Equipment operation life cycle monitoring system and method based on full link

By analyzing the equipment lifecycle and optimizing sensor deployment to improve data acquisition frequency, the problem of insufficient targeting and representativeness in traditional equipment monitoring methods has been solved, thus achieving reliable and intelligent equipment monitoring.

CN120880941AActive Publication Date: 2025-10-31NANJING XIANGTAI SYSTEM TECHNOLOGY CO LTD
View PDF 6 Cites 0 Cited by

Patent Information

Application Number
CN202511351067.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-09-22
Publication Date
2025-10-31
Estimated Expiration
2045-09-22

AI Technical Summary

Technical Problem

Traditional equipment monitoring methods lack specificity and representativeness, resulting in insufficient or excessive monitoring efforts, and failing to effectively address equipment failures at different stages of their life cycle.

Method used

By acquiring historical operation records and monitoring videos of the equipment, analyzing the equipment's lifecycle stages, and combining sensor deployment locations and data changes, the data acquisition frequency of the equipment can be optimized to achieve targeted and representative monitoring.

Benefits of technology

It achieves reliability and balance in equipment monitoring, adapts to the needs of different life cycle stages, and improves the effectiveness and intelligence level of equipment monitoring.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120880941A_ABST
    Figure CN120880941A_ABST
Patent Text Reader

Abstract

The invention discloses an equipment operation life cycle monitoring system and method based on a full link, and relates to the technical field of equipment monitoring, and the method comprises the steps: obtaining an operation record of equipment in a building site, and obtaining an operation data set of each life cycle stage; obtaining a first characteristic value of the equipment in each life cycle stage according to the operation data; deploying a sensor in the building site, obtaining a second characteristic value of each piece of equipment to the building site according to the change conditions of the sensor in the operation stage and the stop stage of the equipment, and obtaining a total target value of each piece of equipment; acquiring the current acquisition frequency when each device in the building site is monitored, calculating the reliability degree, and further obtaining the target acquisition frequency of each device in the building site. According to the invention, analysis is carried out by combining the life cycle stage of the equipment and the layout of the equipment in the building site, the reliable target acquisition frequency is obtained, the pertinence and representativeness of data acquisition are favorably met, and the monitoring strength of the equipment is balanced.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This invention relates to the field of equipment monitoring technology, specifically a system and method for monitoring the entire equipment lifecycle. Background Technology

[0002] Monitoring equipment within a building site is a core component of the efficient operation of modern smart buildings and a key tool for achieving digital building management. Visual monitoring of equipment operation helps to provide timely warnings of equipment anomalies, prevent safety accidents caused by the escalation of equipment failures, and achieve a dual guarantee of comprehensive building operation safety and a high-quality spatial experience. Equipment lifecycle stages are typically divided into break-in period, robust period, and decline period. The probability of equipment failure varies at different lifecycle stages. Traditionally, equipment monitoring involves manually setting the data collection frequency. However, due to the subjectivity of manual settings and the lack of comprehensive consideration of the equipment layout in the building site and the different lifecycle stages of each piece of equipment, the data collection lacks specificity and representativeness, leading to problems such as insufficient or excessive equipment monitoring. Summary of the Invention

[0003] The purpose of this invention is to provide a device operation lifecycle monitoring system and method based on the entire chain, so as to solve the problems raised in the prior art.

[0004] To solve the above-mentioned technical problems, the present invention provides the following technical solution: A method for monitoring the entire device lifecycle includes the following steps: Obtain historical operation records of equipment within the building site, extract the corresponding operation time and operation data from the operation records, analyze the operation time and the expected usage time of the equipment, and determine the life cycle stage of the equipment; divide the day into several time windows evenly, and obtain the operation data set corresponding to each life cycle stage based on the operation time and operation data; Obtain the normal numerical range of the operating data, extract the label set from the operating data set, and obtain the first feature value of the device in each life cycle stage based on the number of label sets in each life cycle stage. A 3D model of the building site is established, historical surveillance videos of the building site are retrieved, the number of existing sensors is obtained, and the deployment location of each sensor in the building site is obtained based on the location of personnel in the surveillance videos. Based on the changes in sensor data during the operation and shutdown phases of the equipment, the second feature value of each device for the building site is obtained. Based on the first and second feature values, the total target value corresponding to each device at present is obtained. The current acquisition frequency for monitoring each device in the building site is obtained. Based on the overall target value, the reliability of the current monitoring is obtained. Based on the reliability, the acquisition frequency of the current device is iteratively optimized to obtain the target acquisition frequency for each device in the building site. Data is then collected from the devices in the building site according to the target acquisition frequency.

