Rail transit hub equipment fault intelligent diagnosis and early warning method

Abstract

The invention discloses a rail transit hub equipment fault intelligent diagnosis and early warning method, and relates to the technical field of rail transit equipment fault diagnosis and predictive maintenance, and the method comprises the steps: collecting multi-modal data, carrying out the time-space alignment of the multi-modal data based on an equipment topological relation and a timestamp, and generating multi-dimensional fault feature data; inputting the multi-dimensional fault feature data into a parallel feature extraction module to generate a fault feature vector; inputting the fault feature vectors into a fault diagnosis model, performing preliminary classification based on a ResNet-18 network backbone structure, and outputting corresponding fault types and confidence coefficients; and calculating the residual service life of the equipment according to a fault development trend prediction result, generating early warning information, and dynamically adjusting the confidence coefficient in combination with historical early warning statistical data of the confidence coefficient and the real-time load rate of the equipment to realize hierarchical management of early warning notification. According to the invention, the accuracy of fault prediction is enhanced, and the intelligence and refinement of the operation and maintenance strategy are realized.

Description

Technical Field

[0001] The present invention relates to the technical field of rail transit equipment fault diagnosis and predictive maintenance, and in particular to a method for intelligent fault diagnosis and early warning of rail transit hub equipment. Background Art

[0002] Currently, urban heating systems commonly use heat exchange stations as the heat exchange link between heat sources and users, achieving efficient transmission and distribution of thermal energy. Due to the widespread distribution of heat exchange stations and their complex operating environments, traditional manual oversight is not only costly but also slow to respond to emergencies and suffers from poor remote monitoring capabilities. This can easily lead to problems such as unstable heating quality, high energy consumption, and delayed equipment maintenance. With the development of smart cities and automated control technologies, the intelligent transformation of heat exchange stations has become an urgent need. However, key technical bottlenecks remain in implementing remote monitoring, automatic adjustment, and fault alarms.

[0003] CN103438503A discloses an unmanned intelligent control method and control system for a heat exchange station. The system uses a programmable controller (PLC) as the core control unit. The input end of the PLC is connected to the outdoor temperature compensator, the temperature and pressure sensors of the heat exchanger inlet and outlet, and the liquid level sensor of the water supply tank. The output end is connected to the electric regulating valve, solenoid valve, frequency converter and other actuators, realizing variable frequency control of the circulation pump and the water supply pump, so that constant temperature and pressure heating, water supply and power outage restart operations can be automatically performed. It also supports sending field data to the remote control terminal in real time, providing users with the ability to remotely access real-time data. However, this technology mainly solves the problems of automatic adjustment and remote monitoring of heating parameters. Predictive maintenance, energy efficiency analysis and multi-point collaborative control of equipment operation status have not yet been involved, making it difficult to adapt to the changing urban heating needs.

[0004] CN102985063A discloses a remote monitoring method for thermal systems based on configuration software. By building a SCADA platform to centrally collect and graphically display data from multiple heat exchange stations, it can centrally monitor the operating status and provide fault prompts. However, this method has high requirements for the real-time and stability of data transmission. When network conditions are unstable or data is lost, it may cause monitoring misjudgments and delayed responses. It also lacks the autonomy of local control logic and still relies on manual intervention to complete fault handling and the formulation of adjustment strategies in actual applications. Therefore, this method still cannot achieve fully automatic intelligent operation and early warning decision-making for complex thermal systems. Summary of the Invention

[0005] In view of the problems of insufficient multi-source data fusion, high false alarm rate of fault warning and lack of dynamic adjustment mechanism of operation and maintenance strategy in existing equipment monitoring methods, the present invention is proposed.

[0006] Therefore, the problem to be solved by the present invention is how to achieve precise alignment and intelligent analysis of multimodal data of rail transit hub equipment, improve the accuracy of fault diagnosis, and establish an adaptive hierarchical early warning mechanism, so as to optimize the configuration efficiency of operation and maintenance resources and the reliability management of equipment.

[0007] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0008] In a first aspect, an embodiment of the present invention provides a method for intelligent diagnosis and early warning of rail transit hub equipment faults, which includes:

[0009] Collect multimodal data from various devices in the rail transit hub, and perform spatiotemporal alignment on the multimodal data based on device topology and timestamps to generate multidimensional fault signature data;

[0010] Inputting the multi-dimensional fault feature data into a parallel feature extraction module to generate a fault feature vector;

[0011] The fault feature vector is input into the fault diagnosis model, and preliminary classification is performed based on the ResNet-18 network backbone structure, and the corresponding fault type and confidence are output;

[0012] The remaining service life of the equipment is calculated based on the fault type and confidence level, and warning information is generated. The confidence level is dynamically adjusted based on historical warning statistics of the confidence level and the real-time load rate of the equipment to achieve hierarchical management of warning notifications.

