Fault monitoring system of power adapter

Abstract

The invention belongs to the technical field of power management, and discloses a fault monitoring system of a power adapter, which comprises a data collection module used for collecting parameter data, electrical performance data and adapter working environment data of the power adapter; the data processing module is used for performing feature extraction on the power adapter parameter data, the electrical performance data and the working environment data to obtain an adapter parameter feature data set, an electrical performance feature data set and a working environment feature data set; the fault state detection module is used for performing weighted fusion on the adapter parameter feature data set, the electrical performance feature data set and the working environment feature data set through a weighted model to obtain a comprehensive feature data set; training according to the comprehensive feature data set to obtain an adapter fault detection model, predicting through the adapter fault detection model to obtain a power adapter fault state evaluation label, and judging whether the power adapter is in a fault state or not; and sudden faults are warned in advance.

Description

Technical Field

[0001] The present invention relates to the technical field of power management, and more particularly to a fault monitoring system for a power adapter. Background Art

[0002] Patent announcement number CN117310348A discloses a real-time monitoring method and system for power adapter faults, including: collecting the output voltage and resistance temperature of the power adapter to obtain a temperature-compensated discrete voltage sequence; obtaining a trend component sequence and a residual component sequence based on the temperature-compensated discrete voltage sequence, and obtaining a trend stability index based on the trend component sequence; obtaining a voltage local nonlinear oscillation index based on the residual component sequence; obtaining an adaptive k value based on the voltage local nonlinear oscillation index and trend stability index of the temperature-compensated discrete voltage sequence, obtaining an abnormal factor for each data point in the temperature-compensated discrete voltage sequence based on the adaptive k value, and completing real-time monitoring of power adapter faults based on the abnormal factor. The present invention solves the problem that different voltage fluctuation characteristics during the operation of the power adapter can easily lead to inaccurate fault detection of the power adapter.

[0003] The existing power adapter fault monitoring system has the following main problems:

[0004] The collected data is not timestamped and sorted, so the data's timing and consistency cannot be guaranteed. Subsequent data processing and analysis may be biased due to inconsistent or missing data, resulting in reduced accuracy of the results. Failure to use empirical mode decomposition to decompose complex signals may fail to fully reveal the different frequency components and local variation characteristics in the data. Power adapter operating data may contain multiple frequency components, and simple traditional signal processing methods may not be able to effectively capture the subtle differences, thus affecting the understanding of the data's inherent characteristics, leading to the risk of misdiagnosis and failure to accurately identify potential equipment failures.

[0005] Failure to dynamically adjust the integral variable range of the Hilbert transform may result in errors and instability in the transformation. Signals with different frequency components may require different integral ranges for accurate transformation. Ignoring this may cause errors in signals with larger or smaller frequency components, thus affecting the Hilbert transform results. This error may directly affect the accuracy and stability of fault detection, especially when the frequency components vary greatly in the electrical performance data of the power adapter.

[0006] The lack of a directed graph model for the power adapter circuit and the weighting of each edge based on different types of faults makes it impossible to accurately reflect the risk of failures between electrical components. Failures between different components are interrelated, and the lack of a comprehensive network model can lead to the omission of key fault paths, resulting in localized fault analysis and an inability to fully identify potential fault points in the adapter.

[0007] There is no mechanism for dynamically adjusting the update factor, and it is impossible to adapt to the actual conditions of different fault types and electrical components in a timely manner; the lack of flexibility in the analysis method will make it difficult to respond quickly when dealing with complex and changeable fault scenarios, and sudden faults may not be discovered in time, or incorrect fault diagnosis paths may not be corrected quickly. There is no accurate fault location and dynamic optimization mechanism, which makes it impossible for maintenance personnel to quickly diagnose problems through accurate fault location, increasing the difficulty and cost of long-term maintenance.

[0008] In view of this, the present invention proposes a fault monitoring system for a power adapter to solve the above problem. Summary of the Invention

[0009] In order to overcome the above-mentioned defects of the prior art and to achieve the above-mentioned purpose, the present invention provides the following technical solution: a fault monitoring system for a power adapter, comprising:

[0010] A data collection module is used to collect power adapter parameter data, electrical performance data, and adapter working environment data;

[0011] A data processing module is used to extract features of power adapter parameter data, electrical performance data, and working environment data based on improved empirical mode decomposition combined with Hilbert transform to obtain adapter parameter feature data sets, electrical performance feature data sets, and working environment feature data sets;

[0012] The fault state detection module is used to perform weighted fusion of the adapter parameter feature data set, the electrical performance feature data set, and the working environment feature data set through a weighted model to obtain a comprehensive feature data set; train an adapter fault detection model, input the comprehensive feature data set into the trained adapter fault detection model, predict the probability of the power adapter fault state, and determine whether the power adapter is in a fault state;

[0013] Fault type diagnosis module: If the power adapter is in a fault state, the power adapter intelligent monitoring terminal will immediately generate an early warning message and automatically collect fault status data. The adapter fault diagnosis model is trained based on the fault status data, and the power adapter fault type is predicted through the adapter fault detection model.

[0014] The fault response module, based on directed graph modeling, combines the weighted Dijkstra algorithm with a dynamically adjusted update factor to locate adapter faults. The power adapter intelligent monitoring terminal automatically triggers the corresponding fault response strategy based on the obtained power adapter fault type and adapter fault location. The various modules are connected via wired and / or wireless means.

[0015] Furthermore, the power adapter parameter data includes the power adapter's input voltage, input current, output voltage, output current, power adapter's operating time, and power adapter's temperature; the electrical performance data includes the power adapter's output power, power adapter's harmonic voltage, power adapter's harmonic current, and total harmonic distortion; and the adapter's working environment data includes the temperature, humidity, vibration frequency, and electromagnetic interference level in the adapter's working environment.

