Equipment remote monitoring method and system based on smart factory

Abstract

The invention relates to an equipment remote monitoring method based on a smart factory. The method comprises the following steps: querying a basic monitoring frequency tree to obtain an initial monitoring frequency of each piece of to-be-monitored product production equipment; the monitoring sensing equipment collects state parameters of the to-be-monitored product production equipment according to the monitoring frequency; calculating an abnormal risk value of the to-be-monitored product production equipment in the current dynamic adjustment period according to the state parameters of the to-be-monitored product production equipment; and according to the abnormal risk value of the to-be-monitored product production equipment, adjusting the current monitoring frequency of the to-be-monitored product production equipment to obtain the monitoring frequency of the to-be-monitored product production equipment in the next dynamic adjustment period, and determining whether to send out an instruction of manual inspection so as to instruct inspection personnel to manually collect state parameters of the to-be-monitored product production equipment. According to the method and the device, the state of the equipment in the smart factory can be accurately monitored, the faulted equipment and problems can be positioned and checked in time, and the situation of insufficient or redundant operation data in equipment state monitoring is avoided.

Description

Technical Field

[0001] This application relates to the field of smart factories, and in particular to a method and system for remote monitoring of equipment in a smart factory. Background Technology

[0002] In today's industrial landscape, driven by the trend of digital transformation, smart factories have become a crucial direction for manufacturing development. With the rise of Industry 4.0, intelligent manufacturing has become key to the transformation and upgrading of the manufacturing industry, and smart factories, as an important carrier of intelligent manufacturing, have received widespread attention for their construction and development. In smart factories, a large number of automated devices, sensors, and actuators work together to ensure the stable operation of production lines and the reliability of product quality. However, the stable operation of this equipment faces many challenges, making real-time monitoring and maintenance extremely urgent.

[0003] Traditional industrial equipment operation and maintenance management relies on manual inspections for sampling. Maintenance personnel need to regularly go to the equipment site to check the equipment's operating status and record operating data. Although this manual inspection sampling method has a high accuracy rate, it is inefficient and makes it difficult to detect equipment problems in a timely manner. Furthermore, once equipment malfunctions, due to the lack of real-time operating data, technicians often find it difficult to locate the problem promptly and need to spend a lot of time troubleshooting. This leads to prolonged equipment downtime, seriously affecting production progress and causing huge economic losses to enterprises.

[0004] Currently, automatic sampling is used for equipment inspection, which typically follows a fixed sampling frequency. This method cannot be dynamically adjusted according to changes in equipment status and environment. Therefore, it may not collect enough operational data at critical moments, while generating a large amount of redundant operational data at normal times. Furthermore, the accuracy of the operational data collected through automatic sampling is easily affected by factors such as the environment and the status of the sampling equipment, thus affecting the accuracy of the equipment status assessment.

[0005] Therefore, how to accurately monitor the status of equipment in a smart factory, promptly locate and troubleshoot faulty equipment and problems, and avoid insufficient or redundant operating data in equipment status monitoring is a technical problem that urgently needs to be solved by those skilled in the art. Summary of the Invention

[0006] This application provides a method and system for remote equipment monitoring in a smart factory, which can accurately monitor the status of equipment in the smart factory, locate and troubleshoot faulty equipment and problems in a timely manner, and avoid insufficient or redundant operating data in equipment status monitoring.

[0007] To solve the above-mentioned technical problems, this application provides the following technical solution:

[0008] A remote equipment monitoring method based on a smart factory, applied to the edge computing device side, includes the following steps: In response to the start of a production cycle, querying the basic monitoring frequency tree stored in the data storage device to obtain the initial monitoring frequency of each production equipment to be monitored; sending the initial monitoring frequency / monitoring frequency in the next dynamic adjustment cycle of the production equipment to be monitored to the corresponding monitoring sensing device, so that it can collect the status parameters of the production equipment to be monitored according to the initial monitoring frequency / monitoring frequency in the next dynamic adjustment cycle; receiving the status parameters of the production equipment to be monitored, and at the end of the current dynamic adjustment cycle, calculating the abnormal risk value of the production equipment to be monitored in the current dynamic adjustment cycle based on the status parameters of the production equipment to be monitored; adjusting the current monitoring frequency of the production equipment to be monitored based on the abnormal risk value of the production equipment to be monitored in the current dynamic adjustment cycle to obtain its monitoring frequency in the next dynamic adjustment cycle, and determining whether to issue a manual inspection instruction to instruct inspection personnel to manually collect the status parameters of the production equipment to be monitored.

[0009] The above-described method for remote equipment monitoring based on smart factories is applied to the edge computing device side. Preferably, in response to the end of the production cycle, the monitoring frequency and abnormal risk value of each production equipment of the product to be monitored in each dynamic adjustment cycle are sent to the cloud processing platform so that the monitoring frequency and abnormal risk value can be stored and / or processed.