[0013] As a preferred solution of the rail transit hub equipment fault intelligent diagnosis and early warning method of the present invention, wherein: the remaining service life of the equipment is calculated according to the fault type and confidence level, and early warning information is generated, including:

[0014] Match the fault type and confidence level with typical fault cases in the historical fault database, build a fault similarity scoring matrix, extract the degradation curve template corresponding to the fault type, and calculate the remaining service life;

[0015] Establish dynamic warning classification rules based on the credibility of typical fault cases, classify warning information into levels, and collect real-time load rates of equipment;

[0016] Correcting the remaining service life according to the real-time load rate; when the real-time load rate is higher than the rated load rate, shortening the remaining service life according to the load ratio;

[0017] Calculate the accuracy of warning levels and construct warning confidence correction coefficients;

[0018] The warning confidence correction coefficient is multiplied by the current confidence to obtain a corrected confidence value, and the warning information is pushed in a graded manner.

[0019] As a preferred solution of the rail transit hub equipment fault intelligent diagnosis and early warning method of the present invention, the fault type and confidence level are matched with typical fault cases in the historical fault database, including:

[0020] When the confidence of the fault type is higher than the first confidence threshold and the historical case matching degree is greater than the first matching threshold, the fault case is marked as a first-level credible matching case;

[0021] When the confidence of the fault type is between the second confidence threshold and the first confidence threshold, and the historical case matching degree is between the second matching threshold and the first matching threshold, the fault case is marked as a second-level credible matching case;

[0022] When the confidence of the fault type is less than the second confidence threshold or the historical case matching degree is less than the second matching threshold, the fault case is marked as a third-level credible matching case.

[0023] As a preferred solution of the rail transit hub equipment fault intelligent diagnosis and early warning method of the present invention, it also includes:

[0024] For the first-level trusted match case: if the remaining service life is less than the first time threshold and the device load rate is greater than the first load threshold, a first-level warning is triggered; if the remaining service life is between the first time threshold and the second time threshold, and the device load rate is between the second load threshold and the first load threshold, a second-level warning is triggered; if the remaining service life is between the second time threshold and the third time threshold, and the device load rate is less than the second load threshold, a third-level warning is triggered;

[0025] For the second-level trusted match case: if the remaining service life is less than the fourth time threshold and the device load rate is greater than the third load threshold, a first-level warning is triggered; if the remaining service life is between the fourth time threshold and the fifth time threshold, and the device load rate is between the fourth load threshold and the third load threshold, a second-level warning is triggered; if the remaining service life is between the fifth time threshold and the sixth time threshold, and the device load rate is less than the fourth load threshold, a third-level warning is triggered;

[0026] For the three-level trusted matching case: if the remaining service life is less than the seventh time threshold and the device load rate is greater than the fifth load threshold, a first-level warning is triggered; if the remaining service life is between the seventh time threshold and the eighth time threshold, and the device load rate is between the sixth load threshold and the fifth load threshold, a second-level warning is triggered; if the remaining service life is between the eighth time threshold and the ninth time threshold, and the device load rate is less than the sixth load threshold, a third-level warning is triggered.

[0027] As a preferred solution of the rail transit hub equipment fault intelligent diagnosis and early warning method of the present invention, wherein: the method for obtaining the fault type and confidence level is:

[0028] Constructing a fault diagnosis model based on the ResNet-18 structure, wherein the fault diagnosis model includes a feature extraction layer, a domain discrimination layer, and a fault classification layer;

[0029] Inputting the fault feature vector into the feature extraction layer to extract a high-dimensional feature representation, wherein the high-dimensional feature representation includes deep semantic information of the device status;

[0030] Calculating a maximum average difference measure between source domain features and target domain features in the domain discrimination layer, and using the maximum average difference measure as an optimization target of a domain adaptation loss function;

[0031] Using labeled samples of rail transit hub equipment in the target domain, and combining the domain adaptation loss function, the parameters of the feature extraction layer are trained to make the features domain invariant;

[0032] The features that have undergone domain adaptation training are input into the fault classification layer, the probability distribution of each fault type is calculated, and the fault type with the highest probability and the confidence value are output.

[0033] As a preferred solution of the method for intelligent diagnosis and early warning of rail transit hub equipment faults of the present invention, the method for obtaining the fault feature vector is as follows:

[0034] The multi-dimensional fault feature data is divided into vibration feature channel, temperature feature channel and current feature channel according to data type;

[0035] Performing wavelet packet decomposition on the data of the vibration characteristic channel to extract the energy characteristics, kurtosis characteristics and skewness characteristics of each frequency band to form a vibration characteristic subvector;

[0036] Performing statistical analysis on the data of the temperature characteristic channel, calculating the temperature mean, standard deviation and change rate, and forming a temperature characteristic subvector;

[0037] Performing Fourier transform on the data of the current characteristic channel to extract the current harmonic ratio, phase difference and waveform distortion rate to form a current characteristic sub-vector;

[0038] The vibration characteristic sub-vector, the temperature characteristic sub-vector, and the current characteristic sub-vector are fused using feature importance weights to generate a fault characteristic vector.