[0016] Furthermore, the method for extracting features from power adapter parameter data, electrical performance data, and working environment data based on improved empirical mode decomposition combined with Hilbert transform includes:

[0017] S31. Timestamp the collected power adapter parameter data, electrical performance data, and adapter working environment data according to a daily collection time interval, and sort the collected power adapter parameter data, electrical performance data, and adapter working environment data in ascending order according to the timestamp;

[0018] S32: Integrate the sorted power adapter parameter data, electrical performance data, and adapter working environment data to obtain a data sequence X. j , for each data sequence X j Data variables in Perform empirical mode decomposition using the empirical mode decomposition formula and decompose it into v intrinsic mode function components;

[0019] The empirical mode decomposition formula is: in, is the signal value of the i-th variable in the j-th type of data at time t; is the kth intrinsic mode function component of the i-th variable signal in the j-th type of data; K i is the number of intrinsic mode function components obtained by decomposing the i-th variable signal; k is the index of the intrinsic mode function component decomposed in each signal; is the low-frequency signal value remaining in the signal decomposition process; j is the index of the collected data category, t is the sampling time of the power adapter parameter data, electrical performance data and adapter working environment data; i is the index of each variable in the collected data category;

[0020] The number of intrinsic mode function components K obtained by decomposing the i-th variable signal through the intrinsic mode function component limitation formula is: i The restriction formula of the intrinsic mode function component is: Among them, K′ i is the number of eigenmode function components after restriction; Q j is the number of data categories collected; P i is the number of variable types in the collected data category; a and b are constant factors that adjust the proportion of the limit formula of the eigenmode function component;

[0021] S33, for each eigenmode function component Perform Hilbert transform using the Hilbert transform formula to obtain the complex signal of each component;

[0022] The Hilbert transform formula is: in, For each eigenmode function component The complex signal of For each eigenmode function component The imaginary signal obtained by Hilbert transform; i′ is the imaginary unit;

[0023] described Where τ is the integral variable used to calculate the Hibbert transform at time t;

[0024] The range of the integral variable τ used to calculate the Hibbert transform at time t is dynamically adjusted and constrained by the integral variable range adjustment formula;

[0025] The integral variable range adjustment formula is: Among them, K′ i To limit the number of eigenmode function components; is the range of the integral variable τ;

[0026] S34, from the complex signal The data sequence X is extracted by the instantaneous amplitude calculation formula and the instantaneous frequency calculation formula j The instantaneous amplitude and instantaneous frequency of

[0027] The instantaneous amplitude calculation formula is: in, is the instantaneous amplitude calculated at time t; For each eigenmode function component The square of the imaginary signal obtained by Hilbert transform;

[0028] The instantaneous frequency calculation formula is:

[0029] in, is the instantaneous frequency calculated at time t; It is the inverse tangent of the ratio of the imaginary part to the real part of the signal, indicating the phase of the complex signal; Indicates the derivation of t;

[0030] S35. Construct the data sequence X using the instantaneous amplitude and instantaneous frequency through the Hilbert energy spectrum formula j The Hilbert energy spectrum of each variable in ;

[0031] The Hilbert energy spectrum formula is: in, is the Hilbert energy spectrum of the i-th variable of the j-th type of data; is the Dirac function, which indicates the instantaneous frequency of the signal A pulse at ; ω is a continuous variable of angular frequency, which is used to represent and analyze the energy distribution of the signal at different frequency components;

[0032] S36. For each data variable The intrinsic mode function components are constructed to construct features, and the statistical characteristics of each intrinsic mode function are extracted. The statistical characteristics include the standard deviation of the instantaneous amplitude and the average value of the instantaneous frequency. By calculating the statistical characteristics of each intrinsic mode function component, a feature vector is constructed, and the feature vector of each data variable is integrated into the corresponding data set to form the adapter parameter feature data set, electrical performance feature data set and working environment feature data set respectively.

[0033] Furthermore, the method of performing weighted fusion on the adapter parameter feature dataset, the electrical performance feature dataset, and the working environment feature dataset through a weighted model to obtain a comprehensive feature dataset includes:

[0034] The adapter parameter characteristic data set is denoted as D1, the electrical performance characteristic data set is denoted as D2, and the working environment characteristic data set is denoted as D3; the weighted model is: Qz=D1·δ1+D2·δ2+D3·δ3; wherein Qz is the comprehensive characteristic data set; δ1 is the weight coefficient of the adapter parameter characteristic data set; δ2 is the weight coefficient of the electrical performance characteristic data set; δ3 is the weight coefficient of the working environment characteristic data set.

[0035] Furthermore, the training method of the adapter fault detection model includes:

[0036] The dataset is divided into training, validation, and test sets to build an adapter fault detection model. The sample set is a subset of the dataset, and each sample set includes a historical comprehensive feature dataset and the corresponding power adapter fault state probability.

[0037] The input data of the model is a historical comprehensive feature dataset, and the output label of the model is the probability of the power adapter fault state; the sigmoid function is used as the activation function; the adapter fault detection model is a gradient boosting decision tree model;

[0038] Initialize the adapter fault detection model and set the number of trees, learning rate, and tree depth hyperparameters. Train the model using different hyperparameter combinations through k-fold cross-validation and use the cross-validation results to fine-tune the initially set hyperparameters and select the best performing hyperparameter combination.

[0039] The logarithmic loss function is used to measure the difference between the model prediction result and the true label; the calculation formula of the logarithmic loss function is:

[0040] Where N is the total number of samples in the adapter fault detection model; y c is the true label of the cth sample, q c The model predicts the probability that the cth sample is a positive class; c is the index of the sample;

[0041] The adapter fault detection model is trained on the training set by training a new decision tree based on the residuals of the current model in each iteration. Based on the model performance feedback, the model hyperparameters are adjusted to tune the model. The model is retrained using the adjusted hyperparameters. After the training process is completed, the optimal hyperparameters are selected through cross-validation.

[0042] When the training reaches the preset model complexity or convergence condition, it stops and obtains the final trained adapter fault detection model; the trained adapter fault detection model is used to predict the current comprehensive feature data set to obtain the power adapter fault state probability.

[0043] Furthermore, the method for determining whether the power adapter is in a fault state includes:

[0044] If the predicted probability of the power adapter being in a faulty state is greater than or equal to a preset power adapter faulty state probability threshold, then the power adapter is determined to be in a faulty state;

[0045] If the predicted probability of the power adapter failure state is less than a preset power adapter failure state probability threshold, it is determined that the power adapter is in a non-fault state.

[0046] Furthermore, the fault status data includes abnormal current, abnormal voltage, abnormal output power, abnormal temperature, abnormal vibration frequency, abnormal electrical noise and abnormal harmonic data of the power adapter.

