Equipment operation and maintenance data management system and method based on multi-modal data fusion

Abstract

The invention provides an equipment operation and maintenance data management system and method based on multi-modal data fusion. The system comprises a backtracking portrait obtaining module used for obtaining a backtracking portrait of a collection moment of target dimension data of a target equipment bit number; the real-time portrait obtaining module is used for obtaining a real-time portrait of a target equipment position number; the portrait deviation analysis module is used for constructing a portrait deviation vector; the threshold judgment module is used for obtaining a data deletion proportion; and the data cleaning module is used for deleting the operation and maintenance data according to the data deletion proportion. The technical problems that in the prior art, the storage pressure is large due to continuous increase of equipment operation and maintenance data, and the data management efficiency is low due to the fact that a traditional deletion method cannot intelligently judge data importance and needs manual intervention are solved, and the purposes of automatically evaluating the data value based on equipment service duration and control parameter changes and improving the data management efficiency are achieved. And the low-reference-value data is intelligently cleaned, so that the technical effects of reducing the storage pressure and improving the data management efficiency are achieved.

Description

Technical Field

[0001] The present invention relates to the field of data management, and in particular to an equipment operation and maintenance data management system and method based on multimodal data fusion. Background Art

[0002] With the continuous development of industrial automation and intelligent manufacturing, the collection and analysis of equipment operation and maintenance data has become an important means to ensure equipment safety, extend equipment life and improve production efficiency. In modern industrial environments, various types of equipment generate a large amount of operation and maintenance data at all times, including but not limited to parameters such as temperature, pressure, vibration, flow, etc. These data are collected through various sensors and stored in the database for equipment status monitoring, fault prediction and maintenance decisions. However, with the increase in data collection frequency and the increase in the number of equipment, equipment operation and maintenance data has grown exponentially, bringing tremendous pressure to data storage and management. A large amount of data not only takes up server disk space, but may also lead to a decrease in data query and analysis efficiency, increasing system operating costs.

[0003] At present, for equipment operation and maintenance data management, common data cleaning is mainly based on time factors, that is, deleting historical data with a long storage time, or deleting data with fewer access times based on frequency of use. Although these data management methods have alleviated storage pressure to a certain extent, they have obvious shortcomings: first, they cannot intelligently judge the importance and reference value of data, which may lead to the accidental deletion of historical data with important reference significance; second, manual intervention is usually required, such as setting deletion rules, confirming the deletion range, etc., which is cumbersome and inefficient; at the same time, simple deletion methods based on time or frequency of use cannot take into account the dynamic changes in the operating status of the equipment, and it is difficult to adapt to the data management needs of the entire life cycle of the equipment. Therefore, the continuous increase of equipment operation and maintenance data in the prior art leads to great storage pressure, and the traditional deletion method cannot intelligently judge the importance of data and requires manual intervention, resulting in inefficient data management. Summary of the invention

[0004] The present invention aims to solve the technical problems in the prior art that the continuous increase of equipment operation and maintenance data leads to great storage pressure, and the traditional deletion method cannot intelligently judge the importance of data and requires manual intervention, resulting in low data management efficiency. An equipment operation and maintenance data management system and method based on multimodal data fusion are provided to solve the problems.

[0005] The technical solution of the present invention to solve the above technical problems is as follows: In a first aspect, the present invention provides an equipment operation and maintenance data management system based on multimodal data fusion, including: a retrospective portrait acquisition module, which is used to obtain a retrospective portrait of the target dimension data of the target equipment position number at the collection time when a preset management cycle is met, wherein the retrospective portrait includes a first service time and a first control parameter; a real-time portrait acquisition module, which is used to obtain a real-time portrait of the target equipment position number, wherein the real-time portrait includes a second service time and a second control parameter; a portrait deviation analysis module, which is used to construct a portrait deviation vector according to the first service time and the first control parameter, and the second service time and the second control parameter; a threshold judgment module, which is used to retrieve a target dimension data deviation module value set that satisfies the portrait deviation vector, and when the variance of the target dimension data deviation module value set is greater than or equal to the variance threshold, calculate the ratio of the first time length between the storage start time and the collection time to the second time length between the storage start time and the current time, and set it as the data deletion ratio; a data cleaning module, which is used to delete the target dimension data from the target equipment position number operation and maintenance data starting from the storage start time according to the data deletion ratio.

[0006] Furthermore, the retrospective portrait acquisition module includes: a parameter acquisition unit, used to obtain the first preset control parameter of the target device position number until the Nth preset control parameter; a first statistical unit, used to use the first preset control parameter as a constraint and to count the first alienated service time of the target dimension data based on the historical sample library; a multi-parameter statistical unit, used to use the Nth preset control parameter as a constraint and to count the Nth alienated service time of the target dimension data based on the historical sample library; a period calculation unit, used to extract 0.5 times the minimum value of the first alienated service time until the Nth alienated service time, and set it as the preset management period.

[0007] Furthermore, the retrospective portrait acquisition module also includes: a storage threshold unit, which is used to obtain the disk space storage capacity threshold of the target device position number operation and maintenance data; and a portrait retrospective trigger unit, which is used to obtain the retrospective portrait of the collection moment of the target dimension data of the target device position number when the amount of operation and maintenance data of the target device position number is greater than or equal to the disk space storage capacity threshold.

[0008] Furthermore, the first statistical unit includes: a data retrieval subunit, which is used to retrieve a number of underlying perception attribute record characteristic values ​​and a number of first service time record values ​​that correspond one to one and meet the first preset control parameters from the historical sample library when the target dimension data is an underlying perception attribute; a deviation calculation subunit, which is used to perform pairwise deviation analysis on a number of underlying perception attribute record characteristic values ​​and a number of first service time record values ​​that correspond one to one, and obtain a set of underlying perception attribute record characteristic value deviation modulus values ​​and a set of first service time record value deviation modulus values; a feature screening subunit, which extracts a set of first service time record value selected deviation modulus values ​​whose underlying perception attribute record characteristic value deviation modulus value set is greater than or equal to a predefined record characteristic value deviation modulus value threshold from the first service time record value deviation modulus value set; and a mode evaluation subunit, which is used to perform mode evaluation on the set of first service time record value selected deviation modulus values ​​to obtain the first alienated service time.