[0010] The above-described remote equipment monitoring method based on smart factories is applied to the edge computing device side. Preferably, the initial monitoring frequency is obtained according to the following sub-steps: traversing the basic monitoring frequency tree, finding the branch of the monitoring frequency tree where the production equipment of the product to be monitored is located, and obtaining the basic monitoring frequency of the production equipment of the product to be monitored and all its superior objects in the monitoring frequency tree branch; multiplying the basic monitoring frequency of the production equipment of the product to be monitored and all its superior objects by the corresponding category weight and rounding up to obtain the monitoring frequency of each level of the production equipment of the product to be monitored; and summing the monitoring frequencies of each level of the production equipment of the product to be monitored as the initial monitoring frequency of the production equipment of the product to be monitored.

[0011] The aforementioned remote equipment monitoring method based on smart factories is applied to the edge computing device side. Preferably, the abnormal risk value of the production equipment of the product to be monitored within the current dynamic adjustment period is obtained according to the following steps: the state parameters of the production equipment of the product to be monitored at each moment within the current dynamic adjustment period are compared with the corresponding standard state parameters stored in the data storage device to determine the standard deviation of each state parameter of the production equipment of the product to be monitored within the current dynamic adjustment period; based on the recorded equipment type, fault frequency, total operating time, and fault type of the production equipment of the product to be monitored, the current risk weight of the production equipment of the product to be monitored is calculated; the abnormal risk value of the production equipment of the product to be monitored within the current dynamic adjustment period is obtained by multiplying the standard deviation of each state parameter and the influence weight of each state parameter within the current dynamic adjustment period, and the current risk weight of the production equipment of the product to be monitored.

[0012] The above-described method for remote equipment monitoring based on smart factories is applied to the edge computing device side. Preferably, the status parameters of the production equipment of the product to be monitored at each moment in the current dynamic adjustment cycle are collected by the monitoring and sensing device alone, or by the monitoring and sensing device and the inspection personnel together.

[0013] The above-described method for remote equipment monitoring based on smart factories is applied to the edge computing device side. Preferably, if the status parameters are collected separately by the monitoring and sensing device, the status parameters of the production equipment of the product to be monitored at each moment in the current dynamic adjustment cycle are compared with the standard status parameters of the production equipment of the product to be monitored to obtain the first standard deviation of each status parameter of the production equipment of the product to be monitored in the current dynamic adjustment cycle.

[0014] The above-described remote equipment monitoring method based on smart factories is applied to the edge computing device side. Preferably, if the status parameters are jointly collected by the monitoring and sensing device and the inspection personnel, the status parameters of the production equipment of the product to be monitored at each moment in the current dynamic adjustment cycle collected by the monitoring and sensing device are compared with the standard status parameters of the production equipment of the product to be monitored, and the first comparison result is multiplied by the weight of the corresponding status parameter. The manually collected status parameters of the production equipment of the product to be monitored in the current dynamic adjustment cycle are compared with the standard status parameters of the production equipment of the product to be monitored, and the second standard deviation of each status parameter of the production equipment of the product to be monitored in the current dynamic adjustment cycle is obtained by multiplying the second comparison result with the above product.

[0015] The above-described method for remote equipment monitoring based on smart factories is applied to the edge computing device side. Preferably, the time interval between the time when the production equipment of the product to be monitored is manually sampled and the time when the monitoring and sensing device samples within the current dynamic adjustment cycle is calculated, and the reciprocal of the time interval is used as the weight of the state parameters collected by the monitoring and sensing device at the corresponding time.

[0016] The above-described remote equipment monitoring method based on smart factories is applied to the edge computing device side. Preferably, the abnormal risk value YF of the i-th product production equipment to be monitored within the current dynamic adjustment cycle is used. idq The expression is:

[0017]

[0018] Where, μ dqi ρ represents the current risk weight of the production equipment for the i-th product to be monitored; iy σ represents the influence weight of the y-th state parameter of the i-th production equipment for the product to be monitored; iy Let σ' be the first standard deviation of the y-th state parameter of the i-th production equipment for the monitored product within the current dynamic adjustment cycle; iy Let Y be the second standard deviation of the y-th state parameter of the i-th production equipment to be monitored within the current dynamic adjustment cycle; Y is the number of state parameter types. XOR.

[0019] A remote equipment monitoring system based on a smart factory includes: product manufacturing equipment, monitoring and sensing equipment, edge computing equipment, data storage equipment, and a cloud processing platform; the product manufacturing equipment, monitoring and sensing equipment, and edge computing equipment are all deployed in each workshop of the smart factory, the data storage equipment is deployed in the control center of the smart factory, and the cloud processing platform is deployed outside the smart factory; the edge computing equipment executes any of the above-described remote equipment monitoring methods based on a smart factory.

[0020] Compared with the above-mentioned background technology, the remote equipment monitoring method and system based on smart factories provided in this application can accurately monitor the status of equipment in smart factories, locate and troubleshoot faulty equipment and problems in a timely manner, and avoid insufficient or redundant operating data in equipment status monitoring. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For those skilled in the art, other drawings can be obtained based on these drawings.

