A smart fusion terminal integrating circuit breaker condition monitoring and adaptive control

Abstract

This invention relates to the field of power monitoring technology, specifically to an intelligent fusion terminal integrating circuit breaker condition monitoring and adaptive control. It obtains the load harmonic coupling coefficient at any given time based on the correlation characteristics of changes in active power and total harmonic distortion rate within preset adjacent time periods. The coupling coefficient sequence is decomposed using STL time series decomposition to obtain a trend term and a residual term. Based on the difference between the trend term and the predicted trend value at any given time, and the residual term, a health deviation index is obtained. The rate of change is obtained based on the changing characteristics of the health deviation index. The future health deviation index for the next time moment is obtained based on the rate of change and the current health deviation index. This invention obtains a safe duration based on a preset health deviation index threshold, the current health deviation index, and the rate of change. It monitors and controls the circuit based on the future health deviation index and the safe duration, improving power supply reliability, early warning, and the accuracy of control.

Description

Technical Field

[0001] This invention relates to the field of power monitoring technology, specifically to an intelligent fusion terminal that integrates circuit breaker status monitoring and adaptive control. Background Technology

[0002] The intelligent fusion terminal integrates real-time acquisition functions of electrical parameters such as current, voltage, power, and power quality, and has built-in protection logic for overcurrent, overload, and short circuit of circuit breakers. It can quickly perform tripping actions when the electrical quantity exceeds the preset fixed threshold to ensure line safety. At the same time, as the core of data aggregation and processing, the intelligent fusion terminal can realize centralized monitoring of power consumption data of multiple circuits, remote visualization display, and basic remote opening and closing control, thereby realizing preliminary perception and basic control of power consumption status.

[0003] While existing intelligent fusion terminals and intelligent circuit breakers can collect, remotely monitor, and provide early warnings of fixed threshold overruns for multiple circuit electrical parameters, and possess basic power management capabilities under steady-state operating conditions, in actual power distribution scenarios, when faced with complex conditions such as dynamic load fluctuations, equipment aging (in the early stages of aging, frequency converters may exhibit abnormally sensitive harmonic responses when power changes occur, even though power and harmonics have not yet exceeded limits), or intermittent anomalies (intermittent faults such as poor contact can trigger transient harmonic spikes, but existing fixed threshold monitoring cannot distinguish between them and normal disturbances), current technologies can only trigger tripping after parameters such as current exceed limits. They cannot capture early risk signs before a fault occurs, nor can they distinguish between normal load fluctuations and abnormal equipment trends, leading to decreased power supply reliability, frequent false trips, and a lack of perception of long-term changes in equipment health status. Summary of the Invention

[0004] To address the aforementioned technical problems, the present invention aims to provide an intelligent fusion terminal integrating circuit breaker status monitoring and adaptive control. The specific technical solution adopted is as follows:

[0005] The data acquisition module is used to acquire the active power sequence and total harmonic distortion (THD) sequence of the loop.

[0006] The first data analysis module is used to obtain the load harmonic coupling coefficient at any given time based on the correlation characteristics of the changes in active power and total harmonic distortion rate within a preset adjacent time period; construct a coupling coefficient sequence based on the load harmonic coupling coefficients at all times; and perform STL time series decomposition on the coupling coefficient sequence to obtain the trend term and residual term.

[0007] The second data analysis module is used to predict the trend item and obtain the trend prediction value; obtain the health deviation index at any time based on the difference characteristics between the trend item and the trend prediction value at any time and the residual item; and obtain the rate of change based on the change characteristics of the health deviation index.

[0008] The monitoring and control module is used to obtain the future health deviation index at the next moment based on the rate of change and the health deviation index at the current moment; to obtain the safe duration based on the preset health deviation index threshold, the health deviation index at the current moment, and the rate of change; and to monitor and control the loop based on the future health deviation index and the safe duration.

[0009] Furthermore, the step of obtaining the load harmonic coupling coefficient at any given time based on the correlation characteristics of changes in active power and total harmonic distortion rate within a preset adjacent time period includes:

[0010] In the formula The load harmonic coupling coefficient is represented at time t, and N represents the number of times within a preset adjacent time period. This represents the active power at time i within a preset adjacent time period at time t. This represents the average active power over a preset adjacent time period at time t. This represents the total harmonic distortion rate at time i within a preset adjacent time period at time t. denoted as the average total harmonic distortion rate within a preset adjacent time period at time t, where a represents a preset minimum positive number.