[0009] Furthermore, the first statistical unit includes: a mapper scheduling subunit, which is used to schedule a target dimension data mapper bound to the high-level mapping attribute and the first preset control parameter when the target dimension data is a high-level mapping attribute, wherein the target dimension data mapper has an input underlying perception attribute; an associated data retrieval subunit, which is used to retrieve from the historical sample library a number of input underlying perception attribute record characteristic values ​​and a number of second service time record values ​​that correspond one to one to satisfy the first preset control parameter; a feature mapping processing subunit, which is used to process the number of input underlying perception attribute record characteristic values ​​respectively through the target dimension data mapper to obtain a number of high-level mapping attribute characteristic values; and an alienated time calculation subunit, which is used to calculate the first alienated service time according to the number of high-level mapping attribute characteristic values ​​and the number of second service time record values.

[0010] Furthermore, the system also includes: an attribute configuration module, which is used to configure the preset input underlying perception attributes of the preset high-level mapping attributes through the user terminal; a mapper training module, which is used to collect multiple sets of data and train the target dimension data mapper with the preset target device model and preset control parameters as constraints; a mapping binding module, which is used to bind the target dimension data mapper to the preset high-level mapping attributes and the preset control parameters; wherein any one of the multiple sets of data includes: preset input underlying perception attribute record data and preset high-level mapping attribute record data.

[0011] Furthermore, the threshold judgment module includes: a deviation decomposition unit, which is used for the portrait deviation vector to include a service time deviation vector and a control parameter deviation vector; a cloud retrieval unit, which is used to initiate a retrieval request to the cloud, obtain a key, encrypt the target dimension, the target device model, the service time deviation vector and the control parameter deviation vector, obtain the ciphertext and upload it to the cloud, and obtain retrieval feedback information, wherein the retrieval feedback information includes an initial target dimension data deviation modulus value set; an outlier processing unit, which is used to perform outlier deletion on the initial target dimension data deviation modulus value set to obtain the target dimension data deviation modulus value set.

[0012] Furthermore, the cloud retrieval unit includes: a cloud decryption sub-unit, used to decrypt the ciphertext through the cloud, obtain the target dimension, the target device model, the service time deviation vector and the control parameter deviation vector, and construct a retrieval task constraint; a node request sub-unit, used to initiate a retrieval request to a distributed node through the cloud, and obtain a distributed node key; an encrypted retrieval sub-unit, used to encrypt the retrieval task constraint and the retrieval key according to the distributed node key, obtain the retrieval task ciphertext, send it to the distributed node, and obtain retrieval feedback information, wherein the retrieval feedback information includes the initial target dimension data deviation module value set.

[0013] In a second aspect, the present invention provides an equipment operation and maintenance data management method based on multimodal data fusion, including: when a preset management cycle is met, obtaining a retrospective portrait of the target device position number at the collection time, wherein the retrospective portrait includes a first service time and a first control parameter; obtaining a real-time portrait of the target device position number, wherein the real-time portrait includes a second service time and a second control parameter; constructing a portrait deviation vector based on the first service time and the first control parameter, as well as the second service time and the second control parameter; retrieving a target dimension data deviation modulus value set that satisfies the portrait deviation vector, and when the variance of the target dimension data deviation modulus value set is greater than or equal to the variance threshold, calculating the ratio of the first time length between the storage start time and the collection time to the second time length between the storage start time and the current time, and setting it as the data deletion ratio; deleting the target dimension data from the target device position number operation and maintenance data starting from the storage start time according to the data deletion ratio.

[0014] The beneficial effects of the present invention are: Through the retrospective portrait acquisition module, when the preset management cycle is met, the retrospective portrait of the target dimension data of the target device bit number is obtained at the collection time, wherein the retrospective portrait includes the first service time and the first control parameter, which provides basic data for subsequent comparative analysis and ensures that the current reference value of historical data can be evaluated. Through the real-time portrait acquisition module, the real-time portrait of the target device bit number is obtained, wherein the real-time portrait includes the second service time and the second control parameter, so as to compare with the historical data and reflect the change of the equipment status. Through the portrait deviation analysis module, according to the first service time and the first control parameter, as well as the second service time and the second control parameter, the portrait deviation vector is constructed to quantify the degree of change of the equipment operation status, providing a basis for judging the value of historical data. Through the threshold judgment module, the target dimension data deviation modulus value set that meets the portrait deviation vector is retrieved. When the variance of the target dimension data deviation modulus value set is greater than or equal to the variance threshold, the first duration between the storage start time and the collection time and the second duration between the storage start time and the current time are calculated, which is set as the data deletion ratio. The significance of data fluctuations is determined through statistical analysis, and the proportion of data that needs to be cleaned is calculated accordingly, realizing the intelligent evaluation of data value. Through the data cleaning module, the target dimension data is deleted from the target device position number operation and maintenance data from the start of storage according to the data deletion ratio, and the actual data cleaning operation is performed. The low-value data is intelligently cleaned according to the calculated deletion ratio, thereby reducing storage pressure.

[0015] Through the above technical solution, the system can automatically identify and clean up historical data that has lost its reference value due to changes in equipment status during equipment operation and maintenance, based on the service life of the equipment and changes in control parameters. When the fluctuation variance of a certain dimension of data is large, it indicates that the reference value of the dimension data for equipment operation and maintenance is reduced. The system will automatically clean up these data in a certain proportion, thereby realizing the intelligent management of equipment operation and maintenance data, improving data management efficiency, and effectively reducing storage pressure. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A schematic diagram of the structure of the equipment operation and maintenance data management system based on multimodal data fusion provided by the present invention; Figure 2 A schematic diagram of the process flow of the equipment operation and maintenance data management method based on multimodal data fusion provided by the present invention.