[0047] Furthermore, the training method of the adapter fault diagnosis model includes:

[0048] The dataset is divided into a training set, a validation set, and a test set; an adapter fault diagnosis model is constructed, which includes an input layer, a self-attention layer, a feedforward network layer, and an output layer; the input layer of the model is used to input historical fault status data, and the output layer of the model is used to output the power adapter fault type; a softmax function is used as an activation function; the adapter fault diagnosis model is a self-attention mechanism model;

[0049] Multi-class cross entropy is used as the loss function of the model to measure the difference between the model's predicted value and the actual value; the multi-class cross entropy loss function is: Where L is the average loss of the data set; N′ is the total number of samples in the adapter fault diagnosis model; D is the number of power adapter fault types; y gd is the true label of the g-th sample for the d-th type; p gd The probability that the g-th sample predicted by the model belongs to the d-th type; g is the index of the sample;

[0050] The adapter fault diagnosis model is trained using the training set and the model parameters are updated using the back-propagation algorithm to minimize the loss function. The performance of the adapter fault diagnosis model is evaluated using the validation set by calculating the accuracy metric.

[0051] The SGD optimization algorithm is selected as the optimizer. The model is tuned according to the performance feedback of the validation set, and the model parameters are adjusted until the performance no longer improves or the preset number of iterations is reached. The performance of the model in the prediction task is evaluated using the test set, and the trained adapter fault diagnosis model is used to predict the current fault status data to obtain the power adapter fault type.

[0052] Furthermore, the method for locating an adapter fault based on directed graph modeling, combined with a weighted Dijkstra algorithm and a dynamically adjusted update factor, includes:

[0053] Power adapter failure types include adapter overheating failure, adapter short circuit failure, and output voltage unstable failure;

[0054] S91. Model the circuit of the power adapter as a directed graph, wherein the directed graph comprises V nodes and E edges; the nodes represent the electrical components in the power adapter, the input end of the graph is the starting node, and the output end of the graph is the target node; the electrical components include the input end, converter, filter, sensor, and output end of the power adapter; and the edges represent the connections between the electrical components.

[0055] S92. Assign a weight to each edge based on different power adapter failure types to indicate the adapter failure risk level. The edge weight is:

[0056] in, is the weight of the edge (e, f), which indicates the fault risk level from node e to node f; α is the weight coefficient corresponding to the adapter short circuit fault; β is the weight coefficient corresponding to the output voltage instability fault; γ is the weight coefficient corresponding to the adapter overheating fault; |I ef -I nom | is the current I ef Relative to the preset normal current I nom Deviation of |V ef -V nom | is the current voltage V ef Relative to the preset normal voltage V nom Deviation of T ef -T se is the current temperature T ef Exceeding the preset safety temperature T se Deviation;

[0057] S93. Starting from the starting node s, find the shortest path from the starting node s to the target node o using the Dijkstra algorithm; define the shortest path cost from the starting node s to any node h as d(h), where d(h) is the sum of the minimum failure risk levels from the starting node s to any node h;

[0058] For each node u, the shortest path cost of all connected arbitrary nodes h is updated by an iterative update formula; the iterative update formula is: Where d′(h) is the updated shortest path cost; is the weight of edge (u,h); ξ is the update factor of the shortest path cost;

[0059] The update factor of the shortest path cost is dynamically adjusted by the update factor adjustment formula, and the update factor adjustment formula is: Where ξ′ is the update factor of the shortest path cost after dynamic adjustment; L is the total number of nodes; w is the number of iterations;

[0060] S94, preset fault risk level threshold is After finding the shortest path from the starting node s to the target node o, if the failure risk level of any node h on the path is greater than the preset failure risk level threshold The node is then determined to be the adapter failure location.

[0061] Furthermore, the method in which the power adapter intelligent monitoring terminal automatically triggers a corresponding fault response strategy according to the obtained power adapter fault type and adapter fault location includes:

[0062] When the power adapter intelligent monitoring terminal detects the short circuit fault location of the adapter, it immediately triggers the power-off protection mechanism, cuts off the power input of the power adapter, and sends an alarm to the staff to inform them of the short circuit fault and the fault location;

[0063] After the power adapter intelligent monitoring terminal detects the location of the unstable output voltage fault, it automatically adjusts the output voltage of the power adapter. If the normal voltage output cannot be restored, it automatically switches to the backup power supply and sends an alarm to the staff to inform them of the unstable output voltage fault and the fault location.

[0064] After the power adapter intelligent monitoring terminal detects the location of the adapter overheating fault, it immediately activates the cooling system to reduce the adapter temperature. If the cooling measures are ineffective and the temperature continues to rise, the power adapter is automatically shut down and an alarm is sent to the staff to inform them of the adapter overheating fault and its location.

[0065] The technical effects and advantages of the power adapter fault monitoring system of the present invention are as follows:

[0066] The present invention ensures the time sequence and consistency of the data by timestamping the collected power adapter parameter data, electrical performance data, and adapter working environment data and sorting them by timestamp, providing a good foundation for subsequent data processing and analysis. It also uses the empirical mode decomposition method to decompose complex data signals into several intrinsic mode function components, each of which represents a different frequency component in the data, which helps to gain a deeper understanding of the intrinsic characteristics of the data. By limiting the number of intrinsic mode function components, it avoids the problem of overfitting in the data decomposition process while ensuring the simplicity and representativeness of the data. When performing the Hilbert transform, the range of the integral variable is dynamically adjusted and constrained through the integral variable range adjustment formula, which can ensure the accuracy and stability of the transformation. This helps to reduce the transformation error caused by frequency component differences and improve the reliability of the transformation results.

[0067] By constructing a directed graph model of the power adapter circuit and assigning weights to each edge based on different types of faults (such as overheating, short circuit, and unstable output voltage), the failure risk level of each electrical component in the adapter can be accurately reflected; by representing electrical components as nodes and the connection relationships between components as edges, this method can cover all electrical components and connection relationships in the adapter, thereby achieving a comprehensive analysis of adapter faults; using the Dijkstra algorithm to find the shortest path from the starting node to the target node, the fault location can be accurately located; through iterative update formulas and update factor adjustment formulas, this method can dynamically adjust the update factor of the shortest path cost, thereby speeding up the algorithm's operation and improving the efficiency of fault location; by accurately and quickly locating the power adapter fault location, the repair time can be significantly shortened and the repair cost can be reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] Figure 1 This is a schematic structural diagram of a fault monitoring system for a power adapter of the present invention;

[0069] Figure 2 The figure is a flow chart of a method for monitoring a power adapter fault according to the present invention. DETAILED DESCRIPTION

[0070] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0071] Example 1

[0072] See also Figure 1 As shown, this embodiment provides a power adapter fault monitoring system, including:

[0073] A data collection module is used to collect power adapter parameter data, electrical performance data, and adapter working environment data;

[0074] A data processing module is used to extract features of power adapter parameter data, electrical performance data, and working environment data based on improved empirical mode decomposition combined with Hilbert transform to obtain adapter parameter feature data sets, electrical performance feature data sets, and working environment feature data sets;

[0075] The fault state detection module is used to perform weighted fusion of the adapter parameter feature data set, the electrical performance feature data set, and the working environment feature data set through a weighted model to obtain a comprehensive feature data set; train an adapter fault detection model, input the comprehensive feature data set into the trained adapter fault detection model, predict the probability of the power adapter fault state, and determine whether the power adapter is in a fault state;

[0076] Fault type diagnosis module: If the power adapter is in a fault state, the power adapter intelligent monitoring terminal will immediately generate an early warning message and automatically collect fault status data. The adapter fault diagnosis model is trained based on the fault status data, and the power adapter fault type is predicted through the adapter fault detection model.