[0039] As a preferred solution of the rail transit hub equipment fault intelligent diagnosis and early warning method of the present invention, wherein: the method for obtaining the multi-dimensional fault feature data is:

[0040] Collecting multimodal data from various devices within a rail transit hub, wherein the multimodal data includes vibration sensor data and device operating condition data;

[0041] Marking the multimodal data with device numbers according to the collection location, and establishing a spatial correlation matrix between devices based on the rail transit hub equipment topology diagram;

[0042] Performing timestamp alignment on the multimodal data, unifying data with different sampling frequencies to the same time scale by a linear interpolation method, and generating a multimodal data sequence;

[0043] Performing spatial correlation analysis on data of adjacent devices in the multimodal data sequence based on the spatial correlation matrix to calculate a fault propagation coefficient between devices;

[0044] The multi-modal data sequence and the fault propagation coefficient are combined to form multi-dimensional fault feature data.

[0045] In a second aspect, an embodiment of the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the processor executes the computer program, it implements any step of the above-mentioned intelligent diagnosis and early warning method for rail transit hub equipment faults.

[0046] In a third aspect, an embodiment of the present invention provides a computer-readable storage medium on which a computer program is stored, wherein: when the computer program is executed by a processor, any step of the above-mentioned intelligent diagnosis and early warning method for rail transit hub equipment faults is implemented.

[0047] Compared with the existing technology, the beneficial effects of the present invention are as follows: through multimodal data acquisition and spatiotemporal alignment technology, full-dimensional monitoring of equipment status is achieved, effectively solving the difficult problems of heterogeneous sensor data synchronization and cross-device fault correlation analysis; based on the parallel feature extraction module, multi-source features such as vibration, temperature, and current are integrated, which significantly improves the recognition ability of complex faults; combined with the dynamic confidence correction mechanism, the warning threshold is adaptively adjusted according to the historical warning accuracy and real-time load rate, which greatly reduces the false alarm rate and optimizes the timeliness of the warning; through the hierarchical push strategy, differentiated warning responses are implemented according to different credibility matching cases, while ensuring the priority processing of high-reliability warnings, and reasonably allocating operation and maintenance resources; this method not only enhances the accuracy of fault prediction, but also realizes the intelligence and refinement of operation and maintenance strategies, providing an efficient and reliable solution for the health management of rail transit hub equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. Those skilled in the art can also derive other drawings based on these drawings without inventive effort. Among them:

[0049] Figure 1 The figure is a flow chart of the intelligent diagnosis and early warning method for rail transit hub equipment failure. DETAILED DESCRIPTION

[0050] To make the above-mentioned objects, features, and advantages of the present invention more clearly understood, the following detailed description of the specific embodiments of the present invention is given in conjunction with the accompanying drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in this field without creative work should fall within the scope of protection of the present invention.

[0051] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0052] Secondly, the term "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in various places throughout this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive of other embodiments.

[0053] The present invention is described in detail with reference to schematic diagrams. For ease of illustration, cross-sectional views of device structures may be partially enlarged and not to scale when describing embodiments of the present invention. Furthermore, the schematic diagrams are merely illustrative and should not limit the scope of the present invention. Furthermore, in actual production, the three-dimensional dimensions of length, width, and depth should be included.

[0054] In the description of the present invention, it should be noted that the terms "upper, lower, inner, and outer" and other references to orientations or positional relationships are based on the orientations or positional relationships shown in the accompanying drawings and are intended solely to facilitate and simplify the description of the present invention. They are not intended to indicate or imply that the devices or components referred to must have, be constructed, or operate in a specific orientation, and therefore should not be construed as limitations on the present invention. Furthermore, the terms "first, second, or third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0055] In this disclosure, unless otherwise specified or limited, the terms "mounted," "connected," and "connected" should be interpreted broadly. For example, they may refer to fixed, removable, or integral connections. They may also refer to mechanical, electrical, or direct connections, indirect connections through an intermediary, or internal communication between two components. Those skilled in the art will understand the specific meanings of these terms in this disclosure.

[0056] Example 1

[0057] Reference Figure 1 , which is the first embodiment of the present invention, provides a method for intelligent diagnosis and early warning of rail transit hub equipment faults, including:

[0058] S1: Collect multimodal data from various devices in the rail transit hub, and align the multimodal data in time and space based on the device topology and timestamps to generate multidimensional fault feature data.

[0059] S1.1: Collect multimodal data from each device in the rail transit hub, where the multimodal data includes vibration sensor data and equipment operating condition data.

