Equipment anomaly monitoring device based on data iterative updates and equipment status monitoring system including the same.

Abstract

This invention discloses a device for monitoring equipment anomalies based on iterative data updates, and a system for monitoring equipment status including the same. The device first acquires first operating status data of equipment within a first predetermined monitoring period to establish a data association model. Then, it acquires second operating status data of the equipment within the next predetermined monitoring period to update the data association model. The updated data association model incorporates the second operating status data, and the weight of the second operating status data is greater than that of the first operating status data. Subsequently, the updated data association model is used to determine whether the equipment's operating status is abnormal, and when the equipment's operating status is determined to be abnormal, an anomaly warning message is output. Therefore, the accuracy and stability of equipment anomaly detection can be improved.

Description

Equipment anomaly monitoring device based on data iterative updates and equipment status monitoring system including the same. Technical Field

[0001] This invention relates to an equipment anomaly monitoring device, and more particularly to an equipment anomaly monitoring device based on data iterative updates and an equipment status monitoring system including the device, which can be widely used in industrial equipment that requires long-term status monitoring, such as, but not limited to, production, processing or power equipment. Prior Technology

[0002] The internal liquid levels of many industrial equipment fluctuate dynamically with operating conditions. These fluctuations are often precursors to equipment malfunctions or direct signs of failure. Failure to detect abnormal liquid levels in a timely manner can lead to equipment damage, safety accidents, production shutdowns, and significant economic losses. Therefore, for critical equipment requiring long-term monitoring, such as transformers, boilers, cooling towers, and chemical storage tanks, the industry commonly uses sensors to continuously monitor internal liquid levels to understand the equipment's operating status in real time. However, existing technologies often rely on fixed thresholds or static models to identify abnormal liquid levels, failing to adequately consider the impact of environmental parameters such as temperature, pressure, or load on liquid level changes. This results in technical bottlenecks such as high false alarm rates and insufficient sensitivity.

[0003] Furthermore, while some existing technologies attempt to incorporate data analysis models to predict liquid level change trends, their model architectures are mostly statically designed, lacking mechanisms for continuous learning and dynamic updates. This rigid modeling approach cannot adapt to the aging phenomena caused by long-term equipment operation, nor can it cope with the variations in liquid level behavior caused by fluctuations in environmental parameters or changes in operating conditions. Moreover, because the model parameters are fixed and cannot be adjusted over time, existing technologies cannot achieve accurate anomaly diagnosis under dynamic operating conditions. Summary of the Invention

[0004] The technical problem this invention aims to solve is to provide a data-based iterative update-based equipment anomaly monitoring device and an equipment status monitoring system including the device, addressing the shortcomings of existing technologies. The concept behind this invention is to continuously integrate new and old data through an iterative update mechanism of a data association model, enabling the model to reflect changes in equipment operating characteristics in real time, thereby improving the accuracy and adaptability of equipment anomaly detection.

[0005] To address the aforementioned technical problems, one technical solution adopted in this invention is to provide a device anomaly monitoring device based on iterative data updates, comprising a data acquisition module, a data modeling module, an anomaly judgment module, and a status indication module. The data acquisition module is configured to acquire first operating status data of a device within a first predetermined monitoring period; the data modeling module is configured to establish a data association model using the first operating status data. Furthermore, the data acquisition module is configured to acquire second operating status data of the device within the next N predetermined monitoring periods, where N is a natural number greater than or equal to 1; the data modeling module is configured to update the data association model using the second operating status data. The updated data association model incorporates the second operating status data, and the weight of the second operating status data is greater than that of the first operating status data. The anomaly judgment module is configured to use the updated data association model to determine whether the device's operating status is abnormal based on changes in the internal liquid level; the status indication module is configured to output an anomaly indication message when the device's operating status is determined to be abnormal.

[0006] In a feasible or preferred embodiment of this invention, the first operating status data includes a dataset sampled by the data acquisition module during a first predetermined monitoring period, reflecting the change of the liquid level height of the internal liquid with the state parameters, and the data association model characterizes the functional correspondence between the state parameters and the liquid level height of the internal liquid established by the data modeling module based on the first operating status data.

[0007] In a feasible or preferred embodiment of this invention, the state parameter is the representative temperature of the internal liquid, and the functional relationship is presented in the form of a curve showing the relationship between liquid level and temperature.