[0077] The fault response module, based on directed graph modeling, combines the weighted Dijkstra algorithm with a dynamically adjusted update factor to locate adapter faults. The power adapter intelligent monitoring terminal automatically triggers the corresponding fault response strategy based on the obtained power adapter fault type and adapter fault location. The various modules are connected via wired and / or wireless means.

[0078] The power adapter parameter data includes the power adapter's input voltage, input current, output voltage, output current, power adapter's operating time, and power adapter's temperature; the electrical performance data includes the power adapter's output power, power adapter's harmonic voltage, power adapter's harmonic current, and total harmonic distortion; the adapter's working environment data includes the temperature, humidity, vibration frequency, and electromagnetic interference level in the adapter's working environment.

[0079] The method for extracting features from power adapter parameter data, electrical performance data, and working environment data based on improved empirical mode decomposition combined with Hilbert transform includes:

[0080] S31. Timestamp the collected power adapter parameter data, electrical performance data, and adapter working environment data according to a daily collection time interval, and sort the collected power adapter parameter data, electrical performance data, and adapter working environment data in ascending order according to the timestamp;

[0081] S32: Integrate the sorted power adapter parameter data, electrical performance data, and adapter working environment data to obtain a data sequence X. j , for each data sequence X j Data variables in Perform empirical mode decomposition using the empirical mode decomposition formula and decompose it into v intrinsic mode function components;

[0082] The empirical mode decomposition formula is: in, is the signal value of the i-th variable in the j-th type of data at time t; is the kth intrinsic mode function component of the i-th variable signal in the j-th type of data; K i is the number of intrinsic mode function components obtained by decomposing the i-th variable signal; k is the index of the intrinsic mode function component decomposed in each signal; is the low-frequency signal value remaining in the signal decomposition process; j is the index of the collected data category, t is the sampling time of the power adapter parameter data, electrical performance data and adapter working environment data; i is the index of each variable in the collected data category;

[0083] The number of intrinsic mode function components K obtained by decomposing the i-th variable signal through the intrinsic mode function component limitation formula is: i To restrict the intrinsic mode function component, the limiting formula is: Among them, K′ i is the number of eigenmode function components after restriction; Q j is the number of data categories collected; P i is the number of variable types in the collected data category; a and b are constant factors that adjust the proportion of the limit formula of the eigenmode function component;

[0084] For example, suppose we have the following data situation: the number of data categories collected is Q j is 3, the number of variable types P1 in the first type of data collected is 5, the number of variable types P2 in the second type of data collected is 8, the number of variable types P3 in the third type of data collected is 3, and the constant factors a and b for adjusting the proportion of the intrinsic mode function component limit formula are 10 and 2 respectively;

[0085] Calculate each K′ i quantity:

[0086] For the first type of data:

[0087] For the second type of data:

[0088] For the third type of data:

[0089] Through the intrinsic mode function component limitation formula, it can be found that when the number of collected variable types increases, the number of intrinsic mode function components decreases. The number of intrinsic mode function components is limited to control the complexity. When the number of collected variable types is small, more intrinsic mode function components are allowed to help control the decomposition complexity and ensure that the number of intrinsic mode function components of each variable is within a reasonable range.

[0090] S33, for each eigenmode function component Perform Hilbert transform using the Hilbert transform formula to obtain the complex signal of each component;

[0091] The Hilbert transform formula is: in, For each eigenmode function component The complex signal of For each eigenmode function component The imaginary signal obtained by Hilbert transform; i′ is the imaginary unit;

[0092] Where τ is the integral variable used to calculate the Hibbert transform at time t;

[0093] The range of the integral variable τ used to calculate the Hibbert transform at time t is dynamically adjusted and constrained by the integral variable range adjustment formula;

[0094] The integral variable range adjustment formula is: Among them, K′ i To limit the number of eigenmode function components; is the range of the integral variable τ;

[0095] For example, assuming that the sampling time t is 10, the number of eigenmode function components after restriction is K′ i is 4,

[0096] According to the formula: The integral range can be calculated:

[0097] That is, when performing the Hilbert transform, the integral variable τ is limited to the range of [8,12] rather than [-∞,∞]; the signal characteristics within this range will have a more direct impact on the Hibbert transform result near time t;

[0098] If we increase the number of eigenmode functions K′ i , for example, K′ i =9, then the integral range becomes: When K′ i When increases, the integral range is further narrowed to [9, 11], and is more concentrated near the time t = 10, showing a stronger instantaneous characteristic; this adjustment mechanism allows the Hilbert transform to dynamically adapt to the component complexity of the signal and capture the instantaneous change characteristics more flexibly.

[0099] S34, from the complex signal The data sequence X is extracted by the instantaneous amplitude calculation formula and the instantaneous frequency calculation formula j The instantaneous amplitude and instantaneous frequency of

[0100] The instantaneous amplitude calculation formula is: in, is the instantaneous amplitude calculated at time t; For each eigenmode function component The square of the imaginary signal obtained by Hilbert transform;

[0101] The instantaneous frequency calculation formula is:

[0102] in, is the instantaneous frequency calculated at time t, which represents the instantaneous rate of change of the signal frequency; It is the inverse tangent of the ratio of the imaginary part to the real part of the signal, indicating the phase of the complex signal; Indicates the derivation of t;

[0103] S35. Construct the data sequence X using the instantaneous amplitude and instantaneous frequency through the Hilbert energy spectrum formula j The Hilbert energy spectrum of each variable in ;

[0104] The Hilbert energy spectrum formula is: in, is the Hilbert energy spectrum of the i-th variable of the j-th type of data; is the Dirac function, which indicates the instantaneous frequency of the signal A pulse at ; ω is a continuous variable of angular frequency, which is used to represent and analyze the energy distribution of the signal at different frequency components; specifically, ω varies over the entire real number range, and is a specific point within this continuum;

[0105] S36. For each data variable The intrinsic mode function components are constructed to construct features, and the statistical characteristics of each intrinsic mode function are extracted. The statistical characteristics include the standard deviation of the instantaneous amplitude and the average value of the instantaneous frequency. By calculating the statistical characteristics of each intrinsic mode function component, a feature vector is constructed, and the feature vector of each data variable is integrated into the corresponding data set to form the adapter parameter feature data set, electrical performance feature data set and working environment feature data set respectively.