[0011] Furthermore, the step of predicting the trend term to obtain the trend prediction value includes:

[0012] The trend term is predicted by using an exponentially weighted moving average algorithm to obtain the trend prediction value at different times.

[0013] Furthermore, the step of obtaining the health deviation index at any given time based on the difference characteristics between the trend term and the predicted trend value, and the residual term, includes:

[0014] In the formula Let W represent the health deviation index at time t, W represent the trend weight value, and a represent a preset minimum positive number. This represents the value of the trend term at time t. This represents the trend prediction value at time t. express The standard deviation of the results Indicates the degree of trend deviation. The standard deviation of the residual term is represented by the standard deviation of the residual term. This represents the value of the residual term at time t. Indicates the degree of abnormality of residuals.

[0015] Furthermore, the steps for obtaining the trend weight value include:

[0016] Calculate the sum of the trend deviation and the residual abnormality to obtain the weight benchmark; calculate the ratio of the trend deviation to the weight benchmark to obtain the trend weight value.

[0017] Furthermore, the step of obtaining the rate of change based on the changing characteristics of the health deviation index includes:

[0018] The rate of change is obtained by calculating the fitted slope of the health deviation index using the least squares method.

[0019] Furthermore, the step of obtaining the future health deviation index at the next moment based on the rate of change and the health deviation index at the current moment includes:

[0020] Calculate the product of the time interval from the current moment to the next moment and the rate of change to obtain the amount of change; calculate the sum of the amount of change and the health deviation index at the current moment to obtain the future health deviation index at the next moment.

[0021] Furthermore, the step of obtaining the safe duration based on the preset health deviation index threshold, the health deviation index at the current moment, and the rate of change includes:

[0022] Calculate the difference between the preset health deviation index threshold and the health deviation index at the current moment to obtain the degree of difference; calculate the ratio of the degree of difference to the rate of change to obtain the safe duration.

[0023] Furthermore, the step of monitoring and regulating the loop based on the future health deviation index and the safety duration includes:

[0024] When the future health deviation index is not less than the preset health deviation index threshold or the safety duration is less than the preset duration, an early warning and control will be implemented.

[0025] The present invention has the following beneficial effects:

[0026] In this invention, the load harmonic coupling coefficient at any given time is obtained based on the correlation characteristics of changes in active power and total harmonic distortion rate within preset adjacent time periods. This transforms the original electrical parameters into highly sensitive fused characteristics that reflect changes in equipment status, effectively amplifying early fault symptoms compared to existing single-data monitoring. The health deviation index at any given time is obtained based on the difference between the trend term and the predicted trend value, as well as the residual term. By decomposing the load harmonic coupling coefficient into trend and residual terms and quantifying them separately, synchronous perception of slow equipment aging and precursors to sudden faults is achieved, enabling the health deviation index to accurately characterize the degree of deviation between the current equipment and its historical normal state. The rate of change is obtained based on the changing characteristics of the health deviation index, allowing for prediction of future health deviation indices and enabling early warning and control. Obtaining future health deviation indices and safe durations allows for the prediction and assessment of future risks, facilitating early control. Finally, monitoring and controlling the circuit based on future health deviation indices and safe durations represents a shift from reactive tripping to proactive prediction, significantly improving the power supply reliability of the distribution system, the early warning capability for equipment faults, and the accuracy of control strategies. Attached Figure Description

[0027] 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.

[0028] Figure 1 This is a block diagram of an intelligent fusion terminal module that integrates circuit breaker status monitoring and adaptive control, provided as an embodiment of the present invention. Detailed Implementation

[0029] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of an intelligent fusion terminal integrating circuit breaker condition monitoring and adaptive control proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0030] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0031] The following description, in conjunction with the accompanying drawings, details a specific solution for an intelligent fusion terminal integrating circuit breaker status monitoring and adaptive control provided by the present invention.

[0032] Please see Figure 1 The diagram illustrates a block diagram of an intelligent fusion terminal module integrating circuit breaker status monitoring and adaptive control according to an embodiment of the present invention. The terminal includes the following modules:

[0033] The data acquisition module S1 is used to acquire the active power sequence and total harmonic distortion rate sequence of the loop.