[0008] In a feasible or preferred embodiment of this invention, the curve showing the relationship between the liquid level height and temperature change is composed of multiple standard corresponding points. In the program of the data modeling module that establishes the data association model, each standard corresponding point is generated by calculation using the following formula 1: Formula 1 In Formula 1, S1 represents the standard liquid level height at a specific temperature at the standard corresponding point of the curve relating liquid level height to temperature; T1 represents the total number of unit time periods within the first predetermined monitoring period; and H1 represents the sum of multiple liquid level heights sampled at the specific temperature within the first predetermined monitoring period.

[0009] In a feasible or preferred embodiment of this invention, in the process of updating the data association model, the data modeling module reconstructs the temperature change curve corresponding to the liquid level height based on the second operating state data. The second operating state data includes a dataset of samples taken by the data acquisition module within the next N predetermined monitoring cycles, reflecting the change of the liquid level height of the internal liquid with the state parameters. The standard corresponding point of the reconstructed temperature change curve corresponding to the liquid level height is generated by calculating the following formula 2: Formula 2 In Equation 2, S2 represents the standard liquid level height at a specific temperature of the standard corresponding point of the reconstructed liquid level height-temperature change curve; T2 represents the total number of unit time periods within the next N predetermined monitoring cycles; and H2 represents the sum of multiple liquid level heights sampled at the specific temperature within the next N predetermined monitoring cycles.

[0010] To address the aforementioned technical problems, another technical solution adopted in this invention is to provide a device status monitoring system, which includes a device and the device anomaly monitoring device as described above. A sensing module is installed on the device, and the data acquisition module is electrically connected to the sensing module to acquire the data measured by the sensing module.

[0011] In a feasible or preferred embodiment of this invention, the sensing module is a temperature-liquid level composite sensor, which is attached to the outer wall of a bottom wall of the device to simultaneously measure the representative temperature and liquid level of an internal liquid of the device.

[0012] In a feasible or preferred embodiment of this invention, the sensing module includes a temperature sensor and a liquid level sensor. The temperature sensor is attached to the outer wall of a side wall or a bottom wall of the device to measure the representative temperature of an internal liquid of the device, and a probe of the liquid level sensor is disposed inside the device to measure the liquid level height of an internal liquid of the device.

[0013] In summary, the device and method for monitoring equipment anomalies based on iterative data updates provided in this invention, by "obtaining first operating status data of a device within the first predetermined monitoring period to establish a data association model", "obtaining second operating status data of the device within the next N predetermined monitoring periods to update the data association model", and "incorporating the second operating status data into the updated data association model, with the weight of the second operating status data being greater than that of the first operating status data", can achieve dynamic information updates and long-term learning capabilities, so as to quickly adapt to changes in the operating environment, load conditions, or device status of the device, and can more timely identify sudden anomalies or long-term accumulated anomaly trends.

[0014] To gain a better understanding of the features and technical content of this work, please refer to the following detailed description and illustrations. However, the illustrations provided are for reference and illustration only and are not intended to limit this work. Simple Explanation of the Diagram

[0015] Figure 1 is a functional block diagram of the device anomaly monitoring device based on data iterative updates according to the first embodiment of this invention.

[0016] Figure 2 is a schematic diagram of one of the usage states of the device anomaly monitoring device according to the first embodiment of this invention.

[0017] Figure 3 is a schematic diagram of another usage state of the device anomaly monitoring device according to the first embodiment of this invention.

[0018] Figure 4 is a partial structural schematic diagram of the equipment anomaly monitoring device according to the first embodiment of this invention.

[0019] Figure 5 is an initial liquid level height-temperature characteristic curve generated by the equipment anomaly monitoring device of the first embodiment of this invention.

[0020] Figure 6 is a reconstructed liquid level height-temperature characteristic curve generated by the equipment anomaly monitoring device of the first embodiment of this invention.

[0021] Figure 7 is a flowchart of the device anomaly monitoring device based on data iterative updates according to the second embodiment of this invention. Implementation

[0022] The following specific embodiments illustrate the implementation of the "Equipment Status Monitoring System and its Data-Based Iterative Update-Based Equipment Anomaly Monitoring Device" disclosed in this invention. Those skilled in the art can understand the advantages and effects of this invention from the content disclosed in this specification. This invention can be implemented or applied through other different specific embodiments, and various details in this specification can also be modified and changed based on different viewpoints and applications without departing from the concept of this invention. Furthermore, the accompanying drawings are for simple illustration only and are not depictions of actual dimensions; this is stated in advance. The following embodiments will further describe the relevant technical content of this invention in detail, but the disclosed content is not intended to limit the scope of protection of this invention.

