usage information template and extracting the image data to realize the analysis operation of the consumable characteristics, and determine whether there is an abnormality on the top surface of the consumable characteristics, after determining that there is an abnormality, determine whether the side consumable characteristics are abnormal, so as to determine the abnormality of the consumables, effectively avoid the problem of paper jam, thereby ensuring the smooth operation of the equipment, and at the same time discovering and solving abnormalities while supervising the equipment data, thereby improving the supervision efficiency.

[0086] In the embodiment of the present invention, whether there is an abnormality on the top surface of the consumables, and after determining that there is an abnormality, the operation of determining whether the side consumables feature is abnormal is as follows:

[0087] Grayscale processing is performed on the image data of the top surface with consumable features, and the shadow area in the image data is partially enlarged. Then, pixel points are set at equal intervals in the horizontal direction from the enlarged area, and the grayscale values of the pixel points are calculated;

[0088] Determine whether the grayscale value of the current magnified area feature changes, and if so, determine it as an abnormal situation;

[0089] Then, the corresponding side image data of the top surface image data of the current consumable feature is extracted, and the side image data is analyzed to determine the boundary of the paper to be processed, and to determine whether the boundary feature has a bending or folding characteristic curve. If so, the current consumable feature needs to be repaired.

[0090] In the embodiment of the present invention, the adaptive prediction compensation operation in step 2 is implemented based on the equipment task and the consumables situation as follows:

[0091] Based on the equipment tasks in the historical data, the corresponding consumables status is extracted, and the consumables replenishment instructions are transmitted after the consumables are completely consumed;

[0092] And according to the working rate change of the corresponding equipment task, the corresponding toner consumption and paper consumption are extracted, and the remaining nodes of the consumables when compensation is required are calculated;

[0093] Then, the remaining nodes of consumables are marked according to the real-time task requirements, thereby realizing adaptive compensation operations.

[0094] Among them, the corresponding consumables situation is extracted based on the equipment tasks in the historical data, and the consumables replenishment instruction is transmitted after the consumables are completely consumed. According to the working rate changes of the corresponding equipment tasks, the corresponding toner consumption and paper consumption are extracted, and the remaining nodes of the consumables when each consumable needs to be compensated are calculated, so that the consumables situation can be predicted in advance to meet the needs of different tasks, thereby effectively completing the compensation of consumables and making the equipment operation more stable.

[0095] In the embodiment of the present invention, the node operation for calculating the remaining amount of consumables when compensation is required based on the toner consumption is as follows:

[0096] By extracting the toner situation inside the ink cartridge, the height of the ink cartridge is set to H1. The distance between the top surface of the toner located directly above the discharge port and the sensor mirror is h1, and the sensor mirror is flush with the top surface of the ink cartridge cavity. The length and width of the bottom surface of the ink cartridge are L1 and L2 respectively.

[0097] Then extract the toner consumption rate under the current task requirement as V n , and the timestamp of the toner being consumed is t1, and the timestamp of the compensation after the instruction transmission is realized is t2;

[0098] Then the margin node after the compensation time is calculated as:

[0099] T1=[(H1-h1)×L1×L2] / V n -(t2-t1);

[0100] And under the current task requirements, the toner inside the ink cartridge reaches the remaining node when the toner is consumed for time T1, and the compensation instruction is transmitted and the consumables filling operation is implemented.

[0101] In the embodiment of the present invention, the node operation for calculating the remaining amount of consumables when compensation is required based on paper consumption is as follows:

[0102] By extracting the paper situation inside the paper box, the height of the paper storage area is set to H2. The distance between the top surface of the paper pile and the sensor mirror is h2, and the sensor mirror is flush with the top surface of the inner cavity of the paper storage area.

[0103] Then extract the paper loss rate under the current task requirements as V m , and the time stamp of the extracted paper being consumed is t3, and the time stamp of the compensation after the instruction transmission is realized is t4;

[0104] Then the margin node after the compensation time is calculated as:

[0105] T2=(H2-h2) / V n -(t4-t3);

[0106] And under the current task requirements, the paper inside the paper storage is the surplus node when the consumption time T1, and the compensation instruction is transmitted and the consumables filling operation is realized.

