Industrial production intelligent inspection method, system, electronic equipment and medium

Abstract

The present application relates to an intelligent inspection method, system, electronic device and medium for industrial production, which is applied to the field of industrial inspection technology. The method includes: obtaining equipment monitoring data and inspector information; performing fault prediction based on a fault prediction model and equipment monitoring data to obtain the equipment fault type and fault occurrence rate; correcting the fault occurrence rate of each device based on the fault occurrence rate and the association of the first device; dividing the equipment into the first device, the second device and the third device based on the fault occurrence rate; determining the inspection time of the second device based on the inspection cycle and historical inspection records; determining the inspection time of the third device based on the inspection cycle, historical inspection records and the first number; determining the inspection level of each device based on the pending tasks corresponding to the device, the fault type and the association of the second device; and determining the inspection plan based on the inspector information, the inspection level and the inspection time. The present application has the effect of improving the inspection efficiency.

Description

Technical Field

[0001] The present application relates to the technical field of industrial inspection, and in particular to an industrial production intelligent inspection method, system, electronic equipment and medium. Background Art

[0002] In large factories, there are a large number of equipment. If an abnormality or failure occurs in the equipment, it will not only delay production but may also cause safety accidents. Therefore, it is very important to monitor and inspect the equipment.

[0003] Currently, inspections are usually carried out periodically according to the inspection cycle. This inspection method may not be able to detect and handle equipment failures in a timely manner, and due to limited inspection personnel, missed inspections often occur, and the inspections are not targeted, resulting in low inspection efficiency. Summary of the invention

[0004] In order to improve inspection efficiency, the present application provides an industrial production intelligent inspection method, system, electronic equipment and medium.

[0005] In the first aspect, the present application provides an industrial production intelligent inspection method, which adopts the following technical solution:

[0006] An industrial production intelligent inspection method, comprising:

[0007] Obtain equipment monitoring data and inspector information;

[0008] Performing fault prediction based on the fault prediction model and the equipment monitoring data to obtain fault information, wherein the fault information includes equipment, fault type, and fault occurrence rate;

[0009] amending the failure occurrence rate of each device based on the failure occurrence rate and the first device association;

[0010] Based on the fault occurrence rate, the devices are divided into first devices, second devices and third devices, the first devices are devices whose fault occurrence rate is greater than a first preset occurrence rate, the second devices are devices whose fault occurrence rate is less than or equal to the first preset occurrence rate and greater than a second preset occurrence rate, the third devices are devices whose fault occurrence rate is less than or equal to the second preset occurrence rate, the first preset occurrence rate is greater than the second preset occurrence rate, and the inspection time of the first devices is the current time;

[0011] Determine the inspection time of the second device based on the inspection cycle and historical inspection records;

[0012] Determine the inspection time of the third device based on the inspection cycle, the historical inspection record and the first number, wherein the first number is used to represent the number of times that the device has not been inspected at the inspection time corresponding to the inspection cycle after the last inspection;

[0013] Determine the inspection level of each device based on the pending tasks, fault type, and second device association corresponding to the device;

[0014] An inspection plan is determined based on the inspector information, the inspection level, and the inspection time.

[0015] By adopting the above technical solution, fault prediction is performed through the fault prediction model and equipment monitoring data, and the failure rate and failure type of the equipment are obtained. The equipment is divided into three categories according to the failure rate, and the inspection time of each type of equipment is determined according to different strategies, which improves the reliability of the inspection time. The inspection level of each device is determined according to the pending tasks, fault type and second device association corresponding to the equipment, and the inspection plan is determined according to the inspector information, inspection level and inspection time, which improves the reliability of the inspection plan and thus improves the inspection efficiency.

[0016] Optionally, before correcting the failure occurrence rate of each device based on the failure occurrence rate and the association with the first device, the method further includes:

[0017] Obtain historical task information and historical fault records;

[0018] Determine a set of production equipment corresponding to each production task based on the historical task information;

[0019] Combining the devices in each of the production equipment sets by an exhaustive method to obtain a plurality of production equipment combinations, each of which includes two devices;

[0020] Analyze the historical fault records to obtain the first fault number of each device and the second fault number of the devices in each production equipment combination that fail simultaneously within a time period;

[0021] Calculate the fault correlation between two devices in each of the production equipment combinations based on a correlation formula, the first fault number, and the second fault number, wherein the correlation formula includes: fault correlation=second fault number / sum(first fault number);

[0022] Determine the production equipment combination whose fault correlation degree is greater than a preset correlation degree as an associated equipment combination, and two equipments in the associated equipment combination have a first equipment correlation;

[0023] Counting the number of identical combinations of production equipment to obtain multiple first numbers;

[0024] The production equipment combination whose first quantity is greater than a preset quantity is determined as a second associated equipment combination, and two equipments in the second associated equipment combination have a second equipment association.

[0025] By adopting the above technical solution, the devices in each production equipment set are combined by exhaustive method to obtain multiple production equipment combinations. The fault correlation between the two devices in each production equipment combination is obtained by analyzing the historical fault records and calculating through the correlation formula. The first equipment association is determined according to the fault correlation, so that the fault occurrence rate can be corrected more accurately according to the first equipment association. The second equipment association is obtained by counting the number of the same production equipment combinations, so that the inspection level of the equipment can be determined more accurately according to the second equipment association.