[0023] It should be understood that while terms such as "first," "second," and "third" may be used in this document to describe various components or signals, these components or signals should not be limited by these terms. These terms are primarily used to distinguish one component from another, or one signal from another. Furthermore, the term "or" as used herein should, as appropriate, include any combination of one or more of the associated listed items.

[0024] The changing patterns of liquid level and state parameters in equipment vary under different operating conditions (such as location, climate, load, etc.). Traditional methods often rely on static thresholds or empirical formulas (such as the linear relationship between liquid level and state parameters) to determine anomalies; however, these standards may become inaccurate once operating conditions change. Therefore, this work proposes a new concept: through an iterative update mechanism of a data association model, new and old data are continuously integrated to enable the model to reflect changes in equipment operating characteristics in real time, thereby improving the accuracy and adaptability of equipment anomaly detection.

[0025] [First Embodiment]

[0026] Referring to Figures 1 and 4, the first embodiment of this invention provides a device anomaly monitoring device 1 based on data iterative updates, which includes a data acquisition module 11, a data modeling module 12, an anomaly judgment module 13, and a status indication module 14. The modules are interconnected or functionally coupled to form a coherent monitoring and processing chain.

[0027] Specifically, the data acquisition module 11 can periodically or instantly acquire operational status data of a device 2, such as, but not limited to, internal liquid temperature, flow rate and level, gas pressure, gas composition, vibration, etc. The data modeling module 12 can establish or update a data association model based on the data acquired by the data acquisition module 11. This model characterizes the correlation and variation range between various data points under normal operating conditions, such as, but not limited to, the correlation between temperature and level, gas pressure and level, or flow rate and level. It is worth noting that as the data acquisition module 11 continuously acquires new data, the data modeling module 12 also continuously adjusts the structure or parameters of the data association model. Therefore, the data association model can evolve and learn over time to more accurately reflect the current operational status characteristics and correlations of the device 2.

[0028] In addition, the anomaly detection module 13 can utilize the latest version of the data association model to determine whether the current operating status of device 2 is abnormal. For example, the anomaly detection module 13 makes a judgment based on the deviation between the model's predicted value and the actual value, or a violation of rule patterns. When the anomaly detection module 13 determines that the current operating status of device 2 is abnormal, the status indication module 14 can output anomaly indication messages, such as, but not limited to, audible and visual alarms, to assist maintenance personnel in immediately grasping the abnormal situation and activating the response mechanism. For example, the status indication module 14 can be a light indicator, as shown in Figure 3, where a solid green indicator light indicates that device 2 is operating normally; a lit yellow indicator light indicates a warning state (such as a liquid level slightly below the normal range); and a lit red indicator light indicates an abnormal state (such as a liquid level that is too low), requiring immediate action. If necessary, a buzzer can be activated simultaneously when the red indicator light is lit.

[0029] In this invention, the data acquisition module 11 is configured to obtain the first operating status data of device 2 within the first predetermined monitoring period; the data modeling module 12 is configured to establish a data association model using the first operating status data. The data association model characterizes the change behavior of the liquid level height inside device 2 with a standard liquid level height as a state parameter changes. Then, the data acquisition module 11 is configured to obtain the second operating status data of device 2 within the next N predetermined monitoring periods, where N is a natural number greater than or equal to 1; the data modeling module 12 is configured to update the data association model using the second operating status data. The updated data association model incorporates the second operating status data, and the weight of the second operating status data is greater than that of the first operating status data. Therefore, the updated data association model better reflects the latest health standards of device 2. Then, the anomaly judgment module 13 uses the updated data association model to determine whether the operating status of device 2 is abnormal based on the change in the liquid level height inside device 2; when the operating status of device 2 is judged to be abnormal, the status indication module outputs an anomaly indication message.