[0005] Preferably, the set of runtime data corresponding to each lifecycle stage is obtained, including: The system retrieves historical operating records of the equipment, which are generated by monitoring the operating data during the equipment's operation. In the case of an air conditioner, the operating data represents power consumption. The system also retrieves the user manual of the equipment to obtain its estimated usage time. Based on the operating time corresponding to the operating records, the system determines the equipment's life cycle stage, which is divided into the break-in period, the robust period, and the decline period. Extract the running time corresponding to each running record, and take the running record whose running time within a certain time window E has a duration greater than a preset duration threshold as the target record of time window E; obtain the life cycle stage P of a certain device when the historical date is adjacent to M days, extract all records of a certain device that belong to the target record of time window E for all M historical days, collect the running data of each record, obtain a set of running data for life cycle stage P, and then obtain all sets of running data corresponding to each life cycle stage.

[0006] Here, operational data from adjacent dates that fall within the same time period of the day are grouped into a single operational data set. This is because, for air conditioners, when dates are adjacent and fall within the same time period, the set mode and temperature will not change significantly, and the power consumption of the air conditioner will not change significantly under normal circumstances. However, if there are large differences in power consumption between multiple days, it indicates that the air conditioner is unstable in the corresponding life cycle stage and has a higher probability of malfunction. The corresponding operational data set should be marked, and the probability of malfunction in each life cycle stage can be obtained by combining the number of marked sets corresponding to each life cycle stage. This is the first characteristic value obtained from the following analysis.

[0007] Preferably, the first characteristic value of the device at each stage of its life cycle is obtained, including: Obtain the normal numerical range of the device's operating data [Q1, Q2], where Q1 and Q2 are the minimum and maximum values ​​preset by the system, respectively; extract all operating data from a certain operating data set J, and calculate the variance between the operating data. If there is operating data that is not within the normal numerical range or the variance is less than the preset variance threshold, then mark the operating data set J. Collect all the tag sets corresponding to each lifecycle stage, add them up to get the total number of sets, and then divide the number of tag sets in each lifecycle stage by the total number of sets to obtain the first feature value of the device in each corresponding lifecycle stage.

[0008] Preferably, obtaining a second characteristic value for each device relative to the building site includes: Extract several surveillance images from historical surveillance videos, capture the location of personnel in the building site in each surveillance image, and mark them in a 3D model; obtain the number N of existing temperature sensors, use a clustering algorithm to aggregate the location points to obtain N target cluster points, and deploy temperature sensors at each target cluster point; All equipment in the building site is run. After a period of time, the target temperature of each temperature sensor is obtained when all temperature sensors are in a stable phase. The stable phase is defined as the period when the variance between the sensing values ​​of the temperature sensors at several moments in the time period is less than a preset variance threshold. The average value between the sensing values ​​at several moments is taken as the corresponding target temperature. Only one device S is stopped from running, and the target temperature of each temperature sensor is obtained when all temperature sensors are in a stable phase after a period of time. Therefore, the second characteristic value of device S with respect to the building site is obtained as follows: Where N is the number of temperature sensors, e is the natural constant, and B n Let A be the target temperature of the nth temperature sensor when device S is running. n The target temperature of the nth temperature sensor when device S stops is obtained, thus yielding the second characteristic value of each device for the building site.

[0009] Formula y=1-e -x It is a function of y taking values ​​from 0 to 1 when x>0, and y increases as x increases. In this scheme, when device S stops running, compared with when device S is running normally, the more the temperature sensor's sensing value changes, the greater the change value, which means that device S has a greater impact on the building site, so the second characteristic value is larger.

[0010] Preferably, obtaining the total feature value corresponding to each device at the present includes: obtaining the first target value X1 of device S based on the life cycle stage of device S, obtaining the second target value X2 of device S based on the second feature value of device S for the building site, setting the weights of the first target value X1 and the second target value X2, obtaining the total target value of device S, and obtaining the total target value corresponding to each device at the present.