[0026] Optionally, the correcting the failure occurrence rate of each device based on the failure occurrence rate and the first device association includes:

[0027] Determine a device that is currently correcting the fault occurrence rate as a correction device, and determine a device that is associated with the correction device as an associated device;

[0028] Correcting the failure occurrence rate of the correction device based on the correction formula, the failure occurrence rate and the failure correlation degree;

[0029] The correction formula includes: the failure rate of the corrected device = the original failure rate of the corrected device × {1 + sum[fault correlation × (failure rate of the associated device - reference failure rate)]}, wherein the reference failure rate is the average of the failure rates of all devices.

[0030] Optionally, determining the inspection level of each device based on the pending tasks corresponding to the device, the fault type, and the second device association includes:

[0031] Get the task level of each pending task;

[0032] Calculating a task impact coefficient based on the weights corresponding to the task levels and the number of pending tasks for each task level;

[0033] Counting the number of associated devices associated with each device that has the second device;

[0034] Obtaining a device impact coefficient based on the number of associated devices;

[0035] Calculate a grade coefficient based on the task impact coefficient, the equipment impact coefficient, and a coefficient weight;

[0036] Obtaining a device level for each device based on the level coefficient;

[0037] Determine a fault level of each device based on the fault occurrence rate and the fault type;

[0038] An inspection level of each device is determined based on the device level and the fault level.

[0039] By adopting the above technical solution, when determining the inspection level of the equipment, the equipment level is first determined based on the task level of the equipment's pending tasks and the number of associated equipment, and then the fault level is determined based on the fault occurrence rate and fault type, thereby determining the inspection level of each device and improving the reliability of the inspection level.

[0040] Optionally, determining the inspection time of the third device based on the inspection cycle, the historical inspection record, and the first number includes:

[0041] Obtaining the last inspection time of the third device from the historical inspection record;

[0042] Calculate the next inspection time based on the time calculation formula, the inspection cycle, the last inspection time and the first number, the time calculation formula includes: next inspection time = last inspection time + (first number + 1) × inspection cycle;

[0043] If the current time is not less than the next inspection time, determining whether the first number is less than a preset number;

[0044] If the first number is greater than or equal to the preset number, the first number is initialized to 0, and the current time is determined as the inspection time of the third device;

[0045] If the first number is less than the preset number, the first number is increased by one, and the inspection time of the third device is calculated based on the new first number.

[0046] By adopting the above technical solution, when determining the inspection time of the third device, not only the inspection cycle but also the first number is taken into account, thereby reducing the inspection times of the third device without affecting the inspection effect of the third device and reducing the waste of inspection resources.

[0047] Optionally, the determining the inspection plan based on the inspector information, the inspection level, and the inspection time includes:

[0048] Divide the equipment with the same inspection time into an inspection group;

[0049] Determine the inspector corresponding to each inspection combination based on the inspection time and the inspector information;

[0050] Arrange the devices in each inspection combination from high to low according to the inspection level to obtain an inspection order;

[0051] An inspection plan is determined based on the inspectors, the inspection time, and the inspection sequence.

[0052] By adopting the above technical solution, inspectors inspect the equipment from high to low according to the inspection level, so that higher-level equipment can be repaired in time, thereby improving the efficiency of equipment maintenance.

[0053] Optionally, before performing fault prediction based on the fault prediction model and the equipment monitoring data, the method further includes:

[0054] Acquire historical fault information, wherein the historical fault information includes historical abnormal data and fault type;

[0055] Dividing the historical fault information based on the fault type to obtain a plurality of fault information combinations, wherein the historical fault information in each of the fault information combinations corresponds to the same fault type;

[0056] The preset algorithm is trained based on a plurality of combinations of the fault information to obtain a fault prediction model.

[0057] By adopting the above technical solution, historical fault information is divided according to fault type, and the preset algorithm is trained according to the combination of the divided fault information, rather than directly using historical fault information for model training, which improves the accuracy of the fault prediction model and thus improves the accuracy of the fault information.

[0058] In the second aspect, the present application provides an industrial production intelligent inspection system, which adopts the following technical solutions:

[0059] An industrial production intelligent inspection system, comprising:

[0060] Monitoring data acquisition module, used to obtain equipment monitoring data and inspector information;

[0061] An equipment fault prediction module, used to perform fault prediction based on a fault prediction model and the equipment monitoring data to obtain fault information, wherein the fault information includes equipment, fault type, and fault occurrence rate;

[0062] A fault occurrence correction module, used to correct the fault occurrence rate of each device based on the fault occurrence rate and the first device association;

[0063] a faulty equipment classification module, configured to classify equipment into first equipment, second equipment, and third equipment based on the fault occurrence rate, wherein the first equipment is equipment whose fault occurrence rate is greater than a first preset occurrence rate, the second equipment is equipment whose fault occurrence rate is less than or equal to the first preset occurrence rate and greater than a second preset occurrence rate, the third equipment is equipment whose fault occurrence rate is less than or equal to the second preset occurrence rate, the first preset occurrence rate is greater than the second preset occurrence rate, and the inspection time of the first equipment is the current time;

[0064] A first time determination module, used to determine the inspection time of the second device based on the inspection cycle and historical inspection records;

[0065] A second time determination module is used to determine the inspection time of the third device based on the inspection cycle, the historical inspection record and the first number, wherein the first number is used to represent the number of times that the device has not been inspected at the inspection time corresponding to the inspection cycle after the last inspection;

[0066] An inspection level determination module, used to determine the inspection level of each device based on the pending tasks, fault type and second device association corresponding to the device;

[0067] An inspection plan determination module is used to determine an inspection plan based on the inspector information, the inspection level and the inspection time.

