Industrial internet of things-based equipment pre-maintenance timing data analysis method and system

Abstract

The application discloses a kind of equipment pre-maintenance timing data analysis method and system based on industrial internet of things, it is related to data transmission processing technical field, including: obtaining historical record period, obtaining historical maintenance interval sequence;Obtain standard maintenance interval, correct standard maintenance interval and generate target maintenance interval;Obtain historical effective maintenance interval, obtain historical interval trend value, obtain a plurality of maintenance equipment set respectively containing a plurality of different internet of things equipment, wherein, the difference of the historical interval trend value of any two internet of things equipment in each maintenance equipment set is less than preset threshold value;According to the pre-maintenance interval sequence of each maintenance equipment set obtained according to a plurality of internet of things equipment in each maintenance equipment set, the pre-maintenance timing of a plurality of internet of things equipment in each maintenance equipment set is obtained according to the pre-maintenance interval sequence of each maintenance equipment set.The application has the advantages of accurate quantization of historical data trend, collaborative maintenance and reducing maintenance cost.

Description

Technical Field

[0001] This invention relates to the field of data transmission processing technology, and specifically to a method and system for analyzing equipment pre-maintenance time-series data based on the Industrial Internet of Things. Background Technology

[0002] In equipment maintenance within an Industrial Internet of Things (IIoT) environment, it is difficult to standardize the differentiated failure modes of clustered devices. Due to variations in the actual operating load environments of similar IoT devices deployed in the same area, the frequency of unplanned maintenance (such as post-failure maintenance) varies significantly. Existing unified maintenance strategies based on fixed intervals cannot adapt to this differentiation, leading to both under-maintenance and over-maintenance, increasing the risk of unexpected downtime and wasting operational resources. Furthermore, equipment maintenance records include scheduled maintenance, temporary maintenance after sudden failures, and preventative maintenance to prevent certain failures. Existing methods fail to effectively extract data for analysis and do not incorporate equipment lifecycle degradation into the correction, resulting in distorted failure trend analysis based on actual maintenance interval sequences, failing to accurately reflect the equipment's maintenance rate. Moreover, existing methods process data from individual devices in isolation, ignoring the inherent correlation between devices with similar failure probabilities (such as the synchronicity of failures due to linkage losses in collaborative devices on the same production line), leading to fragmented maintenance timing. This not only fails to leverage the collaborative patterns of device groups to improve prediction accuracy but also fragments operational actions, significantly increasing scheduling costs. Summary of the Invention

[0003] To address the problems of existing technologies that cannot accurately distinguish fault modes, ignore the impact of lifespan decay, and lack a pre-maintenance timing generation mechanism for clustered collaborative scheduling of converging equipment, this invention provides a method and system for analyzing equipment pre-maintenance timing data based on the Industrial Internet of Things.

[0004] A method for analyzing the pre-maintenance time-series data of devices based on the Industrial Internet of Things (IIoT) includes: obtaining the previous recording period of the current recording period and recording it as the historical record period; obtaining a sequence of historical maintenance intervals for multiple IoT devices of the same type within the historical record period; obtaining a standard maintenance interval based on the type of IoT device; correcting the standard maintenance interval based on the start time of each recorded maintenance interval in the historical maintenance interval sequence and generating a target maintenance interval corresponding to each recorded maintenance interval; obtaining historical effective maintenance intervals based on the target maintenance intervals corresponding to each recorded maintenance interval in the historical maintenance interval sequence; obtaining historical interval trend values ​​based on multiple historical effective maintenance intervals; obtaining multiple maintenance device sets, each containing multiple different IoT devices, based on the historical interval trend values ​​of each IoT device, wherein the difference between the historical interval trend values ​​of any two IoT devices within each maintenance device set is less than a preset threshold; obtaining a pre-maintenance interval sequence for each maintenance device set based on the multiple IoT devices within each maintenance device set; and obtaining the pre-maintenance time sequence for multiple IoT devices within each maintenance device set based on the pre-maintenance interval sequence for each maintenance device set.

[0005] Optionally, obtaining the pre-maintenance interval sequence for each maintenance equipment set based on multiple IoT devices within each maintenance equipment set includes: obtaining a first adjustment coefficient corresponding to the maintenance equipment set based on the historical interval trend value of each IoT device within the maintenance equipment set; obtaining a second adjustment coefficient corresponding to the maintenance equipment set based on the current time; and obtaining the pre-maintenance interval sequence for each maintenance equipment set based on the first adjustment coefficient, the second adjustment coefficient, and the standard maintenance interval.

[0006] Optionally, obtaining the first adjustment coefficient corresponding to the maintenance equipment set based on the historical interval trend value of each IoT device in the maintenance equipment set includes: if the minimum historical interval trend value of the IoT devices in the maintenance equipment set is less than zero, then the minimum adjustment ratio is obtained, and the first adjustment coefficient of the maintenance equipment set is obtained based on the minimum historical interval trend value and the minimum adjustment ratio; if the minimum historical interval trend value of the IoT devices in the maintenance equipment set is not less than zero, then the first adjustment coefficient is 1.

[0007] Optionally, obtaining the second adjustment coefficient corresponding to the maintenance device set based on the current time includes: obtaining the device usage time at the current time and obtaining the maximum lifespan of the IoT device; obtaining the second adjustment coefficient based on the device usage time and the maximum lifespan.

[0008] Optionally, correcting the standard maintenance interval and generating the target maintenance interval corresponding to each recorded maintenance interval based on the start time of each recorded maintenance interval in the historical maintenance interval sequence includes: obtaining the device usage time corresponding to the start time of each recorded maintenance interval in the historical maintenance interval sequence, and obtaining the maximum lifespan of the IoT device; obtaining the correction coefficient corresponding to each recorded maintenance interval based on the device usage time and maximum lifespan corresponding to each start time; correcting the standard maintenance interval based on the correction coefficient corresponding to each recorded maintenance interval and generating the target maintenance interval corresponding to each recorded maintenance interval.

[0009] Optionally, obtaining the historical valid maintenance interval based on the target maintenance interval corresponding to each recorded maintenance interval in the historical maintenance interval sequence includes: determining whether each recorded maintenance interval is less than its corresponding target maintenance interval; if it is less, then the recorded maintenance interval is taken as the historical valid maintenance interval.