[0030] The equipment applicable to this invention includes, but is not limited to: transformers, chemical storage tanks, electrolytic cells, semiconductor process equipment, cooling towers or cooling system water tanks, boiler feedwater tanks, and hydraulic tanks. The equipment status parameters applicable to this invention are highly correlated with changes in liquid level, including but not limited to: thermodynamic parameters (such as temperature and pressure), mechanical parameters (such as flow rate and pump speed), electrical parameters (such as current and power), and chemical parameters (such as concentration and gas production).

[0031] The device anomaly monitoring device 1 of this invention may further include a data storage module 15 and a display module 16. The data storage module 15 is used to store raw data (such as first and second operating status data), judgment information (such as anomaly judgment results), processing intermediate information, model body, etc. The display module 16 is used to display raw data or judgment information. For example, the display module 16 may be a display window, as shown in Figure 2, whose displayed content may include real-time monitoring data obtained by the data acquisition module 11 or information generated by the anomaly judgment module 13.

[0032] In practical applications, the device anomaly monitoring device 1 of this invention may also include a chassis 17, which may be located near the device 2. In addition, at least one circuit board B may be installed inside the chassis 17, and the data acquisition module 11, data modeling module 12, anomaly judgment module 13, status indication module 14, storage module 15 and display module 16 may be integrated on at least one circuit board B. Each module may be implemented by hardware circuitry or executed in the controller through software / firmware, depending on actual needs.

[0033] As shown in Figures 2 and 3, in this embodiment, a sensing module 3 is provided on the device 2. The sensing module 3 can be configured to continuously acquire the operating status data of the device 2 at a fixed sampling frequency in each unit time period (e.g., each day) within each predetermined monitoring cycle (e.g., every 30 days). This data mainly includes the representative temperature of the internal liquid L (e.g., the wall temperature reflecting the actual temperature of the internal liquid L) and the liquid level. Specifically, as shown in Figure 2, the sensing module 3 can be a temperature-liquid level composite sensor, which is attached to the outer wall surface of the bottom wall 21 of the device 2 to simultaneously measure the representative temperature and liquid level of the internal liquid L. Alternatively, as shown in Figure 3, the sensing module 3 can include a temperature sensor 31 and a liquid level sensor 32. The temperature sensor 31 is attached to the outer wall surface of the side wall 22 of the device 2 to measure the representative temperature of the internal liquid L, and the probe of the liquid level sensor 32 is disposed inside the device 2 to measure the liquid level of the internal liquid L. However, the above description is only a feasible implementation of this invention and is not intended to limit this invention. For example, in some embodiments, the temperature sensor 31 may also be attached to the outer wall surface of the bottom wall 21 of the device 2.

[0034] Furthermore, the data acquisition module 11 is electrically connected to the sensing module 3 and configured to acquire data measured by the sensing module 3 via wired or wireless transmission. The data modeling module 12 can preprocess the data acquired by the data acquisition module 11 (such as removing noise, averaging, or medianing), and can use linear regression, multinomial fitting, nonparametric models, and / or machine learning methods to establish or update a data association model based on the equipment operating status data. In this embodiment, the data association model can be characterized as a functional correspondence between the state parameters and the liquid level height established by the data modeling module 12 based on the first operating status data, or modified and optimized based on the second operating status data.

[0035] As shown in Figure 5, the functional relationship between the state parameters and liquid level established based on the first operating state data can be characterized by an initial liquid level-temperature characteristic curve C1. This initial liquid level-temperature characteristic curve C1 consists of multiple standard corresponding points P1-P9, specifically presenting the standard liquid level change behavior of the liquid level inside device 2 with temperature changes during the first predetermined monitoring cycle. This initial liquid level-temperature characteristic curve C1 can be further stored in the storage module 15 as a benchmark for judging abnormal liquid level.

[0036] Furthermore, in the program for establishing a data association model based on the first operating state data, the data modeling module 12 calculates and generates multiple standard corresponding points P1-P9 on the initial liquid level height-temperature characteristic curve C1 according to the following mathematical relationship (Equation 1): Formula 1 In Equation 1, S1 represents the standard liquid level height at specific temperatures for each standard point P1-P9 on the initial liquid level height-temperature characteristic curve C1; T1 represents the total number of unit time periods within the first predetermined monitoring cycle; H1 represents the sum of multiple liquid level heights sampled at specific temperatures within the first predetermined monitoring cycle. Taking a predetermined monitoring cycle of 30 days as an example, if the unit time period is set to 1 day, then T1 is 30; and the sum of the liquid level heights (or average liquid level heights) sampled at specific temperatures within each unit time period, accumulated over all 30 unit time periods within the first predetermined monitoring cycle, is H1.