[0011] Preferably, the target acquisition frequency for each device within the building site is obtained, including: Sort the devices in ascending order according to the total target value of each device in the building site, and establish a target value set; according to the acquisition frequency during the current monitoring of each device, establish a frequency set according to the device serial number, and calculate the cosine similarity between the target value set and the frequency set as the reliability of the current monitoring; If the reliability is less than the preset degree threshold, set the iteration number to 1, and obtain the numerical average value a in the target value set and the numerical average value b in the frequency set. Obtain the values A and B corresponding to a certain device S in the target value set and the frequency set, and obtain the variance between A / a and B / b as the target variance of device S. Furthermore, obtain the target variance of each device, and use the acquisition frequency of the device corresponding to the largest target variance as the adjustment frequency; If A / a > B / b, adjust the value of the adjustment frequency upward; if A / a < B / b, adjust the value of the adjustment frequency downward. The specific adjusted value is: , where k is the adjustment coefficient, 0 < k ≤ 1. According to the acquisition frequency after iteration, obtain a new frequency set, and obtain the reliability again for judgment until the iteration number is greater than the preset number threshold or the obtained reliability is not less than the degree threshold to stop the iteration, and obtain the final target acquisition frequency of each device.

[0012] The goal in this solution is to make A / a approach B / b after adjustment, so is adjusted based on (B - Y) / b = A / a (this formula is obtained according to the situation where the value of the adjustment frequency should be adjusted downward when A / a < B / b) and (B + Y) / b = A / a (this formula is obtained according to the situation where the value of the adjustment frequency should be adjusted upward when A / a > B / b), where Y is the value to be adjusted, || is to take the absolute value, and by setting the adjustment coefficient k, the adjusted value can gradually tend to the said goal according to the actual situation, increasing the adaptability and robustness of the system to the actual scenario.

[0013] A device operation life cycle monitoring system based on the full link includes an operation data set establishment module, a first eigenvalue calculation module, a total target value calculation module, and a target acquisition frequency determination module; The operation data set establishment module: is used to obtain the historical operation records of the devices in the building site, extract the operation time and operation data corresponding to the operation records, analyze the operation time and the expected service time of the devices, and judge the life cycle stage of the devices; divide a day evenly into several time windows, and obtain the operation data set corresponding to each life cycle stage according to the operation time and the operation data; First feature value calculation module: used to obtain the normal numerical range of the running data, extract the label set from the running data set, and obtain the first feature value of the device in each life cycle stage based on the number of label sets in each life cycle stage; Total target value calculation module: used to build a 3D model of the building site, retrieve historical surveillance videos of the building site, obtain the number of existing sensors, and obtain the deployment location of each sensor in the building site based on the location of personnel in the surveillance video; based on the changes in sensor data during the operation and shutdown phases of the equipment, obtain the second feature value of each device for the building site; based on the first and second feature values, obtain the total target value corresponding to each device at present. Target acquisition frequency determination module: used to obtain the acquisition frequency of each device in the building site during current monitoring, obtain the reliability of the current monitoring based on the total target value, and iteratively optimize the acquisition frequency of the current device based on the reliability to obtain the target acquisition frequency of each device in the building site, and collect data from the device in the building site according to the target acquisition frequency.

[0014] Preferably, the runtime data set establishment module includes a lifecycle stage determination unit and a runtime data set establishment unit; Lifecycle stage determination unit: used to obtain the historical operation records of the equipment; obtain the user manual of the equipment, obtain the expected usage time of the equipment, and determine the lifecycle stage of the equipment based on the operation time corresponding to the operation records; Runtime data set establishment unit: used to extract the runtime corresponding to each run record, divide the day into several time windows evenly, and obtain the runtime data set corresponding to each life cycle stage based on the runtime and runtime data.

[0015] Preferably, the first feature value calculation module includes a first feature value calculation unit; First Feature Value Calculation Unit: Used to obtain the normal numerical range of the device's operating data, extract all operating data in the operating data set, extract the label set in the operating data set; collect all label sets corresponding to each life cycle stage, add them together to obtain the total number of sets, and then divide the number of label sets in each life cycle stage by the total number of sets to obtain the first feature value of the device in each corresponding life cycle stage.

