A method and system for monitoring management of device working conditions

Abstract

The application relates to the technical field of monitoring management, and discloses a monitoring management method and system for equipment working conditions, which comprises the following steps: determining the authority importance value of each equipment department according to department information and a department authority model, determining the management authority of each equipment department based on the authority importance value, comparing an equipment monitoring parameter set with a standard equipment monitoring parameter set, dividing each equipment monitoring parameter in the equipment monitoring parameter set according to a comparison result, constructing an equipment monitoring space according to the equipment position of the equipment, mining the association result of an environmental data set and an equipment parameter set according to an association rule algorithm, determining the adjustment coefficient of an initial early warning score based on the association result, comparing a target early warning score with data in a historical target early warning score database, and judging whether to give an early warning according to a comparison result. The application effectively reduces the monitoring difficulty and the workload, thereby guaranteeing the monitoring efficiency.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of monitoring management, in particular to a monitoring management method and system for equipment working conditions. BACKGROUND

[0002] With the continuous improvement of factory automation and intelligence level, the monitoring management of equipment working conditions has become a key link to ensure the smooth progress of production activities. The efficient operation of equipment directly affects the efficiency of production. However, the traditional equipment working condition monitoring management mainly relies on periodic manual inspection. On the one hand, manual inspection cannot capture the dynamic changes in the equipment running process in real time. On the other hand, with the expansion of the factory scale, the environmental conditions in which the equipment is located and the attributes of the equipment itself also have a certain impact on the monitoring management, especially in the case of high correlation between equipment and environmental factors, which makes the difficulty and workload of manual monitoring increase continuously, and it is difficult to guarantee the monitoring efficiency.

[0003] Therefore, it is necessary to design a monitoring management method and system for equipment working conditions to solve the problems existing in the prior art. SUMMARY

[0004] In view of this, the present application provides a monitoring management method and system for equipment working conditions, aiming to solve the problem that manual inspection cannot capture the dynamic changes in the equipment running process in real time, especially in the case of high correlation between equipment and environmental factors, which makes the difficulty and workload of manual monitoring increase continuously, and it is difficult to guarantee the monitoring efficiency.

[0005] In one aspect, the present application provides a monitoring management method for equipment working conditions, comprising:

[0006] establishing a historical database, the historical database comprising a historical initial early warning score database and a historical target early warning score database, obtaining department information of all device departments corresponding to the device, determining the authority importance value of each device department according to the department information and the department authority model, and determining the management authority of each device department based on the authority importance value;

[0007] obtaining the device parameter set and the device monitoring parameter set of the device based on the management authority, comparing the device monitoring parameter set with the standard device monitoring parameter set, dividing each device monitoring parameter in the device monitoring parameter set according to the comparison result, determining the initial early warning score according to the division result, comparing the initial early warning score with the data in the historical initial early warning score database, and judging whether to adjust the initial early warning score according to the comparison result;

[0008] When determining the adjustment of the initial early warning score, a device monitoring space is constructed according to a device location of the device, an environmental data set is obtained in the device monitoring space, a correlation result of the environmental data set and the device parameter set is mined according to a correlation rule algorithm, and an adjustment coefficient of the initial early warning score is determined based on the correlation result;

[0009] A target early warning score is determined according to the adjustment coefficient and the initial early warning score, and the target early warning score is compared with data in the historical target early warning score library, and it is determined whether to issue a warning according to a comparison result.

[0010] Further, when determining the authority importance value of each device department according to the department information and the department authority model and determining the management authority of each device department based on the authority importance value, the method comprises:

[0011] A department information data set is obtained, and a random forest model is preselected, the department information data set is divided into a training set and a test set, the random forest model is iteratively trained according to the training set, the test set is substituted into the iteratively trained random forest model, and a test value is determined;

[0012] When the test value reaches a test threshold value, the iteratively trained random forest model is determined as the department authority model;

[0013] Each department information is substituted into the department authority model to determine the authority importance value of each device department;

[0014] All authority importance values are constructed into a department authority sequence, and the management authority of each device department is determined according to the department authority sequence.

[0015] Further, when determining the management authority of each device department according to the department authority sequence, the method comprises:

[0016] A first preset management authority and a second preset management authority are pre-set, and the management degrees of the first preset management authority and the second preset management authority decrease in turn;

[0017] An authority importance average value of the department authority sequence is obtained;

[0018] Authority importance values greater than or equal to the authority importance average value in the department authority sequence are divided into a first authority set;

[0019] Authority importance values less than the authority importance average value in the department authority sequence are divided into a second authority set;

[0020] The first authority set is determined as the first preset management authority, and the second authority set is determined as the second preset management authority.

[0021] Further, in the process of obtaining the device parameter set and the device monitoring parameter set of the device based on the management authority, comparing the device monitoring parameter set with the standard device monitoring parameter set, dividing each device monitoring parameter in the device monitoring parameter set according to the comparison result, and determining the initial early warning score according to the division result, the method comprises:

[0022] obtaining the device parameter set and the device monitoring parameter set of the device according to the first preset management authority;

[0023] obtaining the standard device monitoring parameter set corresponding to the device monitoring parameter set;

[0024] when the device monitoring parameter in the device monitoring parameter set is less than the standard device monitoring parameter in the standard device monitoring parameter set, the device monitoring parameter is divided into the first monitoring parameter set;

[0025] when the device monitoring parameter in the device monitoring parameter set is equal to the standard device monitoring parameter in the standard device monitoring parameter set, the device monitoring parameter is divided into the second monitoring parameter set;

[0026] when the device monitoring parameter in the device monitoring parameter set is greater than the standard device monitoring parameter in the standard device monitoring parameter set, the device monitoring parameter is divided into the third monitoring parameter set;

[0027] when the first monitoring parameter set and the third monitoring parameter set do not exist, the device is not given early warning, otherwise, the initial early warning score is determined according to the first monitoring parameter set and the third monitoring parameter set.