[0010] Optionally, obtaining the historical interval trend value based on multiple historical effective maintenance intervals includes: obtaining the difference between adjacent historical effective maintenance intervals in the historical maintenance interval sequence, and summing all the differences in the historical maintenance interval sequence to obtain the historical interval trend value.

[0011] A device pre-maintenance time-series data analysis system based on the Industrial Internet of Things (IIoT) is also provided. The system includes a management platform, a sensor network platform, and an object platform connected sequentially. The management platform includes: a data acquisition module, used to acquire the previous recording period of the current recording period and record it as a historical record period, and acquire the historical maintenance interval sequence of multiple IoT devices of the same type within the historical record period; a first analysis module, used to acquire standard maintenance intervals according to the type of IoT device, correct the standard maintenance intervals according to the start time of each recorded maintenance interval in the historical maintenance interval sequence, and generate target maintenance intervals corresponding to each recorded maintenance interval; a second analysis module, used to... The system obtains historical valid maintenance intervals for each recorded maintenance interval in the maintenance interval sequence, and obtains historical interval trend values ​​based on multiple historical valid maintenance intervals. An integration module is used to obtain multiple maintenance device sets, each containing multiple different IoT devices, based on the historical interval trend values ​​of each IoT device. The difference between the historical interval trend values ​​of any two IoT devices within each maintenance device set is less than a preset threshold. A time-series prediction module is used to obtain the pre-maintenance interval sequence of each maintenance device set based on the multiple IoT devices within each maintenance device set, and obtain the pre-maintenance time sequence of multiple IoT devices within each maintenance device set based on the pre-maintenance interval sequence of each maintenance device set.

[0012] Optionally, the time-series prediction module is further configured to: obtain a first adjustment coefficient corresponding to the maintenance equipment set based on the historical interval trend value of each IoT device in the maintenance equipment set; obtain a second adjustment coefficient corresponding to the maintenance equipment set based on the current time; and obtain a pre-maintenance interval sequence for each maintenance equipment set based on the first adjustment coefficient, the second adjustment coefficient, and the standard maintenance interval.

[0013] Optionally, the time-series prediction module is further configured to: if the minimum historical interval trend value of the IoT devices in the maintenance equipment set is less than zero, obtain the minimum adjustment ratio, and obtain the first adjustment coefficient of the maintenance equipment set based on the minimum historical interval trend value and the minimum adjustment ratio; if the minimum historical interval trend value of the IoT devices in the maintenance equipment set is not less than zero, then the first adjustment coefficient is 1.

[0014] An electronic device is also provided, comprising: a memory storing a computer program thereon; and a processor for executing the computer program in the memory to implement the above-described device pre-maintenance timing data analysis method based on the Industrial Internet of Things.

[0015] A non-transitory computer-readable storage medium is also provided, on which a computer program is stored, which, when executed by a processor, implements the above-described device pre-maintenance timing data analysis method based on the Industrial Internet of Things.

[0016] The beneficial effects of this invention are reflected in:

[0017] The entire pre-maintenance time-series data analysis method based on the Industrial Internet of Things (IIoT) firstly introduces a target maintenance interval dynamically adjusted based on equipment usage time to accurately distinguish between scheduled maintenance and unplanned effective maintenance records. Combined with the cumulative trend analysis of the difference between adjacent effective maintenance intervals, it quantifies the acceleration or mitigation of actual equipment failures, addressing the problem of distorted failure trends caused by mixed maintenance. Furthermore, during the pre-maintenance interval generation stage, a dual dynamic adjustment coefficient (a first adjustment coefficient based on the overall failure trend of the equipment set and a second adjustment coefficient based on equipment usage time and maximum service life) is used to adjust the standard maintenance interval in a coordinated manner, ensuring that severely aged or deteriorating equipment receives a more compact maintenance cycle. Finally, based on the similarity of historical interval trend values, the equipment is globally optimized and clustered. Equipment with similar failure evolution patterns (especially those with mechanical linkages or environmental coupling) is dynamically grouped into a unified maintenance set. This not only utilizes the failure resonance characteristics of the equipment set to improve prediction accuracy but also integrates previously scattered maintenance work orders into batch execution tasks through collaborative scheduling, significantly reducing the complexity of operation and maintenance scheduling and decreasing the number of repeated start-ups and shutdowns of the production line. Attached Figure Description

[0018] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the accompanying drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts are not necessarily drawn to scale.

[0019] Figure 1 This is a partial flowchart of the device pre-maintenance time-series data analysis method based on the Industrial Internet of Things of the present invention;

[0020] Figure 2 This is another flowchart illustrating the device pre-maintenance time-series data analysis method based on the Industrial Internet of Things of the present invention;

[0021] Figure 3 This is a schematic diagram illustrating the steps of the device pre-maintenance time-series data analysis method based on the Industrial Internet of Things of the present invention;

[0022] Figure 4 This is a schematic diagram of part of step S5 in the device pre-maintenance time sequence data analysis method based on industrial Internet of Things of the present invention;

[0023] Figure 5 This is a schematic diagram of some steps in S51 of the device pre-maintenance time-series data analysis method based on the Industrial Internet of Things of the present invention;

[0024] Figure 6 This is a schematic diagram of part of step S52 in the device pre-maintenance time-series data analysis method based on the Industrial Internet of Things of the present invention;

[0025] Figure 7 This is a schematic diagram of part of step S2 in the device pre-maintenance time sequence data analysis method based on industrial Internet of Things of the present invention;

[0026] Figure 8 This is a schematic diagram of part of step S3 in the device pre-maintenance time sequence data analysis method based on industrial Internet of Things of the present invention;

[0027] Figure 9 This is a schematic diagram of the composition of the device pre-maintenance time-series data analysis system based on the Industrial Internet of Things of the present invention;

[0028] Figure 10 This is a schematic diagram illustrating the composition of the optimized Industrial Internet of Things (IIoT) involved in this invention.

[0029] Figure 11 This is a block diagram illustrating an electronic device according to an embodiment of the present invention.

[0030] Figure label:

[0031] 700 - Electronic device; 701 - Processor; 702 - Memory; 703 - Multimedia component; 704 - I / O interface; 705 - Communication component. Detailed Implementation

[0032] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0033] Therefore, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the invention without inventive effort are within the scope of protection of the invention.

