An intelligent diagnosis method and system for construction equipment failures

Abstract

The present invention discloses an intelligent diagnosis method and system for building equipment faults, and relates to the technical field of equipment fault diagnosis. An intelligent diagnosis system for building equipment faults includes: a fault component determination module and a comprehensive fault diagnosis module. The present invention constructs a digital model for building equipment fault diagnosis through a digital twin method, and combines multimodal data processing, feature matching and model updating to effectively improve the accuracy of fault diagnosis, especially in the monitoring and analysis of multi-component and complex equipment; through real-time updates based on the digital model of equipment fault diagnosis, it can timely discover and locate equipment faulty components, achieve more efficient and more accurate equipment maintenance, thereby reducing equipment downtime and maintenance costs; using adaptive clustering algorithms and multi-level fault diagnosis analysis, it can dynamically respond to different equipment states and fault types, and improve the real-time and adaptability of fault diagnosis.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment fault diagnosis, and particularly to an intelligent fault diagnosis method and system for construction equipment. Background Art

[0002] In traditional construction equipment fault diagnosis, common methods mainly rely on single-sensor data or manual experience judgment. The limitations of these methods are that the data of a single sensor cannot comprehensively reflect the multi-dimensional state of equipment operation, and potential complex fault modes are easily overlooked. In addition, the diagnosis method relying on manual experience is highly subjective and is easily affected by the experience and judgment ability of operators, resulting in a reduction in the accuracy and efficiency of fault diagnosis. With the diversification and complexity of construction equipment types, traditional diagnosis methods can no longer meet the requirements of modern construction systems for efficient and accurate fault diagnosis.

[0003] Therefore, there is an urgent need to design a method that can perform correlation analysis by combining multiple data and use joint hierarchical reasoning technology for comprehensive fault diagnosis. This method can improve the diagnosis accuracy, expand the decision-making dimension, and enhance the adaptive ability in the fault diagnosis of construction equipment. Summary of the Invention

[0004] The present invention aims to provide an intelligent fault diagnosis method and system for construction equipment to improve the accuracy of fault diagnosis.

[0005] An intelligent fault diagnosis method for construction equipment includes the following steps:

[0006] When a construction equipment fault signal is received, record the current monitoring time point; identify the construction equipment to which the construction equipment fault signal belongs as the faulty construction equipment; for the faulty construction equipment, extract the corresponding digital model for construction equipment fault diagnosis; the digital model for construction equipment fault diagnosis is constructed by the digital twin method; the digital model for construction equipment fault diagnosis includes N construction equipment components B n , n = 1, 2,..., N, where N is the total number of construction equipment components included in the faulty construction equipment;

[0007] Obtain the construction equipment monitoring data D m of the faulty construction equipment for the previous M monitoring time points L m where m = 1, 2,..., M; the monitoring time point L M corresponds to the current monitoring time point;

[0008] Combine the first M pieces of construction equipment monitoring data D m to obtain the monitoring data set of the faulty construction equipment; where D m ={D mi |i = 1, 2,..., I}; Dmi Denote the monitoring data D of construction equipment m as the multi-modal monitoring data from different sensors, where I represents the total number of different sensors;

[0009] Based on the faulty construction equipment monitoring data set and the construction equipment data matching model for analysis, an updated digital model Z of equipment faulty components is obtained n and the time-series monitoring data X of construction equipment components n ;

[0010] Combine all the updated digital models Z of equipment faulty components n to update the construction equipment fault diagnosis digital model of the faulty construction equipment, obtaining a new construction equipment fault diagnosis digital model; utilize the time-series monitoring data X of construction equipment components n and the construction equipment fault intelligent diagnosis model for fault analysis, obtaining the comprehensive diagnosis result of construction equipment faults;

[0011] According to the comprehensive diagnosis result of construction equipment faults and the new construction equipment fault diagnosis digital model, perform maintenance operations on the faulty construction equipment.