[0028] Further, in the process of determining the initial early warning score according to the first monitoring parameter set and the third monitoring parameter set, the method comprises:

[0029] counting the first quantity of device monitoring parameters in the first monitoring parameter set and counting the third quantity of device monitoring parameters in the third monitoring parameter set;

[0030] obtaining the first logarithm of the first quantity with the natural constant e as the base, and obtaining the third logarithm of the third quantity with the natural constant e as the base, and determining the product value of the first logarithm and the third logarithm as the initial early warning score.

[0031] Further, the initial early warning score is compared with the data in the historical initial early warning score library, and whether to adjust the initial early warning score is judged according to the comparison result;

[0032] The historical initial early warning score library comprises a plurality of historical initial early warning scores and a historical initial early warning score average value.

[0033] when the initial early warning score is greater than the average of the historical initial early warning scores, determining not to adjust the initial early warning score, and determining the initial early warning score as the target early warning score;

[0034] when the initial early warning score is less than or equal to the average of the historical initial early warning scores, determining to adjust the initial early warning score.

[0035] Further, when constructing a device monitoring space according to a device position of the device, comprising:

[0036] obtaining a device height, a device width and a device length of the device;

[0037] enlarging the device height, the device width and the device length according to a preset ratio in a four-direction around the geometric center of the device as the origin, to form a cuboid space;

[0038] deleting a device space of the device in the cuboid space, and determining the device monitoring space according to a deletion result.

[0039] Further, when mining a correlation result of the environment data set and the device parameter set according to a correlation rule algorithm, and determining an adjustment coefficient of the initial early warning score based on the correlation result, comprising:

[0040] generating a plurality of candidate item sets according to an Eclat algorithm, determining a frequent item set according to a support degree of the candidate item set, and obtaining the correlation result of the environment data set and the device parameter set based on the frequent item set;

[0041] counting a correlation number of the correlation result, and presetting a first preset correlation number and a second preset correlation number, the first preset correlation number being greater than the second preset correlation number;

[0042] presetting a first preset adjustment coefficient, a second preset adjustment coefficient and a third preset adjustment coefficient, the first preset adjustment coefficient being greater than the second preset adjustment coefficient, and the second preset adjustment coefficient being greater than the third preset adjustment coefficient;

[0043] when the correlation number is greater than the first preset correlation number, taking the first preset adjustment coefficient as the adjustment coefficient of the initial early warning score;

[0044] when the correlation number is less than or equal to the first preset correlation number, and greater than or equal to the second preset correlation number, taking the second preset adjustment coefficient as the adjustment coefficient of the initial early warning score;

[0045] when the correlation number is less than the second preset correlation number, taking the third preset adjustment coefficient as the adjustment coefficient of the initial early warning score.

[0046] Further, in the step of determining a target early warning score according to the adjustment coefficient and the initial early warning score, and comparing the target early warning score with data in the historical target early warning score library, and judging whether to give an early warning according to the comparison result, comprising:

[0047] The target early warning score is a product value of the adjustment coefficient and the initial early warning score.

[0048] A target early warning score threshold is preset, when the target early warning score is greater than the target early warning score threshold, the target early warning score is compared with data in the historical target early warning score library, and an early warning is given according to the comparison result, otherwise, no early warning is given.

[0049] The historical target early warning score library includes several historical target early warning scores, when there is a historical target early warning score same as the target early warning score in the historical target early warning score library, an early warning is given.

[0050] When there is no historical target early warning score same as the target early warning score in the historical target early warning score library, the target early warning score is added to the historical target early warning score library, and an artificial early warning signal is triggered.

[0051] Compared with the prior art, the application has the beneficial effects that: the department information and department authority model are used to determine the authority importance value of each device department and obtain the management authority of each device department, the risk of data abuse and misoperation is avoided, the device monitoring parameter set and the standard device monitoring parameter set are compared, the dynamic change of the device working condition operation parameter can be effectively captured, and the efficiency of the monitoring management is ensured. The initial early warning score is determined according to the device monitoring parameter, the initial early warning score is compared with data in the historical initial early warning score library to determine whether to adjust the initial early warning score, the flexibility of the monitoring management is improved, when adjustment is needed, the device monitoring space is constructed according to the device location, the correlation result of the environmental data set and the device parameter set is mined by using the association rule algorithm, the correlation between the device and the environmental factors is fully considered, and the dynamic flexibility and adaptability of the monitoring management are ensured. Whether the device is long-term stable operation or in a complex and changeable environment, it can effectively adapt to different production scenes, and provides reliable guarantee for the monitoring management of the device working condition.