[0106] The method of performing weighted fusion of the adapter parameter feature dataset, the electrical performance feature dataset, and the working environment feature dataset through a weighted model to obtain a comprehensive feature dataset includes:

[0107] The adapter parameter characteristic data set is denoted as D1, the electrical performance characteristic data set is denoted as D2, and the working environment characteristic data set is denoted as D3; the weighted model is: Qz=D1·δ1+D2·δ2+D3·δ3; among them, Qz is the comprehensive characteristic data set; δ1 is the weight coefficient of the adapter parameter characteristic data set; δ2 is the weight coefficient of the electrical performance characteristic data set; δ3 is the weight coefficient of the working environment characteristic data set.

[0108] The training method for the adapter fault detection model includes:

[0109] The dataset is divided into training, validation, and test sets to build an adapter fault detection model. The sample set is a subset of the dataset, and each sample set includes a historical comprehensive feature dataset and the corresponding power adapter fault state probability.

[0110] The model's input data is a historical comprehensive feature dataset, and the model's output label is the probability of a power adapter failure. The sigmoid function is used as the activation function. The adapter fault detection model is a gradient boosting decision tree model.

[0111] Initialize the adapter fault detection model and set the number of trees, learning rate, and tree depth hyperparameters. Train the model using different hyperparameter combinations through k-fold cross-validation and use the cross-validation results to fine-tune the initially set hyperparameters and select the best performing hyperparameter combination.

[0112] The logarithmic loss function is used to measure the difference between the model prediction result and the true label; the calculation formula of the logarithmic loss function is:

[0113] Where N is the total number of samples in the adapter fault detection model; y c is the true label of the cth sample, q c The model predicts the probability that the cth sample is a positive class; c is the index of the sample;

[0114] The adapter fault detection model is trained on the training set by training a new decision tree based on the residuals of the current model in each iteration. Based on the model performance feedback, the model hyperparameters are adjusted to tune the model. The model is retrained using the adjusted hyperparameters. After the training process is completed, the optimal hyperparameters are selected through cross-validation.

[0115] When the training reaches the preset model complexity or convergence condition, it stops and obtains the final trained adapter fault detection model; the trained adapter fault detection model is used to predict the current comprehensive feature data set to obtain the power adapter fault state probability.

[0116] Methods for determining whether the power adapter is in a fault state include:

[0117] If the predicted probability of the power adapter being in a faulty state is greater than or equal to a preset power adapter faulty state probability threshold, then the power adapter is determined to be in a faulty state;

[0118] If the predicted probability of the power adapter failure state is less than a preset power adapter failure state probability threshold, it is determined that the power adapter is in a non-fault state.

[0119] The fault status data includes abnormal current, abnormal voltage, abnormal output power, abnormal temperature, abnormal vibration frequency, abnormal electrical noise, and abnormal harmonic data of the power adapter.

[0120] The training method of the adapter fault diagnosis model includes:

[0121] The dataset is divided into training, validation, and test sets. An adapter fault diagnosis model is constructed, which includes an input layer, a self-attention layer, a feedforward network layer, and an output layer. The input layer of the model is used to input historical fault status data, and the output layer of the model is used to output the power adapter fault type. The softmax function is used as the activation function. The adapter fault diagnosis model adopts a self-attention mechanism model.

[0122] Use multi-classification cross entropy as the loss function of the model to measure the difference between the model's predicted value and the actual value; the multi-classification cross entropy loss function is: Where L is the average loss of the data set; N′ is the total number of samples in the adapter fault diagnosis model; D is the number of power adapter fault types; y gd is the true label of the g-th sample for the d-th type; p gd The probability that the g-th sample predicted by the model belongs to the d-th type; g is the index of the sample;

[0123] The adapter fault diagnosis model is trained using the training set and the model parameters are updated using the back-propagation algorithm to minimize the loss function. The performance of the adapter fault diagnosis model is evaluated using the validation set by calculating the accuracy metric.

[0124] The SGD optimization algorithm is selected as the optimizer. The model is tuned according to the performance feedback of the validation set, and the model parameters are adjusted until the performance no longer improves or the preset number of iterations is reached. The performance of the model in the prediction task is evaluated using the test set, and the trained adapter fault diagnosis model is used to predict the current fault status data to obtain the power adapter fault type.

[0125] Based on directed graph modeling, combined with the weighted Dijkstra algorithm and dynamically adjusted update factors, the adapter fault location method includes the following:

[0126] Power adapter failure types include adapter overheating failure, adapter short circuit failure, and output voltage unstable failure;

[0127] S91. Model the circuit of the power adapter as a directed graph, comprising V nodes and E edges. The nodes represent the electrical components in the power adapter, the input end of the graph is the starting node, and the output end of the graph is the target node. The electrical components include the input end, converter, filter, sensor, and output end of the power adapter. The edges represent the connections between the electrical components.

