Video inspection control method and system based on digital factory

Abstract

The invention discloses a video inspection control method and system based on a digital factory, relates to the technical field of inspection control, and provides a scientific and efficient equipment management solution by constructing the video inspection control method based on the digital factory. Through comprehensive application of a priority evaluation model, a routing inspection frequency distribution function and an intelligent video routing inspection rule, optimal distribution of equipment routing inspection resources is realized, and high-priority equipment is more accurately concerned and managed; meanwhile, the camera is used for collecting equipment operation videos in real time, the deep analysis technology is combined, the equipment state can be rapidly and comprehensively detected, potential faults can be found in time, the risks of equipment shutdown and production loss are effectively reduced, and through intelligent design of the whole process, the inspection efficiency is improved from priority evaluation to inspection frequency determination to video inspection and state analysis. And a closed-loop monitoring control system is formed.

Description

Technical Field

[0001] The invention relates to the technical field of patrol inspection control, and in particular to a video patrol inspection control method and system based on a digital factory. Background Art

[0002] With the development of industrial automation and intelligent manufacturing, the number and complexity of factory equipment are increasing, which puts higher requirements on efficient management and real-time monitoring of equipment. However, traditional equipment inspection methods mostly rely on manual inspection, which has the disadvantages of low efficiency, incomplete coverage, and delayed problem detection, which makes it difficult to meet the needs of modern factories for efficient and accurate equipment management. At the same time, the equipment's status monitoring and fault warning capabilities are insufficient, which often leads to unforeseen downtime or damage during the production process, directly affecting the stable operation and economic benefits of the production line.

[0003] In recent years, factory equipment management methods based on digital technology have gradually emerged. By combining big data, artificial intelligence and video surveillance technology, real-time monitoring and intelligent analysis of equipment operating status can be performed. However, existing technologies still have much room for improvement in resource allocation, inspection rule formulation, and analysis depth. How to scientifically formulate inspection priorities based on the actual operating status of the equipment, optimize the configuration of inspection resources, and deeply mine equipment status information through video analysis technology has become a key issue that needs to be urgently addressed in the current field of digital factory management. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention provides a video inspection control method and system based on a digital factory, which solves the problems in the background technology.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: A video inspection control method based on a digital factory, comprising:

[0006] Step 1: By building a preset priority evaluation model, the priority of the equipment in the factory is determined, and the final equipment priority list is generated according to the priority evaluation results;

[0007] Step 2: According to the priority list, the inspection frequency of the equipment in the equipment priority list is determined by the allocation function;

[0008] Step 3: Use cameras to conduct real-time video monitoring of factory equipment, and formulate video inspection rules based on the equipment inspection frequency. The camera conducts equipment inspections based on the formulated video inspection rules;

[0009] Step 4: Perform video inspections on each device in the factory according to the video inspection rules, collect the device's operating video through the camera, and analyze and detect the device status.

[0010] As a further solution of the present invention: In the step 1, the priority of the equipment in the factory is determined by constructing a preset priority evaluation model, and the specific method of generating the final equipment priority list according to the priority evaluation result is as follows:

[0011] AS1: Obtain each device in the factory and take each device as the target device in turn for device priority scoring;

[0012] AS2: Get the total number of failures of the target device in the past set time, using the formula Determine the historical failure rate F of the target equipment, where G u Indicates the total number of failures of the target device in the past set time, T u Indicates the set time;

[0013] Then the target equipment historical failure rate F is standardized and the equipment standard historical failure rate F is determined by the following formula: ′ : Where max(F) represents the maximum value of the historical failure rate of all devices as target devices;

[0014] AS3: Determine the impact coefficient I of the target equipment failure on production or operation, which is determined by the following formula: Among them, C i is the impact assessment value of the i-th fault, N is the number of faults in the historical statistical period, T O Represents the historical statistical duration;

[0015] Then the influence coefficient I is standardized and the standard influence coefficient I is determined by the following formula: ′ : Wherein, max(I) represents the maximum value of the influence coefficient among all devices as target devices;

[0016] AS4: Determine the historical statistical duration T of the target device O The maintenance frequency M in is determined by the following formula: Among them, M u It is expressed as the total number of maintenance times in the historical statistical period;