[0034] The active power and total harmonic distortion (THD) of the circuit are acquired using sensors built into the smart circuit breaker at a fixed sampling frequency. In this embodiment, the sampling frequency is once per second, which can be determined by the implementer according to the implementation scenario. Active power reflects the load size and heat generation level of overload protection, while THD measures power quality. The active power and THD are standardized to eliminate the influence of dimensions, ultimately obtaining standardized active power and THD sequences.

[0035] The first data analysis module S2 is used to obtain the load harmonic coupling coefficient at any time based on the correlation characteristics of the changes in active power and total harmonic distortion rate in preset adjacent time periods at any time; to construct a coupling coefficient sequence based on the load harmonic coupling coefficients at all times; and to perform STL time series decomposition on the coupling coefficient sequence to obtain the trend term and residual term.

[0036] To achieve early warning of load anomalies and equipment aging in complex power consumption scenarios, it is necessary to address the problems of traditional single electrical quantity monitoring failing to capture the evolution trend of equipment status and being susceptible to load fluctuation interference. Because equipment absorbs non-sinusoidal current from the grid during operation, generating harmonics, the amount of harmonic generation is closely related to the load size (active power). The total harmonic distortion rate (THD) is typically low under light loads and increases under heavy loads. To extract deep features from the original electrical parameters that can sensitively reflect changes in equipment status, it is necessary to address the locality of traditional single electrical quantity monitoring, which only focuses on numerical magnitude and cannot capture the dynamic coupling relationship between parameters. This invention constructs a load harmonic coupling coefficient by calculating the linear regression slope of active power and THD within pre-set adjacent time periods. This aims to quantify the dynamic response of harmonic characteristics when the load changes, thereby obtaining a highly sensitive fusion feature for changes in equipment status. First, the load change characteristics are analyzed. This feature is based on the dispersion of active power within a local time period. By calculating the deviation of active power at each moment within this local time period from the average active power, the magnitude of the change in the power condition is quantified from the perspective of load fluctuation. Then, harmonic response characteristics are calculated. These characteristics are based on the synchronous change characteristics of the total harmonic distortion rate (THD) within a local time period. By calculating the deviation between the THD and the average THD at each moment, the electromagnetic response of the equipment to load changes is quantified from the perspective of harmonic distortion. Finally, the two characteristics are fitted by linear regression to calculate the slope of the THD response to active power, which is used as the load harmonic coupling coefficient. This coefficient represents the change in THD caused by a unit power change, and can amplify subtle changes in harmonic characteristics during equipment aging or the initial stage of anomalies, providing a highly sensitive input feature for further analysis. Therefore, the load harmonic coupling coefficient at any moment is obtained based on the correlation characteristics of changes in active power and THD within a preset adjacent time period at any moment. Preferably, in this embodiment of the invention, the step of obtaining the load harmonic coupling coefficient includes:

[0037]

[0038] In the formula, The load harmonic coupling coefficient is represented at time t, and N represents the number of times within a preset adjacent time period. This represents the active power at time i within a preset adjacent time period at time t. This represents the average active power over a preset adjacent time period at time t. This represents the total harmonic distortion rate at time i within a preset adjacent time period at time t. This represents the average total harmonic distortion rate over a preset adjacent time period at time t. 'a' represents a preset minimum positive number, which, in this embodiment of the invention, is taken as... In this embodiment of the invention, when the denominator of any formula is 0, it is replaced by a preset minimum positive number. The formula for the load harmonic coupling coefficient corresponds to the slope calculation formula of a univariate linear regression, which characterizes the change in total harmonic distortion rate caused by a unit power change. The upper limit of the summation sign is time t, and the lower limit is the first time within a preset adjacent time period of time t. In this embodiment of the invention, N is 10, which can be determined by the implementer according to the implementation scenario. The longer the preset adjacent time period, the more stable the statistics, but the slower the response to changes; the shorter the preset adjacent time period, the faster the response, but the more susceptible to transient interference. Constructing the load harmonic coupling coefficient can transform the original electrical parameters into highly sensitive fusion features for changes in equipment status, effectively amplifying early fault symptoms compared to existing single-data monitoring.