[0128] S92. Assign a weight to each edge based on different power adapter failure types to indicate the adapter failure risk level. The edge weight is:

[0129] in, is the weight of the edge (e, f), which indicates the fault risk level from node e to node f; α is the weight coefficient corresponding to the adapter short circuit fault; β is the weight coefficient corresponding to the output voltage instability fault; γ is the weight coefficient corresponding to the adapter overheating fault; |I ef -I nom | is the current I ef Relative to the preset normal current I nom Deviation of |V ef -V nom | is the current voltage V ef Relative to the preset normal voltage V nom Deviation of T ef -T se is the current temperature T ef Exceeding the preset safety temperature T se Deviation;

[0130] S93. Starting from the starting node s, find the shortest path from the starting node s to the target node o using the Dijkstra algorithm; define the shortest path cost from the starting node s to any node h as d(h), where d(h) is the sum of the minimum failure risk levels from the starting node s to any node h;

[0131] For each node u, the shortest path cost of all connected arbitrary nodes h is updated through the iterative update formula; the iterative update formula is: Where d′(h) is the updated shortest path cost; is the weight of edge (u,h); ξ is the update factor of the shortest path cost;

[0132] The update factor of the shortest path cost is dynamically adjusted through the update factor adjustment formula. The update factor adjustment formula is: Where ξ′ is the update factor of the shortest path cost after dynamic adjustment; L is the total number of nodes; w is the number of iterations;

[0133] For example, if the total number of nodes is 5 and the number of iterations is 8, then the update factor ξ′ of the shortest path cost after dynamic adjustment is approximately 0.38.

[0134] S94, preset fault risk level threshold After finding the shortest path from the starting node s to the target node o, if the failure risk level of any node h on the path is greater than the preset failure risk level threshold The node is then determined to be the adapter failure location.

[0135] The method for the power adapter intelligent monitoring terminal to automatically trigger a corresponding fault response strategy according to the obtained power adapter fault type and adapter fault location includes:

[0136] When the power adapter intelligent monitoring terminal detects the short circuit fault location of the adapter, it immediately triggers the power-off protection mechanism, cuts off the power input of the power adapter, and sends an alarm to the staff to inform them of the short circuit fault and the fault location;

[0137] After the power adapter intelligent monitoring terminal detects the location of the unstable output voltage fault, it automatically adjusts the output voltage of the power adapter. If the normal voltage output cannot be restored, it automatically switches to the backup power supply and sends an alarm to the staff to inform them of the unstable output voltage fault and the fault location.

[0138] After the power adapter intelligent monitoring terminal detects the location of the adapter overheating fault, it immediately activates the cooling system to reduce the adapter temperature. If the cooling measures are ineffective and the temperature continues to rise, the power adapter is automatically shut down and an alarm is sent to the staff to inform them of the adapter overheating fault and its location.

[0139] The preset power adapter failure state probability threshold is set by the staff. Different power adapter failure state probabilities are collected through the power adapter intelligent monitoring terminal, and the average value of multiple power adapter failure state probabilities is taken as the preset power adapter failure state probability threshold; the failure risk degree threshold is set similarly.

[0140] This embodiment ensures the time sequence and consistency of the data by timestamping the collected power adapter parameter data, electrical performance data, and adapter working environment data and sorting them by timestamp, providing a good foundation for subsequent data processing and analysis. The empirical mode decomposition method is used to decompose complex data signals into several intrinsic mode function components, each of which represents a different frequency component in the data, which helps to gain a deeper understanding of the intrinsic characteristics of the data. By limiting the number of intrinsic mode function components, overfitting problems in the data decomposition process are avoided while ensuring the simplicity and representativeness of the data. When performing the Hilbert transform, the range of the integral variable is dynamically adjusted and constrained by the integral variable range adjustment formula, which can ensure the accuracy and stability of the transformation. This helps to reduce the transformation error caused by frequency component differences and improve the reliability of the transformation results.

[0141] By constructing a directed graph model of the power adapter circuit and assigning weights to each edge based on different types of faults (such as overheating, short circuit, and unstable output voltage), the failure risk level of each electrical component in the adapter can be accurately reflected; by representing electrical components as nodes and the connection relationships between components as edges, this method can cover all electrical components and connection relationships in the adapter, thereby achieving a comprehensive analysis of adapter faults; using the Dijkstra algorithm to find the shortest path from the starting node to the target node, the fault location can be accurately located; through iterative update formulas and update factor adjustment formulas, this method can dynamically adjust the update factor of the shortest path cost, thereby speeding up the algorithm's operation and improving the efficiency of fault location; by accurately and quickly locating the power adapter fault location, the repair time can be significantly shortened and the repair cost can be reduced.

[0142] Example 2

[0143] See also Figure 2 As shown, for the parts not described in detail in this embodiment, please refer to the description of Example 1. A method for monitoring a fault of a power adapter is provided, comprising:

[0144] S1. Collect power adapter parameter data, electrical performance data, and adapter working environment data;

[0145] S2. Perform feature extraction on the power adapter parameter data, electrical performance data, and working environment data based on improved empirical mode decomposition combined with Hilbert transform to obtain an adapter parameter feature dataset, an electrical performance feature dataset, and a working environment feature dataset;

[0146] S3. Perform weighted fusion on the adapter parameter feature dataset, the electrical performance feature dataset, and the working environment feature dataset using a weighted model to obtain a comprehensive feature dataset; train an adapter fault detection model, input the comprehensive feature dataset into the trained adapter fault detection model, predict the probability of a power adapter fault state, and determine whether the power adapter is in a fault state;

[0147] S4. If the power adapter is in a fault state, the power adapter intelligent monitoring terminal immediately generates a warning message and automatically collects fault status data; an adapter fault diagnosis model is trained based on the fault status data, and the power adapter fault type is predicted by the adapter fault detection model;

[0148] S5. Based on directed graph modeling, combined with the weighted Dijkstra algorithm and the dynamic adjustment update factor, the adapter fault location is performed. The power adapter intelligent monitoring terminal automatically triggers the corresponding fault response strategy according to the obtained power adapter fault type and adapter fault location.

[0149] Since the electronic device described in this embodiment is an electronic device used to implement the power adapter fault monitoring system in the embodiment of the present application, those skilled in the art will be able to understand the specific implementation of the electronic device of this embodiment and its various variations based on the power adapter fault monitoring system described in the embodiment of the present application. Therefore, how the electronic device implements the method in the embodiment of the present application will not be described in detail here. As long as those skilled in the art can implement the electronic device used by the power adapter fault monitoring system in the embodiment of the present application, it falls within the scope of protection of this application.

[0150] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters and thresholds in the formulas are set by technicians in this field according to actual conditions.

[0151] The above are merely preferred embodiments of the present invention. The scope of protection of the present invention is not limited to the above embodiments. All technical solutions based on the principles of the present invention are within the scope of protection of the present invention. It should be noted that for users of ordinary skill in the art, various improvements and modifications that do not depart from the principles of the present invention are also within the scope of protection of the present invention.