[0017] Then the maintenance frequency is standardized and the standard maintenance frequency M is determined by the following formula: ′ : Wherein, max(M) represents the maximum value of the maintenance frequency among all devices as target devices;

[0018] AS5: Determine the cumulative operating time T of the target equipment since it was put into operatione , and obtain the equipment's operating life T s , through the formula: Calculate the operating coefficient T of the target equipment ed ;

[0019] AS6: Get the standard historical failure rate F of the target device ′ , Standard influence coefficient I ′ 、Standard maintenance frequency M ′ and operating factor T ed , the priority score of the target device is determined by a preset priority evaluation model, which is embodied by the following formula:

[0020] P j =W1·F ′ +W2·I ′ +W3·M ′ +W4·T ed

[0021] Among them, P j is the priority score of the target equipment, and 1≤j≤z, z represents the total number of equipment in the factory; W1, W2, W3 and W4 are weight coefficients.

[0022] As a further solution of the present invention: the said priority determination of the equipment in the factory is performed by constructing a preset priority evaluation model, and generating a final equipment priority list according to the priority evaluation result also includes:

[0023] AS7: Repeat steps AS2-AS6 to determine that each device in the factory is a target device for device priority scoring, and sort them from high to low according to the priority scores to generate a final priority list.

[0024] As a further solution of the present invention: in the step 2, the specific method of determining the inspection frequency of the devices in the device priority list by using the allocation function is:

[0025] BS1: Determine the inspection frequency of the devices in the device priority list through the allocation function. The allocation function is as follows:

[0026] f j =f basc +k·P j

[0027] Among them, f j It is expressed as the inspection frequency of the jth device, f basc is the minimum inspection frequency, k is the priority score influence coefficient;

[0028] BS2: The device is inspected at a specified interval T1 according to the inspection frequency, where T1 is a preset value.

[0029] As a further solution of the present invention: in the step 3, the real-time video monitoring of the factory equipment is performed by the camera, and video inspection rules are formulated according to the equipment inspection frequency. The specific manner in which the camera conducts equipment inspection according to the formulated video inspection rules is:

[0030] CS1: According to the inspection frequency f of the equipment j and the specified time T1, determine the video inspection collection interval Δt of the equipment j ,

[0031] CS2: Then determine the video inspection duration of the device. The device video inspection duration Th is determined by the following formula: j :

[0032] Th j =T base ·(1+γ·G j )

[0033] Among them, T base It is expressed as the basic inspection duration, γ is the fault weighting factor, G i Indicates the historical failure times of the device;

[0034] CS3: Different depths of inspection are set for different devices. The device video analysis depth A is determined by the following formula: j :

[0035] A j =A base ·(1+α·P j +β·G j )

[0036] Among them, A j Depth A for video analysis j , indicating the amount of video content that needs to be checked; A base It represents the analysis depth of technical videos, represents the analysis depth of standard videos; α and β are weight coefficients;

[0037] CS4: Perform video inspection and analysis on each device based on the device's video inspection collection interval, video inspection duration, and video analysis depth.

[0038] As a further solution of the present invention: in step AS3, the impact assessment value C i It is specifically expressed as the production loss assessment value, which is determined by the following formula:

[0039] C i=T fe ·Us·Vq

[0040] Among them, T fe It is expressed as the downtime caused by equipment failure, Us represents the output loss per hour when the equipment fails; Vq represents the production value of each unit of product.

[0041] A video inspection control system based on a digital factory, comprising:

[0042] The priority assessment module is used to determine the priority of the equipment in the factory by building a preset priority assessment model, and generate the final equipment priority list based on the priority assessment results.

[0043] Inspection frequency allocation module, used to determine the inspection frequency of devices in the device priority list through allocation function according to the priority list

[0044] The inspection rule formulation module is used to conduct real-time video monitoring of factory equipment through cameras and formulate video inspection rules based on the equipment inspection frequency. The camera conducts equipment inspections based on the formulated video inspection rules.

[0045] The video inspection acquisition module is used to conduct video inspections on various equipment in the factory according to video inspection rules, collect the operating video of the equipment through the camera, and analyze the equipment status.