[0012] As a preferred technical solution of the present invention, the construction equipment data matching model includes a monitoring data processing layer, a component feature matching layer, and an analysis result output layer;

[0013] The monitoring data processing layer is used to normalize the format of the multi-modal monitoring data D in the construction equipment monitoring data D m to obtain the preprocessed multi-modal monitoring data D mi '; perform feature matching on all the preprocessed multi-modal monitoring data D mi ' to obtain the construction equipment matching label Q mi ; mi ;

[0014] At the monitoring time point L m , combine the preprocessed multi-modal monitoring data D mi corresponding to the same construction equipment matching label Q mi ' to obtain the construction equipment component monitoring data J mn ; combine the construction equipment component monitoring data J m at all the monitoring time points L mn to obtain the time-series monitoring data X of construction equipment components n ;

[0015] The component feature matching layer is used to perform model update processing based on the construction equipment fault diagnosis digital model and the time-series monitoring data X of construction equipment components n to obtain the updated digital model Z of equipment faulty components n ;

[0016] The analysis result output layer is used to output the updated digital model Z of the faulty components of the device n 。

[0017] As a preferred technical solution of the present invention, the specific steps for model update processing in the component feature matching layer include:

[0018] The component feature matching layer includes a feature extraction layer and a model update layer; among them, the feature extraction layer includes a text data processing unit and an image data processing unit;

[0019] Extract the time-series monitoring data X of the construction equipment components n The text data in it to obtain the time-series text change data T of the construction equipment components n ; In the text data processing unit, convert the time-series text change data T of the construction equipment components n Into the time-series text data vector T' of the construction equipment components n '; Use the pre-trained dynamic time attention mechanism to reconstruct the time-series text data vector T' of the construction equipment components n To obtain the time-series text data feature W of the construction equipment components n ;

[0020] Extract the image data in the time-series monitoring data X of the construction equipment components n To obtain the time-series image change data P of the construction equipment components n ; In the image data processing unit, extract the frequency domain feature and the time domain feature from the time-series image change data P of the construction equipment components n Respectively, to obtain the time-domain feature component P of the time-series image of the construction equipment components n1 And the frequency-domain feature component P of the time-series image of the construction equipment components n2 ; Combine the time-domain feature component P of the time-series image of the construction equipment components n1 And the frequency-domain feature component P of the time-series image of the construction equipment components n2 Using the pre-trained dynamic time attention mechanism to obtain the time-series image data feature U of the construction equipment components n ;

[0021] In the model update layer, based on the time-series text data feature W of the construction equipment components n And the time-series image data feature U of the construction equipment components n Make a prediction to obtain the transformation factor of the digital twin model of the construction equipment; according to the transformation factor of the digital twin model of the construction equipment, update the construction equipment component B in the construction equipment fault diagnosis digital model of the faulty construction equipment n To obtain the updated digital model Z of the faulty components of the device n 。

[0022] As a preferred technical solution of the present invention, the intelligent diagnosis model for construction equipment failures includes a time-series data diagnosis layer, a comprehensive failure diagnosis layer, and a diagnosis result output layer;

[0023] The time-series data diagnosis layer is used to perform data cutting on the basis of the time-series monitoring data X of construction equipment components n by using the improved adaptive clustering algorithm to obtain the fault backtracking points H of construction equipment components a , a = 1, 2,..., A; based on the fault backtracking points H of construction equipment components a perform data segmentation on the time-series monitoring data X of construction equipment components n to obtain the time-slice data blocks G of construction equipment components a ;

[0024] The comprehensive failure diagnosis layer is used to perform failure diagnosis according to the time-slice data blocks G of construction equipment components a and construction equipment component B n to obtain the failure diagnosis results C of construction equipment components na ; combine all the failure diagnosis results C of construction equipment components na to obtain the construction equipment failure diagnosis matrix; perform comprehensive failure diagnosis according to the construction equipment failure diagnosis matrix to obtain the comprehensive failure diagnosis results of construction equipment;

[0025] The diagnosis result output layer is used to output the comprehensive failure diagnosis results of construction equipment.