[0017] In the accompanying drawings, the components represented by the reference numerals are as follows: Retrospective portrait acquisition module 11, real-time portrait acquisition module 12, portrait deviation analysis module 13, threshold judgment module 14, data cleaning module 15. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0019] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0020] In the description of the present invention, the term "for example" is used to mean "used as an example, illustration or explanation". Any embodiment described as "for example" in the present invention is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present invention.

[0021] Embodiment 1, as Figure 1 As shown, the embodiment of the present invention provides an equipment operation and maintenance data management system based on multimodal data fusion, including: The retrospective portrait acquisition module 11 is used to obtain a retrospective portrait of the target dimension data of the target equipment position number at the collection moment when a preset management cycle is met, wherein the retrospective portrait includes a first service time and a first control parameter.

[0022] Specifically, when it is detected that the preset management cycle has been met, the retrospective portrait acquisition module 11 obtains the device status information at the time of data collection for the target dimension data of the target device bit number (for example, a specific data attribute of the device, which may be waveform data, non-waveform data, abnormal identification data or normal identification data, etc.). These status information constitute the retrospective portrait, including the first service time and the first control parameter. Among them, the first service time reflects the cumulative value of the operating time of the target device at that time, and the first control parameter records the control parameter setting value of the target device at that time.

[0023] By obtaining a retrospective portrait, a benchmark of the equipment’s past operating status can be established, providing a basis for subsequent comparative analysis with the real-time status.

[0024] The real-time image acquisition module 12 is used to obtain a real-time image of the target device position number, wherein the real-time image includes the second service time and the second control parameter.

[0025] Specifically, the real-time portrait acquisition module 12 collects the second service time and the second control parameter at the current moment by real-time monitoring of the operating status of the target device number. The second service time represents the cumulative value of the current service time of the target device, and the second control parameter represents the current control parameter setting value of the target device. The second service time and the second control parameter together constitute a real-time portrait reflecting the current status of the target device.

[0026] Through the real-time image acquisition module 12, it is ensured that the system can continuously obtain the latest status information of the equipment, and provide real-time data support for subsequent comparative analysis with retrospective images. By capturing the control parameters and service time of the equipment in real time, it is possible to dynamically track the changes in the equipment status, providing a basis for realizing equipment operation and maintenance data management.

[0027] The portrait deviation analysis module 13 is used to construct a portrait deviation vector according to the first service time and the first control parameter, and the second service time and the second control parameter.

[0028] Specifically, the portrait deviation analysis module 13 is used to compare and analyze the differences between the retrospective portrait and the real-time portrait, and quantify these differences into portrait deviation vectors.

[0029] The portrait deviation analysis module 13 constructs a portrait deviation vector representing the state change of the target device by calculating the difference between the corresponding parameters of the retrospective portrait and the real-time portrait, that is, calculating the difference between the first service time and the first control parameter, and the difference between the second service time and the second control parameter. The portrait deviation vector includes the change in service time and the change in control parameters, and comprehensively reflects the degree of state change of the target device from the historical collection time to the current time.

[0030] As a quantitative indicator to measure the change of equipment operation status, the portrait deviation vector provides a basis for subsequent data value assessment and storage management decisions. In this way, the dynamic change characteristics of the equipment operation status can be accurately captured, thus providing a basis for subsequent data cleaning and realizing intelligent management of equipment operation and maintenance data.

[0031] The threshold judgment module 14 is used to retrieve the target dimension data deviation module value set that satisfies the portrait deviation vector. When the variance of the target dimension data deviation module value set is greater than or equal to the variance threshold, the ratio of the first time length between the storage start time and the collection time and the second time length between the storage start time and the current time is calculated and set as the data deletion ratio.

[0032] Specifically, first, the threshold judgment module 14 retrieves and obtains the target dimension data deviation module value set that satisfies the portrait deviation vector based on the constructed portrait deviation vector; secondly, the statistical variance of the target dimension data deviation module value set is calculated; when the calculated variance value is greater than or equal to the preset variance threshold, it is determined that the target dimension data has large fluctuations, and the reference value for equipment operation and maintenance is reduced; then, the threshold judgment module 14 calculates the proportional relationship between the two time periods, that is, the ratio between the first time length from the storage start time to the data collection time and the second time length from the storage start time to the current time, and sets this ratio as the data deletion ratio.

[0033] The threshold judgment module 14 evaluates the degree of data fluctuation through variance analysis. When the fluctuation is large, it indicates that the target equipment may be worn out due to the increase in service time, resulting in a decrease in the reference value of the data stored earlier under the same control parameters. By dynamically calculating the data deletion ratio, the scope of data cleaning can be accurately controlled, which can effectively reduce storage pressure and retain data with important reference value, thereby improving the intelligence level and efficiency of equipment operation and maintenance.

[0034] The data cleaning module 15 is used to delete the target dimension data from the target device bit number operation and maintenance data starting from the storage start time according to the data deletion ratio.

[0035] Specifically, the data cleaning module 15 selectively cleans the operation and maintenance data of the target device bit number according to the data deletion ratio calculated by the threshold judgment module 14. The data cleaning module 15 receives the data deletion ratio from the threshold judgment module 14, and quantitatively deletes the target dimension data based on the storage start time. The data cleaning module 15 deletes the specified proportion of the target dimension data in chronological order, starting from the storage start time, to ensure that the data deletion operation is accurately performed.

[0036] Through the selective deletion mechanism based on data value judgment, equipment operation and maintenance data can be managed intelligently, storage space can be effectively released, and data with important reference value can be retained. Compared with the traditional method of deleting data based only on the length of time, this system realizes the accurate evaluation of data value, ensuring that data with low reference value is deleted, thereby avoiding the accidental deletion of important data, improving the intelligence level and operation and maintenance efficiency of equipment operation and maintenance data management, and reducing data storage pressure.

[0037] Furthermore, the retrospective portrait acquisition module 11 includes: A parameter acquisition unit, used to obtain the first preset control parameter to the Nth preset control parameter of the target device number; A first statistical unit, configured to count a first alienated service time of the target dimension data based on a historical sample library with the first preset control parameter as a constraint; A multi-parameter statistical unit, used for counting the Nth alienated service time of the target dimension data based on the historical sample library with the Nth preset control parameter as a constraint; The cycle calculation unit is used to extract 0.5 times the minimum value of the first alienated service time to the Nth alienated service time, and set it as the preset management cycle.