[0060] It should be noted that the multimodal data includes vibration sensor data and equipment operating condition data; the vibration sensor data includes the equipment's X-axis vibration acceleration, Y-axis vibration acceleration, and Z-axis vibration acceleration; the equipment operating condition data includes bearing temperature data, motor current data, and speed data.

[0061] S1.2: Label the multimodal data with device numbers according to the collection location, and establish a spatial correlation matrix between devices based on the rail transit hub equipment topology diagram.

[0062] It should be noted that the element values ​​in the spatial correlation matrix represent the physical distances between devices.

[0063] S1.3: Align the timestamps of the multimodal data and unify the data with different sampling frequencies to the same time scale through linear interpolation to generate a multimodal data sequence.

[0064] S1.4: Perform spatial correlation analysis on the data of adjacent devices in the multimodal data sequence based on the spatial correlation matrix and calculate the fault propagation coefficient between devices.

[0065] S1.5: Combine the multimodal data sequence and the fault propagation coefficient to form multidimensional fault feature data.

[0066] It should be noted that the multi-dimensional fault feature data includes the device's own status features and the fault correlation features between devices.

[0067] S2: Input the multi-dimensional fault feature data into the parallel feature extraction module to generate a fault feature vector.

[0068] S2.1: Divide the multi-dimensional fault feature data into vibration feature channels, temperature feature channels, and current feature channels according to data types.

[0069] It should be noted that the vibration characteristic channel includes vibration data in the three directions of X-axis, Y-axis and Z-axis; the temperature characteristic channel includes bearing temperature data; and the current characteristic channel includes motor current data.

[0070] S2.2: Perform wavelet packet decomposition on the data of the vibration feature channel to extract the energy feature, kurtosis feature and skewness feature of each frequency band to form a vibration feature sub-vector.

[0071] S2.3: Perform statistical analysis on the data of the temperature feature channel, calculate the temperature mean, standard deviation, and rate of change, and form a temperature feature subvector.

[0072] S2.4: Perform Fourier transform on the data of the current characteristic channel to extract the current harmonic ratio, phase difference and waveform distortion rate to form a current characteristic sub-vector.

[0073] S2.5: Fuse the vibration feature sub-vector, temperature feature sub-vector, and current feature sub-vector using feature importance weights to generate a fault feature vector.

[0074] It should be noted that the feature importance weights are obtained through training with historical fault samples.

[0075] S3: Input the fault feature vector into the fault diagnosis model, perform preliminary classification based on the ResNet-18 network backbone structure, and output the corresponding fault type and confidence level.

[0076] S3.1: Construct a fault diagnosis model based on the ResNet-18 structure, where the fault diagnosis model includes a feature extraction layer, a domain discrimination layer, and a fault classification layer.

[0077] It should be noted that the feature extraction layer uses historical data of source domain devices for pre-training.

[0078] In an optional implementation, establishing a fault diagnosis model includes: collecting operating data of source domain equipment, labeling the operating data according to fault types, and constructing a source domain training data set; extracting time domain features, frequency domain features, and time-frequency features from the source domain training data set to generate a feature sample matrix.

[0079] In an optional embodiment, the fault diagnosis model is trained in stages: in the first stage, the feature extraction layer and the fault classification layer are pre-trained using the source domain training data set; in the second stage, the feature extraction layer parameters are frozen and the domain discrimination layer is trained separately; in the third stage, the feature extraction layer, the domain discrimination layer and the fault classification layer are jointly optimized.

[0080] It should be noted that after each training stage, the classification accuracy on the validation set is calculated. When the improvement in classification accuracy reaches the maximum training round, the next training stage is entered.

[0081] Specifically, the feature extraction layer contains 4 residual blocks, each of which contains 2 convolutional layer combination units and 1 skip connection path; the domain discrimination layer adopts a 3-layer fully connected network structure; and the fault classification layer adopts a softmax classifier.

[0082] Furthermore, the fault diagnosis model also includes a convolutional layer combination unit and a skip connection path; the convolutional layer combination unit is composed of two 3×3 convolutional layers in series, and each convolutional layer is connected to a batch normalization layer and a ReLU activation function; the skip connection path uses a 1×1 convolutional layer to perform dimensionality reduction transformation on the input features.

[0083] S3.2: Input the fault feature vector into the feature extraction layer to extract high-dimensional feature representation, where the high-dimensional feature representation includes deep semantic information of the device status.

[0084] S3.3: Calculate the maximum average difference measure between the source domain features and the target domain features in the domain discrimination layer, and use the maximum average difference measure as the optimization target of the domain adaptation loss function.

[0085] Preferably, the specific formula for the maximum average difference metric is as follows:

[0086]

[0087] Among them, D max is the maximum average difference metric, N is the total number of samples, T is the signal sampling period, X i (t) is the time domain signal value of the i-th sample at time t, X j (t) is the time domain signal value of the jth sample at time t, K is the total number of frequency domain feature dimensions, F i (m) is the amplitude of the mth frequency component of the ith sample, F j (m) is the amplitude of the mth frequency component of the jth sample, and α is the balance weight coefficient between the time domain features and the frequency domain features.