[0068] By adopting the above technical solution, fault prediction is performed through the fault prediction model and equipment monitoring data, and the failure rate and failure type of the equipment are obtained. The equipment is divided into three categories according to the failure rate, and the inspection time of each type of equipment is determined according to different strategies, which improves the reliability of the inspection time. The inspection level of each device is determined according to the pending tasks, fault type and second device association corresponding to the equipment, and the inspection plan is determined according to the inspector information, inspection level and inspection time, which improves the reliability of the inspection plan and thus improves the inspection efficiency.

[0069] In a third aspect, the present application provides an electronic device, which adopts the following technical solution:

[0070] An electronic device comprises a processor, wherein the processor is coupled to a memory;

[0071] The memory stores a computer program that can be loaded by the processor and execute the industrial production intelligent inspection method described in any one of the first aspects.

[0072] In a fourth aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution:

[0073] A computer-readable storage medium stores a computer program that can be loaded by a processor and execute the industrial production intelligent inspection method described in any one of the first aspects. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] Figure 1 It is a flow chart of an industrial production intelligent inspection method provided in an embodiment of the present application.

[0075] Figure 2 It is a structural block diagram of an industrial production intelligent inspection system provided in an embodiment of the present application.

[0076] Figure 3 It is a structural block diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0077] The present application is further described in detail below in conjunction with the accompanying drawings.

[0078] The embodiment of the present application provides an industrial production intelligent inspection method, which can be executed by an electronic device, which can be a server or a terminal device, wherein the server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. The terminal device can be a smart phone, a tablet computer, a desktop computer, etc., but is not limited thereto.

[0079] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0080] In addition, the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article, unless otherwise specified, generally means that the associated objects before and after are in an "or" relationship.

[0081] like Figure 1 As shown, an industrial production intelligent inspection method, the main process of the method is described as follows (steps S101 to S108):

[0082] Step S101: Obtain equipment monitoring data and inspector information.

[0083] In a factory, various monitoring sensors and various instrumentation devices are installed at various equipment. Equipment monitoring data such as current, voltage, and temperature are obtained from the monitoring sensors and instrumentation devices in real time. The inspector information includes all the inspector information at various locations in a factory, and all the inspector information is obtained from the database.

[0084] Step S102: perform fault prediction based on the fault prediction model and equipment monitoring data to obtain fault information, where the fault information includes equipment, fault type, and fault occurrence rate.

[0085] By inputting the equipment monitoring data into the fault prediction model for fault prediction, information about the upcoming faults can be obtained.

[0086] Specifically, before performing fault prediction based on the fault prediction model and equipment monitoring data, the method also includes: obtaining historical fault information, the historical fault information including historical abnormal data and fault types; dividing the historical fault information based on the fault type to obtain multiple fault information combinations, the historical fault information in each fault information combination corresponds to the same fault type; training a preset algorithm based on multiple fault information combinations to obtain a fault prediction model.

[0087] In this embodiment, historical fault information is obtained from a database, and the historical fault information is divided according to the fault type to obtain multiple fault information combinations, where the number of fault information combinations is equal to the number of fault types. Each fault information combination is labeled according to the fault type, and a preset algorithm is trained with the labeled fault information combinations to obtain a fault prediction model. Fault prediction can be performed using the fault prediction model and equipment monitoring data, wherein the preset algorithm can be a deep learning algorithm or a time series analysis algorithm, which is pre-set by the staff according to actual conditions and is not specifically limited here.

[0088] Step S103: Correct the failure occurrence rate of each device based on the failure occurrence rate and the first device association.

[0089] The failure rate predicted by the fault prediction model is only the failure rate of the device itself. During the operation of the device, many failures will be affected by the failures of other devices. Therefore, the failure rate of the device needs to be corrected to improve the accuracy of the failure rate. Among them, the first device association indicates that the failures of two devices will affect each other.

[0090] Specifically, before correcting the failure rate of each device based on the failure rate and the first device association, the method also includes: obtaining historical task information and historical failure records; determining the production equipment set corresponding to each production task based on the historical task information; combining the devices in each production equipment set by exhaustive method to obtain multiple production equipment combinations, each production equipment combination includes two devices; analyzing the historical failure records to obtain the first failure number of each device and the second failure number of devices in each production equipment combination failing simultaneously within a time period; calculating the failure correlation between the two devices in each production equipment combination based on the correlation formula, the first failure number and the second failure number, the correlation formula including: failure correlation = second failure number / sum (first failure number); determining a production equipment combination whose failure correlation is greater than a preset correlation as an associated equipment combination, and the two devices in the associated equipment combination have a first equipment association; counting the number of identical production equipment combinations to obtain multiple first numbers; determining a production equipment combination whose first number is greater than a preset number as a second associated equipment combination, and the two devices in the second associated equipment combination have a second equipment association.

[0091] In this embodiment, historical task information and historical fault records are obtained from a database, where the historical task information includes production tasks and equipment required to complete the production tasks. The production equipment set corresponding to each production task is found from the historical task information. For each production equipment set, the equipment in the set is combined by exhaustive method to obtain multiple production equipment combinations. It is worth noting that the number of equipment in each production equipment combination is 2. For example, if the production equipment set is {equipment A, equipment B, equipment C}, then the production equipment combinations corresponding to the production equipment set include: production equipment combination 1 (equipment A, equipment B), production equipment combination 2 (equipment A, equipment C), and production equipment combination 3 (equipment B, equipment C).