[0016] Compared with existing technologies, the beneficial effects of this invention are as follows: This invention provides a device operation lifecycle monitoring system and method based on the entire chain, including: acquiring operation records of equipment within a building site to obtain operation data sets for each lifecycle stage; obtaining first characteristic values ​​of the equipment at each lifecycle stage based on the operation data; deploying sensors within the building site, obtaining second characteristic values ​​of each device for the building site based on sensor changes during operation and shutdown stages, and obtaining a total target value for each device; acquiring the current acquisition frequency for monitoring each device within the building site, calculating the reliability, and then obtaining the target acquisition frequency for each device within the building site. This invention, by combining the analysis of equipment lifecycle stages and equipment layout within the building site, obtains a reliable target acquisition frequency, which helps to meet the requirements of data acquisition targeting and representativeness, and balances the intensity of equipment monitoring. Attached Figure Description

[0017] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a flowchart illustrating a device lifecycle monitoring method based on the entire supply chain according to the present invention. Detailed Implementation

[0019] 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. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0020] Example: Figure 1 As shown, this invention provides a technical solution for monitoring the entire device lifecycle, including the following steps: (1) Obtain the historical operation records of equipment in the building site, extract the operation time and operation data corresponding to the operation records, analyze the operation time and the expected usage time of the equipment, and determine the life cycle stage of the equipment; divide the day into several time windows evenly, and obtain the operation data set corresponding to each life cycle stage based on the operation time and operation data.

[0021] The system retrieves historical operating records of the equipment, which are generated by monitoring the operating data during the equipment's operation. In the case of an air conditioner, the operating data represents power consumption. The system also retrieves the user manual of the equipment to obtain its estimated usage time. Based on the operating time corresponding to the operating records, the system determines the equipment's life cycle stage, which is divided into the break-in period, the robust period, and the decline period. Regarding the method of dividing the life cycle stages, the following example is given in this embodiment: the estimated usage time of the device is 10 years, the first stage ratio is set to 10%, the second stage ratio is set to 70%, that is, the device is regarded as the break-in period from 0 to 1 year, the robust period from 1 to 7 years, and the decline period after 7 years. Then, all devices can be classified into the corresponding life cycle stages in this way.

[0022] Extract the running time corresponding to each running record, and take the running record whose running time within a certain time window E has a duration greater than a preset duration threshold as the target record of time window E; obtain the life cycle stage P of a certain device when the historical date is adjacent to M days, extract all records of a certain device that belong to the target record of time window E for all M historical days, collect the running data of each record, obtain a set of running data for life cycle stage P, and then obtain all sets of running data corresponding to each life cycle stage.

[0023] (2) Obtain the normal value range of the running data, extract the tag set in the running data set, and obtain the first feature value of the device in each life cycle stage based on the number of tag sets in each life cycle stage.

[0024] Obtain the normal numerical range of the device's operating data [Q1, Q2], where Q1 and Q2 are the minimum and maximum values ​​preset by the system, respectively; extract all operating data from a certain operating data set J, and calculate the variance between the operating data. If there is operating data that is not within the normal numerical range or the variance is less than the preset variance threshold, then mark the operating data set J. Collect all the tag sets corresponding to each lifecycle stage, add them up to get the total number of sets, and then divide the number of tag sets in each lifecycle stage by the total number of sets to obtain the first feature value of the device in each corresponding lifecycle stage.

[0025] (3) Establish a three-dimensional model of the building site, retrieve historical surveillance videos of the building site, obtain the number of existing sensors, and obtain the deployment location of each sensor in the building site based on the location of personnel in the surveillance video; obtain the second characteristic value of each device for the building site based on the changes in sensor data during the operation and shutdown phases of the equipment.

[0026] Extract several surveillance images from historical surveillance videos, capture the location of personnel in the building site in each surveillance image, and mark them in a 3D model; obtain the number N of existing temperature sensors, use a clustering algorithm to aggregate the location points to obtain N target cluster points, and deploy temperature sensors at each target cluster point; Since the device is an air conditioner, and the main function of an air conditioner is temperature control, the sensor in this solution is a temperature sensor.

[0027] In this embodiment, the k-means clustering algorithm is used to obtain the target cluster point, which is the cluster center after clustering. The specific implementation process is existing technology and will not be described in detail here. The target cluster point is the location where people are commonly present in the building site. If the temperature value at the target cluster point changes significantly after the equipment stops operating due to malfunction, it indicates that the impact on the building site is significant, which means that the second feature value obtained in the following analysis is larger.