[0088] S3.4: Use labeled samples of rail transit hub equipment in the target domain and combine them with the domain adaptation loss function to train the parameters of the feature extraction layer to make the features domain invariant.

[0089] S3.5: Input the features trained through domain adaptation into the fault classification layer, calculate the probability distribution of each fault type, and output the fault type with the highest probability and the confidence value.

[0090] Preferably, the correlation formula between the fault type with the highest probability and the confidence value is as follows:

[0091]

[0092]

[0093] Among them, C is the confidence value, γ(d i ) is based on the sample distance d i The exponential decay function, S is the similarity score, σ 2 is the variance of the current feature set, is the preset maximum allowable variance threshold, δ is the confidence correction coefficient, P(F k |X) is the fault type F under the given feature X k The posterior probability of occurrence, M is the total number of features, w i is the weight coefficient of the i-th feature, is the mapping value of the i-th feature extraction function to the given feature X, λ k is the characteristic vector of the kth type of fault, B is the total number of fault types, H(X) is the information entropy of the current feature X, N is the total number of historical samples, X n is the characteristic value of the nth historical sample.

[0094] S4: Calculate the remaining service life of the equipment based on the fault type and confidence level, generate early warning information, and dynamically adjust the confidence level based on historical warning statistics and the real-time load rate of the equipment to achieve hierarchical management of early warning notifications.

[0095] S4.1: Match the fault type and confidence level with typical fault cases in the historical fault database, construct a fault similarity scoring matrix, extract the degradation curve template corresponding to the fault type, and calculate the remaining service life of the equipment.

[0096] Preferably, the specific formula of the fault similarity scoring matrix is ​​as follows:

[0097]

[0098] Among them, S is the similarity score between the i-th current feature vector and the j-th historical case, d is the Euclidean distance, θ is the feature vector angle, ρ is the Pearson correlation coefficient, and β and γ are weight coefficients.

[0099] In an optional embodiment, when the confidence of the fault type is higher than the first confidence threshold and the historical case matching degree is greater than the first matching threshold, the fault case is marked as a first-level credible matching case; when the confidence of the fault type is between the second confidence threshold and the first confidence threshold, and the historical case matching degree is between the second matching threshold and the first matching threshold, the fault case is marked as a second-level credible matching case; when the confidence of the fault type is less than the second confidence threshold or the historical case matching degree is less than the second matching threshold, the fault case is marked as a third-level credible matching case.

[0100] It should be noted that the first confidence threshold is based on the 85% percentile of the diagnostic accuracy in historical fault diagnosis results; the second confidence threshold is based on the 70% percentile of the diagnostic accuracy in historical fault diagnosis results; the first matching threshold is based on the 80% percentile of the similarity calculation results of historical fault cases; the second matching threshold is based on the 75% percentile of the similarity calculation results of historical fault cases.

[0101] In an optional implementation, for a first-level trusted matching case: if the remaining service life is less than the first time threshold and the device load rate is greater than the first load threshold, a first-level warning is triggered; if the remaining service life is between the first time threshold and the second time threshold, and the device load rate is between the second load threshold and the first load threshold, a second-level warning is triggered; if the remaining service life is between the second time threshold and the third time threshold, and the device load rate is less than the second load threshold, a third-level warning is triggered.

[0102] In an optional embodiment, for the second-level trusted matching case: if the remaining service life is less than the fourth time threshold and the device load rate is greater than the third load threshold, a first-level warning is triggered; if the remaining service life is between the fourth time threshold and the fifth time threshold, and the device load rate is between the fourth load threshold and the third load threshold, a second-level warning is triggered; if the remaining service life is between the fifth time threshold and the sixth time threshold, and the device load rate is less than the fourth load threshold, a third-level warning is triggered.

[0103] In an optional implementation, for a third-level trusted matching case: if the remaining service life is less than the seventh time threshold and the device load rate is greater than the fifth load threshold, a first-level warning is triggered; if the remaining service life is between the seventh time threshold and the eighth time threshold, and the device load rate is between the sixth load threshold and the fifth load threshold, a second-level warning is triggered; if the remaining service life is between the eighth time threshold and the ninth time threshold, and the device load rate is less than the sixth load threshold, a third-level warning is triggered.

[0104] Furthermore, the specific formula for the remaining useful life is as follows:

[0105]

[0106] Where RUL is the remaining useful life, P is the number of historical cases selected, and w a is the weight of the a-th case, w a is the total life of case a, L a is the total life of case a, t a is the time when the ath case reaches the current degradation level, S c is the current degradation state value, S a is the degradation state value of the ath case.