[0038] In a preferred embodiment, the retrospective portrait acquisition module 11 includes a parameter acquisition unit, a first statistical unit, a multi-parameter statistical unit and a cycle calculation unit, which work together to determine the preset management cycle: First, the parameter acquisition unit obtains all preset control parameters of the target device bit number, from the first preset control parameter to the Nth preset control parameter, so as to fully grasp the operating parameter settings of the device under different control modes. For example, for a pump device, these parameters may include operating parameters such as speed, flow, and pressure. Then, under the constraint of the first preset control parameter, the first statistical unit performs a statistical analysis on the alienated service time of the target dimension data by querying the historical sample library, and obtains the first alienated service time, thereby focusing on the historical change law of the target dimension data under a single control parameter. For example, when the pump device is running at a fixed speed of 2000 rpm, the first statistical unit analyzes the average time required for the vibration value data to deviate from the normal range, thereby obtaining the first alienated service time, such as 1500 hours.

[0039] Subsequently, the multi-parameter statistical unit performs historical sample analysis under constraints from the second preset control parameter to the Nth preset control parameter, and obtains complete statistical results from the second alienated service time to the Nth alienated service time, ensuring that the target device has a comprehensive grasp of the alienation rules under various preset control parameters. Afterwards, the cycle calculation unit compares and analyzes all alienated service times (from the first alienated service time to the Nth alienated service time), extracts the minimum value and takes 0.5 times of it as the preset management cycle. In this way, the monitoring cycle can be personalized for the target dimension data to ensure that the evaluation is performed before the data value changes significantly, effectively improving the accuracy and timeliness of equipment operation and maintenance.

[0040] By determining the preset management cycle based on multi-control parameter analysis, a dynamic monitoring mechanism for equipment operation and maintenance data is realized, avoiding the lag problem caused by fixed cycles and improving the system's sensitivity and response speed to changes in equipment status.

[0041] Furthermore, the retrospective portrait acquisition module 11 further includes: A storage threshold unit, used to obtain a disk space storage capacity threshold of the target device bit number operation and maintenance data; The portrait backtracking trigger unit is used to obtain a backtracking portrait of the target dimension data of the target device position number at the collection time when the amount of operation and maintenance data of the target device position number is greater than or equal to the disk space storage capacity threshold.

[0042] In an optional implementation, the retrospective portrait acquisition module 11 includes a storage threshold unit and a portrait retrospective trigger unit, which is used to trigger the retrospective portrait acquisition process based on storage pressure.

[0043] The storage threshold unit is responsible for monitoring and obtaining the disk space storage capacity threshold of the target equipment bit number operation and maintenance data. For example, a pump device sets a storage capacity threshold of 10GB, and a valve device group on a production line sets an overall storage capacity threshold of 50GB. The portrait backtracking trigger unit implements an intelligent triggering mechanism based on storage pressure. When the portrait backtracking trigger unit detects that the amount of operation and maintenance data of the target equipment bit number reaches or exceeds the preset disk space storage capacity threshold, it automatically starts the backtracking portrait acquisition process to obtain the backtracking portrait of the target dimension data of the target equipment bit number at the time of collection. For example, when the operation and maintenance data of a pump device accumulates to 10GB and reaches its preset threshold of 10GB, the backtracking portrait of the vibration data of the pump device at the time of historical collection is automatically obtained.

[0044] The trigger mechanism based on storage pressure complements the management method based on time cycle to form a comprehensive operation and maintenance data management strategy. By monitoring storage capacity in real time and triggering the data analysis process when the disk space storage capacity threshold is reached, storage pressure issues can be responded to in a timely manner to avoid system performance degradation caused by excessive data accumulation, while ensuring that the data cleaning process is based on a scientific assessment of data value rather than a simple chronological order.

[0045] Furthermore, the first statistical unit includes: A data retrieval subunit, configured to retrieve from the historical sample library a plurality of underlying perception attribute record characteristic values ​​and a plurality of first service time record values ​​that correspond one to one and satisfy the first preset control parameter when the target dimension data is an underlying perception attribute; The deviation calculation subunit is used to perform pairwise deviation analysis on a plurality of one-to-one corresponding underlying perception attribute record characteristic values ​​and a plurality of first service duration record values ​​to obtain a set of deviation modulus values ​​of the underlying perception attribute record characteristic values ​​and a set of deviation modulus values ​​of the first service duration record values; A feature screening subunit extracts, from the first service time record value deviation modulus value set, a first service time record value selected deviation modulus value set whose underlying perception attribute record feature value deviation modulus value set is greater than or equal to a predefined record feature value deviation modulus value threshold; The mode evaluation subunit is used to perform mode evaluation on the selected deviation modulus value set of the first service time record value to obtain the first alienated service time.

[0046] In a preferred embodiment, when the target dimension data is the underlying perceptual attribute, the first statistical unit is used to accurately calculate the alienated service time through a data retrieval subunit, a deviation calculation subunit, a feature screening subunit and a mode evaluation subunit.

[0047] When the target dimension data is the underlying perception attribute (such as direct measurement values ​​such as temperature, pressure, vibration, etc.), the data retrieval subunit retrieves data pairs that meet the first preset control parameter conditions from the historical sample library. These data pairs include one-to-one corresponding underlying perception attribute record characteristic values ​​and several first service time record values. For example, when the first preset control parameter is "speed 2000 rpm", all vibration value records of equipment running at this speed and the corresponding service time records are retrieved. Then, the deviation calculation subunit performs a pairwise comparative analysis on the retrieved data pairs. Specifically, the deviation calculation subunit calculates the difference between any two groups of data to form two deviation modulus value sets, namely, the deviation modulus value set of the underlying perception attribute record characteristic value and the deviation modulus value set of the first service time record value. For example, the difference between any two measured vibration values ​​and the corresponding service time difference are calculated.