[0028] All equipment in the building site is run. After a period of time, the target temperature of each temperature sensor is obtained when all temperature sensors are in a stable phase. The stable phase is defined as the period when the variance between the sensing values ​​of the temperature sensors at several moments in the time period is less than a preset variance threshold. The average value between the sensing values ​​at several moments is taken as the corresponding target temperature. Only one device S is stopped from running, and the target temperature of each temperature sensor is obtained when all temperature sensors are in a stable phase after a period of time. Therefore, the second characteristic value of device S with respect to the building site is obtained as follows: Where N is the number of temperature sensors, e is the natural constant, and B n Let A be the target temperature of the nth temperature sensor when device S is running. n The target temperature of the nth temperature sensor when device S stops is obtained, thus yielding the second characteristic value of each device for the building site.

[0029] (4) Based on the first feature value and the second feature value, the total target value corresponding to each device is obtained.

[0030] Based on the life cycle stage of device S, the first target value X1 of device S is obtained. Based on the second characteristic value of device S for the building site, the second target value X2 of device S is obtained. The weights of the first target value X1 and the second target value X2 are set to obtain the total target value of device S. The total target value corresponding to each device is obtained at the present time.

[0031] It should be noted that here, the first target value X1 is also the first characteristic value of the device in the corresponding life cycle stage, and the second target value X2 is also the second characteristic value of the device S for the building site; the weights of the first target value X1 and the second target value X2 are set as W1 and W2 respectively, and the total target value X of the device S is obtained as X = W1×X1 + W2×X2.

[0032] (5) Obtain the acquisition frequency when monitoring each device in the building site currently. According to the total target value, obtain the reliability of the current monitoring, and according to the reliability, iteratively optimize the acquisition frequency of the current device to obtain the target acquisition frequency of each device in the building site, and collect data from the devices in the building site according to the target acquisition frequency.

[0033] Sort the devices according to the total target value of each device in the building site in ascending order and establish a target value set; according to the acquisition frequency when monitoring each device currently, establish a frequency set according to the device serial number, and calculate the cosine similarity between the target value set and the frequency set as the reliability of the current monitoring; Since the greater the total target value of the device, the greater the monitoring intensity of the device, that is, the greater the acquisition frequency, and the greater the cosine similarity, the more consistent the change trends between the target value set and the frequency set, and the more in line with this solution. Therefore, in this solution, it is judged whether the acquisition frequency when monitoring the device currently is reasonable based on the cosine similarity, and then iteratively adjust the unreasonable acquisition frequency, which helps to achieve monitoring intelligence and reliability.

[0034] If the reliability is less than the preset degree threshold, set the iteration number to 1, and obtain the numerical average value a in the target value set and the numerical average value b in the frequency set. Obtain the values A and B corresponding to a certain device S in the target value set and the frequency set, and obtain the variance between A / a and B / b as the target variance of the device S, and then obtain the target variances of each device, and use the acquisition frequency of the device corresponding to the maximum target variance as the adjustment frequency; If A / a > B / b, adjust the value of the adjustment frequency upward. If A / a < B / b, adjust the value of the adjustment frequency downward. The specific adjusted value is: , where k is the adjustment coefficient, 0 < k ≤ 1. According to the acquisition frequency after iteration, obtain a new frequency set, and obtain the reliability again for judgment until the iteration number is greater than the preset number threshold or the obtained reliability is not less than the degree threshold to stop iteration, and obtain the final target acquisition frequency of each device.

[0035] This embodiment also provides a device operation lifecycle monitoring system based on the entire link, including an operation data set establishment module, a first feature value calculation module, a total target value calculation module, and a target acquisition frequency determination module. The operation data set establishment module includes a lifecycle stage determination unit and an operation data set establishment unit, and the first feature value calculation module includes a first feature value calculation unit. When the system executes a computer program, it implements the above-mentioned device operation lifecycle monitoring method based on the entire link. Since the device operation lifecycle monitoring method based on the entire link has been described in detail above, it will not be repeated here.