[0026] As a preferred technical solution of the present invention, the specific steps of using the improved adaptive clustering algorithm for data cutting in the time-series data diagnosis layer include:

[0027] Construct E clustering fault center point division individuals F e , e = 1, 2,..., E; each clustering fault center point division individual F e contains a set of backtracking points for dividing the time-series monitoring data X of construction equipment components n ; combine the E clustering fault center point division individuals F e to obtain the clustering fault center point division iterative population; set the maximum number of iterations;

[0028] The specific steps of constructing different clustering fault center point division individuals F e include:

[0029] Use the K-means clustering algorithm to perform initial clustering on the time-series monitoring data X of construction equipment components n to obtain the initial clustering center set of construction equipment component faults;

[0030] Based on the initial clustering center set of construction equipment component failures, retain the first half of the initial clustering center set of construction equipment component failures, and randomly generate several backtracking points near the second half of the initial clustering center set of construction equipment component failures to obtain a fluctuating clustering center set of construction equipment component failures; arbitrarily combine the first half of the initial clustering center set of construction equipment component failures and the fluctuating clustering center set of construction equipment component failures to obtain E different clustering failure center point division individuals F e ;

[0031] Based on the clustering failure center point division individual F e simulate the division of the time-series monitoring data X of construction equipment components n to obtain simulated data division blocks; calculate the similarity between different simulated data division blocks to obtain the corresponding average similarity; take the reciprocal of the average similarity as the fitness R e of the clustering failure center point division individual F e ;

[0032] When the maximum number of iterations is reached, output the clustering failure center point division individual corresponding to the current maximum fitness, which is the optimal clustering failure center point division individual; perform data cutting based on the optimal clustering failure center point division individual to obtain the construction equipment component failure backtracking points H a , a = 1, 2,..., A.

[0033] As a preferred technical solution of the present invention, the specific steps for fault diagnosis in the comprehensive fault diagnosis layer include:

[0034] The comprehensive fault diagnosis layer includes a component fault identification layer and a comprehensive fault result analysis layer;

[0035] In the component fault identification layer, perform fault diagnosis according to the construction equipment component time slice data block G a and the construction equipment component B n to obtain the construction equipment component fault diagnosis result C na ;

[0036] Among them, the comprehensive fault result analysis layer includes a result matrix analysis unit and a feature analysis unit;

[0037] In the result matrix analysis unit, combine all the construction equipment component fault diagnosis results C na to obtain a construction equipment fault diagnosis matrix;

[0038] In the feature analysis unit, perform feature extraction based on the construction equipment fault diagnosis matrix to obtain the construction equipment fault diagnosis matrix features; perform feature recognition on the construction equipment fault diagnosis matrix features to obtain the construction equipment comprehensive fault diagnosis result.

[0039] As a preferred technical solution of the present invention, the specific steps of the model update layer in the training component feature matching layer include:

[0040] Collect several groups of digital model change prediction training samples; each group of digital model change prediction training samples contains a verified model transformation factor and corresponding data features; combine several groups of digital model change prediction training samples to obtain a digital model change prediction training set;

[0041] Use the digital model change prediction training set for model training to obtain an initial model update layer; perform model evaluation on the initial model update layer. If the initial model update layer passes the model evaluation, use the initial model update layer as the model update layer in the component feature matching layer; otherwise, continue to perform model training using the digital model change prediction training set.

[0042] An intelligent fault diagnosis system for construction equipment includes:

[0043] A fault component determination module, including a data acquisition unit and a data processing unit;

[0044] The data acquisition unit is used to record the current monitoring time point when receiving a construction equipment fault signal; identify the construction equipment to which the construction equipment fault signal belongs as the faulty construction equipment; for the faulty construction equipment, extract the corresponding construction equipment fault diagnosis digital model; the construction equipment fault diagnosis digital model is constructed by the digital twin method; the construction equipment fault diagnosis digital model includes N construction equipment components B n , n = 1, 2,..., N, where N is the total number of construction equipment components included in the faulty construction equipment; obtain the construction equipment monitoring data D m of the faulty construction equipment including the previous M monitoring time points L m where m = 1, 2,..., M; the monitoring time point L M corresponds to the current monitoring time point; combine the previous M construction equipment monitoring data D m to obtain a faulty construction equipment monitoring data set; where D m = {D mi | i = 1, 2,..., I}; D mi represents the multi-modal monitoring data from different sensors in the construction equipment monitoring data D m , and I represents the total number of different sensors;