[0022] Figure 1 This is a schematic diagram of the remote equipment monitoring system based on a smart factory provided in this application;

[0023] Figure 2 This is a schematic diagram of the basic monitoring frequency tree of the smart factory provided in this application;

[0024] Figure 3 This is a flowchart of the remote equipment monitoring method based on a smart factory provided in this application;

[0025] Figure 4 This is a flowchart of the process for obtaining the initial monitoring frequency of the production equipment of the product to be monitored, as provided in this application.

[0026] Figure 5 This is a flowchart of the process for obtaining the abnormal risk values ​​of the production equipment of the product to be monitored within the current dynamic adjustment period provided in this application. Detailed Implementation

[0027] Embodiments of the present invention are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and should not be construed as limiting the present invention.

[0028] Example 1

[0029] like Figure 1 As shown, this application provides a remote equipment monitoring system 100 based on a smart factory, including: product manufacturing equipment 110, monitoring and sensing equipment 120, edge computing equipment 130, data storage equipment 140, and cloud processing platform 150.

[0030] Product manufacturing equipment 110, monitoring and sensing equipment 120, and edge computing equipment 130 are all deployed in each workshop of the smart factory. Data storage equipment 140 is deployed in the control center of the smart factory. All edge computing equipment 130 in all workshops access the same data storage equipment 140. Furthermore, the monitoring and sensing equipment 120 and the edge computing equipment 130, as well as the edge computing equipment 130 and the data storage equipment 140, communicate through the private dedicated network of the smart factory, thereby preventing the smart factory from being attacked from the outside and ensuring the security of the smart factory. The cloud processing platform 150 is deployed outside the smart factory and communicates with the edge computing equipment 130 in all workshops through the public Internet, thereby providing powerful backup computing power for the edge computing equipment 130 in the smart factory.

[0031] Among them, product manufacturing equipment 110 is equipment used for product manufacturing, such as: automated production equipment (industrial robots, programmable logic controllers (PLCs), distributed control systems (DCS), servo motors, etc.), logistics and warehousing equipment (automated guided vehicles (AGVs), robotic arms, etc.), quality inspection and maintenance equipment (AI vision inspection systems, multispectral imaging equipment, remote-controlled robots, etc.), auxiliary equipment (lighting equipment, ventilation equipment, etc.); monitoring and sensing equipment 120 is equipment used to collect the status parameters (e.g., voltage, temperature, vibration frequency, etc.) of product manufacturing equipment 110, such as: various sensors, smart meters, machine vision equipment, and other sensing devices.

[0032] A smart factory has multiple workshops, such as a stamping workshop, a welding workshop, and a final assembly workshop; each workshop has one or more production lines, such as production line A in the stamping workshop, production line B in the stamping workshop, etc.; each production line is divided into different production stations, such as the uncoiling equipment area of ​​production line A, the forming equipment area of ​​production line A, etc.; each production station usually has different types of product manufacturing equipment 110.

[0033] In product manufacturing, management is typically carried out on a workshop-by-workshop basis. Different production lines, workstations, and types of product manufacturing equipment 110 within a workshop have varying degrees of importance and risk levels. When remotely monitoring product manufacturing equipment 110, the workshop's monitoring resources need to be prioritized for high-importance, high-risk equipment 110. Therefore, this application divides the smart factory into multiple levels from top to bottom: workshop, production line, workstation, and product manufacturing equipment 110. Basic monitoring frequencies are set for each level (the first level includes workshops, the second level includes production lines, the third level includes workstations, and the fourth level includes product manufacturing equipment) according to their importance and risk level, thus forming the smart factory's basic monitoring frequency tree (e.g., ...). Figure 2 As shown in the figure, the basic monitoring frequency tree will be pre-stored in the data storage device 140 in the smart factory.

[0034] In addition, the basic monitoring frequency of each object in the basic monitoring frequency tree can be adjusted according to the operation status of the workshop, production line, production station, and product production equipment 110 (e.g., increased failure rate) or changes at each level (e.g., upgrade to core equipment), thereby achieving dynamic adjustment of the monitoring frequency to a certain extent.

[0035] In addition, each product manufacturing equipment 110 has a normal operating state. The state parameters generated in the normal operating state are regarded as standard state parameters. The standard state parameters of each product manufacturing equipment 110 are pre-stored in the data storage device 140 in the smart factory for use in subsequent monitoring to determine whether the corresponding product manufacturing equipment 110 is abnormal.

[0036] Example 2

[0037] like Figure 3 As shown, this application provides a method for remote equipment monitoring based on a smart factory, including the following steps:

[0038] Step S310: In response to the start of the production cycle, the edge computing device queries the basic monitoring frequency tree stored in the data storage device to obtain the initial monitoring frequency of each production equipment for the product to be monitored.

[0039] Specifically, such as Figure 4 As shown, the initial monitoring frequency of the production equipment for the product to be monitored in this step can be obtained by following these steps:

[0040] Step S311: Traverse the basic monitoring frequency tree, find the branch of the monitoring frequency tree where the production equipment of the product to be monitored is located, and obtain the basic monitoring frequency of the production equipment of the product to be monitored and all its parent objects in the monitoring frequency tree branch.