[0036] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, specific embodiments have been described above. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims can be performed in a different order than that shown in the embodiments and still achieve the desired result. Additionally, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0037] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

[0038] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for monitoring the entire device lifecycle, characterized in that, Includes the following steps: Obtain historical operation records of equipment within the building site, extract the corresponding operation time and operation data from the operation records, analyze the operation time and the expected usage time of the equipment, and determine the life cycle stage of the equipment; divide the day into several time windows evenly, and obtain the operation data set corresponding to each life cycle stage based on the operation time and operation data; Obtain the normal numerical range of the operating data, extract the label set from the operating data set, and obtain the first feature value of the device in each life cycle stage based on the number of label sets in each life cycle stage. A 3D model of the building site is established, historical surveillance videos of the building site are retrieved, the number of existing sensors is obtained, and the deployment location of each sensor in the building site is obtained based on the location of personnel in the surveillance videos. Based on the changes in sensor data during the operation and shutdown phases of the equipment, the second feature value of each device for the building site is obtained. Based on the first and second feature values, the total target value corresponding to each device is obtained. The current acquisition frequency for monitoring each device in the building site is obtained. Based on the overall target value, the reliability of the current monitoring is obtained. Based on the reliability, the acquisition frequency of the current device is iteratively optimized to obtain the target acquisition frequency for each device in the building site. Data is then collected from the devices in the building site according to the target acquisition frequency.

2. The method for monitoring the entire device lifecycle based on the whole chain as described in claim 1, characterized in that, Obtain the runtime data set corresponding to each lifecycle stage, including: The historical operation records of the device are obtained. These records are generated by monitoring the operation data during the operation of the device, which is an air conditioner, and the operation data is power. The instruction manual of a certain device is obtained to obtain the estimated usage time of the device. Based on the operation time corresponding to the operation records, the life cycle stage of the device is determined. The life cycle stage is divided into the break-in period, the robust period, and the decline period. Extract the running time corresponding to each running record, and take the running record whose running time within a certain time window E has a duration greater than a preset duration threshold as the target record of the time window E; obtain the life cycle stage P of a certain device when the historical date is adjacent to M days, extract all records of the certain device that belong to the target record of the time window E for the historical M days, collect the running data of each record, obtain a running data set of life cycle stage P, and then obtain all running data sets corresponding to each life cycle stage.

3. The method for monitoring the entire device lifecycle based on the whole chain as described in claim 2, characterized in that, Obtain the first characteristic value of the device at each stage of its life cycle, including: Obtain the normal numerical range of the device's operating data [Q1, Q2], where Q1 and Q2 are the minimum and maximum values ​​preset by the system, respectively; extract all operating data from a certain operating data set J, and calculate the variance between the operating data. If there is operating data that is not within the normal numerical range or the variance is less than the preset variance threshold, then mark the operating data set J. Collect all the tag sets corresponding to each life cycle stage and add them together to get the total number of sets. Then divide the number of tag sets in each life cycle stage by the total number of sets to obtain the first feature value of the device in each corresponding life cycle stage.

4. The method for monitoring the entire device lifecycle based on the whole chain as described in claim 1, characterized in that, Obtain the second characteristic value of each device relative to the building site, including: Extract several surveillance images from historical surveillance videos, capture the location of personnel in the building site in each surveillance image, and mark them in a 3D model; obtain the number N of existing temperature sensors, use a clustering algorithm to aggregate the location points to obtain N target cluster points, and deploy temperature sensors at each target cluster point; All equipment in the building site is run, and the target temperature of each temperature sensor is obtained when all temperature sensors are in a stable phase after a period of time. The stable phase is the period when the variance between the sensing values ​​of the temperature sensors at several moments in the time period is less than a preset variance threshold. The average value between the sensing values ​​at several moments is taken as the corresponding target temperature. Only one device S is stopped, and the target temperature of each temperature sensor is obtained when all temperature sensors are in a stable phase after a period of time. Therefore, the second characteristic value of device S with respect to the building site is obtained as follows: Where N is the number of temperature sensors, e is the natural constant, and B n Let A be the target temperature of the nth temperature sensor when device S is running. n The target temperature of the nth temperature sensor when device S stops is obtained, thus yielding the second characteristic value of each device for the building site.

5. The method for monitoring the entire device lifecycle based on the whole chain according to claim 4, characterized in that, The process of obtaining the total characteristic value corresponding to each device includes: obtaining the first target value X1 of device S based on the life cycle stage of device S; obtaining the second target value X2 of device S based on the second characteristic value of device S for the building site; setting the weights of the first target value X1 and the second target value X2 to obtain the total target value of device S; and obtaining the total target value corresponding to each device.