[0034] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, the terms "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0035] like Figure 1 , Figure 2 and Figure 3 As shown, a method for analyzing equipment pre-maintenance time-series data based on the Industrial Internet of Things (IIoT) is provided. In one embodiment, the method includes:

[0036] S1. Obtain the previous recording period of the current recording period and record it as the historical record period, and obtain the historical maintenance interval sequence of multiple IoT devices of the same type within the historical record period;

[0037] S2. Obtain the standard maintenance interval according to the type of IoT device, correct the standard maintenance interval according to the start time of each recorded maintenance interval in the historical maintenance interval sequence, and generate the target maintenance interval corresponding to each recorded maintenance interval.

[0038] S3. Obtain the historical effective maintenance intervals based on the target maintenance intervals corresponding to each recorded maintenance interval in the historical maintenance interval sequence, and obtain the historical interval trend value based on multiple historical effective maintenance intervals.

[0039] S4. Based on the historical interval trend values ​​of each IoT device, obtain multiple maintenance device sets, each containing multiple different IoT devices, wherein the difference between the historical interval trend values ​​of any two IoT devices in each maintenance device set is less than a preset threshold.

[0040] S5. Obtain the pre-maintenance interval sequence of each maintenance equipment set based on the multiple IoT devices in each maintenance equipment set, and obtain the pre-maintenance timing sequence of the multiple IoT devices in each maintenance equipment set based on the pre-maintenance interval sequence of each maintenance equipment set.

[0041] In this implementation, it should be noted that in S1, a historical data source time frame is determined. Specifically, based on the current recording period (a predefined fixed time interval, such as weekly, monthly, or other business logic-defined periods), a complete recording period is traced back as the historical record period. The purpose of this design is to ensure that the time window for analyzing data remains synchronized with the current operation and is timely, avoiding the use of outdated or irrelevant historical information. For example, on an automated assembly line, if the current maintenance cycle is set to monthly evaluation, then the previous month will be automatically located as the historical record period, thereby capturing the latest equipment operation and maintenance records that have completed a full cycle, laying a consistent time foundation for subsequent differential analysis.

[0042] Furthermore, maintenance interval sequence data for the same type of equipment (such as all motors or sensors of the same model installed in a specific workshop) within these historical data periods are extracted from the Industrial Internet of Things (IIoT) platform, ensuring that all equipment is deployed within the same pre-defined geographical area (such as a complete production line or a processing unit). The maintenance interval sequence is calculated from the start time of consecutive maintenance events for each device, recording the time difference between events (such as the interval between maintenance after a sudden failure and the next maintenance). For example, on a packaging production line, dozens of encoders of the same brand regularly record maintenance operations, and maintenance sequence data for each encoder is compiled. This step integrates the common location and type characteristics of equipment within the area, overcoming the limitations of processing individual devices in isolation, and providing a unified basic dataset so that subsequent steps can more accurately identify the differences in failure frequency and maintenance patterns among clustered equipment.

[0043] In S2, firstly, the inherent standard maintenance interval is obtained based on the type of IoT device (this is a fixed preventative maintenance cycle set based on device design specifications and historical experience). Then, the key factor of device lifespan degradation is taken into consideration. Specifically, each actual maintenance record in the historical maintenance interval sequence is analyzed (each maintenance has a starting time point). By calculating the proportion of the device's accumulated runtime at that starting time point to its theoretical maximum lifespan (i.e., the device's degree of aging at that time), a correction coefficient is dynamically generated for each specific historical maintenance record point. This coefficient directly reflects the actual wear and tear state of the device at that historical moment. Finally, the originally fixed standard maintenance interval is scaled and adjusted using this time-point-related correction coefficient, thereby generating a corresponding target maintenance interval for each historical maintenance record point. This target maintenance interval is the theoretically achievable maintenance cycle benchmark for the device at its specific usage stage; it reflects the actual health condition of the device at that time and the required maintenance interval better than a fixed standard value.

[0044] Furthermore, consider several motors of the same model on the same production line. A brand-new motor might have a fixed standard maintenance interval of 30 days. However, for an older motor that has been running near its maximum lifespan (e.g., assuming a maximum lifespan of 5 years), analyzing its maintenance record from a year ago first determines the motor's operating time at the time of that maintenance (e.g., it had been running for 4 years and 8 months, reaching a high-wear stage). Based on this high usage rate, a correction factor significantly less than 1 (e.g., 0.5) is applied, shortening the "target maintenance interval" corresponding to that maintenance record point to 15 days (30 * 0.5), reflecting the actual need for more frequent maintenance during the high-wear period. Essentially, the core of S2 is to dynamically and personally animate fixed standard values, associating each device's maintenance record at different points in its lifespan with a target maintenance interval that considers the wear state at that time. This baseline serves as a key basis for subsequent steps to distinguish between planned and unplanned maintenance.

[0045] In S3, firstly, based on the target maintenance interval generated in S2, valid maintenance records reflecting unplanned events are filtered out. Specifically, the actual maintenance interval value in the historical maintenance interval sequence of each device is evaluated one by one: if the maintenance interval of a certain record is shorter than the target maintenance interval corresponding to that record point (i.e., unplanned maintenance occurred before the device reached the maintenance cycle it should have for its current life stage), then this maintenance is determined to be valid maintenance driven by sudden failure or unexpected wear and tear (such as temporary repairs after a failure or preventive maintenance triggered by abnormal conditions). Through this mechanism, periodic preventive maintenance records are accurately separated (because periodic maintenance intervals are usually equal to or greater than the target maintenance interval), ultimately forming a historical valid maintenance interval sequence for each device, which only contains key data reflecting the actual failure frequency. For example, in a group of similar heating furnaces on a heat treatment production line, an aging piece of equipment has three consecutive maintenance records with gradually shortening intervals (30 days, 25 days, and 20 days), while the target maintenance interval calculated based on its aging degree is 28 days. In this case, the records of 25 days and 20 days are both identified as valid maintenance intervals, while the record of 30 days (longer than 28 days) is excluded, thus truly showing the trend of accelerated failure of the equipment.