[0092] The historical fault records include fault time and equipment. The historical fault records are analyzed to obtain the number of failures of each equipment, i.e., the first number of failures, and the second number of failures when two equipment in each production equipment combination fails at the same time within a time period (if the time interval between the failures of two equipment in the production equipment combination is less than a preset time length, it is equivalent to the two equipment in the production equipment combination failing at the same time within a time period). The first number of failures and the second number of failures are calculated using the correlation formula (fault correlation = second number of failures / sum (first number of failures)) to obtain the fault correlation between the two equipment in each production equipment combination. The production equipment combination with a fault correlation greater than a preset correlation is determined as an associated equipment combination, and there is a first equipment correlation between the two equipment in each associated equipment combination.

[0093] The number of completely identical production equipment combinations is counted to obtain multiple first quantities, each of which corresponds to a production equipment combination. For example, there are 6 production equipment combinations, namely, production equipment combination 1 (equipment A, equipment B), production equipment combination 2 (equipment A, equipment C), production equipment combination 3 (equipment A, equipment B), production equipment combination 4 (equipment B, equipment C), production equipment combination 5 (equipment A, equipment B), and production equipment combination 6 (equipment A, equipment C). It can be seen that production equipment combination 1, production equipment combination 3 and production equipment combination 5 are completely identical, and production equipment combination 2 is completely identical to production equipment combination 4, that is, there are three first quantities, namely, 1, 2, and 3. The first quantity 1 corresponds to the production equipment combination (equipment B, equipment C), the first quantity 2 corresponds to the production equipment combination (equipment A, equipment C), and the first quantity 3 corresponds to the production equipment combination (equipment A, equipment B). The production equipment combination whose first quantity is greater than the preset quantity is determined as a second associated equipment combination. Two devices in each second associated equipment combination have a second equipment association, and the second equipment association indicates that the two devices are often used simultaneously in a task.

[0094] Optionally, the failure incidence rate of each device is corrected based on the failure incidence rate and the first device association, including: determining the device whose failure incidence rate is currently being corrected as the correction device, and determining the device that has a first device association with the correction device as the associated device; correcting the failure incidence rate of the correction device based on the correction formula, the failure incidence rate and the fault correlation degree; the correction formula includes: failure incidence rate of the correction device = original failure incidence rate of the correction device × {1 + sum[fault correlation degree × (failure incidence rate of associated devices - benchmark failure incidence rate)]}, wherein the benchmark failure incidence rate is the average of the failure incidence rates of all devices.

[0095] In this embodiment, when the failure rate of a device is corrected, the device whose failure rate is currently being corrected is determined as the correction device, and the device that is associated with the correction device as a first device is determined as the associated device. The failure rate and the failure correlation are calculated using a correction formula to obtain the corrected failure rate of the correction device.

[0096] Step S104: divide the devices into first devices, second devices, and third devices based on the failure occurrence rate.

[0097] Among them, the first device is a device with a failure rate greater than a first preset rate, the second device is a device with a failure rate less than or equal to the first preset rate and greater than the second preset rate, and the third device is a device with a failure rate less than or equal to the second preset rate, and the first preset rate is greater than the second preset rate.

[0098] The failure rate of the first device is relatively high, so the inspection time of the first device is the current time.

[0099] Step S105: Determine the inspection time of the second device based on the inspection cycle and historical inspection records.

[0100] The failure rate of the second device is not high, so it can be inspected according to the time corresponding to the inspection cycle. The historical inspection records can be obtained from the database, and the last inspection time of the second device can be found from the historical inspection records. The inspection time of the second device = last inspection time + inspection cycle.

[0101] Step S106: Determine the inspection time of the third device based on the inspection cycle, historical inspection records, and the first number.

[0102] The first number is used to represent the number of times that the equipment has not been inspected at the inspection time corresponding to the inspection cycle since the last inspection.

[0103] If the failure rate of the equipment is low, the number of inspections can be reduced, thereby reducing the waste of inspection resources. However, it is necessary to record the number of times the inspection is not performed according to the inspection cycle, that is, the number of times the inspection is not performed at the inspection time corresponding to the inspection cycle.

[0104] Specifically, the inspection time of the third device is determined based on the inspection cycle, historical inspection records and the first number, including: obtaining the last inspection time of the third device from the historical inspection records; calculating the next inspection time based on the time calculation formula, the inspection cycle, the last inspection time and the first number, the time calculation formula including: next inspection time = last inspection time + (first number + 1) × inspection cycle; if the current time is not less than the next inspection time, determine whether the first number is less than the preset number; if the first number is greater than or equal to the preset number, initialize the first number to 0, and determine the current time as the inspection time of the third device; if the first number is less than the preset number, add one to the first number, and calculate the inspection time of the third device based on the new first number.