[0107] The difference between the second embodiment and the first embodiment is that the present invention further discloses a device data system based on big data, including:

[0108] Data acquisition module, which uses sensors to collect equipment operation data;

[0109] The data analysis module analyzes and processes the collected data, uses historical data to establish a data supervision model to simulate the operation of the equipment, and analyzes, judges and predicts the nodes that need compensation to achieve adaptive adjustment and compensation operations;

[0110] The data display module introduces real-time data for measurement and displays the data values through a combination of charts and text.

[0111] The difference between Example 3 and Example 1 and Example 2 is that the existing device data supervision method and the device data supervision method of the present invention are used to implement application operations on multiple devices, and the task completion rate and the error rate generated are recorded. The specific results are shown in Table 1:

[0112] Table 1 Record results table

[0113] Task completion rate Error rate Existing device data supervision methods 30min 15％ Device data supervision method of the present invention 21min 2％

[0114] In summary, after operating through the device data supervision method of the present invention, the speed of completing tasks according to task requirements is faster and the error rate is lower. Therefore, the device data supervision method of the present invention can better realize the application in actual operation.

[0115] Meanwhile, the contents not described in detail in this specification belong to the prior art known to those skilled in the art.

[0116] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0117] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A device data supervision method based on big data, characterized by: The specific steps include: Step 1: Install a data acquisition module on each device to collect the device's operating data in real time, and transmit and store the data; Step 2: Classify the real-time collected data and then extract historical data. Combined with the equipment parameters, a data supervision model is established to simulate the equipment's operation. After extracting the consumables' features, an analysis is performed to determine whether there are any anomalies. Adaptive prediction and compensation operations are then implemented based on the equipment's tasks and the consumables' conditions. The resulting instruction compensation time is then introduced into the data supervision model for optimization. Step 3: Introduce real-time data into the data supervision model for measurement, implement adaptive supervision operations on the equipment, and display the equipment data through the equipment display.

2. The device data monitoring method based on big data according to claim 1, characterized in that: The operation of classifying the real-time collected data in step 2 is as follows: Set data classification templates, including equipment task information templates, equipment status information templates, and consumables usage information templates; The row category of the task information template is task parameters, and the column category of the task information template is the number of task items; The row category of the device status information template is the status category, and the column category of the device status template is the device name; The row category of the consumables usage information template is the remaining parameters, and the column category of the consumables usage information template is the consumable name; Match the category names of each classification template with the real-time collected equipment operation data, determine the category names of the row and column categories with the same content, and add the corresponding numerical results to the classification template.

3. The device data monitoring method based on big data according to claim 1, characterized in that: The operation of establishing the data supervision model in combination with the device parameters in step 2 is as follows: According to the model parameters of the actual equipment and the position relationship in the three-dimensional space, a data supervision model is established to realize simulation operation; Then, the operation relationship and linkage data between each device are introduced into the data supervision model to realize the linkage operation of the devices after the task information is filled in.

4. The device data monitoring method based on big data according to claim 2, characterized in that: The operation of analyzing and judging whether there is an abnormality after extracting the consumables features in step 2 is as follows: Extract the consumables information data from the consumables usage information template and extract the image data to perform consumables feature analysis. After extracting the image data, the origin is set based on the position corresponding to the center of the crosshair cursor of the acquisition camera. Then, the X-axis and Y-axis are established respectively based on the extension direction of the crosshair cursor with the origin as the starting point. A reference point A and a reference point B are set on the same boundary of the image data and in the positive direction of the X / Y coordinate system, and whether the consumable feature is offset is determined based on the reference point A and the reference point B; And determine whether there is any abnormality on the top surface of the consumables. After determining that there is an abnormality, determine whether the side consumables features are abnormal.