[0046] The present invention provides a video inspection control method and system based on a digital factory. Compared with the prior art, it has the following beneficial effects:

[0047] The present invention provides a scientific and efficient equipment management solution by constructing a video inspection control method based on a digital factory; through the comprehensive application of a priority evaluation model, an inspection frequency allocation function and intelligent video inspection rules, the optimal allocation of equipment inspection resources is achieved, so that high-priority equipment can receive more accurate attention and management; at the same time, by using a camera to collect equipment operation video in real time and combining it with deep analysis technology, the equipment status can be quickly and comprehensively detected, potential faults can be discovered in time, and the risk of equipment downtime and production loss can be effectively reduced.

[0048] This method forms a closed-loop monitoring and control system through intelligent design of the entire process, from priority assessment to inspection frequency determination, and then to video inspection and status analysis. It not only improves inspection efficiency, reduces manual intervention and resource waste, but also significantly improves the safety of equipment operation and the reliability of the overall factory operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The present invention will be further described below in conjunction with the accompanying drawings.

[0050] Figure 1 A flowchart of the steps of a video inspection control method based on a digital factory of the present invention;

[0051] Figure 2 The present invention is a framework diagram of a video inspection control system based on a digital factory. DETAILED DESCRIPTION

[0052] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions 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 are within the scope of protection of the present invention.

[0053] Embodiment 1

[0054] See also Figure 1-Figure 2 ,The present invention provides a video inspection control method based on a digital factory, comprising:

[0055] Step 1: By building a preset priority evaluation model, the priority of the equipment in the factory is determined, and the final equipment priority list is generated according to the priority evaluation results;

[0056] The specific method of constructing a preset priority evaluation model to determine the priority of the equipment in the factory and generating the final equipment priority list according to the priority evaluation result is as follows:

[0057] AS1: Obtain each device in the factory and take each device as the target device in turn for device priority scoring;

[0058] AS2: Get the total number of failures of the target device in the past set time, using the formula Determine the historical failure rate F of the target equipment, where G u Indicates the total number of failures of the target device in the past set time, T u Indicates the set time, which is a preset value and is set by professional personnel;

[0059] Then the target equipment historical failure rate F is standardized and the equipment standard historical failure rate F is determined by the following formula: ′ : Among them, max(F) represents the maximum value of the historical failure rate of all devices as target devices, indicating the failure rate of the device with the highest failure frequency;

[0060] AS3: Determine the impact coefficient I of the target equipment failure on production or operation, which is determined by the following formula: Among them, C i is the impact assessment value of the i-th fault, N is the number of faults in the historical statistical period, T O It is expressed as the historical statistical duration. The specific duration of the historical statistical duration is set by professional staff;

[0061] Then the influence coefficient I is standardized and the standard influence coefficient I is determined by the following formula: ′ : Wherein, max(I) represents the maximum value of the influence coefficient among all devices as target devices;

[0062] AS4: Determine the historical statistical duration T of the target device O The maintenance frequency M in is determined by the following formula: Among them, M u It is expressed as the total number of maintenance times in the historical statistical period;

[0063] Then the maintenance frequency is standardized and the standard maintenance frequency M is determined by the following formula: ′ : Wherein, max(M) represents the maximum value of the maintenance frequency among all devices as target devices;

[0064] AS5: Determine the cumulative operating time T of the target equipment since it was put into operation e , and obtain the equipment's operating life T s , through the formula: Calculate the operating coefficient T of the target equipment ed ;

[0065] AS6: Get the standard historical failure rate F of the target device ′ , Standard influence coefficient I ′ 、Standard maintenance frequency M ′ and operating factor T ed , the priority score of the target device is determined by a preset priority evaluation model, which is embodied by the following formula:

[0066] P j =W1·F ′ +W2·I ′ +W3·M ′ +W4·T ed

[0067] Among them, P j It is the priority score of the target equipment, and 1≤j≤z, z represents the total number of equipment in the factory; W1, W2, W3 and W4 are weight coefficients; the specific number is determined by professional staff;

[0068] AS7: Repeat steps AS2-AS6 to determine that each device in the factory is a target device for device priority scoring, and sort them from high to low according to the priority scores to generate a final priority list;