[0052] On the other hand, the application also provides a device working condition monitoring management system, which is applied to the device working condition monitoring management method described above, comprising:

[0053] The first processing unit is configured to establish a history database including a history initial early warning score database and a history target early warning score database, acquire department information of all device departments corresponding to the device, determine a permission importance value of each device department according to the department information and a department permission model, and determine a management permission of each device department based on the permission importance value;

[0054] The second processing unit is configured to acquire a device parameter set and a device monitoring parameter set of the device based on the management permission, compare the device monitoring parameter set with a standard device monitoring parameter set, divide each device monitoring parameter in the device monitoring parameter set according to a comparison result, determine an initial early warning score according to a division result, compare the initial early warning score with data in the history initial early warning score database, and determine whether to adjust the initial early warning score according to a comparison result.

[0055] The data correlation unit is configured to, when it is determined to adjust the initial early warning score, construct a device monitoring space according to a device location of the device, acquire an environment data set in the device monitoring space, mine a correlation result of the environment data set and the device parameter set according to a correlation rule algorithm, and determine an adjustment coefficient of the initial early warning score based on the correlation result.

[0056] The monitoring and early warning unit is configured to determine a target early warning score according to the adjustment coefficient and the initial early warning score, compare the target early warning score with data in the history target early warning score database, and determine whether to early warn according to a comparison result.

[0057] It can be understood that the above-mentioned device working condition monitoring and management method and system have the same beneficial effects, which will not be described here. BRIEF DESCRIPTION OF DRAWINGS

[0058] Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The detailed description is made with reference to the accompanying drawings.

[0059] Figure 1 A flowchart of a device working condition monitoring and management method provided by an embodiment of the present application;

[0060] Figure 2 A functional block diagram of a device working condition monitoring and management system provided by an embodiment of the present application. DETAILED DESCRIPTION

[0061] Exemplary embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it is to be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the present disclosure to those skilled in the art. It should be noted that the embodiments in the present disclosure and the features in the embodiments can be combined with each other without conflict. The present disclosure will be described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.

[0062] In some embodiments of the present application, referring to Figure 1 A monitoring management method for equipment working conditions is shown, comprising:

[0063] S100: Establish a historical database, which includes a historical initial early warning score database and a historical target early warning score database, obtain department information of all equipment departments corresponding to the equipment, determine the authority importance value of each equipment department according to the department information and the department authority model, and determine the management authority of each equipment department based on the authority importance value.

[0064] S200: Obtain the equipment parameter set and the equipment monitoring parameter set of the equipment based on the management authority, compare the equipment monitoring parameter set with the standard equipment monitoring parameter set, divide each equipment monitoring parameter in the equipment monitoring parameter set according to the comparison result, determine the initial early warning score according to the division result, compare the initial early warning score with the data in the historical initial early warning score database, and judge whether to adjust the initial early warning score according to the comparison result.

[0065] S300: When it is determined to adjust the initial early warning score, construct an equipment monitoring space according to the equipment location of the equipment, obtain an environmental data set in the equipment monitoring space, mine the association result of the environmental data set and the equipment parameter set according to an association rule algorithm, and determine the adjustment coefficient of the initial early warning score based on the association result.

[0066] S400: Determine the target early warning score according to the adjustment coefficient and the initial early warning score, compare the target early warning score with the data in the historical target early warning score database, and judge whether to issue an early warning according to the comparison result.

[0067] Specifically, the historical initial early warning score library and the historical target early warning score library record the initial early warning scores and the target early warning scores in different periods, and the historical initial early warning score library and the historical target early warning score library are stored separately, providing extensive reference data for subsequent monitoring management. The equipment in the factory can be collaboratively managed by multiple equipment departments, such as the production department, the quality department, the equipment management department, and the procurement department, etc. The department information of each department includes the department name and the department responsibility, which reflects the management boundaries and responsibility attribution of the department. Since different departments have different responsibilities and influences in monitoring management, the department authority model is used to determine the authority value of each department, thereby clarifying the management authority and ensuring the normativity of the management of the equipment parameter set and the equipment monitoring parameter set, avoiding the risk of data leakage and management confusion. The equipment parameter set and the equipment monitoring parameter set of the equipment are obtained based on the management authority. The equipment parameter set includes parameters such as equipment material properties, protection properties, and explosion-proof properties. The equipment monitoring parameter set includes parameters such as the rated power, the rated current, the working pressure, and the rotational speed of the equipment. The equipment parameter set and the equipment monitoring parameter set reflect the actual operating conditions of the equipment. The equipment monitoring parameter set is compared with the standard equipment monitoring parameter set, which is obtained according to the factory parameters and the usage instructions of the equipment, reflecting the theoretical operating conditions of the equipment. The equipment monitoring parameter set is compared with the standard equipment monitoring parameter set, and the initial early warning score is determined based on the difference. If there is a difference between the initial early warning score and the data in the historical initial early warning score library, the initial early warning score may need to be adjusted to avoid the risk of false comparison of parameters, improving the reliability and stability of the equipment operating condition monitoring management.