[0107] It should be noted that the first time threshold is based on the 25th percentile of the equipment failure development cycle statistics; the second time threshold is based on the 50th percentile of the equipment failure development cycle statistics; the third time threshold is based on the 75th percentile of the equipment failure development cycle statistics; the fourth time threshold is based on the average development cycle of the first-level credibility failure case; the fifth time threshold is based on the average development cycle of the second-level credibility failure case; the sixth time threshold is based on the average development cycle of the third-level credibility failure case; the seventh time threshold is based on the shortest response time of the critical failure; the eighth time threshold is based on the shortest response time of the important failure; the ninth time threshold is based on the shortest response time of the general failure; the first load threshold is based on the 80th percentile of the equipment rated load; the second load threshold is based on the 75th percentile of the equipment rated load; the third load threshold is based on the upper limit of the equipment safe operation load; the fourth load threshold is based on the upper limit of the equipment optimal operation load range; the fifth load threshold is based on the statistical results of the equipment peak load; the sixth load threshold is based on the statistical results of the equipment average load.

[0108] S4.2: Establish dynamic warning classification rules based on the credibility of typical fault cases, classify warning information into levels, and collect real-time load rates of equipment.

[0109] In an optional implementation, the warning classification rules include:

[0110] The triggering conditions for the first-level warning (any of the following conditions): the fault type is a key component fault and the fault evolution rate exceeds the first rate threshold; the equipment vibration amplitude exceeds the safe operation upper limit and affects the normal operation of adjacent equipment; the fault causes the equipment efficiency to decrease by more than the first efficiency reduction threshold and the duration exceeds the first time threshold; multiple monitoring points have abnormalities at the same time and the degree of abnormality exceeds the first abnormality threshold;

[0111] The triggering conditions for the second-level warning (any of the following conditions is met): the fault type is a major component fault and the fault evolution rate is between the second rate threshold and the first rate threshold; the equipment vibration amplitude is close to the safe operation upper limit but does not affect adjacent equipment; the equipment efficiency reduction caused by the fault is between the second efficiency reduction threshold and the first efficiency reduction threshold; the abnormality level of a single key monitoring point exceeds the second abnormality threshold and the duration exceeds the second time threshold;

[0112] The triggering conditions for the third-level warning (any of the following conditions is met): the fault type is a general component failure and the fault evolution rate is lower than the second rate threshold; the equipment vibration amplitude fluctuates but does not exceed the safe operating range; the fault causes the equipment efficiency to decrease by less than the second efficiency reduction threshold; intermittent abnormalities occur at the monitoring point and the degree of abnormality is lower than the second abnormality threshold.

[0113] It should be noted that the first rate threshold is based on the rate of change of characteristic parameters in the rapid development stage of the fault; the second rate threshold is based on the rate of change of characteristic parameters in the stable development stage of the fault; the first efficiency reduction threshold is based on the statistical value of the inflection point where the equipment efficiency drops sharply; the second efficiency reduction threshold is based on the statistical value of the inflection point where the equipment efficiency drops slowly; the first abnormality threshold is based on 2 times the standard deviation of the fluctuation range of the equipment's normal operating parameters; the second abnormality threshold is based on 1.5 times the standard deviation of the fluctuation range of the equipment's normal operating parameters.

[0114] S4.3: The remaining service life is corrected according to the real-time load rate. When the real-time load rate is higher than the rated load rate, the remaining service life is shortened according to the load ratio.

[0115] S4.4: Calculate the accuracy of the warning level and construct the warning confidence correction coefficient.

[0116] It should be noted that the warning confidence correction coefficient increases with the improvement of warning accuracy.

[0117] S4.5: Multiply the warning confidence correction coefficient by the current confidence to obtain the corrected confidence value, and push the warning information in a graded manner.

[0118] As illustrated in the example, during the operation of a certain rail transit hub equipment, the bearing fault type was identified through the fault diagnosis model with a confidence level of 0.88, which is higher than the first confidence threshold of 0.85; the fault case was matched with the historical database, and the fault similarity score matrix was calculated, with the highest matching degree of 0.83, which is higher than the first matching degree threshold of 0.80, so the case was marked as a first-level credible matching case; the degradation curve template of the bearing fault was extracted from the matched historical cases, and based on the vibration characteristics, temperature characteristics and other parameters of the current equipment, the remaining service life was calculated to be 120 hours; because the real-time load rate of the current equipment is 85%, which is higher than the first load threshold of 80%, and the remaining service life is less than the first time threshold of 150 hours, the system triggers a first-level warning.

[0119] In this example, the bearing fault's evolution rate is 0.15 / hour, exceeding the first rate threshold of 0.12 / hour. Furthermore, the equipment's vibration amplitude has reached 1.8 times the safe operating limit, impacting the normal operation of adjacent equipment. Furthermore, the equipment's efficiency has decreased by 15%, exceeding the first efficiency reduction threshold of 12%, and the duration of this condition has exceeded the first time threshold. The abnormality levels at multiple monitoring points have exceeded the first abnormality threshold, validating the validity of the Level 1 warning.