[0045] The data processing unit is used to analyze based on the faulty construction equipment monitoring data set and the construction equipment data matching model to obtain an updated equipment fault component digital model Z n and the construction equipment component time series monitoring data X n ;

[0046] A comprehensive fault diagnosis module, including a comprehensive diagnosis unit and a model updating unit;

[0047] Integrated diagnostic unit for utilizing time series monitoring data from building equipment components n Conduct fault analysis with the intelligent fault diagnosis model of building equipment to obtain comprehensive fault diagnosis results of building equipment; perform maintenance operations on faulty building equipment based on the comprehensive fault diagnosis results of building equipment and the new digital fault diagnosis model of building equipment;

[0048] The model updating unit is used to update the digital model Z of all the faulty parts of the equipment n The construction equipment fault diagnosis digital model of the faulty construction equipment is updated to obtain a new construction equipment fault diagnosis digital model.

[0049] The present invention has the following advantages:

[0050] 1. The present invention constructs a digital model for building equipment fault diagnosis through a digital twin method, and combines multimodal data processing, feature matching and model updating to effectively improve the accuracy of fault diagnosis, especially in the monitoring and analysis of multi-component and complex equipment; through real-time updates based on the digital model of equipment fault diagnosis, it is possible to timely discover and locate equipment faulty components, achieve more efficient and accurate equipment maintenance, and thus reduce equipment downtime and maintenance costs; using adaptive clustering algorithms and multi-level fault diagnosis analysis, the model can dynamically respond to different equipment states and fault types, improve the real-time and adaptability of fault diagnosis, and ensure that the equipment can resume normal operation in the shortest time.

[0051] 2. The present invention can accurately divide the time-series monitoring data of building equipment components into reasonable data blocks through an improved adaptive clustering algorithm. This data cutting method can more accurately identify the changing trend of equipment failures, especially through the reasonable setting of backtracking points, to ensure the accurate identification of equipment failures; in the clustering process, after the initial fault clustering center is generated by the K-means clustering algorithm, it is optimized in combination with the fluctuating clustering center and the randomly generated backtracking points to ensure that the clustering center can adapt to the fluctuations of the equipment operating status. This adaptive adjustment improves the adaptability of the clustering process to different failure modes. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 The present invention is a schematic diagram of the structure of an intelligent diagnosis system for building equipment faults used in an embodiment of the present invention. DETAILED DESCRIPTION

[0053] To enable those skilled in the art to better understand the technical solutions in the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention.

[0054] Embodiment 1, an intelligent fault diagnosis method for construction equipment, includes the following steps:

[0055] When a construction equipment fault signal is received, record the current monitoring time point; identify the construction equipment to which the construction equipment fault signal belongs as the faulty construction equipment; among them, for the faulty construction equipment, extract the corresponding construction equipment fault diagnosis digital model; the construction equipment fault diagnosis digital model is constructed by the digital twin method; the construction equipment fault diagnosis digital model includes N construction equipment components B n , n = 1, 2,..., N, where N is the total number of construction equipment components included in the faulty construction equipment;

[0056] By constructing the construction equipment fault diagnosis digital model through the digital twin method, the status and performance of the construction equipment and its components can be comprehensively reflected. The digital model of each construction equipment component ensures precise monitoring of all links of the equipment, thus helping to detect potential faults in a timely manner; decomposing the equipment into multiple components and establishing independent fault diagnosis models for each component makes the fault analysis more detailed and accurate, enabling the identification of faults in specific components rather than just the faults of the entire equipment, improving the diagnosis accuracy; using the digital twin technology to create virtual models for each construction equipment enhances the digital management of the equipment. This method provides a powerful data support and analysis basis for the health monitoring, fault prediction, and maintenance decision-making of the equipment;