[0068] It can be understood that when it is determined that the initial early warning score needs to be adjusted, the environmental data set is obtained by constructing the equipment monitoring space according to the equipment location. The environmental data set includes temperature, humidity, and air pressure data, which are obtained by equipment such as temperature sensors, humidity sensors, and air pressure sensors in the equipment monitoring space. The association rule algorithm is used to mine the association results of the environment where the equipment is located and the equipment parameter set, so as to determine the adjustment coefficient. The equipment operating condition is not only dependent on its own parameters, but also influenced by environmental factors. For example, when the environmental temperature exceeds 50℃, the equipment material will expand and deform due to heat, which will affect the parameters such as rotational speed in the equipment monitoring parameter set. By constructing the equipment monitoring space and mining the association results of the environmental data set and the equipment parameter set, the internal and external factors of the equipment operation can be considered comprehensively, so that the target early warning score can be adjusted to the actual equipment operating condition. After comparing the target early warning score with the historical target early warning score library, it is determined whether to issue a warning, effectively reducing the monitoring difficulty and workload, thereby ensuring the monitoring efficiency.

[0069] In some embodiments of the present application, when determining the management authority of each device department according to the department information and the department authority model, the method comprises: obtaining a department information dataset and preselecting a random forest model, dividing the department information dataset into a training set and a test set, iteratively training the random forest model according to the training set, substituting the test set into the iteratively trained random forest model and determining a test value, when the test value reaches a test threshold, determining the iteratively trained random forest model as the department authority model, substituting each department information into the department authority model to determine the authority importance value of each device department, and constructing a department authority sequence from all the authority importance values to determine the management authority of each device department.

[0070] In some embodiments of the present application, when determining the management authority of each device department according to the department authority sequence, the method comprises: pre-setting a first preset management authority and a second preset management authority, the management degree of the first preset management authority and the second preset management authority decreasing in turn, obtaining an authority importance average value of the department authority sequence, dividing the authority importance values in the department authority sequence that are greater than or equal to the authority importance average value into a first authority set, dividing the authority importance values in the department authority sequence that are less than the authority importance average value into a second authority set, and determining the first authority set as the first preset management authority and the second authority set as the second preset management authority.

[0071] Specifically, the department information dataset contains department information of each department, covering all department names and department responsibility data. The department information dataset is divided into a training set and a test set, generally in a ratio of 7:3, which can be adjusted according to the data volume of the department information dataset to improve the generalization ability of the model. The training set is used to train the random forest model, and the test set is used to evaluate the performance of the trained model. The random forest model contains the number of trees and the maximum depth of the trees, aiming to capture the complex relationships in the data. The training set is used to train the random forest model. In each iteration training process, the model attempts to learn the patterns and relationships in the data to improve its prediction ability. After each iteration training, the data in the test set is used to test the model. The test value includes accuracy, F1 value, recall rate, etc., which are used to measure the performance of the model. When the test value reaches the test threshold, it is considered that the trained random forest model has reached a satisfactory performance level, so the iteratively trained random forest model is determined as the department authority model, and each department information is substituted into the department authority model to output the authority importance value of each department information, making the authority management more standardized and reliable, avoiding data abuse and improving the efficiency of monitoring and management.

[0072] It can be understood that, taking the average value of the importance of the department authority sequence as the division basis, the human factor interference is avoided, the allocation of the first preset management authority and the second preset management authority conforms to the actual functions of each department, the reliability of the authority allocation is ensured, the department with high importance value of authority is included in the first authority set, and the first preset management authority is assigned, so that the key department can have sufficient authority to effectively monitor and manage the equipment, and the operation safety of the equipment is ensured, the second preset management authority corresponds to the department with low importance value of authority, and the authority range of the department is reasonably limited, so that the risk of data abuse and misoperation is avoided, for example, the management degree of the equipment management department is high, and the management degree of the procurement department is low.

[0073] In some embodiments of the present application, when the device parameter set and the device monitoring parameter set of the device are obtained based on the management authority, the device monitoring parameter set and the standard device monitoring parameter set are compared, each device monitoring parameter in the device monitoring parameter set is divided according to the comparison result, and the initial early warning score is determined according to the division result, including: determining the device parameter set and the device monitoring parameter set of the device according to the first preset management authority, obtaining the standard device monitoring parameter set corresponding to the device monitoring parameter set, when the device monitoring parameter in the device monitoring parameter set is less than the standard device monitoring parameter in the standard device monitoring parameter set, the device monitoring parameter is divided into a first monitoring parameter set, when the device monitoring parameter in the device monitoring parameter set is equal to the standard device monitoring parameter in the standard device monitoring parameter set, the device monitoring parameter is divided into a second monitoring parameter set, when the device monitoring parameter in the device monitoring parameter set is greater than the standard device monitoring parameter in the standard device monitoring parameter set, the device monitoring parameter is divided into a third monitoring parameter set, when there is no first monitoring parameter set and third monitoring parameter set, the device is not early warned, otherwise, the initial early warning score is determined according to the first monitoring parameter set and the third monitoring parameter set.

[0074] In some embodiments of the present application, when the initial early warning score is determined according to the first monitoring parameter set and the third monitoring parameter set, including: counting the first number of device monitoring parameters in the first monitoring parameter set, counting the third number of device monitoring parameters in the third monitoring parameter set, obtaining the first logarithm of the first number with the natural constant e as the base, and obtaining the third logarithm of the third number with the natural constant e as the base, and the product value of the first logarithm and the third logarithm is determined as the initial early warning score.