[0046] Furthermore, the effective maintenance interval sequence for each device is dynamically trend-quantified. By calculating the difference between adjacent effective maintenance intervals in the sequence (i.e., the later interval minus the previous interval) and summing all differences, the historical interval trend value for that device is obtained. This value clearly reveals the direction of change in the device's failure frequency: if the accumulated result is negative, it indicates that the effective maintenance interval is shortening successively (e.g., a difference sequence of -5 days, -5 days), reflecting that the device failure is accelerating; if the accumulated result is positive (e.g., a difference sequence of +3 days, +2 days), it indicates that the failure frequency is gradually decreasing.

[0047] In S4, clustering is performed by quantifying the fault evolution characteristics of the devices. Specifically, based on the historical interval trend value of each IoT device calculated in S3 (reflecting the accelerating or decelerating trend of device fault frequency), a preset difference threshold (e.g., 2 days) is used as the clustering criterion: all devices are traversed, and devices with trend value differences less than this threshold are dynamically grouped into the same maintenance device set. This process ensures that devices within each set have highly similar fault change characteristics—for example, devices in the same group may all show a continuous increase in fault frequency (negative trend values ​​converge) or synchronously tend to stabilize (positive trend values ​​converge). A globally optimal matching strategy is used during grouping, and the differences within the group are minimized through multiple iterative adjustments, ultimately forming multiple mutually exclusive cluster units.

[0048] Furthermore, dynamic collaborative grouping driven by fault evolution patterns has been implemented. The division of maintenance equipment sets directly reflects the implicit correlation loss patterns between equipment: conveyor belt motors and drive gearboxes on the same production line bearing the same linkage load, despite being installed in different locations, will be automatically grouped into the same set because their fault acceleration trend value due to linkage loss is -15±1. This enables subsequent maintenance scheduling to be collaboratively optimized based on the resonance characteristics of equipment faults: equipment in the same group will be assigned synchronized maintenance sequences, thereby reducing the fragmented cost of operation and maintenance while avoiding the risk of chain shutdowns caused by asynchronous failures of collaborative equipment. For example, in a certain refining and chemical production line, five parallel pumps are grouped together due to their similar corrosion rates, and their pre-maintenance times will be forcibly aligned to the same window period to avoid forcing the entire production line to operate at reduced frequency due to a sudden failure of a single pump.

[0049] In S5, a collaboratively optimized pre-maintenance strategy is generated. First, dual dynamic adjustment coefficients are calculated for each device set: the standard maintenance interval is dynamically adjusted based on the overall failure trend of all IoT devices within the set (first adjustment coefficient) and lifespan depletion (second adjustment coefficient). Specifically, if all devices in a device set show a slowing failure trend, the standard maintenance interval is shortened only appropriately based on the lifespan depletion ratio; if at least one device in the set shows an accelerating failure trend, an additional adjustment is made—the compression ratio of the maintenance interval is calculated based on the severity of the most severely affected device, while ensuring that it does not fall below a preset safety lower limit. Finally, the adjusted maintenance intervals are sequentially combined to form a pre-maintenance interval sequence.

[0050] Furthermore, the dynamically adjusted pre-maintenance interval sequence is transformed into a concrete and executable collaborative maintenance schedule. Based on the end timestamp of the last maintenance for each device in the equipment set, new strictly aligned intervals are generated for all devices according to the order of the obtained pre-maintenance interval sequence, thus obtaining a pre-maintenance sequence including multiple specific maintenance time points. This process can choose to forcibly unify the maintenance windows of devices in the same group. For example, in a conveyor belt group of an automotive welding line with 7 devices: device 1's last maintenance ended on Monday, and device 2's ended on Wednesday, but the next maintenance window will be uniformly set to Wednesday + the new interval (e.g., next Monday 5 days later) based on the largest timestamp in the group (e.g., Wednesday for device 2), and all subsequent maintenance plans will be adjusted synchronously.

[0051] In summary, the entire pre-maintenance time-series data analysis method based on the Industrial Internet of Things (IIoT) firstly introduces a target maintenance interval dynamically adjusted based on equipment usage time to accurately distinguish between scheduled maintenance and unplanned effective maintenance records. Combined with the cumulative trend analysis of the difference between adjacent effective maintenance intervals, it quantifies the acceleration or mitigation of actual equipment failures, addressing the problem of distorted failure trends caused by mixed maintenance. Furthermore, during the pre-maintenance interval generation stage, a dual dynamic adjustment coefficient (a first adjustment coefficient based on the overall failure trend of the equipment set and a second adjustment coefficient based on equipment usage time and maximum service life) is used to adjust the standard maintenance interval in a coordinated manner, ensuring that severely aged or deteriorating equipment receives a more compact maintenance cycle. Finally, based on the similarity of historical interval trend values, global optimization clustering is performed on the equipment, dynamically grouping equipment with similar failure evolution patterns (especially those with mechanical linkages or environmental coupling) into a unified maintenance set. This not only utilizes the failure resonance characteristics of the equipment set to improve prediction accuracy but also integrates previously scattered maintenance work orders into batch execution tasks through collaborative scheduling, significantly reducing the complexity of operation and maintenance scheduling and decreasing the number of repeated start-ups and shutdowns of the production line.

[0052] like Figure 2 and Figure 4 As shown, in one embodiment, S5, obtaining the pre-maintenance interval sequence of each maintenance equipment set based on multiple IoT devices within each maintenance equipment set includes:

[0053] S51. Obtain the first adjustment coefficient corresponding to the maintenance equipment set based on the historical interval trend value of each IoT device in the maintenance equipment set;

[0054] S52. Obtain the second adjustment coefficient corresponding to the maintenance equipment set based on the current time.

[0055] S53. Obtain the pre-maintenance interval sequence for each maintenance equipment set based on the first adjustment coefficient, the second adjustment coefficient, and the standard maintenance interval.

[0056] In this embodiment, it should be noted that in S51, the historical interval trend values ​​of all devices in the equipment set are checked, especially the worst trend value (minimum value). If it is found that the equipment set has an accelerated deterioration risk (minimum value < 0), a first adjustment coefficient (< 1) for compressing the interval is calculated based on this worst trend value. This aims to proactively shorten subsequent maintenance intervals to prevent risks, while ensuring that the minimum safety threshold is not lowered. If there is no deterioration risk (minimum value ≥ 0), adjustment is avoided, and the first adjustment coefficient is equal to 1.