[0105] In this embodiment, historical inspection records are obtained from the database, the last inspection time of the third device is found from the historical inspection records, and the next inspection time is calculated according to the time calculation formula, the next inspection time = last inspection time + (first number + 1) × inspection cycle, if the current time is less than the next inspection time, that is, the time for inspection according to the inspection cycle has not yet arrived, the next inspection time is determined as the inspection time of the third device, if the current time is not less than the next inspection time, that is, the time for inspection according to the inspection cycle has arrived, it is determined whether the first number is less than the preset number; if the first number is greater than or equal to the preset number, That is, it has been a long time since the last inspection, and an inspection is needed this time. The first number is initialized to 0, and the current time is determined as the inspection time of the third device; if the first number is less than the preset number, no inspection is performed this time, then the first number is increased by 1, and the next inspection time = last inspection time + (new first number + 1) × inspection cycle, and the next inspection time is determined as the inspection time of the third device. It is worth noting that if the inspection time of the third device is the next inspection time, when the next inspection time arrives, whether to inspect needs to be re-determined according to the above method. After each inspection, the first number is initialized to 0.

[0106] Step S107: Determine the inspection level of each device based on the pending tasks, fault type, and second device association corresponding to the device.

[0107] Specifically, the inspection level of each device is determined based on the pending tasks corresponding to the device, the fault type and the second device association, including: obtaining the task level of each pending task; calculating the task impact coefficient based on the weight corresponding to the task level and the number of pending tasks of each task level; counting the number of associated devices associated with each device that has a second device association; obtaining the device impact coefficient based on the number of associated devices; calculating the grade coefficient based on the task impact coefficient, the device impact coefficient and the coefficient weight; obtaining the device level of each device based on the grade coefficient; determining the fault level of each device based on the fault occurrence rate and the fault type; and determining the inspection level of each device based on the device level and the fault level.

[0108] In this embodiment, the task level of all pending tasks of each device and the weight corresponding to each task level are obtained from the database, and the task impact coefficient = the weight corresponding to the task level * the number of pending tasks corresponding to the task level; the number of associated devices associated with each device is counted, and the corresponding relationship between the number of associated devices and the device impact coefficient is stored in the database, and the device impact coefficient is obtained from the database according to the number of associated devices, and the first coefficient weight corresponding to the task impact coefficient and the second coefficient weight corresponding to the device impact coefficient are obtained from the database, the level coefficient = the task impact coefficient * the first coefficient weight + the device impact coefficient * the second coefficient weight, and the corresponding relationship between the level coefficient and the device level is obtained from the database, and the device level of each device is determined according to the corresponding relationship between the level coefficient and the device level; the corresponding relationship between the fault occurrence rate, the fault type and the fault level is obtained from the database, and the fault level of each device is searched from the corresponding relationship according to the fault occurrence rate and the fault type, and the corresponding relationship between the equipment level, the fault level and the inspection level is obtained from the database, and the inspection level of each device is searched from the corresponding relationship according to the equipment level and the fault level.

[0109] Step S108: Determine the inspection plan based on the inspector information, inspection level and inspection time.

[0110] Specifically, the inspection plan is determined based on the inspector information, inspection level and inspection time, including: dividing the equipment corresponding to the same inspection time into an inspection combination; determining the inspector corresponding to each inspection combination based on the inspection time and inspector information; sorting the equipment in each inspection combination from high to low according to the inspection level to obtain the inspection order; determining the inspection plan based on the inspector, inspection time and inspection order.

[0111] In this embodiment, the equipment corresponding to the same inspection time is divided into an inspection combination, that is, each inspection combination corresponds to an inspection time, the inspector for each inspection time is found from the inspector information, the inspector is matched with the inspection combination according to the inspection time, and the inspector corresponding to each inspection combination is obtained. The equipment in each inspection combination is sorted from high to low according to the inspection level to obtain the inspection order. The inspection plan is that the inspector inspects the equipment according to the inspection order at the inspection time.

[0112] Figure 2 A structural block diagram of an industrial production intelligent inspection system 200 provided in an embodiment of the present application.

[0113] like Figure 2 As shown, the industrial production intelligent inspection system 200 mainly includes:

[0114] Monitoring data acquisition module 201, used to obtain equipment monitoring data and inspector information;

[0115] The equipment failure prediction module 202 is used to perform failure prediction based on the failure prediction model and equipment monitoring data to obtain failure information, where the failure information includes equipment, failure type, and failure occurrence rate;

[0116] A fault occurrence correction module 203, configured to correct the fault occurrence rate of each device based on the fault occurrence rate and the first device association;

[0117] The faulty equipment classification module 204 is used to classify the equipment into first equipment, second equipment and third equipment based on the fault occurrence rate, wherein the first equipment is equipment with a fault occurrence rate greater than a first preset occurrence rate, the second equipment is equipment with a fault occurrence rate less than or equal to the first preset occurrence rate and greater than the second preset occurrence rate, the third equipment is equipment with a fault occurrence rate less than or equal to the second preset occurrence rate, the first preset occurrence rate is greater than the second preset occurrence rate, and the inspection time of the first equipment is the current time;

[0118] A first time determination module 205, configured to determine the inspection time of the second device based on the inspection cycle and historical inspection records;

[0119] A second time determination module 206 is used to determine the inspection time of the third device based on the inspection cycle, the historical inspection records and the first number, where the first number is used to represent the number of times that the device has not been inspected at the inspection time corresponding to the inspection cycle after the last inspection;

[0120] An inspection level determination module 207, configured to determine the inspection level of each device based on the pending tasks, the fault type, and the second device association corresponding to the device;

[0121] The inspection plan determination module 208 is used to determine the inspection plan based on the inspector information, the inspection level and the inspection time.