[0037] As shown in Figure 6, the functional relationship between the state parameters corrected and optimized based on the second operating state data and the liquid level height can be characterized by a reconstructed liquid level height-temperature characteristic curve C2. This reconstructed liquid level height-temperature characteristic curve C2 consists of multiple standard corresponding points P10-P18, specifically presenting the standard liquid level height change behavior of the liquid inside device 2 with temperature changes over the next N predetermined monitoring cycles. This reconstructed liquid level height-temperature characteristic curve C2 can be further stored in the storage module 15 as a reference model for judging abnormal liquid level heights.

[0038] Furthermore, in the process of correcting and optimizing the data association model based on the second operating state data, the data modeling module 12 generates a reconstructed liquid level-temperature characteristic curve C2 by fusing the first and second operating state data. The data modeling module 12 calculates and generates multiple standard corresponding points P10-P18 on the reconstructed liquid level-temperature characteristic curve C2 according to the following mathematical relationship (Equation 2): Formula 2 In Equation 2, S2 represents the standard liquid level height at specific temperatures for each standard point P10-P18 on the reconstructed liquid level height-temperature characteristic curve C2; ​​T2 represents the total number of unit time periods within the next N predetermined monitoring cycles; H2 represents the sum of multiple liquid level heights sampled at specific temperatures within the next N predetermined monitoring cycles. Taking a predetermined monitoring cycle of 30 days as an example, if the unit time period is set to 1 day, then T2 is 30; and the sum of the liquid level heights (or average liquid level heights) sampled at specific temperatures within each unit time period, accumulated over all 30 unit time periods within the next N predetermined monitoring cycles, is H2.

[0039] In practical applications, the anomaly detection module 13 can set an upper limit value and a lower limit value of the liquid level height corresponding to a predetermined temperature according to the reconstructed liquid level height-temperature characteristic curve C2. When the temperature sampled by the data acquisition module 11 reaches the predetermined temperature, the anomaly detection module 13 determines whether the sampled liquid level height is higher than the upper limit value or lower than the lower limit value. If so, the anomaly detection module 13 determines that the operating equipment has an abnormal condition.

[0040] It is worth noting that the data modeling module 12 can continuously import new data acquired during subsequent monitoring cycles to dynamically update the established data association model, enabling it to adaptively adjust and reflect the latest operating status of the equipment in real time. Through this mechanism, the anomaly detection module 13 can make judgments based on continuously optimized health assessment standards. This architecture can be widely applied to equipment fields requiring long-term condition monitoring, such as, but not limited to, power equipment and industrial machinery. Furthermore, the equipment anomaly monitoring device 1 of this invention employs a dynamic data weighting adjustment mechanism. Utilizing the characteristic that data weights decay over time, it automatically reduces the weight of earlier data in model calculations, maintaining model accuracy while effectively reducing the storage requirements for earlier data, further improving storage space utilization and overall computational performance.

[0041] [Second Embodiment]

[0042] Referring to Figure 7, the second embodiment of this invention provides an anomaly monitoring method based on iterative data updates. Step S100 involves obtaining first operating status data of the device within a first predetermined monitoring period to establish a data association model; step S102 involves obtaining second operating status data of the device within the next N predetermined monitoring periods to update the data association model; step S104 involves using the updated data association model to determine if the device's operating status is abnormal; and step S106 involves outputting an anomaly warning message when the device's operating status is determined to be abnormal. This anomaly monitoring method can be implemented using the device anomaly monitoring device described in the first embodiment.

[0043] As shown in Figure 5, in step S100, the first operating status data includes a dataset of samples taken during the first predetermined monitoring period reflecting the changes in the liquid level height of the internal liquid with the state parameters; and the established data association model can be characterized as a functional correspondence between the equipment state parameters and the liquid level height based on the first operating status data. In this embodiment, the conversion function relationship between the equipment state parameters and the liquid level height based on the first operating status data can be characterized by an initial liquid level height-temperature characteristic curve C1.