[0039] Furthermore, in this formula, if the numerator is large and the denominator increases accordingly, the ratio will be normal. For example, during periods of high electricity consumption, active power increases, and harmonics also increase, thus keeping the load harmonic coupling coefficient within the normal range and preventing false alarms caused by power increases. However, an abnormally large numerator will result in a large ratio, indicating unstable harmonic fluctuations, which is a clear anomaly. If the numerator is large but the denominator is small, it means that the power change is not significant, but the system is very sensitive to harmonics. In this case, even slight early signs of harmonic anomalies will cause the abnormal fluctuations to be significantly amplified, resulting in a large load harmonic coupling coefficient. If both the numerator and denominator are small, it indicates that the system is in a normal low-load state, and the coupling coefficient is within the normal range. It should be noted that if the numerator is small but the denominator is large, it means that the system is designed to decouple the load and harmonics. This situation occurs in cases such as purely resistive circuits, but will not occur in normal circuits. In this embodiment of the invention, it is not considered; only scenarios where the load and harmonics are coupled are analyzed.

[0040] Load harmonic coupling coefficients can sensitively reflect changes in equipment status from a dynamic coupling perspective. However, as a statistical feature based on a local time period, it still contains various components such as long-term aging trends, periodic load fluctuations (e.g., daily and weekly variations), sudden anomalies, and random noise, making it difficult to directly use as a stable health monitoring indicator. Therefore, this paper first introduces the existing STL time-series decomposition method to construct a coupling coefficient sequence from the load harmonic coupling coefficients at different times, and then decomposes this sequence. Specifically, a coupling coefficient sequence is constructed based on the load harmonic coupling coefficients at all times; the coupling coefficient sequence is then subjected to STL time-series decomposition to obtain the trend term and residual term. It should be noted that STL is an existing technology, and the specific steps are not detailed here. This algorithm can decompose the sequence into a trend term, a seasonal term, and a residual term. The trend term characterizes the long-term performance evolution of the equipment, the seasonal term characterizes the periodic load fluctuation pattern, and the residual term characterizes sudden anomalies and random fluctuations. Removing the seasonal term after decomposition allows the trend term and residual term to be free from the interference of periodic external factors, more accurately reflecting changes in the equipment's own status.

[0041] The second data analysis module S3 is used to predict the trend term and obtain the trend prediction value; to obtain the health deviation index at any time based on the difference characteristics between the trend term and the trend prediction value at any time and the residual term; and to obtain the rate of change based on the change characteristics of the health deviation index.

[0042] After obtaining the trend term and residual term of the coupling coefficient sequence, for the trend term, a trend deviation can be constructed based on the prediction error to reflect the degree of equipment aging or performance degradation; for the residual term, the degree of residual can reflect the intensity of sudden anomalies; and to further improve the robustness of the evaluation, the proportion of real-time deviation is introduced as an independent evaluation criterion to adjust the weights, thereby realizing the quantification of the adaptive weighted health deviation index. First, the trend term is predicted to obtain the trend prediction value. In this embodiment of the invention, the existing exponentially weighted moving average algorithm is used to predict the trend term with a longer historical history to obtain the trend prediction values ​​at different recent times. Then, based on the difference characteristics between the trend term and the trend prediction value at any given time, and the residual term, the health deviation index at any given time is obtained; preferably, in this embodiment of the invention, the step of obtaining the health deviation index includes:

[0043]

[0044] In the formula, Let W represent the health deviation index at time t, W represent the trend weight value, and a represent a preset minimum positive number. This represents the value of the trend term at time t. This represents the trend prediction value at time t. express The standard deviation of the results Indicates the degree of trend deviation. The standard deviation of the residual term is represented by the standard deviation of the residual term. This represents the value of the residual term at time t. This indicates the residual abnormality. It should be noted that in this formula... and Calculations are performed using extensive historical data to improve the reliability of the results. The standard deviation of the denominator allows for normalization of the numerator. The trend deviation represents the degree to which the trend deviates from the expected normality at a given moment. A larger value indicates more significant equipment aging or performance degradation. A larger residual indicates greater residual abnormality and a more severe sudden anomaly. The steps to obtain the trend weight value include: calculating the sum of the trend deviation and the residual abnormality to obtain the weight benchmark; and calculating the ratio of the trend deviation to the weight benchmark to obtain the trend weight value. A larger trend deviation corresponds to a larger trend weight value, enabling the health deviation index to dynamically focus on the most significant risk source and sensitively reflect the most significant changes in equipment status. Thus, the coupling coefficient sequence is decomposed into trend and residual terms and quantified separately, achieving synchronous perception of equipment aging and precursors to sudden failures. Simultaneously, adaptive weights are obtained through the trend deviation ratio, generating a stable and robust health deviation index.