[0120] For example, querying historical warning statistics shows that the Level 1 warning accuracy for this type of fault is 92%, and the corresponding warning confidence correction factor is 1.05. Multiplying this correction factor by the current confidence level of 0.88 yields a revised confidence level of 0.924. Based on the final confidence level and warning level, the system sends a Level 1 warning to equipment management and maintenance personnel, recommending equipment maintenance within 24 hours.

[0121] In summary, the present invention realizes full-dimensional monitoring of equipment status through multimodal data acquisition and spatiotemporal alignment technology, effectively solving the problems of heterogeneous sensor data synchronization and cross-device fault correlation analysis; based on the parallel feature extraction module, it integrates multi-source features such as vibration, temperature, and current, and significantly improves the recognition ability of complex faults; combined with the dynamic confidence correction mechanism, the warning threshold is adaptively adjusted according to the historical warning accuracy and real-time load rate, which greatly reduces the false alarm rate and optimizes the timeliness of the warning; through the hierarchical push strategy, differentiated warning responses are implemented according to different credibility matching cases, while ensuring the priority processing of high-reliability warnings, and reasonably allocating operation and maintenance resources; this method not only enhances the accuracy of fault prediction, but also realizes the intelligence and refinement of operation and maintenance strategies, providing an efficient and reliable solution for the health management of rail transit hub equipment.

[0122] This embodiment also provides a computer device suitable for the case of an intelligent diagnosis and early warning method for rail transit hub equipment faults, including a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute computer-executable instructions to implement the intelligent diagnosis and early warning method for rail transit hub equipment faults proposed in the above embodiment.

[0123] This embodiment also provides an electronic device, which includes a processor, memory, a communication interface, a display screen, and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner. The wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a multi-task edge computing resource scheduling method is implemented. The display screen of the computer device can be a liquid crystal display or an electronic ink display screen. The input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad provided on the computer device housing, or an external keyboard, touchpad or mouse.

[0124] This embodiment further provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the method proposed in the above embodiment is implemented.

[0125] The storage medium proposed in this embodiment and the method proposed in the above embodiment belong to the same inventive concept. For technical details not fully described in this embodiment, please refer to the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0126] Through the above description of the implementation methods, those skilled in the art can clearly understand that the present invention can be implemented with the help of software and necessary general-purpose hardware, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory (FLASH), hard disk or optical disk, etc., including a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute the method of the embodiment of the present invention.

[0127] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

[0128] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code. The scheme in the embodiment of the present application can be implemented in various computer languages.

[0129] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0130] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0131] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0132] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present application.

[0133] Obviously, those skilled in the art may make various changes and modifications to this application without departing from the spirit and scope of this application. Thus, if these modifications and variations of this application fall within the scope of the claims of this application and their equivalents, this application is intended to include these modifications and variations.

Claims

1. A method for intelligent diagnosis and early warning of rail transit hub equipment faults, characterized by: include, Collect multimodal data from various devices in the rail transit hub, and perform spatiotemporal alignment on the multimodal data based on device topology and timestamps to generate multidimensional fault signature data; Inputting the multi-dimensional fault feature data into a parallel feature extraction module to generate a fault feature vector; The fault feature vector is input into the fault diagnosis model, and preliminary classification is performed based on the ResNet-18 network backbone structure, and the corresponding fault type and confidence are output; The remaining service life of the equipment is calculated based on the fault type and confidence level, and warning information is generated. The confidence level is dynamically adjusted based on historical warning statistics of the confidence level and the real-time load rate of the equipment to achieve hierarchical management of warning notifications.

2. The method for intelligent diagnosis and early warning of rail transit hub equipment failures according to claim 1, characterized in that: The remaining service life of the equipment is calculated based on the fault type and confidence level, and early warning information is generated, including: Match the fault type and confidence level with typical fault cases in the historical fault database, build a fault similarity scoring matrix, extract the degradation curve template corresponding to the fault type, and calculate the remaining service life; Establish dynamic warning classification rules based on the credibility of typical fault cases, classify warning information into levels, and collect real-time load rates of equipment; Correcting the remaining service life according to the real-time load rate; when the real-time load rate is higher than the rated load rate, shortening the remaining service life according to the load ratio; Calculate the accuracy of warning levels and construct warning confidence correction coefficients; The warning confidence correction coefficient is multiplied by the current confidence to obtain a corrected confidence value, and the warning information is pushed in a graded manner.