[0041] When a production cycle T begins, the edge computing devices in each workshop of the smart factory access the basic monitoring frequency tree stored in the data storage device of the control center of the smart factory, and traverse the basic monitoring frequency tree to find the branch of the monitoring frequency tree where the production equipment of the product to be monitored in that workshop is located. For example: stamping workshop - production line A of stamping workshop - uncoiling equipment area of ​​production line A - industrial robot (automatic guided vehicle, multispectral imaging equipment, lighting equipment, ventilation equipment), where the industrial robot is the production equipment of the product to be monitored, and obtain the basic monitoring frequency of the production equipment of the product to be monitored from the branch of the monitoring frequency tree.

[0042] Since the initial monitoring frequency of a single product manufacturing equipment is determined not only by its own basic monitoring frequency, but also by the basic monitoring frequencies of all the parent objects of the monitoring frequency tree branch to which it belongs, the edge computing device also obtains the basic monitoring frequencies of all the parent objects of the product manufacturing equipment to be monitored (the uncoiling equipment area of ​​production line A, production line A of the stamping workshop, and the stamping workshop) from the monitoring frequency tree branch.

[0043] Step S312: Multiply the basic monitoring frequency of the production equipment of the product to be monitored and all its superior objects by the corresponding category weights and round up to obtain the monitoring frequency of each level of the production equipment of the product to be monitored.

[0044] After obtaining the basic monitoring frequency of the i-th production equipment for the product to be monitored and the basic monitoring frequencies of all its superiors, the edge computing device will use the basic monitoring frequency P of the i-th production equipment for the product to be monitored. ci The weight ω of the type of production equipment for the i-th product to be monitored i Multiply and round up Obtain the current level monitoring frequency of the production equipment for the i-th product to be monitored.

[0045] The edge computing device will monitor the j-th level object of the i-th product manufacturing equipment at a base frequency P. cji Weight of the type of the j-th level object Multiply and round up Obtain the hierarchical monitoring frequency of the j-th level above the production equipment of the i-th product to be monitored.

[0046] Step S313: The sum of the monitoring frequencies of each level of the production equipment of the product to be monitored is used as the initial monitoring frequency of the production equipment of the product to be monitored.

[0047] The edge computing device will monitor the current level of the production equipment for the i-th product to be monitored at a certain frequency. The hierarchical monitoring frequency of the j-th level above the production equipment of the i-th product to be monitored The sum is added together, and the result is used as the initial monitoring frequency P of the production equipment for the i-th product to be monitored. si .

[0048] Furthermore, the initial monitoring frequency P of the production equipment for the i-th product to be monitored si The expression is:

[0049]

[0050] Step S320: The edge computing device sends the initial monitoring frequency of the production equipment of the product to be monitored to the corresponding monitoring and sensing device, and the monitoring and sensing device collects the status parameters of the production equipment of the product to be monitored according to the initial monitoring frequency.

[0051] The initial monitoring frequency P of the production equipment for the i-th product to be monitored is obtained. si Subsequently, the edge computing devices in each workshop of the smart factory will use the initial monitoring frequency P si The initial monitoring frequency P is sent to the i-th monitoring and sensing device in the workshop in response to receiving the initial monitoring frequency P of the production equipment for the i-th product to be monitored. si The i-th monitoring and sensing device follows the initial monitoring frequency P. siStart collecting the status parameters of the i-th production equipment of the product to be monitored, and the i-th monitoring and sensing device sends the collected status parameters of the i-th production equipment of the product to be monitored to the edge computing device.

[0052] Step S330: The edge computing device receives the status parameters of the production equipment of the product to be monitored, and at the end of the current dynamic adjustment cycle, calculates the abnormal risk value of the production equipment of the product to be monitored within the current dynamic adjustment cycle based on the status parameters of the production equipment of the product to be monitored.

[0053] Within different dynamic adjustment cycles of the production cycle T, the edge computing devices in each workshop of the smart factory will instruct the monitoring and sensing devices to collect the status parameters of the production equipment of the product to be monitored according to the corresponding monitoring frequency. Furthermore, the edge computing devices in each workshop of the smart factory will also instruct the inspection personnel whether manual sampling is required based on the abnormal risk value of the production equipment of the product to be monitored. Therefore, the status parameters of the production equipment of the product to be monitored received by the edge computing devices may be collected by the monitoring and sensing devices alone, or they may be collected jointly by the monitoring and sensing devices and the inspection personnel.

[0054] Furthermore, the edge computing device also sends the status parameters of the production equipment of the product to be monitored to the data storage device for storage. This way, if the equipment fails, a large amount of data can be used for troubleshooting. Moreover, storing the original data in the internal storage of the smart factory can improve data security and prevent data leakage.

