Equipment monitoring system based on cloud deployment
By deploying a cloud-based equipment monitoring system, the system dynamically adjusts data collection tasks and multi-dimensional scoring, solving the problems of resource waste and low operational efficiency in equipment monitoring systems. This enables real-time perception and precise positioning of equipment status, improving assessment accuracy and system stability.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-12-09
- Publication Date
- 2026-03-10
AI Technical Summary
Existing equipment monitoring systems lack dynamic sensing capabilities, leading to resource waste and omissions of key data. The assessment methods are simplistic and lack environmental adaptability, while the independent operation of each functional module results in low maintenance efficiency.
The equipment monitoring system is deployed in the cloud and includes a data acquisition module, a task scheduling module, and a scoring calculation module. By dynamically adjusting the acquisition tasks and multi-dimensional scoring models, it can achieve real-time perception and accurate positioning of equipment status.
Reduce redundant data collection, shorten troubleshooting time, improve assessment accuracy and system stability, and enhance operation and maintenance efficiency.
Smart Images
Figure CN121644341A_ABST
Abstract
Description
Technical Field
[0001] This disclosure relates to the field of hardware device monitoring technology, and in particular to a cloud-based device monitoring system. Background Technology
[0002] As a core component of the Industrial Internet of Things (IIoT), the intelligence level of equipment monitoring systems directly impacts the reliability and operational efficiency of production systems. With the deepening of digital transformation in manufacturing, traditional equipment monitoring solutions are increasingly unable to meet the diverse needs of modern industrial scenarios. Current mainstream equipment monitoring systems generally employ fixed-period data collection and static scoring mechanisms; this rigid architecture reveals significant limitations in practical applications.
[0003] From a data acquisition perspective, existing systems primarily rely on preset acquisition cycles or manually configured acquisition tasks, lacking the ability to dynamically perceive the operating status of equipment. This static acquisition strategy often leads to two extremes: on the one hand, current static acquisition schemes continuously perform high-frequency acquisition during periods of stable equipment operation, wasting computing resources and network bandwidth; on the other hand, when abnormal symptoms appear in the equipment, the acquisition density cannot be increased in a timely manner, resulting in the omission of critical status data. Especially when dealing with sudden failures, this passive acquisition mode struggles to provide sufficient data support for fault diagnosis.
[0004] In terms of condition assessment, traditional scoring mechanisms typically employ fixed thresholds or linear weighting methods, resulting in a single assessment dimension and a lack of environmental adaptability. Modern industrial equipment often operates in complex and variable environments, and its performance is affected by multiple factors such as regional differences, seasonal variations, and operating hours. For example, the operating condition of the same piece of equipment may differ significantly between the humid and hot environment of the south and the dry environment of the north, but existing static scoring models cannot accurately quantify the degree of impact of these environmental factors on the health status of the equipment.
[0005] More concerning is the lack of effective collaboration mechanisms between the various functional modules of the current monitoring system. Data acquisition, task scheduling, and status assessment services often operate independently, creating information silos. This fragmented system architecture not only reduces operational efficiency but also leads to significant delays in anomaly response. When equipment performance deteriorates, the system struggles to trigger targeted in-depth detection in a timely manner, missing the optimal window for fault handling. Summary of the Invention
[0006] This disclosure aims to at least partially solve one of the technical problems in the aforementioned technologies, and to this end proposes a cloud-based device monitoring system, comprising: The module comprises a data acquisition module, a task scheduling module, and a scoring calculation module; among which, The data acquisition module is deployed on the side of the device to be monitored; The task scheduling module and the scoring calculation module are deployed in the cloud. The task scheduling module is configured as follows: Data acquisition instructions are generated based on the scores of the monitored equipment. The data acquisition command is sent to the data acquisition module to collect the operating data of the monitored device and send it to the scoring calculation module; and The scoring calculation module receives the score of the monitored device calculated based on the operational data.
[0007] Furthermore, the data acquisition instructions include: incremental data acquisition instructions and full data acquisition instructions.
[0008] Furthermore, the task scheduling module is configured to generate a full data acquisition instruction and send it to the data acquisition module during system initialization, so that the module can perform full data acquisition on the device to be monitored.
[0009] Furthermore, the task scheduling module is configured to: when it is determined that the overall project score calculated by the scoring calculation module based on the operating data of all monitored devices is lower than a threshold, generate a full data acquisition instruction for all monitored devices and send it to the data acquisition module.
[0010] Furthermore, the task scheduling module is configured to: when it is determined that the single-device score calculated by the scoring calculation module based on the operating data of the target device under monitoring is lower than a threshold, generate an incremental data acquisition instruction for the target device under monitoring and send it to the data acquisition module.