[0057] In S52, the inherent reliability decline of a set of equipment due to natural service life is considered. It calculates the proportion of the average service life of the set of equipment to its maximum design service life. As the service life of the set of equipment increases (the proportion increases), an aging attenuation coefficient (<1) is applied to progressively and linearly shorten the maintenance interval according to the degree of aging, in order to cope with the potential random failure risk caused by aging.

[0058] In S53, a pre-maintenance interval sequence is collaboratively generated. Using the standard maintenance interval as an initial baseline, it is simultaneously integrated with a first adjustment factor and a second adjustment factor to calculate a new maintenance interval value. This new value represents the optimal preventative maintenance cycle length for the equipment set under its current operating state and lifecycle stage. This new maintenance interval value is used as a new interval point in the sequence, and this process is repeated to generate the entire sequence. Ultimately, these dynamically adjusted interval values ​​are arranged sequentially to form the pre-maintenance interval sequence for the equipment set over a future period. This sequence responds to the urgent needs of the highest-risk equipment while also taking into account the aging effects of the entire equipment set over time, representing a highly personalized and dynamically adaptable maintenance baseline.

[0059] like Figure 2 and Figure 5 As shown, in one embodiment, obtaining the first adjustment coefficient corresponding to the maintenance equipment set in S51 based on the historical interval trend values ​​of each IoT device within the maintenance equipment set includes:

[0060] S511. If the minimum historical interval trend value of the IoT devices in the maintenance equipment set is less than zero, then obtain the minimum adjustment ratio, and obtain the first adjustment coefficient of the maintenance equipment set based on the minimum historical interval trend value and the minimum adjustment ratio.

[0061] S512. If the minimum historical interval trend value of the centralized IoT devices in the maintenance equipment is not less than zero, then the first adjustment coefficient is 1.

[0062] In this embodiment, it should be noted that in S511, the overall trend of fault evolution of all equipment within the maintenance equipment set is examined, with particular attention paid to the most severe deterioration signal (i.e., the minimum value of the historical interval trend value of all equipment in the equipment set). If this minimum value is less than zero (indicating that at least one equipment exhibits a continuous acceleration in the frequency of faults), the entire equipment set is considered to be in a high-risk state. At this point, proactive intervention is implemented, and a compression coefficient (first adjustment coefficient) is calculated based on the severity of this most severe deterioration (the magnitude of the negative value). This aims to significantly shorten subsequent standard maintenance intervals, enabling more frequent preventative maintenance to prevent sudden equipment failures due to accelerated deterioration. Simultaneously, a minimum adjustment ratio is set as a safety baseline to ensure that the compressed maintenance intervals are not excessively frequent, thus wasting resources. For example, if most equipment in an equipment set has a stable trend, but one critical equipment exhibits a significantly deteriorated trend value (severe negative value), a compression coefficient will be calculated based on this weak link equipment, resulting in a substantial reduction in the maintenance intervals of the entire equipment set.

[0063] In S512, if this minimum value is not less than zero, it means that the entire set of devices has not continued to deteriorate and the failure frequency is stable or slowed down. In this case, no additional risk compression is required, and the first adjustment coefficient is set to 1.

[0064] like Figure 2 and Figure 6 As shown, in one embodiment, obtaining the second adjustment coefficient corresponding to the maintenance equipment set based on the current time in S52 includes:

[0065] S521. Obtain the device usage time at the current moment and the maximum lifespan of the IoT device based on the current moment.

[0066] S522. Obtain the second adjustment coefficient based on the equipment usage time and maximum service life.

[0067] In this embodiment, it should be noted that in S521, the potential reliability decline caused by natural aging of the equipment set is further considered. It calculates the proportion of the average usage time of the equipment set to its maximum designed service life. As the usage time of the equipment increases (the proportion increases), the overall aging and wear of the equipment intensifies, and the inherent reliability decreases. Even if the failure trend does not show accelerated deterioration, more frequent maintenance is required than for new equipment to prevent aging-related random failures.

[0068] In S522, an aging degradation coefficient (second adjustment coefficient) that is consistently less than 1 is generated based on this aging ratio, causing the pre-maintenance interval to decrease linearly and gradually as the average service life of the equipment set increases. For example, a set of equipment whose average service time is close to half of its design life will have a shorter maintenance interval than that of brand-new equipment, even if the equipment set does not currently show a significant specific deterioration trend.

[0069] It should also be noted that the pre-maintenance interval sequence obtained from multiple IoT devices within each maintenance device set in S5 can be represented as:

[0070]

[0071] ;in, Let be the value of the i-th maintenance interval in the pre-maintenance interval sequence of the k-th maintenance equipment set. For standard maintenance intervals, The current device usage duration. The maximum lifespan of IoT devices. Let be the number of IoT devices in the k-th maintenance equipment cluster. For the historical interval trend value of the j-th IoT device in the k-th maintenance equipment set, This is the minimum adjustment ratio.

[0072] It should also be noted that the entire expression implements three levels of adaptive adjustment. Specifically, the first level of adaptive adjustment is... This represents the basic aging degradation regulation; among which, This represents the average wear and tear rate of the equipment set (e.g., 0.8 if the equipment has reached 80% of its maximum lifespan). Due to the asymptotic nature of material fatigue, the linear attenuation factor accurately simulates lifespan decay, while also incorporating a coefficient... As an adjustment threshold, it directly avoids over-maintenance after full aging, assuming no coefficient. Then the original term is When fully aged ( If the attenuation factor is zero, the maintenance interval will eventually approach 0.

[0073] Furthermore, the second-level adaptive adjustment is as follows: The historical interval trend value of the equipment with the most severe deterioration within the equipment set is used for exponential decay adjustment. When When the value is negative (fault acceleration), The smaller, the better The smaller the value, the more drastic the compression of maintenance intervals. The exponential function amplifies the deterioration signals of high-risk equipment, conforming to the nonlinear acceleration law of fault evolution (such as the exponential increase in failure rate in the later stages of bearing wear). This solves the problem that existing linear corrections cannot capture the risk of sudden equipment failures, leading to delayed maintenance of high-risk equipment.

[0074] Furthermore, the third-level adaptive adjustment is... ,in, This is the minimum adjustment ratio (e.g., 0.4), when The calculated value is less than At that time, forced removal Value. Preventing extreme degradation of equipment, that is... When the value is too low, the maintenance interval approaches zero. Limiting resource allocation to a minimum (e.g., the interval must not be less than 40% of the standard value) helps prevent uncontrolled operation and maintenance resources from deteriorating due to extreme degradation of a single device, ensuring reasonable resource allocation.