[0069] By establishing a preset priority evaluation model, a multi-dimensional, multi-indicator comprehensive analysis of the equipment in the factory is conducted. Starting from key data such as the historical failure rate, impact coefficient, maintenance frequency, and operation coefficient of the equipment, through standardized processing and weighted evaluation, the interference of human subjective factors is effectively removed to ensure the scientificity and fairness of the evaluation process. At the same time, this method can focus on high-priority equipment in combination with the importance of equipment in production and operation, thereby providing strong support for the optimal allocation of inspection resources, reducing resource waste, and improving the equipment management efficiency of the factory.

[0070] Step 2: According to the priority list, the inspection frequency of the equipment in the equipment priority list is determined by the allocation function;

[0071] The specific method of determining the inspection frequency of the devices in the device priority list by using the allocation function is as follows:

[0072] BS1: Determine the inspection frequency of the devices in the device priority list through the allocation function. The allocation function is as follows:

[0073] f j =f basc +k·P j

[0074] Among them, f j It is expressed as the inspection frequency of the jth device, f basc is the minimum inspection frequency, which is set by professional staff, and k is the priority score influence coefficient;

[0075] BS2: Perform inspections on the equipment at specified intervals T1 according to the inspection frequency. The specified intervals T1 are determined by professional staff. In this embodiment, the specified interval T1 is one hour.

[0076] By using the allocation function, the inspection frequency is dynamically adjusted according to the device priority score, so that high-priority devices can be inspected more frequently to ensure the reliability and safety of their operating status; the setting of the inspection frequency not only improves the pertinence of the inspection work, but also effectively avoids excessive inspection of low-priority devices, thereby reducing the waste of inspection time and cost;

[0077] Step 3: Use cameras to conduct real-time video monitoring of factory equipment, and formulate video inspection rules based on the equipment inspection frequency. The camera conducts equipment inspections based on the formulated video inspection rules;

[0078] The camera is used to conduct real-time video monitoring of the factory equipment, and video inspection rules are formulated according to the equipment inspection frequency. The specific way in which the camera conducts equipment inspection according to the formulated video inspection rules is as follows:

[0079] CS1: According to the inspection frequency f of the equipment j and the specified time T1, determine the video inspection collection interval Δt of the equipment j ,

[0080] CS2: Then determine the video inspection duration of the device. The device video inspection duration Th is determined by the following formula: j :

[0081] Th j =T base ·(1+γ·G j )

[0082] Among them, T base It is the basic inspection time, which is the minimum inspection time set for all equipment. It is set by professional staff and is usually set to 0.5 hours. γ is the fault weighting factor. G i Indicates the historical failure times of the device;

[0083] CS3: Different depths of inspection are set for different devices. The device video analysis depth A is determined by the following formula: j :

[0084] A j =A base ·(1+α·P j +β·G j )

[0085] Among them, A j Depth A for video analysis j , indicating the amount of video content that needs to be checked; A base Indicates the analysis depth of the technical video, which is set by professionals and is usually set to 1, representing the standard video analysis depth; α and β are weight coefficients;

[0086] It should be noted that the depth of video analysis refers to the degree, detail and complexity of the analysis of the collected video data when performing video inspections. It not only refers to the physical content of the video data (such as image resolution, video frame rate, etc.), but also includes how to process these video contents, involving the depth of analysis of the equipment status, the complexity of data processing, the sophistication of the detection task, etc. Specifically, if the video analysis depth is high, a higher resolution may be required to capture more detailed image information; this allows the video analysis system to see the status of the equipment more clearly and discover minor faults or damage. The specific provisions for the division of video analysis depth are set by professional staff.

[0087] CS4: Perform video inspection and analysis on each device based on the device’s video inspection collection interval, video inspection duration, and video analysis depth;

[0088] Real-time video monitoring of factory equipment is carried out through cameras, and exclusive video inspection rules are formulated according to the inspection frequency, which greatly improves the flexibility and accuracy of inspections. Inspection rules comprehensively consider parameters such as video acquisition interval, video inspection duration and video analysis depth, so that inspection coverage is both wide and deep, thus being able to adapt to the operating characteristics and inspection needs of different equipment;

[0089] Step 4: Perform video inspections on each device in the factory according to the video inspection rules, collect the device's operating video through the camera, and analyze and detect the device status.