[0011] Furthermore, the calculation formula corresponding to the single device score includes:
[0012] in, Indicates a single device score; Indicates the target device to be monitored. The sub-scores for each parameter include: CPU utilization, memory utilization, disk capacity utilization, the ratio of current disk speed to rated speed, network card bandwidth utilization, the ratio of current fan speed to rated speed, and the degree of deviation of device temperature. express The total number of items.
[0013] Furthermore, the calculation formula for the overall project score includes:
[0014] in, Indicates the overall score of the project; Indicates the first Individual device rating for each device to be monitored; express Dynamic weights.
[0015] Furthermore, the dynamic weights Based on the The external environmental factors of each device to be monitored are determined; wherein, the external environmental factors include: the device deployment area, the current season, and the current time.
[0016] Furthermore, the cloud-based device monitoring system also includes: a human-computer interaction module; the task scheduling module is configured to: receive operation instructions sent by the user through the human-computer interaction module, generate incremental data acquisition instructions or full data acquisition instructions according to the operation instructions, and send them to the data acquisition module.
[0017] Furthermore, the task scheduling module is also configured to: reset the score of the corresponding monitored device to zero when it is determined that the data acquisition time of the data acquisition module exceeds a threshold.
[0018] Compared with the prior art, the beneficial effects of this disclosure are: the cloud-based equipment monitoring system provided in this disclosure dynamically adjusts the collection tasks through scoring feedback, reducing redundant data collection; its local anomaly triggering mechanism can accurately locate problematic equipment and shorten the troubleshooting time; the multi-dimensional dynamic scoring model significantly improves the accuracy of evaluation; and the closed-loop design based on global scoring and task scheduling enhances system stability.
[0019] Other features and advantages of this disclosure will be set forth in the following description, and will be apparent in part from the description, or may be learned by practicing the disclosure. The objects and other advantages of this disclosure may be realized and obtained by means of the structures particularly pointed out in the written description and the accompanying drawings. The technical solutions of this disclosure will be further described below with reference to the accompanying drawings and embodiments. Attached Figure Description
[0020] The accompanying drawings are provided to further illustrate the present disclosure and form part of the specification. They are used together with the embodiments of the present disclosure to explain the disclosure and do not constitute a limitation thereof. In the drawings: Figure 1 This is a schematic diagram of a cloud-based device monitoring system provided as an example. Figure 2 This is a schematic diagram of a cloud-based device monitoring system, as shown in another embodiment. Detailed Implementation
[0021] The present disclosure will be described below with reference to the accompanying drawings. The preferred embodiments described herein are for illustration and explanation only and are not intended to limit the present disclosure.
[0022] Figure 1 The cloud-based device monitoring system disclosed herein includes: The module comprises a data acquisition module, a task scheduling module, and a scoring calculation module; among which, The data acquisition module is deployed on the side of the device to be monitored; The task scheduling module and the scoring calculation module are deployed in the cloud. The task scheduling module is configured as follows: Data acquisition instructions are generated based on the scores of the monitored equipment. The data acquisition command is sent to the data acquisition module to collect the operating data of the monitored device and send it to the scoring calculation module; and The scoring calculation module receives the score of the monitored device calculated based on the operational data.
[0023] According to some embodiments of this disclosure, such as Figure 2 As shown in the embodiments of this disclosure, the cloud-based device monitoring system adopts a cloud-based hybrid architecture (B / S + C / S), including: (1) Browser (human-computer interaction module): providing a user interface, supporting task management, report display and data export; (2) Task scheduling service (task scheduling module): dynamically generating full / incremental collection tasks, triggering collection instructions based on scoring results; (3) Data collection agent (data collection module): deployed on the device, executing collection instructions and reporting data to the message queue; (4) Scoring service (scoring calculation module): calculating the overall score of the device and project in real time, driving task scheduling decisions. In this embodiment, when the scheduling service issues a collection instruction, it simultaneously sends a pre-scoring instruction to the scoring service, including a device list and data collection instructions, for the scoring service to verify the integrity of the collected data.
[0024] Furthermore, data acquisition instructions include: Incremental data acquisition command and full data acquisition command.
[0025] Furthermore, the task scheduling module is configured as follows: During system initialization, a full data acquisition command is generated and sent to the data acquisition module to enable it to acquire full data from the monitored devices.
[0026] According to some embodiments of this disclosure, the cloud-based device monitoring system provided in this disclosure forces a full data collection command during network initialization, collecting the rated values, full load values, and real-time data of all devices to be monitored. In addition, the cloud-based device monitoring system provided in this disclosure can also realize intelligently triggered full data collection or incremental data collection, and the specific triggering mechanism is described below.