[0057] Obtain the construction equipment monitoring data D of the previous M monitoring time points L including the current monitoring time point for the faulty construction equipment m , m = 1, 2,..., M; the monitoring time point L m corresponds to the current monitoring time point; M The monitoring time points are generally used to collect data from sensors at fixed time intervals. The monitoring time points usually correspond to the timestamps of data collection, that is, the moments when the sensors record data; when a fault in the construction equipment is detected, the generation time of the fault signal is the current monitoring time point; the value of M can be set to the monitoring data within the past few minutes or hours according to the data collection frequency and the response time of the equipment;

[0058] Combine the first M pieces of construction equipment monitoring data D

[0059] to obtain the monitoring data set of the faulty construction equipment; among them, D m ={D m |i = 1, 2,..., I}; D mi miRepresents building equipment monitoring data D m The multimodal monitoring data comes from different sensors, and I represents the total number of different sensors;

[0060] In building equipment monitoring, common sensor types include but are not limited to the following, each of which can collect multiple physical quantities and environmental parameters to facilitate comprehensive monitoring of the equipment status, such as temperature sensors, pressure sensors, vibration sensors, current and voltage sensors, etc.

[0061] When a fault signal is received, the faulty equipment can be quickly identified and further analyzed through real-time monitoring data to ensure that the fault is located in time, buy time for subsequent processing, and reduce equipment downtime; by collecting the first M pieces of building equipment monitoring data and combining them into a faulty equipment monitoring data set, more comprehensive equipment operation status information can be provided. This fusion of multiple historical data improves the accuracy of fault diagnosis and avoids the risk of misjudgment by relying solely on a single data point; by using the monitoring data of I different sensors, the operation of the equipment can be comprehensively evaluated from multiple dimensions. Diversified data sources help to more accurately identify the type of fault and improve the reliability of diagnosis;

[0062] Based on the faulty building equipment monitoring data set and the building equipment data matching model, the digital model Z of the updated equipment faulty component is obtained. n and building equipment component time series monitoring data X n ; The building equipment data matching model effectively improves the accuracy and real-time performance of intelligent diagnosis of building equipment faults and optimizes equipment maintenance capabilities through multimodal data processing, feature matching and model updating;

[0063] The building equipment data matching model includes a monitoring data processing layer, a component feature matching layer, and an analysis result output layer;

[0064] The monitoring data processing layer is used to process the building equipment monitoring data D m Multimodal monitoring data D mi Normalize the format to obtain the preprocessed multimodal monitoring data D mi '; For all pre-processed multimodal monitoring data D mi 'Perform feature matching to obtain the building equipment matching label Q mi ;

[0065] At the monitoring time point L m In the example, the same building equipment is matched with label Q mi The corresponding preprocessed multimodal monitoring data D mi 'Combined to obtain construction equipment component monitoring data J mn ; Set all monitoring time points L mMonitoring data J of construction equipment components mn Combined to obtain the time-series monitoring data X of construction equipment components n ;

[0066] The component feature matching layer is used to perform model update processing based on the construction equipment fault diagnosis digital model and the time-series monitoring data X of construction equipment components n To obtain the updated equipment fault component digital model Z n ;

[0067] The analysis result output layer is used to output the updated equipment fault component digital model Z n ;

[0068] Through the construction equipment data matching model, combining multi-modal data processing, feature matching, and model update, the accuracy and real-time performance of fault diagnosis can be improved. Timely updating the digital model of equipment fault components can more accurately reflect the actual state of the equipment, thereby improving the accuracy of diagnosis; by continuously updating the digital model and time-series monitoring data of construction equipment, the monitoring of the equipment health status can be enhanced, potential problems can be discovered in advance, and it helps to formulate an optimized equipment maintenance plan, which reduces the occurrence of sudden failures and improves the efficiency of equipment maintenance; through feature matching and model update, various monitoring data can be effectively matched with the fault equipment model, helping to generate a digital model consistent with the current equipment state. This dynamic update method can reflect the real-time changes of equipment faults and improve the adaptability and flexibility of the diagnosis model;

[0069] The specific steps for performing model update processing in the component feature matching layer include:

[0070] The component feature matching layer includes a feature extraction layer and a model update layer; among them, the feature extraction layer includes a text data processing unit and an image data processing unit;