[0075] Furthermore, the expression is through and Implement differentiated strategy generation. In a stable state, Only basic aging degradation adjustment is applied. When the condition deteriorates, that is... This, coupled with risk amplification mechanisms and safety thresholds, means that existing methods cannot distinguish between stable and high-risk equipment, leading to the ineffectiveness of homogenized maintenance strategies.

[0076] In summary, the entire expression enables maintenance intervals to adapt to individual risks (focusing on the worst-performing equipment), satisfy group collaboration, and take into account resource constraints, thus fundamentally solving the problem of unified handling of differentiated failure modes.

[0077] like Figure 1 and Figure 7 As shown, in one embodiment, step S2, which involves correcting the standard maintenance interval based on the start time of each recorded maintenance interval in the historical maintenance interval sequence and generating the target maintenance interval corresponding to each recorded maintenance interval, includes:

[0078] S21. Obtain the device usage time corresponding to the start time point of each recorded maintenance interval in the historical maintenance interval sequence, and obtain the maximum lifespan of the IoT device.

[0079] S22. Obtain the correction coefficient corresponding to each record maintenance interval based on the equipment usage time and maximum service life corresponding to each start time point;

[0080] S23. Correct the standard maintenance interval according to the correction coefficient corresponding to each record maintenance interval and generate the target maintenance interval corresponding to each record maintenance interval.

[0081] In this embodiment, it should be noted that in S21, the cumulative runtime of the equipment at the start time of each maintenance operation (i.e., how long the equipment has been used when the maintenance occurs) is calculated, and the maximum design lifespan of the equipment model is obtained. The purpose is to anchor the specific life cycle stage of the equipment at the time of each maintenance, laying a time-space benchmark for subsequent personalized modifications.

[0082] In S22, a correction factor is calculated for each historical maintenance record point based on the equipment's status at the time of positioning in S21 (mainly the percentage of lifespan consumed at that time). This factor dynamically reflects the degree to which the standard maintenance interval should be compressed given the equipment's usage duration at that time. For example, for a valve in a highly corrosive environment that has been used near its maximum lifespan, the system will generate a strong correction factor much less than 1 (e.g., 0.6).

[0083] In step S23, the correction coefficient calculated in S22 is used to dynamically adjust the standard maintenance interval of the equipment, generating the target maintenance interval corresponding to the historical maintenance record point. This is equivalent to establishing a target maintenance interval that reflects the actual needs of the equipment at that time for each historical maintenance operation. The significance of the target maintenance interval lies in identifying valid maintenance records that reflect real faults, thereby providing an accurate data source for subsequent fault trend analysis.

[0084] like Figure 1 and Figure 8 As shown, in one embodiment, obtaining the historical valid maintenance interval in S3 based on the target maintenance interval corresponding to each recorded maintenance interval in the historical maintenance interval sequence includes:

[0085] S31. Determine whether the maintenance interval of each record is less than its corresponding target maintenance interval. If it is less, then the maintenance interval of that record is taken as the historical valid maintenance interval.

[0086] In this embodiment, it should be noted that in S31, the target maintenance interval generated in S23 is used as the criterion to scan the actual maintenance records of each device. When an actual maintenance interval is shorter than the target interval at that time, it is determined to be a valid maintenance event. For example, if the target interval for a centrifugal pump at a certain maintenance point should be 200 hours, but maintenance is only required after 150 hours of operation due to bearing wear, then this event is identified as valid maintenance. Through this personalized benchmark filtering, regular maintenance records are eliminated, and only maintenance data driven by sudden failures and abnormal wear are retained.

[0087] like Figure 1 and Figure 8 As shown, in one embodiment, obtaining historical interval trend values ​​based on multiple historical valid maintenance intervals in S3 includes:

[0088] S32. Obtain the difference between adjacent historical effective maintenance intervals in the historical maintenance interval sequence, and sum all the differences in the historical maintenance interval sequence to obtain the historical interval trend value.

[0089] In this embodiment, it should be noted that in S32, a historical interval trend value is generated by calculating the change in the time difference between adjacent effective maintenance intervals (the difference between the last interval and the previous interval) and accumulating the sum of the differences over all consecutive time periods. A positive trend value indicates an extended maintenance interval (mitigation of failure), while a negative value indicates a shortened interval (accelerated failure). For example, if a reactor has three effective maintenance intervals of 160, 130, 150, 120, and 140 hours, its difference sequence is -30, 20, -30, and 20 hours. The strong negative trend of the accumulated value of -20 hours directly quantifies the worsening of the failure. This cumulative difference mechanism accurately captures the degree of change in the frequency of equipment failures.

[0090] like Figure 9 As shown, a device pre-maintenance time-series data analysis system based on the Industrial Internet of Things is also provided. The system includes a management platform, a sensor network platform, and an object platform that are sequentially connected in communication. The management platform includes:

[0091] The data acquisition module is used to acquire the previous recording period of the current recording period and record it as the historical record period, and to acquire the historical maintenance interval sequence of multiple IoT devices of the same type within the historical record period;

[0092] The first analysis module is used to obtain the standard maintenance interval according to the type of IoT device, correct the standard maintenance interval according to the start time of each recorded maintenance interval in the historical maintenance interval sequence, and generate the target maintenance interval corresponding to each recorded maintenance interval.

[0093] The second analysis module is used to obtain historical effective maintenance intervals based on the target maintenance intervals corresponding to each recorded maintenance interval in the historical maintenance interval sequence, and to obtain historical interval trend values ​​based on multiple historical effective maintenance intervals.

[0094] An integrated module is used to obtain multiple maintenance device sets, each containing multiple different IoT devices, based on the historical interval trend values ​​of each IoT device. The difference between the historical interval trend values ​​of any two IoT devices in each maintenance device set is less than a preset threshold.

[0095] The timing prediction module is used to obtain the pre-maintenance interval sequence of each maintenance equipment set based on multiple IoT devices within each maintenance equipment set, and to obtain the pre-maintenance timing sequence of multiple IoT devices within each maintenance equipment set based on the pre-maintenance interval sequence of each maintenance equipment set.