Claims

1. A fault monitoring system for a power adapter, characterized in that: include: A data collection module, used to collect power adapter parameter data, electrical performance data and adapter working environment data; A data processing module, used to extract features of power adapter parameter data, electrical performance data and working environment data based on improved empirical mode decomposition combined with Hilbert transform, to obtain adapter parameter feature data set, electrical performance feature data set and working environment feature data set; A fault state detection module is used to perform weighted fusion on the adapter parameter feature data set, the electrical performance feature data set and the working environment feature data set through a weighted model to obtain a comprehensive feature data set; Train and obtain an adapter fault detection model, input the comprehensive feature data set into the trained adapter fault detection model, predict the probability of the power adapter fault state, and determine whether the power adapter is in a fault state; Fault type diagnosis module: if the power adapter is in a fault state, the power adapter intelligent monitoring terminal immediately generates warning information and automatically collects fault status data; The adapter fault diagnosis model is obtained by training the fault status data, and the power adapter fault type is predicted by the adapter fault detection model; The fault response module locates the adapter fault based on directed graph modeling, combined with the weighted Dijkstra algorithm and the dynamic adjustment update factor. The power adapter intelligent monitoring terminal automatically triggers the corresponding fault response strategy according to the obtained power adapter fault type and adapter fault location; The modules are connected to each other via wired and / or wireless means.

2. The power adapter fault monitoring system according to claim 1, characterized in that: The power adapter parameter data includes the input voltage, input current, output voltage, output current, operation time of the power adapter and temperature of the power adapter; The electrical performance data includes the output power of the power adapter, the harmonic voltage of the power adapter, the harmonic current of the power adapter and the total harmonic distortion; The adapter working environment data includes temperature, humidity, vibration frequency and electromagnetic interference level in the adapter working environment.

3. The fault monitoring system for a power adapter according to claim 2, characterized in that: The method for extracting features of power adapter parameter data, electrical performance data and working environment data based on improved empirical mode decomposition combined with Hilbert transform includes: S31, stamping the collected power adapter parameter data, electrical performance data, and adapter working environment data with a time stamp according to a daily collection time interval, and sorting the collected power adapter parameter data, electrical performance data, and adapter working environment data in ascending order according to the time stamp; S32, integrating the sorted power adapter parameter data, electrical performance data, and adapter working environment data to obtain a data sequence X j , for each data sequence X j Data variables in Perform empirical mode decomposition using the empirical mode decomposition formula and decompose it into v intrinsic mode function components; The empirical mode decomposition formula is: in, is the signal value of the i-th variable in the j-th type of data at time t; is the kth intrinsic mode function component of the i-th variable signal in the j-th type of data; K i is the number of intrinsic mode function components obtained by decomposing the i-th variable signal; k is the index of the intrinsic mode function component decomposed in each signal; is the low-frequency signal value remaining in the signal decomposition process; j is the index of the collected data category, t is the sampling time of the power adapter parameter data, electrical performance data and adapter working environment data; i is the index of each variable in the collected data category; The number of intrinsic mode function components K obtained by decomposing the i-th variable signal through the intrinsic mode function component restriction formula i The restriction is performed, and the intrinsic mode function component restriction formula is: Among them, K′ i is the number of eigenmode function components after restriction; Q j is the number of data categories collected; P i is the number of variable types in the collected data category; a and b are constant factors that adjust the proportion of the limit formula of the eigenmode function component; S33, for each eigenmode function component Perform Hilbert transform using the Hilbert transform formula to obtain the complex signal of each component; The Hilbert transform formula is: in, For each eigenmode function component The complex signal of For each eigenmode function component The imaginary signal obtained by Hilbert transform; i′ is the imaginary unit; Said Where τ is the integral variable used to calculate the Hibbert transform at time t; The range of the integral variable τ used to calculate the Hibbert transform at time t is dynamically adjusted and constrained by the integral variable range adjustment formula; The integral variable range adjustment formula is: Among them, K i ′ is the number of eigenmode function components after restriction; is the range of the integral variable τ; S34, from the complex signal The data sequence X is extracted by the instantaneous amplitude calculation formula and the instantaneous frequency calculation formula j The instantaneous amplitude and instantaneous frequency of The instantaneous amplitude calculation formula is: in, is the instantaneous amplitude calculated at time t; For each eigenmode function component The square of the imaginary signal obtained by Hilbert transform; The instantaneous frequency calculation formula is: in, is the instantaneous frequency calculated at time t; It is the inverse tangent of the ratio of the imaginary part to the real part of the signal, indicating the phase of the complex signal; represents the derivation of t; S35. Construct the data sequence X using the instantaneous amplitude and instantaneous frequency through the Hilbert energy spectrum formula j The Hilbert energy spectrum of each variable in ; The Hilbert energy spectrum formula is: in, is the Hilbert energy spectrum of the i-th variable of the j-th type of data; is the Dirac function, which indicates the instantaneous frequency of the signal A pulse at ; ω is a continuous variable of angular frequency, which is used to represent and analyze the energy distribution of the signal at different frequency components; S36. For each data variable The intrinsic mode function components are constructed with features, and the statistical features of each intrinsic mode function are extracted. The statistical features include the standard deviation of the instantaneous amplitude and the average value of the instantaneous frequency. A feature vector is constructed by calculating the statistical features of each intrinsic mode function component, and the feature vector of each data variable is integrated into the corresponding data set to form the adapter parameter feature data set, electrical performance feature data set and working environment feature data set respectively.

4. The fault monitoring system for a power adapter according to claim 3, characterized in that: The method of performing weighted fusion on the adapter parameter feature data set, the electrical performance feature data set and the working environment feature data set through a weighted model to obtain a comprehensive feature data set includes: The adapter parameter characteristic data set is denoted as D1, the electrical performance characteristic data set is denoted as D2, and the working environment characteristic data set is denoted as D3; the weighted model is: Qz=D1·δ1+D2·δ2+D3·δ3; wherein Qz is the comprehensive characteristic data set; δ1 is the weight coefficient of the adapter parameter characteristic data set; δ2 is the weight coefficient of the electrical performance characteristic data set; δ3 is the weight coefficient of the working environment characteristic data set.