[0071] Extract the text data in the time-series monitoring data X of construction equipment components n To obtain the time-series text change data T of construction equipment components n ; In the text data processing unit, convert the time-series text change data T of construction equipment components n Into the time-series text data vector T' of construction equipment components n '; Use the pre-trained dynamic time attention mechanism to reconstruct the time-series text data vector T' of construction equipment components n To obtain the time-series text data feature W of construction equipment components n ;

[0072] Extract the image data in the time-series monitoring data X of construction equipment components n To obtain the time-series image change data P of construction equipment components nIn the image data processing unit, the building equipment component time series image change data P n The frequency domain features and time domain features are extracted respectively to obtain the time domain feature component P of the time series image of the building equipment components. n1 and the frequency domain feature component P of the time series image of building equipment parts n2 ; The time domain feature component P of the building equipment component time series image n1 and the frequency domain feature component P of the time series image of building equipment parts n2 The pre-trained dynamic time attention mechanism is used to combine and obtain the temporal image data features U of the building equipment components. n ;

[0073] The training process of the pre-trained dynamic temporal attention mechanism usually includes the following steps: First, the model is pre-trained using a large amount of historical data to capture the temporal dependencies and feature changes in the time series data; during the training process, the model automatically learns the weight distribution between different time steps through the attention mechanism, focusing on the moments or features that are most important to the current task and ignoring irrelevant or noisy data; the dynamic temporal attention mechanism not only considers the global time series information during training, but also adaptively adjusts the importance of each time point, so that the model can freely weight when processing different types of time series data, thereby improving the prediction accuracy and flexibility of the model; finally, the trained model can accurately reconstruct the change pattern of the time series data and effectively support the analysis and prediction of real-time data;

[0074] In the model update layer, based on the temporal text data features W of building equipment components n and building equipment component time series image data features U n Predictions are made to obtain the transformation factor of the digital twin model of the building equipment; the building equipment component B in the building equipment fault diagnosis digital model of the faulty building equipment is predicted according to the transformation factor of the digital twin model of the building equipment. n Update and obtain the digital model Z of the updated equipment fault component n ;

[0075] Through the text data processing unit and the image data processing unit in the feature extraction layer, rich text and image features can be extracted from the time-series monitoring data of construction equipment components. The text data is reconstructed through the dynamic time attention mechanism, and the image data is processed by frequency-domain and time-domain feature extraction methods, ensuring the accurate expression of multi-modal data and providing a solid foundation for subsequent diagnosis. The combination of text and image data is fused using the dynamic time attention mechanism, which can more comprehensively capture the multi-dimensional information of equipment failures. The text data provides the changing trend of the equipment operation state, and the image data reveals the physical state of the equipment components through time-domain and frequency-domain features. The combination of the two significantly improves the comprehensiveness and accuracy of fault diagnosis. By using the time-series text data features and time-series image data features for prediction in the model update layer, the transformation factors of the digital twin model of construction equipment can be generated in real time, thereby dynamically updating the equipment fault diagnosis model. This dynamic update method can quickly adapt to the changes in equipment state and improve the real-time performance and accuracy of fault diagnosis. Combining multiple data features and the adaptive update mechanism enables the equipment fault diagnosis model to accurately reflect the current health state of the equipment. The digital model after model update is more in line with the actual equipment situation, thus improving the accuracy and reliability of diagnosis.

[0076] The specific steps for training the model update layer in the component feature matching layer include:

[0077] Collect several groups of digital model change prediction training samples; each group of digital model change prediction training samples contains verified model transformation factors and corresponding data features; combine several groups of digital model change prediction training samples to obtain a digital model change prediction training set.

[0078] Use the digital model change prediction training set for model training to obtain an initial model update layer; conduct model evaluation on the initial model update layer. If the initial model update layer passes the model evaluation, then use the initial model update layer as the model update layer in the component feature matching layer; otherwise, continue to use the digital model change prediction training set for model training.