[0045] The health deviation index characterizes the degree of deviation of a device from its historical normal state. A larger value indicates a higher likelihood of anomalies. However, this value is still a quantitative description of the current state and cannot predict the evolution trend and timing of future risks. Therefore, a prediction mechanism is introduced. First, the rate of change is obtained based on the changing characteristics of the health deviation index. In this embodiment, the rate of change is obtained by calculating the fitting slope of the health deviation index using the least squares method. The rate of change characterizes the recent trend of the health deviation index, and thus, the future health deviation index can be predicted based on the rate of change.

[0046] The monitoring and control module S4 is used to obtain the future health deviation index at the next moment based on the rate of change and the health deviation index at the current moment; to obtain the safe duration based on the preset health deviation index threshold, the health deviation index at the current moment and the rate of change; and to monitor and control the loop based on the future health deviation index and the safe duration.

[0047] After obtaining the rate of change, the future health deviation index for the next moment can be obtained based on the rate of change and the health deviation index at the current moment. Specifically, this includes: calculating the product of the time interval from the current moment to the next moment and the rate of change to obtain the amount of change; and calculating the sum of the amount of change and the health deviation index at the current moment to obtain the future health deviation index for the next moment. By calculating the future health deviation index for the next moment, early warning and control can be achieved. Simultaneously, the time to reach a preset health deviation index threshold can be determined based on the rate of change. Therefore, a safe duration is obtained based on the preset health deviation index threshold, the health deviation index at the current moment, and the rate of change. Preferably, in this embodiment of the invention, the step of obtaining the safe duration includes: calculating the difference between the preset health deviation index threshold and the health deviation index at the current moment to obtain the degree of difference; and calculating the ratio of the degree of difference to the rate of change to obtain the safe duration. It should be noted that when the rate of change is less than 0, it means that the equipment status has improved, and the safe duration does not need to be calculated. The safe duration represents the remaining time before the warning is needed. Based on this safe duration, the equipment should be controlled as soon as possible to ensure safe operation. In this embodiment of the invention, the preset health deviation index threshold is taken as the 99.9th percentile of the historical health deviation index sequence without warning, and the implementer can determine it according to the implementation scenario.

[0048] After obtaining the future health deviation index and safe duration for the next moment, the circuit can be monitored and controlled based on these indicators. In this embodiment of the invention, multiple threshold levels are preset, and differentiated control commands are dynamically decided and executed to achieve adaptive hierarchical protection of the power circuit. When the future health deviation index is not less than the preset health deviation index threshold or the safe duration is less than the preset duration, an early warning and control are initiated. For example, when the future health deviation index is less than the preset health deviation index threshold and the safe duration is not less than the preset duration, it means the circuit is operating normally and no early warning is issued. In this embodiment of the invention, the preset duration is 60 minutes. When the safe duration is between 10 and 60 minutes, the circuit is in a monitoring state; when the safe duration is less than 10 minutes, the circuit is in an early warning state; and when the future health deviation index is greater than the preset health deviation index threshold, the circuit is in an emergency state. Furthermore, corresponding control schemes are matched based on the determined risk level, such as flexible adjustment of power reduction operation, intermittent power supply, and emergency tripping. The implementer can determine the early warning and control methods according to the implementation scenario. After the control command is issued, the health deviation index of the circuit is continuously monitored. If the risk is not eliminated, the control level is automatically upgraded. If the risk has been resolved, the circuit is gradually restored to the normal power supply mode.

[0049] In summary, this invention provides an intelligent fusion terminal integrating circuit breaker condition monitoring and adaptive control. It obtains the load harmonic coupling coefficient at any given time based on the correlation characteristics of changes in active power and total harmonic distortion rate within preset adjacent time periods. The coupling coefficient sequence is decomposed using STL time series decomposition to obtain a trend term and a residual term. The health deviation index at any given time is obtained based on the difference between the trend term and the predicted trend value, and the residual term. The rate of change is obtained based on the changing characteristics of the health deviation index. The future health deviation index for the next time moment is obtained based on the rate of change and the current health deviation index. This invention obtains a safe duration based on a preset health deviation index threshold, the current health deviation index, and the rate of change. It monitors and controls the circuit based on the future health deviation index and the safe duration, improving power supply reliability, early warning, and the accuracy of control.