[0122] As an optional implementation of this embodiment, the equipment fault prediction module 202 is also specifically used to, before performing fault prediction based on the fault prediction model and equipment monitoring data, also include: obtaining historical fault information, the historical fault information including historical abnormal data and fault type; dividing the historical fault information based on the fault type to obtain multiple fault information combinations, the historical fault information in each fault information combination corresponds to the same fault type; training a preset algorithm based on multiple fault information combinations to obtain a fault prediction model.

[0123] As an optional implementation of this embodiment, the fault occurrence correction module 203 is also specifically used to correct the fault occurrence rate of each device based on the fault occurrence rate and the first device association, and also includes: obtaining historical task information and historical fault records; determining the production equipment set corresponding to each production task based on the historical task information; combining the devices in each production equipment set by exhaustive method to obtain multiple production equipment combinations, each production equipment combination includes two devices; analyzing the historical fault records to obtain the first fault number of each device and the second fault number of the devices in each production equipment combination simultaneously failing within a time period; calculating the fault correlation between the two devices in each production equipment combination based on the correlation formula, the first fault number and the second fault number, the correlation formula includes: fault correlation = second fault number / sum (first fault number); determining a production equipment combination with a fault correlation greater than a preset correlation as an associated equipment combination, and the two devices in the associated equipment combination have a first equipment association; counting the number of identical production equipment combinations to obtain multiple first numbers; determining a production equipment combination with a first number greater than a preset number as a second associated equipment combination, and the two devices in the second associated equipment combination have a second equipment association.

[0124] As an optional implementation of this embodiment, the fault occurrence correction module 203 is also specifically used to correct the fault occurrence rate of each device based on the fault occurrence rate and the first device association, including: determining the device whose fault occurrence rate is currently being corrected as the correction device, and determining the device that has a first device association with the correction device as the associated device; correcting the fault occurrence rate of the corrected device based on the correction formula, the fault occurrence rate and the fault correlation degree; the correction formula includes: the fault occurrence rate of the corrected device = the original fault occurrence rate of the corrected device × {1 + sum[fault correlation degree × (failure occurrence rate of associated devices - baseline fault occurrence rate)]}, wherein the baseline fault occurrence rate is the average of the fault occurrence rates of all devices.

[0125] As an optional implementation of this embodiment, the second time determination module 206 is also specifically used to determine the inspection time of the third device based on the inspection cycle, historical inspection records and the first number, including: obtaining the last inspection time of the third device from the historical inspection records; calculating the next inspection time based on the time calculation formula, the inspection cycle, the last inspection time and the first number, the time calculation formula includes: next inspection time = last inspection time + (first number + 1) × inspection cycle; if the current time is not less than the next inspection time, determine whether the first number is less than the preset number; if the first number is greater than or equal to the preset number, initialize the first number to 0, and determine the current time as the inspection time of the third device; if the first number is less than the preset number, add one to the first number, and calculate the inspection time of the third device based on the new first number.

[0126] As an optional implementation of this embodiment, the inspection level determination module 207 is also specifically used to determine the inspection level of each device based on the pending tasks corresponding to the device, the fault type and the second device association, including: obtaining the task level of each pending task; calculating the task impact coefficient based on the weight corresponding to the task level and the number of pending tasks of each task level; counting the number of associated devices associated with each device that has a second device association; obtaining the device impact coefficient based on the number of associated devices; calculating the grade coefficient based on the task impact coefficient, the device impact coefficient and the coefficient weight; obtaining the device level of each device based on the grade coefficient; determining the fault level of each device based on the fault occurrence rate and the fault type; determining the inspection level of each device based on the equipment level and the fault level.

[0127] As an optional implementation of this embodiment, the inspection plan determination module 208 is also specifically used to determine the inspection plan based on the inspector information, inspection level and inspection time, including: dividing the equipment corresponding to the same inspection time into an inspection combination; determining the inspector corresponding to each inspection combination based on the inspection time and inspector information; sorting the equipment in each inspection combination from high to low according to the inspection level to obtain the inspection order; determining the inspection plan based on the inspector, inspection time and inspection order.

[0128] In one example, the module in any of the above devices can be one or more integrated circuits configured to implement the above methods, such as: one or more application specific integrated circuits (ASICs), or, one or more digital signal processors (DSPs), or, one or more field programmable gate arrays (FPGAs), or a combination of at least two of these integrated circuit forms.

[0129] For another example, when the modules in the device can be implemented in the form of a processing element scheduling program, the processing element can be a general-purpose processor, such as a central processing unit (CPU) or other processor that can call a program. For another example, these modules can be integrated together and implemented in the form of a system-on-a-chip (SOC).

[0130] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices and modules can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0131] Figure 3 A structural block diagram of an electronic device 300 provided in an embodiment of the present application.

[0132] like Figure 3 As shown, the electronic device 300 includes a processor 301 and a memory 302 , and may further include an information input / information output (I / O) interface 303 , one or more of a communication component 304 , and a communication bus 305 .

[0133] The processor 301 is used to control the overall operation of the electronic device 300 to complete all or part of the steps of the above-mentioned industrial production intelligent inspection method; the memory 302 is used to store various types of data to support the operation of the electronic device 300, and these data may include, for example, instructions for any application or method used to operate on the electronic device 300, and data related to the application. The memory 302 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, EEPROM), erasable programmable read-only memory (Erasable Programmable Read-Only Memory, EPROM), programmable read-only memory (Programmable Read-Only Memory, PROM), read-only memory (Read-Only Memory, ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0134] The I / O interface 303 provides an interface between the processor 301 and other interface modules, and the above-mentioned other interface modules can be keyboards, mice, buttons, etc. These buttons can be virtual buttons or physical buttons. The communication component 304 is used for wired or wireless communication between the electronic device 300 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G or 4G, or a combination of one or more of them, so the corresponding communication component 304 can include: Wi-Fi components, Bluetooth components, NFC components.