[0075] Specifically, the device parameter set and the device monitoring parameter set are acquired based on the first preset management permission, which can ensure that the acquired data is comprehensive, and the device monitoring parameters in the device monitoring parameter set correspond one-to-one to the standard device monitoring parameters in the standard device monitoring parameter set. By comparing the device monitoring parameters in the device monitoring parameter set with the standard device monitoring parameters in the standard device monitoring parameter set, and dividing them into different monitoring parameter sets according to the size relationship, the difference between the device operating condition and the theoretical condition can be accurately located. For example, when the device monitoring parameter is less than the standard device monitoring parameter, it means that the device may have insufficient performance or hidden trouble, and when it is greater than the standard device monitoring parameter, the device may be overloaded and cause device wear. When there is no first monitoring parameter set and third monitoring parameter set, it means that the device monitoring parameters of the device are all within the standard device monitoring parameters, and no warning is needed, otherwise, the operating condition of the device is inconsistent with the theoretical condition, and may have a fault or the like. The first number refers to the total number of device monitoring parameters in the first monitoring parameter set, and the third number refers to the total number of device monitoring parameters in the third monitoring parameter set. Once the operating condition of the device is inconsistent with the theoretical condition, it will inevitably lead to an increase in the first number and the third number, and the device monitoring parameters will not all be greater than the standard device monitoring parameters. For example, a hydraulic device, when the throttle opening of the hydraulic device changes, the pressure and flow will be affected at the same time. If the throttle opening is reduced, the pressure will rise, but the flow will decrease accordingly, and the pressure and flow will not be greater than the standard value at the same time. The initial warning score is used to quantify the actual situation of the device condition, which provides a data basis for subsequent warning and ensures the reliability of monitoring management.

[0076] In some embodiments of the present application, the initial warning score is compared with the data in the historical initial warning score library, and whether to adjust the initial warning score is determined according to the comparison result. The historical initial warning score library includes a plurality of historical initial warning scores and a historical initial warning score average. When the initial warning score is greater than the historical initial warning score average, it is determined that the initial warning score is not adjusted, and the initial warning score is determined as the target warning score. When the initial warning score is less than or equal to the historical initial warning score average, it is determined that the initial warning score is adjusted.

[0077] Specifically, the historical initial early warning score library is taken as a reference to construct a dynamically adjusted early warning score mechanism, avoiding misjudgment and missed judgment caused by simple calculation. The historical initial early warning score mean in the historical initial early warning score library represents the average level of possible abnormalities in the past operation of the equipment. When the initial early warning score is greater than the historical initial early warning score mean, it indicates that the possible abnormalities of the equipment exceed the historical average level, and the initial early warning score is determined as the target early warning score. When the initial early warning score is less than or equal to the historical initial early warning score mean, it indicates that there may be score deviation or potential changes in the equipment operating state, and the initial early warning score needs to be further adjusted to avoid misjudgment or missed judgment caused by data fluctuations. By establishing a judgment benchmark through the historical initial early warning score library, the initial early warning score is adjusted adaptively, making the result conform to the long-term operation rule of the equipment and ensuring the reliability and stability of the monitoring management.

[0078] In some embodiments of the present application, when the equipment monitoring space is constructed according to the equipment position of the equipment, the following steps are included: obtaining the equipment height, equipment width and equipment length of the equipment, taking the geometric center of the equipment as the origin, magnifying the equipment height, equipment width and equipment length according to a preset ratio in the four directions, forming a cuboid space, deleting the equipment space of the equipment in the cuboid space, and determining the equipment monitoring space according to the deletion result.

[0079] Specifically, the geometric center of the equipment is taken as the origin, and the cuboid space is constructed by magnifying the equipment height, equipment width and equipment length according to a preset ratio. The preset ratio is dynamically set according to the equipment height, equipment width and equipment length of the equipment. For example, when one of the equipment height, equipment width and equipment length is large enough, it can be magnified by 1-2 times at the same ratio. When one of the equipment height, equipment width and equipment length is small enough, magnifying by 5-6 times may still not cover the environment where the equipment is located. Therefore, the specific preset ratio is set according to the equipment height, equipment width and equipment length. Compared with the space monitoring of the equipment itself, the equipment monitoring space is determined to effectively avoid data omission caused by insufficient environmental monitoring range. For example, the change of temperature and humidity around the equipment during operation, the diffusion of dust concentration, etc. may affect the equipment outside the equipment space. The comprehensiveness of the environmental data set is ensured, and the interference of data caused by the structure and operation of the equipment, such as electromagnetic interference, is avoided in the cuboid space to improve the effectiveness of the analysis of the environmental data set and the equipment parameter set. Whether the equipment is in long-term stable operation or in a complex and changeable environment, it can effectively adapt to different production scenes and provide reliable protection for the monitoring and management of the equipment working condition.

[0080] In some embodiments of the present application, when the association results of the environmental data set and the device parameter set are mined according to the association rule algorithm, and the adjustment coefficient of the initial early warning score is determined based on the association results, the method comprises: generating a plurality of candidate item sets according to the Eclat algorithm, determining a frequent item set according to the support of the candidate item set, obtaining the association results of the environmental data set and the device parameter set based on the frequent item set, counting the number of associations of the association results, and pre-setting a first preset association number and a second preset association number, the first preset association number being greater than the second preset association number, pre-setting a first preset adjustment coefficient, a second preset adjustment coefficient and a third preset adjustment coefficient, the first preset adjustment coefficient being greater than the second preset adjustment coefficient, and the second preset adjustment coefficient being greater than the third preset adjustment coefficient, when the number of associations is greater than the first preset association number, the first preset adjustment coefficient is taken as the adjustment coefficient of the initial early warning score, when the number of associations is less than or equal to the first preset association number and greater than or equal to the second preset association number, the second preset adjustment coefficient is taken as the adjustment coefficient of the initial early warning score, and when the number of associations is less than the second preset association number, the third preset adjustment coefficient is taken as the adjustment coefficient of the initial early warning score.