[0048] Next, the feature screening subunit extracts the items whose corresponding underlying perceptual attribute record feature value deviation modulus is greater than or equal to the predefined record feature value deviation modulus threshold from the first service time record value deviation modulus set, forming the first service time record value selected deviation modulus set, so as to identify which service time differences are associated with significant data feature changes. For example, when the difference in vibration values ​​between two measurements exceeds 5 mm / s, the corresponding service time difference is recorded. Afterwards, the mode evaluation subunit analyzes the first service time record value selected deviation modulus set by statistical methods, determines the service time difference value with the highest frequency, and determines it as the first alienated service time. For example, if in most cases, the service time difference required for a significant change in vibration value is 1500 hours, the first alienated service time is determined to be 1500 hours.

[0049] Through the above sub-units, the alienated service time of the underlying perception attribute data under specific control parameter conditions can be objectively determined, providing an accurate basis for the subsequent calculation of the preset management cycle.

[0050] Furthermore, the first statistical unit includes: a mapper scheduling subunit, configured to schedule a target dimension data mapper bound to the high-level mapping attribute and the first preset control parameter when the target dimension data is a high-level mapping attribute, wherein the target dimension data mapper has an input low-level perception attribute; An associated data retrieval subunit, configured to retrieve from the historical sample library a number of input underlying perception attribute record feature values ​​and a number of second service time record values ​​that correspond one to one to satisfy the first preset control parameter; A feature mapping processing subunit, used to process the plurality of input bottom-level perception attribute record feature values ​​respectively through the target dimension data mapper to obtain a plurality of high-level mapping attribute feature values; The alienated duration calculation subunit is used to calculate the first alienated service duration according to the plurality of high-level mapping attribute characteristic values ​​and the plurality of second service duration record values.

[0051] In a preferred embodiment, when the target dimension data is a high-level mapping attribute, the first statistical unit accurately determines the first alienated service time through a mapper scheduling subunit, an associated data retrieval subunit, a feature mapping processing subunit and an alienated time calculation subunit.

[0052] When the target dimension data is identified as a high-level mapping attribute (such as a comprehensive index such as a health index and a remaining service life), the mapper scheduling subunit schedules a specific target dimension data mapper bound to the current high-level mapping attribute and the first preset control parameter. For example, when it is necessary to analyze the alienation law of the equipment health index under the condition of "speed 2000 rpm", the target dimension data mapper pre-trained for the scenario is called. Among them, the target dimension data mapper has an input underlying perception attribute, that is, the mapper receives multiple underlying perception parameters (such as vibration, temperature, pressure and other data) as input to generate high-level comprehensive indicators. The associated data retrieval subunit is responsible for obtaining the input data required for mapping. The associated data retrieval subunit retrieves data pairs that meet the first preset control parameter conditions from the historical sample library, including a number of input underlying perception attribute record feature values ​​(such as vibration values, temperature values ​​and other data) and a second service time record value corresponding to each other. For example, the original data such as temperature, pressure, vibration and the corresponding service time records of all equipment running at a specific speed are retrieved.

[0053] The feature mapping processing subunit performs data conversion operations. The feature mapping processing subunit inputs the retrieved several underlying perception attribute record feature values ​​into the target dimension data mapper for processing, and converts and generates several high-level mapping attribute feature values. For example, multiple data such as temperature and vibration are input into the mapper to generate high-level indicators such as equipment health index values ​​or remaining service life estimates. The alienation time calculation subunit systematically analyzes several high-level mapping attribute feature values ​​and several second service time record values. Specifically, first, the alienation time calculation subunit calculates the deviation value between any two sets of data to form a high-level mapping attribute feature value deviation modulus value set and a service time record value deviation modulus value set; secondly, from the service time record value deviation modulus value set, extract the corresponding high-level mapping attribute feature value deviation exceeding the predetermined threshold; then, perform mode evaluation on the screened service time difference data, and determine the service time difference value with the highest frequency of occurrence as the first alienated service time. For example, through the above method, it is calculated that the average service time required for the equipment health index to drop from 90 points to 70 points is 2000 hours.

[0054] Through the above sub-units, multi-source underlying data can be mapped into high-level comprehensive indicators, and then their alienation rules can be analyzed, which can more comprehensively evaluate the characteristics of equipment status changes and provide more valuable reference basis for data management decisions.

[0055] Furthermore, the embodiment of the present application also includes: An attribute configuration module, used for configuring preset input low-level perception attributes of preset high-level mapping attributes through a user terminal; A mapper training module, used to collect multiple sets of data and train the target dimension data mapper based on preset target device models and preset control parameters as constraints; A mapping binding module, used to bind the target dimension data mapper with the preset high-level mapping attributes and the preset control parameters; Among them, any one of the multiple groups of data includes: preset input bottom-level perception attribute record data and preset high-level mapping attribute record data.

[0056] In a preferred implementation, the embodiment of the present application further includes an attribute configuration module, a mapper training module and a mapping binding module to construct a target dimension data mapper, thereby supporting data processing of high-level mapping attributes.

[0057] The attribute configuration module is used to implement user-defined mapping relationship configuration. Through the user interface, the system administrator or equipment engineer can configure the preset input low-level perception attributes (such as vibration, temperature, pressure and other parameters) required for the preset high-level mapping attributes (such as equipment health index, remaining service life, etc.). For example, the user can specify that the "bearing health index" needs to collect the three low-level perception attributes of "vibration value", "temperature value" and "sound characteristics" as input. Through the attribute configuration module, it is ensured that the system can flexibly build mapping relationships according to actual equipment characteristics and user needs.

[0058] The mapper training module is responsible for building the mapper. The mapper training module first collects multiple sets of data with the preset target equipment model (such as GE-T100 gas turbine) and preset control parameters (such as 75% load operation) as constraints. Then, the model is trained on the collected multiple sets of data through machine learning algorithms such as neural networks, decision trees or support vector machines to generate the target dimension data mapper.