[0027] Furthermore, the task scheduling module is configured to generate a full data acquisition instruction for all monitored devices when the overall project score calculated by the scoring calculation module based on the operating data of all monitored devices is lower than the threshold, and send it to the data acquisition module.
[0028] According to some embodiments of this disclosure, the scoring calculation module is used to calculate the overall project score (the method for calculating the overall project score is described below), and triggers full data collection when the overall project score is lower than a set threshold (e.g., 80%).
[0029] According to other embodiments of this disclosure, the cloud-based device monitoring system provided in this disclosure can also perform full data collection according to a user-defined cycle.
[0030] Furthermore, the task scheduling module is configured to: when the score of a single device calculated by the scoring calculation module based on the operating data of the target device being monitored is lower than a threshold, generate an incremental data acquisition instruction for the target device being monitored and send it to the data acquisition module.
[0031] According to some embodiments of this disclosure, the scoring calculation module is also used to calculate the score of a single device (the method for calculating the score of a single device is described below), and to trigger incremental data collection for the device when the score of a single device is lower than a set threshold; the scoring calculation module is also used to trigger data collection for a single parameter when it is determined that a single parameter of a single device is abnormal. For example, when the score of a server drops to 70% due to an abnormal disk capacity, the task scheduling service sends a disk-related incremental data collection instruction, and after collecting data multiple times, it confirms whether the score is still lower than the threshold. If so, it issues an alarm and suggests maintenance intervention.
[0032] According to some other embodiments of this disclosure, when the task scheduling module collects incremental data for a single device, if the score calculation result of the single device remains basically the same or improves after three consecutive collections, the task scheduling module stops collecting incremental data; if the trend deteriorates, the task scheduling module issues an alarm to remind the operation and maintenance to intervene.
[0033] Furthermore, the calculation formula for the single-device score includes:
[0034] in, Indicates a single device score; Indicates the target device to be monitored. The sub-scores for each parameter include: CPU utilization, memory utilization, disk capacity utilization, the ratio of current disk speed to rated speed, network card bandwidth utilization, the ratio of current fan speed to rated speed, and the degree of deviation of device temperature. express The total number of items.
[0035] Furthermore, the calculation formula for the overall project score includes:
[0036] in, Indicates the overall score of the project; Indicates the first Individual device rating for each device to be monitored; express Dynamic weights.
[0037] Furthermore, dynamic weights Based on the The external environmental factors for each device to be monitored are determined; these external environmental factors include: the device deployment area, the current season, and the current time.
[0038] According to some embodiments of this disclosure, variations in the actual deployment area, season, and ambient temperature and workload at different times of day will all affect the fluctuations of various device indicators. Therefore, a dynamic weighting method is adopted for scoring to minimize false alarms and missed alarms caused by changes in environment and workload. When the task scheduling module of the cloud-based device monitoring system provided in this disclosure issues a collection command, it calculates the current dynamic weight of the device in real time based on parameters such as the device deployment area, current season, and current time, and synchronously sends this dynamic weight to the data acquisition module for use in edge preprocessing scoring.
[0039] According to other embodiments of this disclosure, the dynamic weight calculation formulas are shown in Table 1: Table 1
[0040] For example, for GPU monitoring in Shanghai during the summer, with base = 0.6, area = 1.2, season = 1.5, time = 1.3, and cooling = 0.9, the monitored adjusted_weight = base * area * season * time * cooling = 1.26. Therefore, the actual alarm threshold = 95% * 1.26 = 119.7%, which means that short-term overclocking is allowed.
[0041] Based on this, the overall project score calculation formula is as follows:
[0042] in, Indicates the overall score of the project; Indicates the first Individual device rating for each device to be monitored; express Dynamic weights; express Total number of items; This represents the sub-scores of various parameters of the target monitoring equipment.
[0043] In some embodiments, The expression is as follows:
[0044] in, Indicates a single device score; Indicates CPU utilization; Indicates memory usage; This indicates the disk capacity utilization rate; This indicates the ratio of the disk's current rotational speed to its rated rotational speed. Indicates the network card bandwidth utilization rate; This indicates the ratio of the fan's current speed to its rated speed. Indicates the rated temperature of the equipment; This indicates the actual temperature of the equipment.
[0045] According to other embodiments of this disclosure, the single-device score is calculated by weighted summation of the sub-scores of various parameters of the device to be monitored. After the data acquisition module collects data according to the acquisition command, it promptly performs weighted calculation on the collected data according to the weights carried in the command: if the calculated scores are all normal (not significantly different from historical data and within the set fluctuation range), it directly reports as normal; if there is abnormal data, it reports the abnormal data and updates the abnormal data to the local SQLite database; after receiving normal feedback, the cloud does not add new records, only records of devices with abnormal data are added.