[0055] Specifically, such as Figure 5 As shown, the abnormal risk value of the production equipment of the product to be monitored within the current dynamic adjustment cycle in this step can be obtained by following these steps:

[0056] Step S331: Compare the status parameters of the production equipment of the product to be monitored at each moment in the current dynamic adjustment cycle with the corresponding standard status parameters stored in the data storage device to determine the standard deviation of each status parameter of the production equipment of the product to be monitored in the current dynamic adjustment cycle.

[0057] After the start of production cycle T, edge computing devices in each workshop of the smart factory receive the status parameters {a} of the i-th monitoring and sensing device for the i-th product production equipment to be monitored, collected by the i-th monitoring and sensing device in that workshop. ix1 a ix2 ... a ixy ...}, where a ix1 For the first state parameter of the i-th product manufacturing equipment collected by the i-th monitoring and sensing device at time x, a ix2 For the second state parameter a collected by the i-th monitoring and sensing device at time x for the i-th product manufacturing equipment to be monitored, let a ixyThe y-th state parameter of the i-th product manufacturing equipment to be monitored, collected by the i-th monitoring and sensing device at time x.

[0058] In response to receiving the status parameters of the production equipment for the product to be monitored, the edge computing devices in each workshop of the smart factory access the standard status parameters of all production equipment for the product stored in the data storage device, and find the standard status parameter {A} of the i-th production equipment for the product to be monitored. i1 A i2 A iy ...}, where A i1 Let A be the first standard state parameter of the i-th production equipment for the product to be monitored. i2 Let A be the second standard status parameter of the i-th production equipment for the product to be monitored. iy Let y be the standard status parameter of the i-th production equipment for the product to be monitored.

[0059] At the end of the current dynamic adjustment cycle, if the edge computing device has only received the status parameters of the i-th monitored product production equipment collected by the i-th monitoring and sensing device, then the status parameters {a} of the i-th monitored product production equipment collected by the i-th monitoring and sensing device at each moment during the current dynamic adjustment cycle will be updated. ix1 a ix2 ... a ixy All of these are related to the standard state parameter {A} of the i-th production equipment for the product to be monitored. i1 A i2 A iy By comparing the parameters of each state parameter of the i-th monitored product production equipment within the current dynamic adjustment cycle, the first standard deviation of each state parameter is obtained.

[0060] Furthermore, the first standard deviation σ of the y-th state parameter of the i-th monitored product manufacturing equipment within the current dynamic adjustment cycle. iy The expression is:

[0061]

[0062] Where X is the number of sampling moments within the current dynamic adjustment period.

[0063] If the inspection personnel perform manual sampling during the current dynamic adjustment cycle, at the end of the current dynamic adjustment cycle, the edge computing device will not only receive the status parameters {a} of the i-th monitored product production equipment collected by the i-th monitoring and sensing device, but also... ix1 a ix2 ... a ixy ...}, will also receive manually collected status parameters {b} of the i-th monitored product production equipment within the current dynamic adjustment cycle. i1 bi2 ... b iy ...}, where b i1 b is the first status parameter of the i-th production equipment for the product to be monitored, collected manually. i2 b is the second status parameter of the production equipment for the i-th product to be monitored, collected manually. iy This refers to the y-th status parameter of the i-th production equipment for the product to be monitored, which is collected manually.

[0064] Because manually sampled data has high accuracy, when determining the standard deviation of each state parameter of the i-th monitored product production equipment within the current dynamic adjustment cycle, it is necessary to consider the manually collected state parameters {b} of the i-th monitored product production equipment within the current dynamic adjustment cycle. i1 b i2 ... b iy ...}, to improve the accuracy of monitoring.

[0065] Furthermore, the edge computing devices in each workshop of the smart factory calculate the time interval between the moment t when manual sampling is performed on the production equipment of the i-th monitored product and the moment x when sampling is performed by the monitoring and sensing equipment within the current dynamic adjustment cycle. Thus, the weights of the state parameters collected by the monitoring and sensing device at time x are obtained. in To round up to the nearest positive integer, d(·) represents the time interval function.

[0066] At the end of the current dynamic adjustment cycle, the state parameters {a} of the i-th monitored product production equipment collected by the i-th monitoring and sensing device at each moment during the current dynamic adjustment cycle will be... ix1 a ix2 ... a ixy All of these are related to the standard state parameter {A} of the i-th production equipment for the product to be monitored. i1 A i2 A iy The comparison is performed between the first comparison result and the weight of the corresponding state parameter. Multiply; multiply the manually collected artificial state parameters {b} of the i-th monitored product production equipment within the current dynamic adjustment cycle. i1 b i2 ... b iy All of these are related to the standard state parameter {A} of the i-th production equipment for the product to be monitored. i1 A i2 A iy By comparing the results of the first comparison with the product of the first comparison, we obtain the second standard deviation of each state parameter of the production equipment of the i-th product to be monitored within the current dynamic adjustment cycle.

[0067] Furthermore, the second standard deviation σ' of the y-th state parameter of the i-th monitored product manufacturing equipment within the current dynamic adjustment cycle. iy The expression is:

[0068]

[0069] Step S332: Based on the recorded equipment type, failure frequency, total operating time, and failure type of the production equipment of the product to be monitored, calculate the current risk weight of the production equipment of the product to be monitored.