[0090] Embodiment 2

[0091] In the specific implementation process, this embodiment is based on the first embodiment, and the difference from the first embodiment is that in step AS3, the impact assessment value C i It is specifically expressed as the production loss assessment value, which is determined by the following formula:

[0092] C i =T fe ·Us·Vq

[0093] Among them, T fe It is represented by the downtime caused by equipment failure, Us represents the output loss per hour when the equipment fails; Vq represents the production value of each unit of product;

[0094] Specifically, downtime is the length of time a machine is stopped due to a failure in the equipment. If the equipment stops working completely, the downtime is equal to the total length of time the equipment is unable to produce. This time can be calculated using historical data and is usually the time from when the equipment fails to when it is repaired. Output loss refers to the number of products produced per hour during the equipment failure. This depends on the equipment's production capacity and the production lines affected by the equipment failure, and it can be estimated based on the equipment's specifications and production efficiency. The production value per unit product refers to the production cost of each product. The production cost of the product can be used to calculate production loss.

[0095] Embodiment 3

[0096] See also Figure 2 In the specific implementation process, this embodiment is based on the first and second embodiments, and the difference from the first and second embodiments is that this embodiment further provides a video inspection control system based on a digital factory, including:

[0097] The priority assessment module is used to determine the priority of the equipment in the factory by building a preset priority assessment model, and generate the final equipment priority list based on the priority assessment results.

[0098] Inspection frequency allocation module, used to determine the inspection frequency of devices in the device priority list through allocation function according to the priority list

[0099] The inspection rule formulation module is used to conduct real-time video monitoring of factory equipment through cameras and formulate video inspection rules based on the equipment inspection frequency. The camera conducts equipment inspections based on the formulated video inspection rules.

[0100] The video inspection acquisition module is used to conduct video inspections on various equipment in the factory according to video inspection rules, collect the operating video of the equipment through the camera, and analyze the equipment status.

[0101] Embodiment 4

[0102] The specific implementation process of this embodiment includes all the implementation processes of the above three groups of embodiments.

[0103] Some of the data in the above formulas are dimensionless and numerically calculated. Meanwhile, the contents not described in detail in this specification belong to the prior art known to those skilled in the art.

[0104] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A video inspection control method based on a digital factory, characterized in that: include: Step 1: By building a preset priority evaluation model, the priority of the equipment in the factory is determined, and the final equipment priority list is generated according to the priority evaluation results; Step 2: According to the priority list, the inspection frequency of the equipment in the equipment priority list is determined by the allocation function; Step 3: Use cameras to conduct real-time video monitoring of factory equipment, and formulate video inspection rules based on the equipment inspection frequency. The camera conducts equipment inspections based on the formulated video inspection rules; Step 4: Perform video inspections on each device in the factory according to the video inspection rules, collect the device's operating video through the camera, and analyze and detect the device status.

2. A video inspection control method based on a digital factory according to claim 1, characterized in that: In the step 1, the priority of the equipment in the factory is determined by constructing a preset priority evaluation model, and the specific method of generating the final equipment priority list according to the priority evaluation result is as follows: AS1: Obtain each device in the factory and take each device as the target device in turn for device priority scoring; AS2: Get the total number of failures of the target device in the past set time, using the formula Determine the historical failure rate F of the target equipment, where G u Indicates the total number of failures of the target device in the past set time, T u Indicates the set time; Then the target equipment historical failure rate F is standardized and the equipment standard historical failure rate F′ is determined by the following formula: Where max(F) represents the maximum value of the historical failure rate of all devices as target devices; AS3: Determine the impact coefficient I of the target equipment failure on production or operation, which is determined by the following formula: Among them, C i is the impact assessment value of the i-th fault, N is the number of faults in the historical statistical period, T O Represents the historical statistical duration; Then the influence coefficient I is standardized and the standard influence coefficient I′ is determined by the following formula: Wherein, max(I) represents the maximum value of the influence coefficient among all devices as target devices; AS4: Determine the historical statistical duration T of the target device O The maintenance frequency M in is determined by the following formula: Among them, M u It is expressed as the total number of maintenance times in the historical statistical period; Then the maintenance frequency is standardized and the standard maintenance frequency M is determined by the following formula: ′ : Wherein, max(M) represents the maximum value of the maintenance frequency among all devices as target devices; AS5: Determine the cumulative operating time T of the target equipment since it was put into operation e , and obtain the equipment's operating life T s , through the formula: Calculate the operating coefficient T of the target equipment ed ; AS6: Get the standard historical failure rate F of the target device ′ , Standard influence coefficient I ′ 、Standard maintenance frequency M ′ and operating factor T ed , the priority score of the target device is determined by a preset priority evaluation model, which is embodied by the following formula: P j =W1·F ′ +W2·I ′ +W3·M ′ +W4·T ed Among them, P j is the priority score of the target equipment, and 1≤j≤z, z represents the total number of equipment in the factory; W1, W2, W3 and W4 are weight coefficients.