[0046] Furthermore, the cloud-based equipment monitoring system also includes: a human-machine interaction module; and a task scheduling module, configured to: receive operation instructions sent by the user through the human-machine interaction module, generate incremental data acquisition instructions or full data acquisition instructions based on the operation instructions, and send them to the data acquisition module.
[0047] According to some embodiments of this disclosure, the cloud-based device monitoring system provided in this disclosure supports users to manually trigger data collection tasks for specified devices (such as verification after replacing spare parts), and also supports hardware-forced marking of items, devices, and hardware as normal.
[0048] Furthermore, the task scheduling module is also configured to reset the score of the corresponding monitored device to zero when the data acquisition module's acquisition time exceeds a threshold.
[0049] According to some embodiments of this disclosure, when the task scheduling module determines that the data acquisition module's acquisition time exceeds a first threshold (e.g., 24 hours), it multiplies the data acquisition module's score by a first correction coefficient (0 in this embodiment) to obtain the final score. When the task scheduling module determines that the data acquisition module's acquisition time exceeds a second threshold (e.g., 1 hour) but does not exceed the first threshold, it multiplies the corresponding device's score by a second correction coefficient (e.g., 0.3) to obtain the final score. When the task scheduling module determines that the data acquisition module's acquisition time exceeds a third threshold (e.g., 30 seconds) but does not exceed the second threshold, it multiplies the corresponding device's score by a third correction coefficient (e.g., 0.3) to obtain the final score.
[0050] It is obvious that those skilled in the art can make various modifications and variations to this disclosure without departing from its spirit and scope. Therefore, if such modifications and variations fall within the scope of the claims of this disclosure and their equivalents, this disclosure is also intended to include such modifications and variations.
Claims
1. A cloud-based deployment based device monitoring system, characterized in that, The system comprises a data collection module, a task scheduling module and a score calculation module, wherein The data collection module is disposed on the side of the equipment to be monitored. The task scheduling module and the score calculation module are disposed on the cloud. The task scheduling module is configured to: generate a data collection instruction according to the score of the equipment to be monitored; send the data collection instruction to the data collection module, so that the data collection module collects the operation data of the equipment to be monitored and sends the operation data to the score calculation module; and receive the score of the equipment to be monitored calculated by the score calculation module according to the operation data. The data collection instruction comprises an incremental data collection instruction and a full-amount data collection instruction.
2. The system of claim 1, wherein, The task scheduling module is configured to, at system initialization, generate a full-amount data collection instruction and send the full-amount data collection instruction to the data collection module, so that the data collection module collects full-amount data of the equipment to be monitored.
3. The system of claim 2, wherein, The task scheduling module is configured to, when it is determined that the overall score of the project calculated by the score calculation module according to the operation data of all the equipment to be monitored is lower than a threshold value, generate a full-amount data collection instruction for all the equipment to be monitored and send the full-amount data collection instruction to the data collection module.
4. The system of claim 3, wherein, The task scheduling module is configured to, when it is determined that the single-equipment score calculated by the score calculation module according to the operation data of a target equipment to be monitored is lower than a threshold value, generate an incremental data collection instruction for the target equipment to be monitored and send the incremental data collection instruction to the data collection module.
5. The system of claim 4, wherein, The calculation formula corresponding to the single-equipment score comprises:
6. The system of claim 5, wherein, The calculation formula corresponding to the overall score of the project comprises: wherein, represents a single-device score; represents a target device to be monitored item parameter sub-score, including: CPU occupancy, memory occupancy, disk capacity usage, ratio of current disk rotation speed to rated rotation speed, network card bandwidth usage, ratio of current fan rotation speed to rated rotation speed, and device temperature deviation; represents total number of 7. The system of claim 6, wherein, The system further comprises a human-computer interaction module. wherein, represents an overall score for the project; represents a single-device score for the device under monitoring; represents a dynamic weight.
8. The system of claim 7, wherein, The dynamic weight based on external environmental factors of the device to be monitored, wherein the external environmental factors include: a device deployment area, a current season, and a current time.
9. The system of claim 2, wherein, The task scheduling module is configured to receive an operation instruction sent by a user through the human-computer interaction module, generate an incremental data collection instruction or a full-amount data collection instruction according to the operation instruction, and send the incremental data collection instruction or the full-amount data collection instruction to the data collection module. The task scheduling module is further configured to, when it is determined that the collection time of the data collection module exceeds a threshold value, reset the score of the corresponding equipment to be monitored to zero. 10. The system of any of claims 1-9, wherein,