[0070] The equipment type, failure frequency, total operating time, and failure type of each monitored product manufacturing equipment affect its risk weight. Therefore, edge computing devices in each workshop of the smart factory record these risk level parameters for each monitored product manufacturing equipment and send them to a data storage device for storage. This provides a large amount of data for troubleshooting should a device malfunction. Furthermore, storing the raw data in the smart factory's internal storage improves data security and prevents data leakage. When calculating the abnormal risk value of the i-th monitored product manufacturing equipment, the current risk weight ω of the i-th monitored product manufacturing equipment needs to be calculated first using the currently recorded risk level parameters of the i-th monitored product manufacturing equipment. idq .

[0071] Furthermore, the current risk weight μ of the i-th production equipment for the product to be monitored dqi The expression is:

[0072]

[0073] Among them, B i Let β be the equipment type parameter for the production equipment of the i-th product to be monitored, and let β be the risk weight of the equipment type parameter; C i Let α be the fault frequency parameter of the i-th production equipment for the product to be monitored, and let α be the risk weight of the fault frequency parameter; D i Let γ be the total operating time parameter of the i-th product manufacturing equipment to be monitored, and let E be the risk weight of the total operating time parameter; iz ε represents the fault type parameter for the i-th product manufacturing equipment to be monitored. z π represents the type weight of the fault type parameter, Z represents the number of fault type parameters, and θ represents the overall risk weight of the variable parameters.

[0074] Step 333: Obtain the abnormal risk value of the production equipment of the product to be monitored in the current dynamic adjustment period by multiplying the standard deviation of each state parameter and the influence weight of each state parameter, and the current risk weight of the production equipment of the product to be monitored.

[0075] The degree of influence of each state parameter (e.g., temperature, vibration) on the risk level of the production equipment of the monitored product is different. Therefore, the edge computing devices in each workshop of the smart factory will match the influence weight {ρ} for each state parameter of the i-th production equipment of the monitored product. i1 ρ i2 、…、ρ iy , ...}, where ρ i1 Let ρ be the influence weight of the first state parameter of the i-th product manufacturing equipment to be monitored. i2 ρ represents the influence weight of the second state parameter of the i-th product manufacturing equipment to be monitored. iy Let y be the influence weight of the yth state parameter of the i-th product manufacturing equipment to be monitored. The influence weight of each state parameter comes from the cloud processing platform. The cloud processing platform will periodically or in response to predetermined conditions to send the influence weight of each state parameter to the edge computing device.

[0076] In a smart factory, edge computing devices in each workshop multiply the standard deviation of each state parameter of the production equipment to be monitored within the current dynamic adjustment period by the influence weight of each state parameter, and then multiply the sum of all products by the current risk weight of the production equipment to be monitored to obtain the abnormal risk value of the production equipment to be monitored within the current dynamic adjustment period.

[0077] Furthermore, the abnormal risk value YF of the i-th monitored product production equipment within the current dynamic adjustment cycle. idq The expression is:

[0078]

[0079] Where Y is the number of types of state parameters, XOR, For σ iy Occurrence or σ' iy It occurs, and σ iy and σ' iy They do not occur at the same time.

[0080] Step S340: The edge computing device adjusts the current monitoring frequency of the production equipment of the product to be monitored based on the abnormal risk value of the production equipment of the product to be monitored in the current dynamic adjustment cycle to obtain its monitoring frequency in the next dynamic adjustment cycle, and determines whether to issue a manual inspection instruction based on the abnormal risk value of the production equipment of the product to be monitored in the current dynamic adjustment cycle, so as to instruct the inspection personnel to manually collect the status parameters of the production equipment of the product to be monitored.

[0081] In a smart factory, edge computing devices in each workshop obtain the abnormal risk value YF of the i-th monitored product production equipment within the current dynamic adjustment cycle. dqi Then, the abnormal risk value YF of the i-th monitored product production equipment within the current dynamic adjustment cycle is... dqi The current monitoring frequency P of the production equipment for the i-th product to be monitored dqi Multiply the product and then multiply it by the initial monitoring frequency P of the production equipment for the i-th product to be monitored. si The sum is added together, and half of the sum is used as the monitoring frequency P of the i-th product production equipment to be monitored in the next dynamic adjustment cycle. xyi .

[0082] Furthermore, the monitoring frequency P of the production equipment for the i-th product to be monitored in the next dynamic adjustment cycle. xyi The expression is:

[0083]

[0084] Among them, the initial monitoring frequency P of the production equipment of the i-th product to be monitored is... si The monitoring frequency P of the i-th production equipment of the product to be monitored will be included in the next dynamic adjustment cycle. xyi The calculation can prevent the monitoring frequency P of the production equipment of the i-th product to be monitored from occurring in the next dynamic adjustment cycle when the standard deviation of each state parameter is 0 in the current dynamic adjustment cycle. xyi If the standard deviation of each state parameter is 0 within the current dynamic adjustment period, then the task has no abnormal risk. Therefore, the monitoring frequency of the i-th monitored product production equipment in the next dynamic adjustment period is restored to its initial monitoring frequency P. si .