3. The method for intelligent diagnosis and early warning of rail transit hub equipment faults according to claim 2, characterized in that: Match the fault type and confidence level with typical fault cases in the historical fault database, including: When the confidence of the fault type is higher than the first confidence threshold and the historical case matching degree is greater than the first matching threshold, the fault case is marked as a first-level credible matching case; When the confidence of the fault type is between the second confidence threshold and the first confidence threshold, and the historical case matching degree is between the second matching threshold and the first matching threshold, the fault case is marked as a second-level credible matching case; When the confidence of the fault type is less than the second confidence threshold or the historical case matching degree is less than the second matching threshold, the fault case is marked as a third-level credible matching case.

4. The intelligent diagnosis and early warning method for rail transit hub equipment faults according to claim 3, characterized in that: Also includes, For the first-level trusted match case: if the remaining service life is less than the first time threshold and the device load rate is greater than the first load threshold, a first-level warning is triggered; if the remaining service life is between the first time threshold and the second time threshold, and the device load rate is between the second load threshold and the first load threshold, a second-level warning is triggered; if the remaining service life is between the second time threshold and the third time threshold, and the device load rate is less than the second load threshold, a third-level warning is triggered; For the second-level trusted match case: if the remaining service life is less than the fourth time threshold and the device load rate is greater than the third load threshold, a first-level warning is triggered; if the remaining service life is between the fourth time threshold and the fifth time threshold, and the device load rate is between the fourth load threshold and the third load threshold, a second-level warning is triggered; if the remaining service life is between the fifth time threshold and the sixth time threshold, and the device load rate is less than the fourth load threshold, a third-level warning is triggered; For the three-level trusted matching case: if the remaining service life is less than the seventh time threshold and the device load rate is greater than the fifth load threshold, a first-level warning is triggered; if the remaining service life is between the seventh time threshold and the eighth time threshold, and the device load rate is between the sixth load threshold and the fifth load threshold, a second-level warning is triggered; if the remaining service life is between the eighth time threshold and the ninth time threshold, and the device load rate is less than the sixth load threshold, a third-level warning is triggered.

5. The method for intelligent diagnosis and early warning of rail transit hub equipment faults according to claim 2, characterized in that: The method for obtaining the fault type and confidence level is as follows: Constructing a fault diagnosis model based on the ResNet-18 structure, wherein the fault diagnosis model includes a feature extraction layer, a domain discrimination layer, and a fault classification layer; Inputting the fault feature vector into the feature extraction layer to extract a high-dimensional feature representation, wherein the high-dimensional feature representation includes deep semantic information of the device status; Calculating a maximum average difference measure between source domain features and target domain features in the domain discrimination layer, and using the maximum average difference measure as an optimization target of a domain adaptation loss function; Using labeled samples of rail transit hub equipment in the target domain, and combining the domain adaptation loss function, the parameters of the feature extraction layer are trained to make the features domain invariant; The features that have undergone domain adaptation training are input into the fault classification layer, the probability distribution of each fault type is calculated, and the fault type with the highest probability and the confidence value are output.

6. The method for intelligent diagnosis and early warning of rail transit hub equipment faults according to claim 3, characterized in that: The method for obtaining the fault feature vector is: The multi-dimensional fault feature data is divided into vibration feature channel, temperature feature channel and current feature channel according to data type; Performing wavelet packet decomposition on the data of the vibration characteristic channel to extract the energy characteristics, kurtosis characteristics and skewness characteristics of each frequency band to form a vibration characteristic subvector; Performing statistical analysis on the data of the temperature characteristic channel, calculating the temperature mean, standard deviation and change rate, and forming a temperature characteristic subvector; Performing Fourier transform on the data of the current characteristic channel to extract the current harmonic ratio, phase difference and waveform distortion rate to form a current characteristic sub-vector; The vibration characteristic sub-vector, the temperature characteristic sub-vector, and the current characteristic sub-vector are fused using feature importance weights to generate a fault characteristic vector.

7. The method for intelligent diagnosis and early warning of rail transit hub equipment faults according to claim 6, characterized in that: The method for obtaining the multi-dimensional fault feature data is: Collecting multimodal data from various devices within a rail transit hub, wherein the multimodal data includes vibration sensor data and device operating condition data; Marking the multimodal data with device numbers according to the collection location, and establishing a spatial correlation matrix between devices based on the rail transit hub equipment topology diagram; Performing timestamp alignment on the multimodal data, unifying data with different sampling frequencies to the same time scale by a linear interpolation method, and generating a multimodal data sequence; Performing spatial correlation analysis on data of adjacent devices in the multimodal data sequence based on the spatial correlation matrix to calculate a fault propagation coefficient between devices; The multimodal data sequence and the fault propagation coefficient are combined to form multidimensional fault feature data.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method for intelligent diagnosis and early warning of rail transit hub equipment faults according to any one of claims 1 to 7 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for intelligent diagnosis and early warning of rail transit hub equipment faults according to any one of claims 1 to 7 are implemented.

Images