[0096] In one implementation, the time-series prediction module is further configured to: obtain a first adjustment coefficient corresponding to the maintenance equipment set based on the historical interval trend value of each IoT device in the maintenance equipment set; obtain a second adjustment coefficient corresponding to the maintenance equipment set based on the current time; and obtain a pre-maintenance interval sequence for each maintenance equipment set based on the first adjustment coefficient, the second adjustment coefficient, and the standard maintenance interval.

[0097] In one implementation, the time-series prediction module is further configured to: if the minimum historical interval trend value of the IoT devices in the maintenance equipment set is less than zero, obtain the minimum adjustment ratio, and obtain the first adjustment coefficient of the maintenance equipment set based on the minimum historical interval trend value and the minimum adjustment ratio; if the minimum historical interval trend value of the IoT devices in the maintenance equipment set is not less than zero, then the first adjustment coefficient is 1.

[0098] In this embodiment, it should be noted that the specific method of performing the operation in the above-mentioned equipment pre-maintenance time-series data analysis system based on the Industrial Internet of Things has been described in detail in the embodiments of the equipment pre-maintenance time-series data analysis method based on the Industrial Internet of Things, and will not be elaborated here.

[0099] It should also be noted that the entire equipment pre-maintenance time-series data analysis system based on the Industrial Internet of Things can be applied to the optimized Industrial Internet of Things. Figure 9 This is a schematic diagram of the composition of the device pre-maintenance timing data analysis system based on the Industrial Internet of Things of the present invention. Figure 10 This is a schematic diagram illustrating the optimized industrial Internet of Things (IIoT) involved in this invention. (See diagram below.) Figure 9 and Figure 10 As shown, the optimized Industrial Internet of Things (IIoT) includes a user platform, a service platform, a management platform, a sensor network platform, and an object platform that establish communication in sequence.

[0100] The user platform is configured to provide front-end services to users; users obtain the necessary perception service information through the user platform, process the perception service information, and transform it into user perception information; users analyze the user perception information and make corresponding decisions based on their own wishes, and transform the user perception information into user control information through the corresponding information system and send it to the service platform, thereby demonstrating the user's corresponding service needs and wishes.

[0101] The physical entities of the user platform include various user terminals, such as mobile phones, computers, and dedicated terminals, which provide user services through integration with user information system software.

[0102] The service platform is configured as an API server or other server used to establish communication between the management platform and the user platform to achieve corresponding functions; the physical entity of the service platform includes various servers.

[0103] The management platform is configured to perform at least one of the following: device operation status monitoring and management, data monitoring and management, device parameter management, and lifecycle management; the management platform is the overall operation platform for the Internet of Things, which may include various management sub-platforms, with different management sub-platforms performing different management tasks; the physical entities of the management platform include various servers.

[0104] The sensor network platform is configured to perform at least one of the following functions: network management, command management, device status management, data protocol management, data parsing, data classification, data transmission monitoring, and data transmission security management. The sensor network platform provides functions such as data communication, transmission, parsing, identification, and classification, avoiding the direct aggregation of data from various object platforms onto the management platform, which would otherwise result in data redundancy and low data processing efficiency. The physical entities of the object platforms include various gateways, edge computing devices, etc.

[0105] The object platform is configured to perform specific production control, detection, measurement and other production tasks; the physical entities of the production objects include various production equipment, sensors and so on.

[0106] Figure 11 This is a block diagram of an electronic device illustrating a device pre-maintenance time-series data analysis method based on the Industrial Internet of Things (IIoT) according to an exemplary embodiment. Figure 11 As shown, the electronic device 700 may include: a processor 701 and a memory 702. The electronic device 700 may also include one or more of a multimedia component 703, an I / O interface 704 (input / output interface), and a communication component 705.

[0107] The processor 701 controls the overall operation of the electronic device 700 to complete all or part of the steps in the aforementioned device pre-maintenance timing data analysis method based on the Industrial Internet of Things. The memory 702 stores various types of data to support the operation of the electronic device 700. This data may include, for example, instructions for any application or method operating on the electronic device 700, and application-related data such as contact data, sent and received messages, images, audio, video, etc. The memory 702 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. Multimedia component 703 may include a screen and an audio component. The screen may be, for example, a touchscreen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signals may be further stored in memory 702 or transmitted via communication component 705. The audio component also includes at least one speaker for outputting audio signals. I / O interface 704 provides an interface between processor 701 and other interface modules, such as a keyboard, mouse, buttons, etc. These buttons may be virtual or physical buttons. Communication component 705 is used for wired or wireless communication between the electronic device 700 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, 4G, NB-IoT, eMTC, or other 5G technologies, or combinations thereof, is not limited here. Therefore, the corresponding communication component 705 may include: a Wi-Fi module, a Bluetooth module, an NFC module, etc.

[0108] In an exemplary embodiment, the electronic device 700 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above-described device pre-maintenance timing data analysis method based on the Industrial Internet of Things.

[0109] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided. When executed by a processor, these program instructions implement the steps of the above-described industrial Internet of Things (IIoT)-based device pre-maintenance timing data analysis method. For example, the computer-readable storage medium may be the memory 702 including the program instructions, which may be executed by the processor 701 of the electronic device 700 to complete the above-described industrial Internet of Things (IIoT)-based device pre-maintenance timing data analysis method.

[0110] In another exemplary embodiment, a computer program product is also provided, the computer program product comprising a computer program executable by a programmable device, the computer program having a code portion for performing the above-described device pre-maintenance timing data analysis method based on the Industrial Internet of Things when executed by the programmable device.

[0111] The preferred embodiments of this disclosure have been described in detail above with reference to the accompanying drawings. However, this disclosure is not limited to the specific details of the above embodiments. Within the scope of the technical concept of this disclosure, various simple modifications can be made to the technical solutions of this disclosure, and these simple modifications all fall within the protection scope of this disclosure.

[0112] It should also be noted that the various specific technical features described in the above embodiments can be combined in any suitable manner without contradiction. To avoid unnecessary repetition, this disclosure will not describe the various possible combinations separately.

[0113] Furthermore, various different embodiments of this disclosure can be combined in any way, as long as they do not violate the spirit of this disclosure, they should also be regarded as the content disclosed in this disclosure.

[0114] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be covered within the scope of the claims and specification of the present invention.