[0085] In addition, the edge computing devices in each workshop of the smart factory will also dynamically adjust the abnormal risk value YF of the i-th monitoring product production equipment within the current dynamic adjustment period. dqi Compared with the preset abnormal risk threshold YF of the i-th production equipment of the product to be monitored yzi Comparison: If the abnormal risk value YF of the i-th monitored product production equipment in the current dynamic adjustment cycle is... dqi The abnormal risk threshold YF of the i-th monitored product production equipment exceedsyzi If the signal is clear, a manual inspection instruction will be issued, such as an audio instruction for manual inspection, to instruct the inspector to manually collect the status parameters of the i-th production equipment to be monitored.

[0086] Step S350: The edge computing device sends the monitoring frequency of the production equipment of the product to be monitored in the next dynamic adjustment cycle to the corresponding monitoring and sensing device. The monitoring and sensing device collects the status parameters of the production equipment of the product to be monitored according to the monitoring frequency.

[0087] The monitoring frequency P of the production equipment for the i-th product to be monitored is obtained in the next dynamic adjustment cycle. xyi Subsequently, the edge computing devices in each workshop of the smart factory will dynamically adjust the monitoring frequency P for the next cycle. xyi The message is sent to the i-th monitoring and sensing device in the workshop in response to receiving the monitoring frequency P of the i-th product manufacturing equipment in the next dynamic adjustment cycle. xyi The i-th monitoring and sensing device follows the monitoring frequency P. xyi The system begins collecting status parameters of the i-th production equipment for the product to be monitored, and the i-th monitoring and sensing device sends these parameters to the edge computing device. By adjusting the monitoring frequency in each dynamic adjustment cycle, monitoring is conducted rationally, avoiding resource waste due to over-frequent monitoring or risk oversight due to under-frequent monitoring.

[0088] Step S360: In response to the end of the production cycle, the edge computing device sends the monitoring frequency and abnormal risk value of each production equipment of the product to be monitored in each dynamic adjustment cycle to the cloud processing platform. The cloud processing platform stores and / or processes the monitoring frequency and abnormal risk value.

[0089] At the end of production cycle T, the edge computing devices in each workshop of the smart factory send the monitoring frequency and abnormal risk value of each product production equipment during each dynamic adjustment cycle of production cycle T to the cloud processing platform. The cloud processing platform stores these monitoring frequencies and abnormal risk values, and can also use these monitoring frequencies and abnormal risk values ​​to train a more accurate influence weight for each state parameter. Then, the optimized influence weight for each state parameter is distributed to the edge computing devices. In this way, the powerful computing capabilities of the cloud processing platform can be used to supplement the computing power of the edge computing devices. Moreover, the data uploaded to the cloud processing platform is not the original data, thus ensuring data security and preventing data leakage.

[0090] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the invention can be implemented in other specific forms without departing from its spirit or essential characteristics. Therefore, the embodiments should be considered in all respects as exemplary and non-limiting, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be included within the present invention. No reference numerals in the claims should be construed as limiting the scope of the claims.

[0091] Furthermore, it should be understood that although this specification describes embodiments, not every embodiment contains only one independent technical solution. This narrative style is merely for clarity. Those skilled in the art should consider the specification as a whole, and the technical solutions in each embodiment can also be appropriately combined to form other embodiments that can be understood by those skilled in the art.

Claims

1. A method for remote equipment monitoring in a smart factory, applied to the edge computing device side, characterized in that, Includes the following steps: In response to the start of the production cycle, the basic monitoring frequency tree stored in the data storage device is queried to obtain the initial monitoring frequency of each product production equipment to be monitored. Send the initial monitoring frequency / monitoring frequency in the next dynamic adjustment cycle of the production equipment of the product to be monitored to the corresponding monitoring and sensing equipment so that it can collect the status parameters of the production equipment of the product to be monitored according to the initial monitoring frequency / monitoring frequency in the next dynamic adjustment cycle. Receive the status parameters of the production equipment of the product to be monitored, and at the end of the current dynamic adjustment cycle, calculate the abnormal risk value of the production equipment of the product to be monitored within the current dynamic adjustment cycle based on the status parameters of the production equipment of the product to be monitored. Based on the abnormal risk value of the production equipment of the product to be monitored within the current dynamic adjustment cycle, the current monitoring frequency of the production equipment of the product to be monitored is adjusted to obtain its monitoring frequency in the next dynamic adjustment cycle, and it is determined whether to issue an instruction for manual inspection, so as to instruct the inspection personnel to manually collect the status parameters of the production equipment of the product to be monitored.

2. The remote equipment monitoring method based on a smart factory according to claim 1, applied to the edge computing device side, is characterized in that, In response to the end of the production cycle, the monitoring frequency and abnormal risk value of each production equipment of the product to be monitored in each dynamic adjustment cycle are sent to the cloud processing platform so that the monitoring frequency and abnormal risk value can be stored and / or processed.