[0081] Specifically, compared with other association rule mining algorithms, the Eclat algorithm uses vertical data format for intersection operation, and can mine potential association relationships in the environmental data set and the device parameter set. According to the Eclat algorithm, a plurality of candidate item sets are generated, and the support of each candidate item set is calculated. The minimum support threshold is preferably 2. If the support is greater than or equal to the minimum support threshold, the candidate item set is determined as a frequent item set. According to the frequent item set, the association results are obtained, for example: when the environmental temperature exceeds 50℃, the thermal expansion deformation of the device material always occurs. The first preset association number is preferably 15, the second preset association number is preferably 10, the first preset adjustment coefficient is preferably 1.5, the second preset adjustment coefficient is preferably 1.3, and the third preset adjustment coefficient is preferably 1.1. When the number of associations of the environmental data set and the device parameter set is large, it indicates that the correlation between environmental factors and device operating state is strong. At this time, a larger first preset adjustment coefficient is used to improve the adjustment range of the initial early warning score. When the number of associations is small, a smaller third preset adjustment coefficient is used. By dynamically selecting the corresponding preset adjustment coefficient according to the number of associations, the reliability and stability of the device working condition monitoring and management are ensured.

[0082] In some embodiments of the present application, when determining the target early warning score according to the adjustment coefficient and the initial early warning score, comparing the target early warning score with the data in the historical target early warning score library, and judging whether to issue a warning according to the comparison result, the target early warning score is the product of the adjustment coefficient and the initial early warning score, a target early warning score threshold is preset, when the target early warning score is greater than the target early warning score threshold, the target early warning score is compared with the data in the historical target early warning score library, and a warning is issued according to the comparison result, otherwise, no warning is issued, the historical target early warning score library includes a plurality of historical target early warning scores, when there is a historical target early warning score identical to the target early warning score in the historical target early warning score library, a warning is issued, and when there is no historical target early warning score identical to the target early warning score in the historical target early warning score library, the target early warning score is added to the historical target early warning score library and an artificial warning signal is triggered.

[0083] Specifically, the target early warning score threshold is preferably 7.5, the target early warning score is compared with the historical target early warning score library, and the historical data of the equipment is fully utilized as a reference, when the same target early warning score as the historical target early warning score appears, it indicates that the target early warning score of the equipment has appeared in the history, the warning can be quickly determined, repeated analysis is avoided, the response speed of the equipment working condition monitoring management is improved, if there is no identical historical target early warning score in the historical target early warning score library, the new target early warning score is added to the historical target early warning score library, thereby continuously enriching the historical target early warning score library, and an artificial warning signal is triggered, realizing the combination of data driving and manual operation, ensuring that each new target early warning score can be carefully checked and evaluated, reducing the risk of ignoring or missing the equipment working condition, effectively reducing the monitoring difficulty and workload, thereby ensuring the monitoring efficiency.

[0084] In summary, the beneficial effects of the present application are that the department information and department authority model are used to determine the authority importance value of each equipment department and obtain the management authority of each equipment department, the risk of data abuse and misoperation is avoided, the equipment monitoring parameter set is compared with the standard equipment monitoring parameter set, the dynamic change of the equipment working condition operation parameter can be effectively captured, and the efficiency of the monitoring management is ensured. The initial early warning score is determined according to the equipment monitoring parameter, and whether to adjust the initial early warning score is judged by comparing with the data in the historical initial early warning score library, the flexibility of the monitoring management is improved, when adjustment is needed, the equipment monitoring space is constructed according to the equipment location, the association result of the environmental data set and the equipment parameter set is mined by using the association rule algorithm, the correlation between the equipment and the environmental factors is fully considered, and the dynamic flexibility and adaptability of the monitoring management are ensured. Whether it is a long-term stable running equipment or an equipment in a complex and changeable environment, it can effectively adapt to different production scenes, and provides reliable protection for the monitoring management of the equipment working condition.

[0085] In another preferred mode based on the above-mentioned embodiments, referring to Figure 2 The present embodiment provides a monitoring management system for equipment working conditions, applied to the above-mentioned monitoring management method for equipment working conditions, comprising:

[0086] The first processing unit is configured to establish a historical database, the historical database comprising a historical initial early warning score database and a historical target early warning score database, obtain department information of all equipment departments corresponding to the equipment, determine the authority importance value of each equipment department according to the department information and the department authority model, and determine the management authority of each equipment department based on the authority importance value.

[0087] The second processing unit is configured to obtain the equipment parameter set and the equipment monitoring parameter set of the equipment based on the management authority, compare the equipment monitoring parameter set with the standard equipment monitoring parameter set, divide each equipment monitoring parameter in the equipment monitoring parameter set according to the comparison result, determine the initial early warning score according to the division result, compare the initial early warning score with the data in the historical initial early warning score database, and determine whether to adjust the initial early warning score according to the comparison result.