Claims

1. A method for analyzing equipment pre-maintenance time-series data based on the Industrial Internet of Things, characterized in that, include: Obtain the previous recording period of the current recording period and record it as the historical record period; and obtain the historical maintenance interval sequence of multiple IoT devices of the same type within the historical record period. Obtain the standard maintenance interval based on the type of IoT device, correct the standard maintenance interval based on the start time of each recorded maintenance interval in the historical maintenance interval sequence, and generate the target maintenance interval corresponding to each recorded maintenance interval. The historical effective maintenance interval is obtained by identifying the target maintenance interval corresponding to each recorded maintenance interval in the historical maintenance interval sequence, and the historical interval trend value is obtained based on multiple historical effective maintenance intervals. Based on the historical interval trend values ​​of each IoT device, multiple maintenance device sets are obtained, each containing multiple different IoT devices. The difference between the historical interval trend values ​​of any two IoT devices in each maintenance device set is less than a preset threshold. The first adjustment coefficient corresponding to the maintenance equipment set is obtained based on the historical interval trend value of each IoT device in the maintenance equipment set; the second adjustment coefficient corresponding to the maintenance equipment set is obtained based on the current time; and the pre-maintenance interval sequence of each maintenance equipment set is obtained based on the first adjustment coefficient, the second adjustment coefficient and the standard maintenance interval. The pre-maintenance timing sequence of multiple IoT devices within each maintenance device set is obtained based on the pre-maintenance interval sequence of each maintenance device set.

2. The method for analyzing equipment pre-maintenance time-series data based on the Industrial Internet of Things according to claim 1, characterized in that, The step of obtaining the first adjustment coefficient corresponding to the maintenance equipment set based on the historical interval trend values ​​of each IoT device in the maintenance equipment set includes: If the minimum historical interval trend value of the IoT devices in the maintenance equipment set is less than zero, then the minimum adjustment ratio is obtained, and the first adjustment coefficient of the maintenance equipment set is obtained based on the minimum historical interval trend value and the minimum adjustment ratio. If the minimum historical interval trend value of the centralized IoT devices in the maintenance equipment is not less than zero, then the first adjustment coefficient is 1.

3. The method for analyzing equipment pre-maintenance time-series data based on the Industrial Internet of Things according to claim 1, characterized in that, The second adjustment coefficient corresponding to the maintenance equipment set obtained based on the current time includes: Get the device usage time at the current moment and the maximum lifespan of the IoT device; The second adjustment coefficient is obtained based on the equipment's usage time and maximum service life.

4. The method for analyzing equipment pre-maintenance time-series data based on the Industrial Internet of Things according to claim 1, characterized in that, The step of correcting the standard maintenance interval based on the start time of each recorded maintenance interval in the historical maintenance interval sequence and generating the target maintenance interval corresponding to each recorded maintenance interval includes: Obtain the device usage time corresponding to the start time point of each maintenance interval in the historical maintenance interval sequence, and obtain the maximum lifespan of the IoT device; The correction coefficients for each record maintenance interval are obtained based on the equipment usage time and maximum service life corresponding to each start time point. The standard maintenance interval is adjusted based on the correction coefficient corresponding to each record maintenance interval, and the target maintenance interval corresponding to each record maintenance interval is generated.

5. The method for analyzing equipment pre-maintenance time-series data based on the Industrial Internet of Things according to claim 1, characterized in that, The step of obtaining the historical valid maintenance interval based on the target maintenance interval corresponding to each recorded maintenance interval in the historical maintenance interval sequence includes: Determine whether the maintenance interval of each record is less than its corresponding target maintenance interval. If it is less, then the maintenance interval of that record is taken as the historical valid maintenance interval.

6. The method for analyzing equipment pre-maintenance time-series data based on the Industrial Internet of Things according to claim 1, characterized in that, The process of obtaining historical interval trend values ​​based on multiple historical valid maintenance intervals includes: Obtain the difference between adjacent historical effective maintenance intervals in the historical maintenance interval sequence, and sum all the differences in the historical maintenance interval sequence to obtain the historical interval trend value.

7. A device pre-maintenance time-series data analysis system based on the Industrial Internet of Things, characterized in that, The system includes a management platform, a sensor network platform, and an object platform that are sequentially connected in communication. The management platform includes: The data acquisition module is used to acquire the previous recording period of the current recording period and record it as the historical record period, and to acquire the historical maintenance interval sequence of multiple IoT devices of the same type within the historical record period; The first analysis module is used to obtain the standard maintenance interval according to the type of IoT device, correct the standard maintenance interval according to the start time of each recorded maintenance interval in the historical maintenance interval sequence, and generate the target maintenance interval corresponding to each recorded maintenance interval. The second analysis module is used to obtain historical effective maintenance intervals based on the target maintenance intervals corresponding to each recorded maintenance interval in the historical maintenance interval sequence, and to obtain historical interval trend values ​​based on multiple historical effective maintenance intervals. An integrated module is used to obtain multiple maintenance device sets, each containing multiple different IoT devices, based on the historical interval trend values ​​of each IoT device. The difference between the historical interval trend values ​​of any two IoT devices in each maintenance device set is less than a preset threshold. The timing prediction module is used to obtain the pre-maintenance interval sequence of each maintenance equipment set based on multiple IoT devices within each maintenance equipment set, and to obtain the pre-maintenance timing sequence of multiple IoT devices within each maintenance equipment set based on the pre-maintenance interval sequence of each maintenance equipment set. The time-series prediction module is also used to: obtain the first adjustment coefficient corresponding to the maintenance equipment set based on the historical interval trend value of each IoT device in the maintenance equipment set; obtain the second adjustment coefficient corresponding to the maintenance equipment set based on the current time; and obtain the pre-maintenance interval sequence of each maintenance equipment set based on the first adjustment coefficient, the second adjustment coefficient and the standard maintenance interval.

8. The equipment pre-maintenance time-series data analysis system based on the Industrial Internet of Things according to claim 7, characterized in that, The time series prediction module is also used for: If the minimum historical interval trend value of the IoT devices in the maintenance equipment set is less than zero, then the minimum adjustment ratio is obtained, and the first adjustment coefficient of the maintenance equipment set is obtained based on the minimum historical interval trend value and the minimum adjustment ratio. If the minimum historical interval trend value of the centralized IoT devices in the maintenance equipment is not less than zero, then the first adjustment coefficient is 1.

Images