[0135] The electronic device 300 can be implemented by one or more application specific integrated circuits (ASIC), digital signal processors (DSP), digital signal processing devices (DSPD), programmable logic devices (PLD), field programmable gate arrays (FPGA), controllers, microcontrollers, microprocessors or other electronic components to execute the industrial production intelligent inspection method given in the above embodiment.

[0136] The communication bus 305 may include a path to transmit information between the above components. The communication bus 305 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. The communication bus 305 may be divided into an address bus, a data bus, a control bus, etc.

[0137] The electronic device 300 may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc., and may also be servers, etc.

[0138] The present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned industrial production intelligent inspection method are implemented.

[0139] The computer-readable storage medium may include: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0140] 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 expressly listed, or also includes elements inherent to such process, method, article, or apparatus.

[0141] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of application involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the aforementioned application concept. For example, the above features are replaced with (but not limited to) technical features with similar functions applied in the present application.

Claims

1. An industrial production intelligent inspection method, characterized in that: include: Obtain equipment monitoring data and inspector information; Performing fault prediction based on the fault prediction model and the equipment monitoring data to obtain fault information, wherein the fault information includes equipment, fault type, and fault occurrence rate; correcting the failure occurrence rate of each device based on the failure occurrence rate and a first device association, wherein the first device association indicates that failure occurrences of two devices may affect each other; Based on the fault occurrence rate, the devices are divided into first devices, second devices and third devices, the first devices are devices whose fault occurrence rate is greater than a first preset occurrence rate, the second devices are devices whose fault occurrence rate is less than or equal to the first preset occurrence rate and greater than a second preset occurrence rate, the third devices are devices whose fault occurrence rate is less than or equal to the second preset occurrence rate, the first preset occurrence rate is greater than the second preset occurrence rate, and the inspection time of the first devices is the current time; Determine the inspection time of the second device based on the inspection cycle and historical inspection records; Determine the inspection time of the third device based on the inspection cycle, the historical inspection record and the first number, wherein the first number is used to represent the number of inspection cycles during which no inspection is performed after the last inspection of the device; Determine the inspection level of each device based on the pending tasks corresponding to the device, the fault type, and the second device association, wherein the second device association indicates that the first number corresponding to the two devices is greater than a preset number, and the first number is the number of times the two devices are used simultaneously in the task; Determine an inspection plan based on the inspector information, the inspection level, and the inspection time; Before correcting the failure occurrence rate of each device based on the failure occurrence rate and the first device association, the method further includes: Obtain historical task information and historical fault records; Determine a set of production equipment corresponding to each production task based on the historical task information; Combining the devices in each of the production equipment sets by an exhaustive method to obtain a plurality of production equipment combinations, each of which includes two devices; Analyze the historical fault records to obtain the first fault number of each device and the second fault number of the devices in each production equipment combination that fail simultaneously within a time period; Calculate the fault correlation between two devices in each of the production equipment combinations based on a correlation formula, the first fault number, and the second fault number, wherein the correlation formula includes: fault correlation=second fault number / sum(first fault number); Determine the production equipment combination whose fault correlation degree is greater than a preset correlation degree as an associated equipment combination, and two equipments in the associated equipment combination have a first equipment correlation; Counting the quantity of each combination of the production equipment to obtain a plurality of first quantities, each of the first quantities corresponding to one combination of the production equipment; Determine the production equipment combination whose first quantity is greater than a preset quantity as a second associated equipment combination, and two equipments in the second associated equipment combination have a second equipment association; The correcting the failure occurrence rate of each device based on the failure occurrence rate and the first device association includes: Determine a device that is currently correcting the fault occurrence rate as a correction device, and determine a device that is associated with the correction device as an associated device; Correcting the failure occurrence rate of the correction device based on the correction formula, the failure occurrence rate and the failure correlation degree; The correction formula includes: the failure rate of the corrected device = the original failure rate of the corrected device × {1 + sum [failure correlation × (failure rate of the associated device - reference failure rate)]}, wherein the reference failure rate is the average of the failure rates of all devices; The step of determining the inspection level of each device based on the pending tasks corresponding to the device, the fault type, and the second device association includes: Get the task level of each pending task; Calculating a task impact coefficient based on the weights corresponding to the task levels and the number of pending tasks for each task level; Counting the number of associated devices associated with each device that has the second device; Obtaining a device impact coefficient based on the number of associated devices; Calculate a grade coefficient based on the task impact coefficient, the equipment impact coefficient, and a coefficient weight; Obtaining a device level for each device based on the level coefficient; Determine a fault level of each device based on the fault occurrence rate and the fault type; An inspection level of each device is determined based on the device level and the fault level.

2. The method according to claim 1, characterized in that The determining the inspection time of the third device based on the inspection cycle, the historical inspection record, and the first number includes: Obtaining the last inspection time of the third device from the historical inspection record; Calculate the next inspection time based on the time calculation formula, the inspection cycle, the last inspection time and the first number, the time calculation formula includes: next inspection time = last inspection time + (first number + 1) × inspection cycle; If the current time is not less than the next inspection time, determining whether the first number is less than a preset number; If the first number is greater than or equal to the preset number, the first number is initialized to 0, and the current time is determined as the inspection time of the third device; If the first number is less than the preset number, the first number is increased by one, and the inspection time of the third device is calculated based on the new first number.