[0088] The data correlation unit is configured to, when it is determined to adjust the initial early warning score, construct an equipment monitoring space according to the equipment location of the equipment, obtain an environmental data set in the equipment monitoring space, mine the correlation result of the environmental data set and the equipment parameter set according to a correlation rule algorithm, and determine the adjustment coefficient of the initial early warning score based on the correlation result.

[0089] The monitoring and early warning unit is configured to determine the target early warning score according to the adjustment coefficient and the initial early warning score, compare the target early warning score with the data in the historical target early warning score database, and determine whether to give an early warning according to the comparison result.

[0090] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system or a computer program product. Therefore, the present application can be in the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can be in the form of a computer program product implemented on one or more computer usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer usable program code.

[0091] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart or flowsheet block or blocks. Figure 1 one or more flowcharts and / or blocks Figure 1 one or more flowcharts and / or blocks

[0092] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the function specified in the flowchart or flowsheet block or blocks. Figure 1 one or more flowcharts and / or blocks Figure 1 one or more flowcharts and / or blocks

[0093] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart or flowsheet block or blocks. Figure 1 one or more flowcharts and / or blocks Figure 1 one or more flowcharts and / or blocks

[0094] Finally, it should be noted that the above-mentioned embodiments are merely intended to illustrate the technical solutions of the present application, rather than limit the same. Although the present application has been described in detail with reference to the above-mentioned embodiments, those skilled in the art should understand that the specific embodiments of the present application can be modified or replaced equivalently without departing from the spirit and scope of the present application, and any modification or replacement without departing from the spirit and scope of the present application should be included in the protection scope of the present application.

Claims

1. A method for monitoring management of a device condition, characterized by, The method comprises the following steps: establishing a historical database, the historical database comprising a historical initial early warning score database and a historical target early warning score database, obtaining department information of all device departments corresponding to a device, determining a permission importance value of each device department according to the department information and a department permission model, and determining a management permission of each device department based on the permission importance value; obtaining a device parameter set and a device monitoring parameter set of the device based on the management permission, comparing the device monitoring parameter set with a standard device monitoring parameter set, dividing each device monitoring parameter in the device monitoring parameter set according to a comparison result, determining an initial early warning score according to the division result, comparing the initial early warning score with data in the historical initial early warning score database, and judging whether to adjust the initial early warning score according to a comparison result; when it is determined to adjust the initial early warning score, constructing a device monitoring space according to a device location of the device, obtaining an environmental data set in the device monitoring space, mining a correlation result of the environmental data set and the device parameter set according to a correlation rule algorithm, and determining an adjustment coefficient of the initial early warning score based on the correlation result; determining a target early warning score according to the adjustment coefficient and the initial early warning score, comparing the target early warning score with data in the historical target early warning score database, and judging whether to issue an early warning according to a comparison result; comparing the initial early warning score with data in the historical initial early warning score database, and judging whether to adjust the initial early warning score according to a comparison result; the historical initial early warning score database comprises a plurality of historical initial early warning scores and a historical initial early warning score average value; when the initial early warning score is greater than the historical initial early warning score average value, it is determined that the initial early warning score is not adjusted, and the initial early warning score is determined as the target early warning score; when the initial early warning score is less than or equal to the historical initial early warning score average value, it is determined that the initial early warning score is adjusted; the target early warning score is a product value of the adjustment coefficient and the initial early warning score.

2. The method for monitoring management of equipment working conditions according to claim 1, characterized in that, In the step of determining a permission importance value of each device department according to the department information and a department permission model, and determining a management permission of each device department based on the permission importance value, the method comprises the following steps: obtaining a department information data set and preselecting a random forest model, dividing the department information data set into a training set and a test set, iteratively training the random forest model according to the training set, and determining a test value by substituting the test set into the iteratively trained random forest model; when the test value reaches a test threshold value, the iteratively trained random forest model is determined as the department permission model; substituting each department information into the department permission model to determine the permission importance value of each device department; constructing a department permission sequence from all the permission importance values, and determining the management permission of each device department according to the department permission sequence.

3. The method for monitoring management of equipment working conditions according to claim 2, characterized in that, In the step of determining the management permission of each device department according to the department permission sequence, the method comprises the following steps: predefining a first preset management permission and a second preset management permission, and the management degree of the first preset management permission and the second preset management permission decreases in turn. obtaining an average of importance values of the department authority sequence; dividing importance values greater than or equal to the average of importance values of the department authority sequence into a first authority set; dividing importance values less than the average of importance values of the department authority sequence into a second authority set; the first authority set is determined as the first preset management authority, and the second authority set is determined as the second preset management authority.

4. The method for monitoring management of equipment working conditions according to claim 3, characterized in that, when obtaining a device parameter set and a device monitoring parameter set of the device based on the management authority, comparing the device monitoring parameter set with a standard device monitoring parameter set, dividing each device monitoring parameter in the device monitoring parameter set according to a comparison result, and determining an initial early warning score according to a division result, comprising: determining the device parameter set and the device monitoring parameter set of the device according to the first preset management authority; obtaining the standard device monitoring parameter set corresponding to the device monitoring parameter set; when a device monitoring parameter in the device monitoring parameter set is less than a standard device monitoring parameter in the standard device monitoring parameter set, the device monitoring parameter is divided into a first monitoring parameter set; when a device monitoring parameter in the device monitoring parameter set is equal to a standard device monitoring parameter in the standard device monitoring parameter set, the device monitoring parameter is divided into a second monitoring parameter set; when a device monitoring parameter in the device monitoring parameter set is greater than a standard device monitoring parameter in the standard device monitoring parameter set, the device monitoring parameter is divided into a third monitoring parameter set; when the first monitoring parameter set and the third monitoring parameter set do not exist, the device is not early warned, otherwise, the initial early warning score is determined according to the first monitoring parameter set and the third monitoring parameter set.