5. The power adapter fault monitoring system according to claim 4, characterized in that: The training method of the adapter fault detection model includes: The data set is divided into a training set, a validation set, and a test set to build an adapter fault detection model; the sample set is a subset of the data set, and each sample set includes a historical comprehensive feature data set and the corresponding power adapter fault state probability; The input data of the model is a historical comprehensive feature data set, and the output label of the model is the probability of the power adapter fault state; the sigmoid function is used as the activation function; the adapter fault detection model is a gradient boosting decision tree model; Initialize the adapter fault detection model and set the number of trees, learning rate, and tree depth hyperparameters. Use k-fold cross-validation to train the model using different hyperparameter combinations and use the cross-validation results to tune the initially set hyperparameters and select the best performing hyperparameter combination. The logarithmic loss function is used to measure the difference between the model prediction result and the true label; the calculation formula of the logarithmic loss function is: Where N is the total number of samples in the adapter fault detection model; y c is the true label of the cth sample, q c The model predicts the probability that the cth sample is a positive class; c is the index of the sample; Train the adapter fault detection model in the training set by training a new decision tree based on the residual of the current model in each iteration; adjust the model's hyperparameters to tune the model based on the model performance feedback, retrain the model with the adjusted hyperparameters, and select the optimal hyperparameters through cross-validation after the training process is completed; When the training reaches the preset model complexity or convergence condition, it stops and obtains the final trained adapter fault detection model; the trained adapter fault detection model is used to predict the current comprehensive feature data set to obtain the power adapter fault state probability.

6. The power adapter fault monitoring system according to claim 5, characterized in that: The method for determining whether the power adapter is in a fault state comprises: If the predicted probability of a power adapter failure state is greater than or equal to a preset power adapter failure state probability threshold, then the power adapter is determined to be in a failure state; If the predicted probability of the power adapter failure state is less than a preset power adapter failure state probability threshold, the power adapter is determined to be in a non-fault state.

7. The fault monitoring system for a power adapter according to claim 6, characterized in that: The fault status data includes abnormal current, abnormal voltage, abnormal output power, abnormal temperature, abnormal vibration frequency, abnormal electrical noise and abnormal harmonic data of the power adapter.

8. The power adapter fault monitoring system according to claim 7, characterized in that: The training method of the adapter fault diagnosis model includes: The data set is divided into a training set, a validation set and a test set; an adapter fault diagnosis model is constructed, and the adapter fault diagnosis model includes an input layer, a self-attention layer, a feedforward network layer and an output layer; the input layer of the model is used to input historical fault state data, and the output layer of the model is used to output the power adapter fault type; a softmax function is used as an activation function; the adapter fault diagnosis model is a self-attention mechanism model; Multi-classification cross entropy is used as the loss function of the model to measure the difference between the predicted value and the actual value of the model; the multi-classification cross entropy loss function is: Where L is the average loss of the data set; N′ is the total number of samples in the adapter fault diagnosis model; D is the number of power adapter fault types; y gd is the true label of the g-th sample for the d-th type; p gd The probability that the g-th sample predicted by the model belongs to the d-th type; g is the index of the sample; The adapter fault diagnosis model is trained using the training set, and the model parameters are updated through the back-propagation algorithm to minimize the loss function. The performance of the adapter fault diagnosis model is evaluated by calculating the accuracy index using the validation set. The SGD optimization algorithm is selected as the optimizer, and the model is tuned according to the performance feedback of the validation set. The model parameters are adjusted until the performance no longer improves or the preset number of iterations is reached. The test set is used to evaluate the performance of the model in the prediction task, and the trained adapter fault diagnosis model is used to predict the current fault status data to obtain the power adapter fault type.

9. The power adapter fault monitoring system according to claim 8, characterized in that: The method for locating adapter faults based on directed graph modeling, combined with a weighted Dijkstra algorithm and a dynamically adjusted update factor, includes: Power adapter failure types include adapter overheating failure, adapter short circuit failure, and output voltage unstable failure; S91. Model the circuit of the power adapter as a directed graph, wherein the directed graph includes V nodes and E edges; the nodes represent the electrical components in the power adapter, the input end of the graph is the start node, and the output end of the graph is the target node; the electrical components include the input end, the converter, the filter, the sensor, and the output end of the power adapter; and the edges represent the connection relationship between the electrical components; S92. Assign a weight to each edge according to different power adapter failure types to indicate the risk level of the adapter failure; the edge weight is: in, is the weight of edge (e,f), indicating the degree of fault risk from node e to node f; α is the weight coefficient corresponding to the adapter short circuit fault; β is the weight coefficient corresponding to the output voltage instability fault; γ is the weight coefficient corresponding to the adapter overheating fault; |I ef -I nom | is the current I ef Relative to the preset normal current I nom Deviation of |V ef -V nom | is the current voltage V ef Relative to the preset normal voltage V nom Deviation of T ef -T se is the current temperature T ef Exceeding the preset safety temperature T se Deviation; S93, starting from the starting node s, find the shortest path from the starting node s to the target node o through the Dijkstra algorithm; define the shortest path cost from the starting node s to any node h as d(h), where d(h) is the sum of the minimum failure risk levels from the starting node s to any node h; For each node u, the shortest path cost of all connected arbitrary nodes h is updated by an iterative update formula; the iterative update formula is: Among them, d′(h) is the updated shortest path cost; is the weight of edge (u,h); ξ is the update factor of the shortest path cost; The update factor of the shortest path cost is dynamically adjusted by the update factor adjustment formula, and the update factor adjustment formula is: Among them, ξ′ is the update factor of the shortest path cost after dynamic adjustment; L is the total number of nodes; w is the number of iterations; S94, preset fault risk level threshold is After finding the shortest path from the starting node s to the target node o, if the failure risk level of any node h on the path is greater than the preset failure risk level threshold The node is then determined to be the adapter failure location.

10. The power adapter fault monitoring system according to claim 9, characterized in that: The method in which the power adapter intelligent monitoring terminal automatically triggers a corresponding fault response strategy according to the obtained power adapter fault type and adapter fault location includes: After the power adapter intelligent monitoring terminal detects the short-circuit fault location of the adapter, it immediately triggers the power-off protection mechanism, cuts off the power input of the power adapter, and sends an alarm to the staff to inform them of the short-circuit fault and its location; After the power adapter intelligent monitoring terminal detects the location of the unstable output voltage fault, it automatically adjusts the output voltage of the power adapter. If the normal voltage output cannot be restored, it automatically switches to the backup power supply and sends an alarm to the staff to inform them of the unstable output voltage fault and its location; After the power adapter intelligent monitoring terminal detects the location of the adapter overheating fault, it immediately activates the cooling system to reduce the adapter temperature. If the cooling measures are ineffective and the temperature continues to rise, the power adapter is automatically shut down and an alarm is sent to the staff to inform them of the adapter overheating fault and its location.

Images