[0059] The mapping binding module is used to implement the index management of the mapper. The mapping binding module binds the trained target dimension data mapper with specific preset high-level mapping attributes (such as bearing health index) and preset control parameters (such as 75% load operation), establishes a corresponding relationship between the three, and stores this relationship in the system database. This binding mechanism ensures that the matching mapper can be quickly called during the analysis process, improving data processing efficiency. Among them, the multiple sets of data collected by the training target dimension data mapper have a unified structure, and each set of data contains preset input underlying perception attribute record data (such as vibration value of 3.2mm / s, temperature of 85℃, etc.) and corresponding preset high-level mapping attribute record data (such as health index of 82 points).

[0060] Through the collaborative work of the above modules, a dedicated data mapping model can be built according to equipment characteristics and operating conditions, and high-level indicators that are difficult to obtain directly can be calculated and predicted through underlying perception data, thereby improving the comprehensiveness and accuracy of equipment status assessment.

[0061] Furthermore, the threshold determination module 13 includes: A deviation decomposition unit, for the portrait deviation vector including a service time deviation vector and a control parameter deviation vector; A cloud retrieval unit is used to initiate a retrieval request to the cloud, obtain a key, encrypt the target dimension, the target device model, the service time deviation vector and the control parameter deviation vector, obtain a ciphertext and upload it to the cloud, and obtain retrieval feedback information, wherein the retrieval feedback information includes an initial target dimension data deviation modulus value set; An outlier processing unit is used to perform outlier removal on the initial target dimensional data deviation module value set to obtain the target dimensional data deviation module value set.

[0062] In a preferred embodiment, the threshold determination module 13 includes a deviation decomposition unit, a cloud retrieval unit and an outlier processing unit to achieve accurate data deviation analysis.

[0063] The deviation decomposition unit is responsible for structured decomposition of the portrait deviation vector. The deviation decomposition unit splits the overall portrait deviation vector into two sub-vectors, namely the service time deviation vector and the control parameter deviation vector. For example, when the target device changes from the historical state to the current state, it includes the service time deviation from 1000 hours to 2500 hours, and the control parameter deviation from 2000 rpm to 2200 rpm. By decomposing the portrait deviation vector into the service time deviation vector and the control parameter deviation vector, the characteristics of the device state change can be described more finely.

[0064] The cloud retrieval unit is used to implement an intelligent retrieval mechanism based on a distributed database. First, the cloud retrieval unit initiates a retrieval request to the cloud server to obtain the key; then, the key is used to encrypt the target dimension (such as vibration value), target device model, service time deviation vector, and control parameter deviation vector to generate ciphertext; then, the ciphertext is uploaded to the cloud server for retrieval and matching; after that, the retrieval feedback information returned by the cloud is received, which contains the initial target dimension data deviation module value set. Retrieval in the cloud through the cloud retrieval unit expands the sample range of data analysis and improves the accuracy of deviation analysis.

[0065] The outlier processing unit is responsible for data cleaning of the retrieval results. The outlier processing unit applies statistical analysis methods to the initial target dimension data deviation modulus value set obtained by the cloud retrieval unit from the cloud, identifies and deletes outliers that may affect the reliability of the results, and obtains an optimized target dimension data deviation modulus value set. For example, when there are obvious abnormal values ​​in the retrieved vibration value deviation data (such as a value that is much higher than other values), the outlier processing unit removes it to ensure the accuracy of the subsequent variance analysis.

[0066] Through the deviation analysis mechanism based on cloud collaboration, it is possible to use a wider range of data resources for decision support, breaking through the limitations of single device data analysis and improving the accuracy and reliability of data cleaning decisions. At the same time, the encryption processing mechanism also ensures the security of the data analysis process and protects the privacy of equipment operation and maintenance data.

[0067] Furthermore, the cloud retrieval unit includes: A cloud decryption subunit is used to decrypt the ciphertext through the cloud, obtain the target dimension, the target device model, the service time deviation vector and the control parameter deviation vector, and construct a retrieval task constraint; A node request subunit, used to initiate a retrieval request to a distributed node through the cloud to obtain a distributed node key; The encrypted retrieval sub-unit is used to encrypt the retrieval task constraints and the retrieval key according to the distributed node key, obtain the retrieval task ciphertext, send it to the distributed node, and obtain retrieval feedback information, wherein the retrieval feedback information includes the initial target dimension data deviation modulus value set.

[0068] In an optional implementation, the cloud retrieval unit includes a cloud decryption subunit, a node request subunit and an encryption retrieval subunit, which are used to implement secure retrieval of distributed data resources.

[0069] The cloud decryption subunit is responsible for decrypting the ciphertext uploaded to the cloud. The cloud decryption subunit parses the ciphertext uploaded from the local computer through the decryption service of the cloud server, and recovers the original target dimension, target device model, service time deviation vector, and control parameter deviation vector. Subsequently, a standardized retrieval task constraint is constructed based on the decrypted information to prepare for the subsequent distributed retrieval. Subsequently, the node request subunit initiates a retrieval request to multiple distributed nodes (such as equipment management systems in different factories and enterprises) through the cloud platform, and obtains the encryption key returned by each distributed node. For example, the node request subunit simultaneously sends retrieval requests to equipment operation and maintenance systems in 20 different regions, and collects their respective encryption keys to prepare for the subsequent secure data exchange. After that, the encrypted retrieval subunit uses the key obtained from the distributed node to perform secondary encryption on the retrieval task constraint and the local retrieval key to generate the retrieval task ciphertext. These retrieval task ciphertexts are sent to each distributed node respectively. When the distributed node has data that meets the retrieval conditions, the corresponding retrieval feedback information will be returned. Thereafter, the encrypted retrieval subunit summarizes all the returned information to form a complete feedback containing the initial target dimension data deviation modulus value set.

[0070] Through a multi-layer encrypted distributed retrieval mechanism, it is possible to securely integrate equipment operation and maintenance experience data from multiple factories and enterprises, greatly expanding the sample base for data analysis while ensuring the security and privacy of data from all parties. This collaborative analysis model enables accurate deviation analysis based on a large amount of operating data from similar equipment, even if the historical data of a single device is limited, thus improving the accuracy and reliability of data management decisions.