3. The remote equipment monitoring method based on a smart factory according to claim 1 or 2, applied to the edge computing device side, is characterized in that... The initial monitoring frequency is obtained through the following sub-steps: Traverse the basic monitoring frequency tree, find the branch of the monitoring frequency tree where the production equipment of the product to be monitored is located, and obtain the basic monitoring frequency of the production equipment of the product to be monitored and all its parent objects in the monitoring frequency tree branch. Multiply the basic monitoring frequency of the production equipment of the product to be monitored and all its superior objects by the corresponding category weights and round up to obtain the monitoring frequency of each level of the production equipment of the product to be monitored. The sum of the monitoring frequencies of each level of the production equipment of the product to be monitored is used as the initial monitoring frequency of the production equipment of the product to be monitored.

4. The remote equipment monitoring method based on a smart factory according to claim 1 or 2, applied to the edge computing device side, is characterized in that, The abnormal risk values ​​of the production equipment for the product to be monitored during the current dynamic adjustment period are obtained according to the following steps: The status parameters of the production equipment of the product to be monitored at each moment in the current dynamic adjustment cycle are compared with the corresponding standard status parameters stored in the data storage device to determine the standard deviation of each status parameter of the production equipment of the product to be monitored in the current dynamic adjustment cycle. Based on the recorded equipment type, failure frequency, total operating time, and failure type of the production equipment for the product to be monitored, the current risk weight of the production equipment for the product to be monitored is calculated. The abnormal risk value of the production equipment of the product to be monitored in the current dynamic adjustment period is obtained by multiplying the standard deviation of each state parameter and the influence weight of each state parameter in the current dynamic adjustment period, and the current risk weight of the production equipment of the product to be monitored.

5. The remote equipment monitoring method based on a smart factory according to claim 4, applied to the edge computing device side, is characterized in that... The status parameters of the production equipment of the product to be monitored at each moment in the current dynamic adjustment cycle are collected by the monitoring and sensing equipment alone, or by the monitoring and sensing equipment and the inspection personnel together.

6. The remote equipment monitoring method based on a smart factory according to claim 5, applied to the edge computing device side, is characterized in that... If the status parameters are collected separately by the monitoring and sensing device, then the status parameters of the production equipment of the product to be monitored at each moment in the current dynamic adjustment cycle are compared with the standard status parameters of the production equipment of the product to be monitored to obtain the first standard deviation of each status parameter of the production equipment of the product to be monitored in the current dynamic adjustment cycle.

7. The remote equipment monitoring method based on a smart factory according to claim 5, applied to the edge computing device side, is characterized in that... If the status parameters are collected jointly by the monitoring and sensing equipment and the inspection personnel, the status parameters of the production equipment of the product to be monitored at each moment in the current dynamic adjustment cycle collected by the monitoring and sensing equipment are compared with the standard status parameters of the production equipment of the product to be monitored, and the first comparison result is multiplied by the weight of the corresponding status parameter. The manually collected state parameters of the production equipment of the product to be monitored within the current dynamic adjustment cycle are compared with the standard state parameters of the production equipment of the product to be monitored. The second standard deviation of each state parameter of the production equipment of the product to be monitored within the current dynamic adjustment cycle is obtained by multiplying the second comparison result with the above.

8. The remote equipment monitoring method based on a smart factory according to claim 7, applied to the edge computing device side, is characterized in that, Calculate the time interval between the moment when manual sampling is performed on the production equipment of the product to be monitored and the moment when sampling is performed by the monitoring and sensing equipment within the current dynamic adjustment cycle, and use the reciprocal of the time interval as the weight of the state parameters collected by the monitoring and sensing equipment at the corresponding moment.

9. The remote equipment monitoring method based on a smart factory according to claim 7, applied to the edge computing device side, is characterized in that, The abnormal risk value YF of the i-th monitored product production equipment within the current dynamic adjustment period. idq The expression is: Where, μ dqi ρ represents the current risk weight of the production equipment for the i-th product to be monitored; iy σ represents the influence weight of the y-th state parameter of the i-th production equipment for the product to be monitored; iy Let σ' be the first standard deviation of the y-th state parameter of the i-th production equipment for the monitored product within the current dynamic adjustment cycle; iy Let Y be the second standard deviation of the y-th state parameter of the i-th production equipment to be monitored within the current dynamic adjustment cycle; Y is the number of state parameter types. XOR.

10. A remote equipment monitoring system based on a smart factory, characterized in that, include: Product manufacturing equipment, monitoring and sensing equipment, edge computing equipment, data storage equipment, and cloud processing platforms; Product manufacturing equipment, monitoring and sensing equipment, and edge computing equipment are all deployed in each workshop of the smart factory, data storage equipment is deployed in the control center of the smart factory, and cloud processing platform is deployed outside the smart factory; The edge computing device performs the remote equipment monitoring method based on a smart factory as described in any one of claims 1 to 9.

Images