5. The device data monitoring method based on big data according to claim 4 is characterized by: The operation of determining whether a feature is offset based on reference point A and reference point B is as follows: Based on the distance measurement on the image, the coordinates of reference point A are determined to be (x1, y1), and the coordinates of reference point B are determined to be (x2, y2); Determining whether a boundary where a reference point of the current image data is located is a vertical boundary or a horizontal boundary; When the boundary is a vertical boundary, compare whether x1 is equal to x2. If x1 is not equal to x2, there is a deviation in the consumable characteristics; When the boundary is a horizontal boundary, compare whether y1 is equal to y2. If y1 is not equal to y2, there is a deviation in the consumable characteristics.

6. The device data monitoring method based on big data according to claim 1, characterized in that: The operation of determining whether there is an abnormality on the top surface of the consumables and determining whether there is an abnormality on the side surface of the consumables is as follows: Grayscale processing is performed on the image data of the top surface with consumable features, and the shadow area in the image data is partially enlarged. Then, pixel points are set at equal intervals in the horizontal direction from the enlarged area, and the grayscale values of the pixel points are calculated; Determine whether the grayscale value of the current magnified area feature changes, and if so, determine it as an abnormal situation; Then, the corresponding side image data of the top surface image data of the current consumable feature is extracted, and the side image data is analyzed to determine the boundary of the paper to be processed, and to determine whether the boundary feature has a bending or folding characteristic curve. If so, the current consumable feature needs to be repaired.

7. The device data monitoring method based on big data according to claim 1, characterized in that: In step 2, the adaptive prediction compensation operation is implemented based on the equipment task and the consumables situation as follows: Based on the equipment tasks in the historical data, the corresponding consumables status is extracted, and the consumables replenishment instructions are transmitted after the consumables are completely consumed; And according to the working rate change of the corresponding equipment task, the corresponding toner consumption and paper consumption are extracted, and the remaining nodes of the consumables when compensation is required are calculated; Then, the remaining nodes of consumables are marked according to the real-time task requirements, thereby realizing adaptive compensation operations.

8. The device data monitoring method based on big data according to claim 7, characterized in that: The node operation for calculating the remaining amount of consumables that need to be compensated based on the toner consumption is as follows: By extracting the toner situation inside the ink cartridge, the height of the ink cartridge is set to H1. The distance between the top surface of the toner located directly above the discharge port and the sensor mirror is h1, and the sensor mirror is flush with the top surface of the ink cartridge cavity. The length and width of the bottom surface of the ink cartridge are L1 and L2 respectively. Then extract the toner consumption rate under the current task requirement as V n , and the timestamp of the toner being consumed is t1, and the timestamp of the compensation after the instruction transmission is realized is t2; Then the margin node after the compensation time is calculated as: T1=[(H1-h1)×L1×L2] / V n -(t2-t1); And under the current task requirements, the toner inside the ink cartridge reaches the remaining node when the toner is consumed for time T1, and the compensation instruction is transmitted and the consumables filling operation is implemented.

9. The device data monitoring method based on big data according to claim 7, characterized in that: The node operation for calculating the remaining amount of consumables that need to be compensated based on paper consumption is as follows: By extracting the paper situation inside the paper box, the height of the paper storage area is set to H2. The distance between the top surface of the paper pile and the sensor mirror is h2, and the sensor mirror is flush with the top surface of the inner cavity of the paper storage area. Then extract the paper loss rate under the current task requirements as V m , and the time stamp of the extracted paper being consumed is t3, and the time stamp of the compensation after the instruction transmission is realized is t4; Then the margin node after the compensation time is calculated as: T2=(H2-h2) / V n -(t4-t3); And under the current task requirements, the paper inside the paper storage is the surplus node when the consumption time T1, and the compensation instruction is transmitted and the consumables filling operation is realized.

10. A big data-based device data system, using the big data-based device data supervision method according to any one of claims 1 to 9, characterized in that: include: Data acquisition module, which uses sensors to collect equipment operation data; The data analysis module analyzes and processes the collected data, uses historical data to establish a data supervision model to simulate the operation of the equipment, and analyzes, judges and predicts the nodes that need compensation to achieve adaptive adjustment and compensation operations; The data display module introduces real-time data for measurement and displays the data values through a combination of charts and text.

Images