6. The method for monitoring the entire device lifecycle based on the whole chain as described in claim 1, characterized in that, The target acquisition frequency for each device within the building site is obtained, including: Based on the total target value of each piece of equipment in the building site, the equipment is sorted in ascending order and a target value set is established; based on the current acquisition frequency of each piece of equipment during monitoring, a frequency set is established according to the equipment serial number, and the cosine similarity between the target value set and the frequency set is calculated as the reliability of the current monitoring. If the reliability is less than the preset threshold, the number of iterations is set to 1, and the average value a in the target value set and the average value b in the frequency set are obtained. The values ​​A and B corresponding to a certain device S in the target value set and frequency set are obtained, and the variance between A / a and B / b is obtained as the target variance of device S. Then the target variance of each device is obtained, and the acquisition frequency of the device with the largest target variance is used as the adjustment frequency. If A / a > B / b, the value of the adjusted frequency will be adjusted upward; if A / a < B / b, the value of the adjusted frequency will be adjusted downward. The specific adjusted value is: , where k is the adjustment coefficient, 0 < k ≤ 1. According to the acquired frequency after iteration, a new frequency set is obtained, and the reliability is obtained again for judgment. The iteration stops until the number of iterations is greater than the preset number threshold or the obtained reliability is not less than the degree threshold, and the target acquisition frequency of each device is obtained finally.

7. A device lifecycle monitoring system, used to execute the device lifecycle monitoring method based on the entire chain as described in any one of claims 1-6, characterized in that, The system includes a running data set establishment module, a first feature value calculation module, a total target value calculation module, and a target acquisition frequency determination module; Operational Data Set Establishment Module: This module is used to acquire historical operation records of equipment within the building site, extract the corresponding operation time and operation data from the operation records, analyze the operation time and the expected usage time of the equipment, and determine the life cycle stage of the equipment; it divides a day into several time windows and obtains the operational data set corresponding to each life cycle stage based on the operation time and operation data. First feature value calculation module: used to obtain the normal numerical range of the running data, extract the label set from the running data set, and obtain the first feature value of the device in each life cycle stage based on the number of label sets in each life cycle stage; Overall target value calculation module: used to build a 3D model of the building site, retrieve historical surveillance videos of the building site, obtain the number of existing sensors, and obtain the deployment location of each sensor in the building site based on the location of personnel in the surveillance video; based on the changes in sensor data during the operation and shutdown phases of the equipment, obtain the second characteristic value of each device for the building site; Based on the first and second feature values, the total target value corresponding to each device is obtained. Target acquisition frequency determination module: used to obtain the acquisition frequency of each device in the building site during current monitoring, obtain the reliability of the current monitoring based on the total target value, and iteratively optimize the acquisition frequency of the current device based on the reliability to obtain the target acquisition frequency of each device in the building site, and collect data from the device in the building site according to the target acquisition frequency.

8. The equipment lifecycle monitoring system according to claim 7, characterized in that, The runtime data set establishment module includes a lifecycle stage determination unit and a runtime data set establishment unit; Lifecycle stage determination unit: used to obtain the historical operation records of the equipment; obtain the user manual of the equipment, obtain the expected usage time of the equipment, and determine the lifecycle stage of the equipment based on the operation time corresponding to the operation records; Runtime data set establishment unit: used to extract the runtime corresponding to each run record, divide the day into several time windows evenly, and obtain the runtime data set corresponding to each life cycle stage based on the runtime and runtime data.

9. A device lifecycle monitoring system according to claim 7, characterized in that, The first feature value calculation module includes a first feature value calculation unit; First feature value calculation unit: used to obtain the normal numerical range of the device's operating data, extract all operating data in the operating data set, extract the tag set in the operating data set; collect all tag sets corresponding to each life cycle stage, add them together to obtain the total number of sets, and then divide the number of tag sets in each life cycle stage by the total number of sets to obtain the first feature value of the device in each corresponding life cycle stage.

Citation Information

Patent Citations

  • Adaptive operation and maintenance management method and system for power distribution cabinet

    CN118070042A

  • Intelligent building full life cycle monitoring management method and system

    CN119313172A

  • Electric power material life cycle evaluation method and system

    CN120069645A

  • Geological disaster early warning method and system based on dynamic data monitoring

    CN120220328A

  • Self-adaptive operation and maintenance method for transformer substation video

    WO2023169207A1