[0050] 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. The processes depicted in the accompanying 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.

[0051] 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.

Claims

1. An intelligent fusion terminal integrating circuit breaker status monitoring and adaptive regulation, characterized in that, The terminal includes the following modules: The data acquisition module is used to acquire the active power sequence and total harmonic distortion (THD) sequence of the loop. The first data analysis module is used to obtain the load harmonic coupling coefficient at any given time based on the correlation characteristics of the changes in active power and total harmonic distortion rate within a preset adjacent time period; and to construct a coupling coefficient sequence based on the load harmonic coupling coefficients at all times. STL time series decomposition is performed on the coupling coefficient sequence to obtain the trend term and residual term; The second data analysis module is used to predict the trend item and obtain the trend prediction value; The health deviation index at any given time is obtained based on the difference characteristics between the trend term and the predicted trend value at any given time, and the residual term. The rate of change is obtained based on the changing characteristics of the health deviation index; The monitoring and control module is used to obtain the future health deviation index at the next moment based on the rate of change and the health deviation index at the current moment. The safe duration is obtained based on the preset health deviation index threshold, the health deviation index at the current moment, and the rate of change. The loop is monitored and regulated based on the future health deviation index and the safety duration. The step of obtaining the load harmonic coupling coefficient at any given time based on the correlation characteristics of changes in active power and total harmonic distortion rate within a preset adjacent time period includes: In the formula The load harmonic coupling coefficient is represented at time t, and N represents the number of times within a preset adjacent time period. Let represent the active power at time i within a preset adjacent time period at time t. This represents the average active power over a preset adjacent time period at time t. This represents the total harmonic distortion rate at time i within a preset adjacent time period at time t. This represents the average total harmonic distortion rate within a preset adjacent time period at time t, where a represents a preset minimum positive number; The step of obtaining the health deviation index at any given time based on the difference characteristics between the trend term and the predicted trend value, and the residual term, includes: In the formula Let W represent the health deviation index at time t, W represent the trend weight value, and a represent a preset minimum positive number. This represents the value of the trend term at time t. This represents the trend prediction value at time t. express The standard deviation of the results Indicates the degree of trend deviation. The standard deviation of the residual term is represented by the standard deviation of the residual term. This represents the value of the residual term at time t. Indicates the degree of abnormality of residuals.

2. The intelligent fusion terminal integrating circuit breaker condition monitoring and adaptive control according to claim 1, characterized in that, The step of predicting the trend term and obtaining the trend prediction value includes: The trend term is predicted by using an exponentially weighted moving average algorithm to obtain the trend prediction value at different times.

3. The intelligent fusion terminal integrating circuit breaker condition monitoring and adaptive control according to claim 1, characterized in that, The steps for obtaining the trend weight value include: Calculate the sum of the trend deviation and the residual abnormality to obtain the weight benchmark; calculate the ratio of the trend deviation to the weight benchmark to obtain the trend weight value.

4. The intelligent fusion terminal integrating circuit breaker condition monitoring and adaptive control according to claim 1, characterized in that, The step of obtaining the rate of change based on the change characteristics of the health deviation index includes: The rate of change is obtained by calculating the fitted slope of the health deviation index using the least squares method.

5. The intelligent fusion terminal integrating circuit breaker condition monitoring and adaptive control according to claim 1, characterized in that, The step of obtaining the future health deviation index at the next moment based on the rate of change and the current health deviation index includes: Calculate the product of the time interval from the current moment to the next moment and the rate of change to obtain the amount of change; calculate the sum of the amount of change and the health deviation index at the current moment to obtain the future health deviation index at the next moment.

6. The intelligent fusion terminal integrating circuit breaker condition monitoring and adaptive control according to claim 1, characterized in that, The step of obtaining the safe duration based on a preset health deviation index threshold, the current health deviation index, and the rate of change includes: Calculate the difference between the preset health deviation index threshold and the health deviation index at the current moment to obtain the degree of difference; calculate the ratio of the degree of difference to the rate of change to obtain the safe duration.

7. The intelligent fusion terminal integrating circuit breaker condition monitoring and adaptive control according to claim 1, characterized in that, The step of monitoring and regulating the loop based on the future health deviation index and the safe duration includes: When the future health deviation index is not less than the preset health deviation index threshold or the safety duration is less than the preset duration, an early warning and control will be implemented.

Images