3. A video inspection control method based on a digital factory according to claim 2, characterized in that: The above-mentioned construction of a preset priority evaluation model to determine the priority of the equipment in the factory and generating a final equipment priority list according to the priority evaluation result also includes: AS7: Repeat steps AS2-AS6 to determine that each device in the factory is a target device for device priority scoring, and sort them from high to low according to the priority scores to generate a final priority list.

4. The video inspection control method based on digital factory according to claim 1 is characterized in that: In the step 2, the specific method of determining the inspection frequency of the devices in the device priority list by using the allocation function is: BS1: Determine the inspection frequency of the devices in the device priority list through the allocation function. The allocation function is as follows: f j =f basc +k·P j Among them, f j It is expressed as the inspection frequency of the jth device, f basc is the minimum inspection frequency, k is the priority score influence coefficient; BS2: The device is inspected at a specified interval T1 according to the inspection frequency, where T1 is a preset value.

5. The video inspection control method based on digital factory according to claim 1 is characterized in that: In step 3, the camera is used to conduct real-time video monitoring of the factory equipment, and video inspection rules are formulated according to the equipment inspection frequency. The specific manner in which the camera conducts equipment inspection according to the formulated video inspection rules is as follows: CS1: According to the inspection frequency f of the equipment j and the specified time T1, determine the video inspection collection interval Δt of the equipment j , CS2: Then determine the video inspection duration of the device. The device video inspection duration Th is determined by the following formula: j : Th j =T base ·(1+γ·G j ) Among them, T base It is expressed as the basic inspection duration, γ is the fault weighting factor, G i Indicates the historical failure times of the device; CS3: Different depths of inspection are set for different devices. The device video analysis depth A is determined by the following formula: j : A j =A base ·(1+α·P j +β·G j ) Among them, A j Depth A for video analysis j , indicating the amount of video content that needs to be checked; A base It represents the analysis depth of technical videos, represents the analysis depth of standard videos; α and β are weight coefficients; CS4: Perform video inspection and analysis on each device based on the device's video inspection collection interval, video inspection duration, and video analysis depth.

6. The video inspection control method based on digital factory according to claim 2 is characterized in that: In step AS3, the impact assessment value C i It is specifically expressed as the production loss assessment value, which is determined by the following formula: C i =T fe ·Us·Vq Among them, T fe It is expressed as the downtime caused by equipment failure, Us represents the output loss per hour when the equipment fails; Vq represents the production value of each unit of product.

7. A video inspection control system based on a digital factory, characterized in that: include: The priority assessment module is used to determine the priority of the equipment in the factory by building a preset priority assessment model, and generate the final equipment priority list based on the priority assessment results. Inspection frequency allocation module, used to determine the inspection frequency of devices in the device priority list through allocation function according to the priority list The inspection rule formulation module is used to conduct real-time video monitoring of factory equipment through cameras and formulate video inspection rules based on the equipment inspection frequency. The camera conducts equipment inspections based on the formulated video inspection rules. The video inspection acquisition module is used to conduct video inspections on various equipment in the factory according to video inspection rules, collect the operating video of the equipment through the camera, and analyze the status of the detection equipment.

Images