5. The method for monitoring management of equipment working conditions according to claim 4, characterized in that, when the initial early warning score is determined according to the first monitoring parameter set and the third monitoring parameter set, comprising: statistically obtaining a first number of device monitoring parameters in the first monitoring parameter set and a third number of device monitoring parameters in the third monitoring parameter set; obtaining a first logarithm of the first number with a natural constant e as a base, and obtaining a third logarithm of the third number with the natural constant e as a base, and determining a product value of the first logarithm and the third logarithm as the initial early warning score.

6. The method for monitoring management of equipment working conditions according to claim 5, characterized in that, when a device monitoring space is constructed according to a device position of the device, comprising: obtaining a device height, a device width and a device length of the device; enlarging the device height, the device width and the device length according to a preset proportion in all directions around the geometric center of the device to form a cuboid space; deleting a device space of the device in the cuboid space, and determining the device monitoring space according to a deletion result.

7. The method for monitoring management of equipment working conditions according to claim 6, characterized in that, when an association result of the environment data set and the device parameter set is mined according to an association rule algorithm, and an adjustment coefficient of the initial early warning score is determined based on the association result, comprising: generating a plurality of candidate item sets according to the Eclat algorithm, determining a frequent item set according to a support degree of the candidate item set, and obtaining the association result of the environment data set and the device parameter set based on the frequent item set; counting a quantity of the association results, and presetting a first preset association quantity and a second preset association quantity, the first preset association quantity being greater than the second preset association quantity; presetting a first preset adjustment coefficient, a second preset adjustment coefficient and a third preset adjustment coefficient, the first preset adjustment coefficient being greater than the second preset adjustment coefficient, and the second preset adjustment coefficient being greater than the third preset adjustment coefficient; when the quantity of the association results is greater than the first preset association quantity, taking the first preset adjustment coefficient as the adjustment coefficient of the initial early warning score; when the quantity of the association results is less than or equal to the first preset association quantity and greater than or equal to the second preset association quantity, taking the second preset adjustment coefficient as the adjustment coefficient of the initial early warning score; when the quantity of the association results is less than the second preset association quantity, taking the third preset adjustment coefficient as the adjustment coefficient of the initial early warning score.

8. The method for monitoring management of equipment working conditions according to claim 7, characterized in that, In determining a target early warning score according to the adjustment coefficient and the initial early warning score, and comparing the target early warning score with data in the historical target early warning score library, and judging whether to give an early warning according to a comparison result, comprising: presetting a target early warning score threshold, when a target early warning score is greater than the target early warning score threshold, comparing the target early warning score with data in the historical target early warning score library, and giving an early warning according to a comparison result, otherwise, not giving an early warning; the historical target early warning score library comprising a plurality of historical target early warning scores, when there is a historical target early warning score identical to the target early warning score in the historical target early warning score library, giving an early warning; when there is no historical target early warning score identical to the target early warning score in the historical target early warning score library, adding the target early warning score to the historical target early warning score library, and triggering an artificial early warning signal.

9. A monitoring management system for equipment operation, applied to the monitoring management method for equipment operation according to any one of claims 1 to 8, characterized by, comprising: a first processing unit configured to establish a historical database, the historical database comprising a historical initial early warning score library and a historical target early warning score library, acquire department information of all device departments corresponding to a device, determine an authority importance value of each device department according to the department information and a department authority model, and determine a management authority of each device department based on the authority importance value; a second processing unit configured to acquire a device parameter set and a device monitoring parameter set of the device based on the management authority, compare the device monitoring parameter set with a standard device monitoring parameter set, divide each device monitoring parameter in the device monitoring parameter set according to a comparison result, determine an initial early warning score according to a division result, compare the initial early warning score with data in the historical initial early warning score library, and judge whether to adjust the initial early warning score according to a comparison result; a data association unit configured to, when it is determined to adjust the initial early warning score, construct a device monitoring space according to a device location of the device, acquire an environment data set in the device monitoring space, mine association results of the environment data set and the device parameter set according to an association rule algorithm, and determine an adjustment coefficient of the initial early warning score based on the association results. The monitoring and early warning unit is configured to determine a target early warning score according to the adjustment coefficient and the initial early warning score, compare the target early warning score with data in the historical target early warning score library, and determine whether to issue an early warning according to a comparison result; The initial early warning score is compared with data in the historical initial early warning score library, and it is determined whether to adjust the initial early warning score according to a comparison result; The historical initial early warning score library includes a plurality of historical initial early warning scores and a historical initial early warning score average value; When the initial early warning score is greater than the historical initial early warning score average value, it is determined that the initial early warning score is not adjusted, and the initial early warning score is determined as the target early warning score; When the initial early warning score is less than or equal to the historical initial early warning score average value, it is determined that the initial early warning score is adjusted; The target early warning score is a product value of the adjustment coefficient and the initial early warning score.

Images