[0071] Embodiment 2, the embodiment of the present invention also provides a device operation and maintenance data management method based on multi-modal data fusion, such as Figure 2As shown, including: When the preset management cycle is met, a retrospective portrait of the target dimension data of the target equipment number at the collection time is obtained, wherein the retrospective portrait includes the first service time and the first control parameter; Obtaining a real-time portrait of the target device number, wherein the real-time portrait includes a second service time and a second control parameter; constructing a portrait deviation vector according to the first service time and the first control parameter, and the second service time and the second control parameter; Retrieve the target dimension data deviation modulus value set that satisfies the portrait deviation vector. When the variance of the target dimension data deviation modulus value set is greater than or equal to the variance threshold, calculate the ratio of the first duration between the storage start time and the acquisition time to the second duration between the storage start time and the current time, and set it as the data deletion ratio. The target dimension data is deleted from the target device bit number operation and maintenance data starting from the storage start time according to the data deletion ratio.

[0072] Furthermore, when the preset management cycle is met, a retrospective portrait of the target dimension data of the target device number at the collection time is obtained, including: Obtain a first preset control parameter of the target device number up to an Nth preset control parameter; Taking the first preset control parameter as a constraint, calculating the first alienated service time of the target dimension data based on a historical sample library; Until the Nth alienated service time of the target dimension data is counted based on the historical sample library with the Nth preset control parameter as a constraint; 0.5 times of the minimum value of the first alienated service time to the Nth alienated service time is extracted and set as the preset management period.

[0073] Furthermore, when the preset management cycle is met, a retrospective portrait of the target dimension data of the target device number at the collection time is obtained, which also includes: Obtain the disk space storage capacity threshold of the target equipment bit number operation and maintenance data; When the amount of operation and maintenance data of the target device number is greater than or equal to the disk space storage capacity threshold, a retrospective portrait of the target dimension data of the target device number at the collection time is obtained.

[0074] Furthermore, taking the first preset control parameter as a constraint, the first alienated service time of the target dimension data is counted based on the historical sample library, including: When the target dimension data is an underlying perception attribute, a plurality of underlying perception attribute record characteristic values ​​and a plurality of first service time record values ​​that correspond one to one and satisfy the first preset control parameter are retrieved from the historical sample library; Performing pairwise deviation analysis on a number of one-to-one corresponding underlying perception attribute record characteristic values ​​and a number of first service duration record values ​​to obtain a set of deviation modulus values ​​of the underlying perception attribute record characteristic values ​​and a set of deviation modulus values ​​of the first service duration record values; Extracting, from the first service time record value deviation modulus value set, a first service time record value selected deviation modulus value set whose underlying perception attribute record feature value deviation modulus value set is greater than or equal to a predefined record feature value deviation modulus value threshold value; A mode evaluation is performed on a selected deviation modulus value set of the first service duration record value to obtain the first alienated service duration.

[0075] Furthermore, taking the first preset control parameter as a constraint, the first alienated service time of the target dimension data is counted based on the historical sample library, including: When the target dimensional data is a high-level mapping attribute, scheduling a target dimensional data mapper bound to the high-level mapping attribute and the first preset control parameter, wherein the target dimensional data mapper has an input low-level perception attribute; Retrieving from the historical sample library a number of input underlying perception attribute record feature values ​​and a number of second service time record values ​​that correspond one to one to the first preset control parameter; Processing the plurality of input bottom-level perception attribute record feature values ​​respectively through the target dimension data mapper to obtain a plurality of high-level mapping attribute feature values; The first alienated service duration is calculated according to the plurality of high-level mapping attribute characteristic values ​​and the plurality of second service duration record values.

[0076] Furthermore, the target dimension data mapper construction step includes: By means of a user terminal, configuring a preset input low-level perception attribute of a preset high-level mapping attribute; Taking preset target device models and preset control parameters as constraints, collecting multiple sets of data and training the target dimension data mapper; Binding the target dimension data mapper to the preset high-level mapping attributes and the preset control parameters; Among them, any one of the multiple groups of data includes: preset input bottom-level perception attribute record data and preset high-level mapping attribute record data.

[0077] Further, a target dimension data deviation modulus set satisfying the portrait deviation vector is retrieved, and when the variance of the target dimension data deviation modulus set is greater than or equal to the variance threshold, the target dimension data is deleted from the target device position number operation and maintenance data, including: The portrait deviation vector includes a service time deviation vector and a control parameter deviation vector; Initiate a search request to the cloud, obtain a key, encrypt the target dimension, the target device model, the service time deviation vector and the control parameter deviation vector, obtain the ciphertext and upload it to the cloud, and obtain search feedback information, wherein the search feedback information includes an initial target dimension data deviation modulus value set; Outlier removal is performed on the initial target dimensional data deviation modulus value set to obtain the target dimensional data deviation modulus value set.

[0078] Furthermore, the search feedback information is obtained, including: Decrypting the ciphertext through the cloud, obtaining the target dimension, the target device model, the service time deviation vector and the control parameter deviation vector, and constructing a retrieval task constraint; Initiate a search request to the distributed node through the cloud to obtain the distributed node key; The retrieval task constraint and the retrieval key are encrypted according to the distributed node key to obtain the retrieval task ciphertext, which is sent to the distributed node to obtain retrieval feedback information, wherein the retrieval feedback information includes the initial target dimension data deviation modulus value set.

[0079] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0080] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0081] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0082] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0083] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0084] Although preferred embodiments of the present invention have been described, additional changes and modifications may occur to these embodiments once those skilled in the art understand the basic inventive concepts.

[0085] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention belong to the scope of the present invention and its equivalent technologies, the present invention is also intended to include these changes and variations.