[0044] Furthermore, in the process of establishing the data association model, multiple standard corresponding points P1-P9 on the initial liquid level height-temperature characteristic curve C1 can be calculated and generated according to the following mathematical relationship (Equation 1): Formula 1 In Equation 1, S1 represents the standard liquid level height at a specific temperature at each standard corresponding point P1-P9 on the initial liquid level height-temperature characteristic curve C1; T1 represents the total number of unit time periods within the first predetermined monitoring cycle; H1 represents the sum of multiple liquid level heights sampled at a specific temperature within the first predetermined monitoring cycle.

[0045] As shown in Figure 6, in step S102, the second operating status data includes a dataset reflecting the changes in the liquid level height of the internal liquid with the state parameters, sampled over the next N predetermined monitoring periods, where N is a natural number greater than or equal to 1; and the updated data association model can be characterized as a functional correspondence between the equipment state parameters and the liquid level height based on the first and second operating status data. In this embodiment, the functional correspondence between the equipment state parameters and the liquid level height based on the first and second operating status data can be characterized by a reconstructed liquid level height-temperature characteristic curve C2.

[0046] Furthermore, in the process of updating the data association model, the reconstructed liquid level-temperature characteristic curve C2 is generated by fusing the first operating state data and the second operating state data. Multiple standard corresponding points P10-P18 on the reconstructed liquid level-temperature characteristic curve C2 can be calculated and generated according to the following mathematical relationship (Equation 2): Formula 2 In Equation 2, S2 represents the standard liquid level height at a specific temperature for each standard corresponding point P10-P18 on the reconstructed liquid level height-temperature characteristic curve C2; ​​T2 represents the total number of unit time periods within the next N predetermined monitoring cycles; H2 represents the sum of multiple liquid level heights sampled at a specific temperature within the next N predetermined monitoring cycles.

[0047] In step S104, an upper limit value and a lower limit value of the liquid level height corresponding to a predetermined temperature can be set according to the reconstructed liquid level height-temperature characteristic curve C2; ​​when the sampling temperature reaches the predetermined temperature, it is determined whether the sampling liquid level height is higher than the upper limit value of the oil level height or lower than the lower limit value of the oil level height. If so, it is determined that there is an abnormal condition in the operating equipment.

[0048] In step S106, when the operating equipment is determined to have an abnormal condition, an audible and visual alarm can be output (such as lighting up a red indicator light and activating a buzzer) to help maintenance personnel immediately grasp the abnormal condition and activate the emergency response mechanism.

[0049] [Beneficial Effects of the Examples]

[0050] In summary, the device and method for monitoring equipment anomalies based on iterative data updates provided in this invention, by "obtaining first operating status data of a device within the first predetermined monitoring period to establish a data association model", "obtaining second operating status data of the device within the next N predetermined monitoring periods to update the data association model", and "incorporating the second operating status data into the updated data association model, with the weight of the second operating status data being greater than that of the first operating status data", can achieve dynamic information updates and long-term learning capabilities, so as to quickly adapt to changes in the operating environment, load conditions, or device status of the device, and can more timely identify sudden anomalies or long-term accumulated anomaly trends.

[0051] Furthermore, the equipment anomaly monitoring device and method of this invention can continuously import new data acquired in subsequent monitoring cycles to dynamically update the established data association model, enabling it to adaptively adjust and reflect the latest operating status of the equipment in real time. This allows for judgment based on continuously optimized health assessment standards. Such an architecture can be widely applied to equipment fields that require long-term condition monitoring, such as, but not limited to, power equipment and industrial machinery.

[0052] Furthermore, the device and method for monitoring equipment anomalies in this invention employs a dynamic data weighting adjustment mechanism. It utilizes the characteristic that data weights decay over time to automatically reduce the weight of early data in model calculations, thereby maintaining model accuracy while effectively reducing the storage requirements for early data, further improving the efficiency of storage space utilization and overall computing performance.

[0053] The content disclosed above is only a preferred and feasible embodiment of this invention, and is not intended to limit the scope of the patent application of this invention. Therefore, all equivalent technical changes made using the contents of this invention's specification and drawings are included within the scope of the patent application of this invention.