3. The method according to claim 1, characterized in that The determining of the inspection plan based on the inspector information, the inspection level and the inspection time includes: Divide the equipment with the same inspection time into an inspection group; Determine the inspector corresponding to each inspection combination based on the inspection time and the inspector information; Arrange the devices in each inspection combination from high to low according to the inspection level to obtain an inspection order; An inspection plan is determined based on the inspectors, the inspection time, and the inspection sequence.

4. The method according to claim 1, characterized in that: Before performing fault prediction based on the fault prediction model and the equipment monitoring data, the method further includes: Acquire historical fault information, wherein the historical fault information includes historical abnormal data and fault type; Dividing the historical fault information based on the fault type to obtain a plurality of fault information combinations, wherein the historical fault information in each of the fault information combinations corresponds to the same fault type; The preset algorithm is trained based on a plurality of combinations of the fault information to obtain a fault prediction model.

5. An industrial production intelligent inspection system, characterized in that: include: Monitoring data acquisition module, used to obtain equipment monitoring data and inspector information; An equipment fault prediction module, used to perform fault prediction based on a fault prediction model and the equipment monitoring data to obtain fault information, wherein the fault information includes equipment, fault type, and fault occurrence rate; a fault occurrence correction module, configured to correct the fault occurrence rate of each device based on the fault occurrence rate and a first device association, wherein the first device association indicates that the fault occurrence of two devices may affect each other; a faulty equipment classification module, configured to classify equipment into first equipment, second equipment, and third equipment based on the fault occurrence rate, wherein the first equipment is equipment whose fault occurrence rate is greater than a first preset occurrence rate, the second equipment is equipment whose fault occurrence rate is less than or equal to the first preset occurrence rate and greater than a second preset occurrence rate, the third equipment is equipment whose fault occurrence rate is less than or equal to the second preset occurrence rate, the first preset occurrence rate is greater than the second preset occurrence rate, and the inspection time of the first equipment is the current time; A first time determination module, used to determine the inspection time of the second device based on the inspection cycle and historical inspection records; A second time determination module, used to determine the inspection time of the third device based on the inspection cycle, the historical inspection record and the first number, wherein the first number is used to represent the number of inspection cycles during which no inspection is performed after the last inspection of the device; An inspection level determination module, configured to determine an inspection level of each device based on a pending task corresponding to the device, a fault type, and a second device association, wherein the second device association indicates that a first number corresponding to two devices is greater than a preset number, and the first number is the number of times the two devices are used simultaneously in a task; An inspection plan determination module, used to determine an inspection plan based on the inspector information, the inspection level and the inspection time; The fault occurrence correction module is specifically used for, before correcting the fault occurrence rate of each device based on the fault occurrence rate and the first device association, further comprising: Obtain historical task information and historical fault records; Determine a set of production equipment corresponding to each production task based on the historical task information; Combining the devices in each of the production equipment sets by an exhaustive method to obtain a plurality of production equipment combinations, each of which includes two devices; Analyze the historical fault records to obtain the first fault number of each device and the second fault number of the devices in each production equipment combination that fail simultaneously within a time period; Calculate the fault correlation between two devices in each of the production equipment combinations based on a correlation formula, the first fault number, and the second fault number, wherein the correlation formula includes: fault correlation=second fault number / sum(first fault number); Determine the production equipment combination whose fault correlation degree is greater than a preset correlation degree as an associated equipment combination, and two equipments in the associated equipment combination have a first equipment correlation; Counting the quantity of each combination of the production equipment to obtain a plurality of first quantities, each of the first quantities corresponding to one combination of the production equipment; Determine the production equipment combination whose first quantity is greater than a preset quantity as a second associated equipment combination, and two equipments in the second associated equipment combination have a second equipment association; The fault occurrence correction module is specifically used to correct the fault occurrence rate of each device based on the fault occurrence rate and the first device association, including: Determine a device that is currently correcting the fault occurrence rate as a correction device, and determine a device that is associated with the correction device as an associated device; Correcting the failure occurrence rate of the correction device based on the correction formula, the failure occurrence rate and the failure correlation degree; The correction formula includes: the failure rate of the corrected device = the original failure rate of the corrected device × {1 + sum[failure correlation × (failure rate of the associated device - reference failure rate)]}, wherein the reference failure rate is the average of the failure rates of all devices; The inspection level determination module is specifically used to determine the inspection level of each device based on the pending tasks corresponding to the device, the fault type and the second device association, including: Get the task level of each pending task; Calculating a task impact coefficient based on the weights corresponding to the task levels and the number of pending tasks for each task level; Counting the number of associated devices associated with each device that has the second device; Obtaining a device impact coefficient based on the number of associated devices; Calculate a grade coefficient based on the task impact coefficient, the equipment impact coefficient, and a coefficient weight; Obtaining a device level for each device based on the level coefficient; Determine a fault level of each device based on the fault occurrence rate and the fault type; An inspection level of each device is determined based on the device level and the fault level.

6. An electronic device, characterized in that: comprising a processor coupled to a memory; The processor is configured to execute a computer program stored in the memory, so that the electronic device executes the method according to any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that: The method comprises a computer program or an instruction, which, when executed on a computer, causes the computer to execute the method according to any one of claims 1 to 4.

Images