Claims

1. Equipment operation and maintenance data management system based on multimodal data fusion, characterized by: include: A retrospective portrait acquisition module, used to obtain a retrospective portrait of the target dimension data of the target equipment number at the collection time when a preset management cycle is met, wherein the retrospective portrait includes a first service time and a first control parameter; A real-time image acquisition module, used to obtain a real-time image of the target device number, wherein the real-time image includes a second service time and a second control parameter; a portrait deviation analysis module, configured to construct a portrait deviation vector according to the first service time and the first control parameter, and the second service time and the second control parameter; A threshold judgment module is used to retrieve a target dimension data deviation modulus set that satisfies the portrait deviation vector. When the variance of the target dimension data deviation modulus set is greater than or equal to the variance threshold, the ratio of the first duration between the storage start time and the acquisition time to the second duration between the storage start time and the current time is calculated and set as the data deletion ratio. A data cleaning module is used to delete the target dimension data from the target device position number operation and maintenance data starting from the storage start time according to the data deletion ratio.

2. The system according to claim 1, characterized in that The retrospective portrait acquisition module includes: A parameter acquisition unit, used to obtain the first preset control parameter to the Nth preset control parameter of the target device number; A first statistical unit, configured to count a first alienated service time of the target dimension data based on a historical sample library with the first preset control parameter as a constraint; A multi-parameter statistical unit, used for counting the Nth alienated service time of the target dimension data based on the historical sample library with the Nth preset control parameter as a constraint; The cycle calculation unit is used to extract 0.5 times the minimum value of the first alienated service time to the Nth alienated service time, and set it as the preset management cycle.

3. The system according to claim 1, characterized in that The retrospective portrait acquisition module also includes: A storage threshold unit, used to obtain a disk space storage capacity threshold of the target device bit number operation and maintenance data; The portrait backtracking trigger unit is used to obtain a backtracking portrait of the target dimension data of the target device position number at the collection time when the amount of operation and maintenance data of the target device position number is greater than or equal to the disk space storage capacity threshold.

4. The system according to claim 2, characterized in that The first statistical unit includes: A data retrieval subunit, configured to retrieve from the historical sample library a plurality of underlying perception attribute record characteristic values ​​and a plurality of first service time record values ​​that correspond one to one and satisfy the first preset control parameter when the target dimension data is an underlying perception attribute; The deviation calculation subunit is used to perform pairwise deviation analysis on a plurality of one-to-one corresponding underlying perception attribute record characteristic values ​​and a plurality of first service duration record values ​​to obtain a set of deviation modulus values ​​of the underlying perception attribute record characteristic values ​​and a set of deviation modulus values ​​of the first service duration record values; A feature screening subunit extracts, from the first service time record value deviation modulus value set, a first service time record value selected deviation modulus value set whose underlying perception attribute record feature value deviation modulus value set is greater than or equal to a predefined record feature value deviation modulus value threshold; The mode evaluation subunit is used to perform mode evaluation on the selected deviation modulus value set of the first service time record value to obtain the first alienated service time.

5. The system according to claim 2, characterized in that The first statistical unit includes: a mapper scheduling subunit, configured to schedule a target dimension data mapper bound to the high-level mapping attribute and the first preset control parameter when the target dimension data is a high-level mapping attribute, wherein the target dimension data mapper has an input low-level perception attribute; An associated data retrieval subunit, configured to retrieve from the historical sample library a number of input underlying perception attribute record feature values ​​and a number of second service time record values ​​that correspond one to one to satisfy the first preset control parameter; A feature mapping processing subunit, used to process the plurality of input bottom-level perception attribute record feature values ​​respectively through the target dimension data mapper to obtain a plurality of high-level mapping attribute feature values; The alienated duration calculation subunit is used to calculate the first alienated service duration according to the plurality of high-level mapping attribute characteristic values ​​and the plurality of second service duration record values.

6. The system according to claim 5, characterized in that The system further comprises: An attribute configuration module, used for configuring preset input low-level perception attributes of preset high-level mapping attributes through a user terminal; A mapper training module, used to collect multiple sets of data and train the target dimension data mapper based on preset target device models and preset control parameters as constraints; A mapping binding module, used to bind the target dimension data mapper with the preset high-level mapping attributes and the preset control parameters; Among them, any one of the multiple groups of data includes: preset input bottom-level perception attribute record data and preset high-level mapping attribute record data.

7. The system according to claim 1, characterized in that The threshold determination module comprises: A deviation decomposition unit, for the portrait deviation vector including a service time deviation vector and a control parameter deviation vector; A cloud retrieval unit is used to initiate a retrieval request to the cloud, obtain a key, encrypt the target dimension, the target device model, the service time deviation vector and the control parameter deviation vector, obtain a ciphertext and upload it to the cloud, and obtain retrieval feedback information, wherein the retrieval feedback information includes an initial target dimension data deviation modulus value set; An outlier processing unit is used to perform outlier removal on the initial target dimensional data deviation module value set to obtain the target dimensional data deviation module value set.

8. The system according to claim 7, characterized in that The cloud retrieval unit includes: A cloud decryption subunit is used to decrypt the ciphertext through the cloud, obtain the target dimension, the target device model, the service time deviation vector and the control parameter deviation vector, and construct a retrieval task constraint; A node request subunit, used to initiate a retrieval request to a distributed node through the cloud to obtain a distributed node key; The encrypted retrieval sub-unit is used to encrypt the retrieval task constraints and the retrieval key according to the distributed node key, obtain the retrieval task ciphertext, send it to the distributed node, and obtain retrieval feedback information, wherein the retrieval feedback information includes the initial target dimension data deviation modulus value set.

9. The equipment operation and maintenance data management method based on multimodal data fusion is characterized by: The method comprises: When the preset management cycle is met, a retrospective portrait of the target dimension data of the target equipment number at the collection time is obtained, wherein the retrospective portrait includes the first service time and the first control parameter; Obtaining a real-time portrait of the target device number, wherein the real-time portrait includes a second service time and a second control parameter; constructing a portrait deviation vector according to the first service time and the first control parameter, and the second service time and the second control parameter; Retrieve the target dimension data deviation modulus value set that satisfies the portrait deviation vector. When the variance of the target dimension data deviation modulus value set is greater than or equal to the variance threshold, calculate the ratio of the first duration between the storage start time and the acquisition time to the second duration between the storage start time and the current time, and set it as the data deletion ratio. The target dimension data is deleted from the target device bit number operation and maintenance data starting from the storage start time according to the data deletion ratio.

Images