[0054] 1: Equipment anomaly monitoring device 11: Data Acquisition Module 12: Data Modeling Module 13: Anomaly Detection Module 14: Status Indicator Module 15: Data Storage Module 16: Display Module 2: Equipment 21:Bottom wall 22: Sidewall 3: Sensing Module 31: Temperature sensor 32: Liquid level sensor C1: Initial liquid level height-temperature characteristic curve C2: Reconstructed liquid level-temperature characteristic curve L: Internal fluid P1-P18: Standard Corresponding Points S100-S106: Steps

Claims

1. A device for monitoring equipment anomalies based on iterative data updates, comprising a chassis and a circuit board disposed within the chassis, wherein the circuit board integrates a data acquisition module, a data modeling module, an anomaly detection module, and a status indication module; wherein, The data acquisition module is configured to obtain first operating status data of a device within a first predetermined monitoring period; the data modeling module is configured to establish a data association model using the first operating status data; wherein, the data acquisition module is configured to obtain second operating status data of the device within the next N predetermined monitoring periods, where N is a natural number greater than or equal to 1; the data modeling module is configured to update the data association model using the second operating status data; wherein, the updated data association model incorporates the second operating status data, and the weight of the second operating status data is greater than that of the first operating status data; wherein, the anomaly judgment module is configured to use the updated data association model to determine whether the operating status of the device is abnormal based on the change in the liquid level height inside one of the devices; the status indication module is configured to output an anomaly indication message when the operating status of the device is determined to be abnormal.

2. The device anomaly monitoring device based on data iterative updates as described in claim 1, wherein, The first operating status data includes a dataset of samples taken by the data acquisition module during the first predetermined monitoring period, reflecting the change of the liquid level height of the internal liquid with the state parameters, and the data association model characterizes the functional correspondence between the state parameters and the liquid level height of the internal liquid established by the data modeling module based on the first operating status data.

3. The device anomaly monitoring device based on data iterative updates as described in claim 2, wherein, The functional relationship is presented in the form of a curve showing the relationship between liquid level and temperature.

4. The device for monitoring equipment anomalies based on iterative data updates as described in claim 3, wherein, The curve relating liquid level height to temperature is composed of multiple standard corresponding points. In the data modeling module's program for establishing the data association model, each standard corresponding point is generated by the following formula 1: Formula 1 In Formula 1, S1 represents the standard liquid level height at a specific temperature of the standard corresponding point of the curve relating liquid level height to temperature; T1 represents the total number of unit time periods within the first predetermined monitoring period; H1 represents the sum of multiple liquid level heights sampled at the specific temperature within the first predetermined monitoring period.

5. The device for monitoring equipment anomalies based on iterative data updates as described in claim 4, wherein, In the process of updating the data association model, the data modeling module reconstructs the temperature change relationship curve corresponding to the liquid level height based on the second operating status data. The second operating status data includes a dataset of liquid level heights reflecting the changes in the state parameters of the internal liquid sampled by the data acquisition module within the next N predetermined monitoring periods. The standard corresponding point of the reconstructed temperature change relationship curve is generated by the following formula 2: Formula 2 In Formula 2, S2 represents the standard liquid level height at a specific temperature of the standard corresponding point of the reconstructed temperature change relationship curve; T2 represents the total number of unit time periods within the next N predetermined monitoring periods; H2 represents the sum of multiple liquid level heights sampled at the specific temperature within the next N predetermined monitoring periods.

6. The device for monitoring equipment anomalies based on iterative data updates as described in claim 1, wherein, The status indicator module is a light indicator, which includes a green indicator light, a yellow indicator light and a red indicator light.

7. The device anomaly monitoring apparatus based on data iterative updates as described in claim 1, wherein, A display module is integrated on the circuit board and is exposed outside the chassis.

8. A device status monitoring system, comprising a device and a device anomaly monitoring apparatus as described in claim 1, wherein a sensing module is provided on the device, and the data acquisition module is electrically connected to the sensing module to acquire data measured by the sensing module.

9. The equipment condition monitoring system as described in claim 8, wherein, The sensing module is a temperature-liquid level composite sensor, which is attached to the outer wall of a bottom wall of the device to simultaneously measure the representative temperature and liquid level of an internal liquid in the device.

10. The equipment condition monitoring system as described in claim 8, wherein, The sensing module includes a temperature sensor and a liquid level sensor. The temperature sensor is attached to the outer wall of one side wall or one bottom wall of the device to measure the representative temperature of an internal liquid in the device, and a probe of the liquid level sensor is disposed inside the device to measure the liquid level height of an internal liquid in the device.

Images