[0079] By collecting digital model change prediction training samples and conducting training, it can be ensured that the model update layer can accurately predict the changes in the equipment digital model based on the existing model transformation factors and data features. This training based on sample data improves the adaptability and prediction ability of the model to equipment state changes. By conducting model evaluation on the initial model update layer, it can be ensured that only the models that have been verified and perform excellently are adopted, thereby improving the effectiveness and stability of the model. If the initial model fails to pass the evaluation, it can still be continuously optimized, ensuring continuous improvement and high-quality output during the training process.

[0080] Combine all to update the digital model Z of the equipment fault component nUpdate the digital model for diagnosing construction equipment failures of faulty construction equipment to obtain a new digital model for diagnosing construction equipment failures; utilize the time-series monitoring data X of construction equipment components n and the intelligent diagnostic model for construction equipment failures to conduct failure analysis and obtain the comprehensive diagnostic results of construction equipment failures;

[0081] According to the comprehensive diagnostic results of construction equipment failures and the new digital model for diagnosing construction equipment failures, perform maintenance operations on the faulty construction equipment; the intelligent diagnostic model for construction equipment failures realizes the precise identification and comprehensive diagnosis of construction equipment failures through an adaptive clustering algorithm and multi-level failure diagnostic analysis, improving the efficiency and accuracy of equipment failure detection;

[0082] The intelligent diagnostic model for construction equipment failures includes a time-series data diagnostic layer, a comprehensive failure diagnostic layer, and a diagnostic result output layer;

[0083] The time-series data diagnostic layer is used to perform data cutting on the basis of the time-series monitoring data X of construction equipment components n using the improved adaptive clustering algorithm to obtain the failure backtracking points H of construction equipment components, a = 1, 2,..., A; based on the failure backtracking points H of construction equipment components a perform data segmentation on the time-series monitoring data X of construction equipment components a to obtain the time-slice data blocks G of construction equipment components n ; a ;

[0084] The comprehensive failure diagnostic layer is used to conduct failure diagnosis based on the time-slice data blocks G of construction equipment components a and the construction equipment components B n to obtain the failure diagnostic results C of construction equipment components na ; combine all the failure diagnostic results C of construction equipment components na to obtain the failure diagnostic matrix of construction equipment; conduct comprehensive failure diagnosis according to the failure diagnostic matrix of construction equipment to obtain the comprehensive diagnostic results of construction equipment failures;

[0085] The diagnostic result output layer is used to output the comprehensive diagnostic results of construction equipment failures;

[0086] By updating the digital model of equipment failure components and combining time series monitoring data with the improved adaptive clustering algorithm, the failure mode of building equipment can be identified more accurately, which enables fault diagnosis to be predicted and analyzed based on the actual operation of the equipment, thereby improving the accuracy and efficiency of fault detection; the adaptive clustering algorithm in the time series data diagnosis layer can dynamically trace back faults based on the real-time monitoring data of the equipment and automatically identify the time point of potential equipment failures; through this dynamic adaptation process, diagnosis can update fault analysis in real time and provide continuously optimized equipment status assessment; the comprehensive fault diagnosis layer generates a building equipment fault diagnosis matrix by summarizing the fault diagnosis results of each component, and conducts detailed fault analysis from multiple levels. This multi-level diagnostic method helps to fully identify the overall problems of the equipment and avoid the risk of a single component failure going unnoticed; based on the analysis of time series data and component failure traceback points, the failure trend of the equipment can be identified in advance, providing earlier warnings for equipment maintenance. This fault prediction capability provides equipment managers with enough time to perform preventive maintenance and avoid losses caused by sudden failures;

[0087] The specific steps of using the improved adaptive clustering algorithm to perform data cutting in the time series data diagnosis layer include:

[0088] Construct E clusters to divide the fault center points into individual F e , e=1, 2, ..., E; each cluster fault center is divided into individual F e Contains a method for monitoring the time series data of building equipment components X n The set of backtracking points to be divided; E cluster fault centers are divided into individual F e Combine and obtain the cluster fault center point to divide the iterative population; set the maximum number of iterations; the maximum number of iterations is set by professional technicians according to actual conditions;

[0089] Construct different cluster fault center points to divide individual F e The specific steps include:

[0090] Using K-means clustering algorithm to classify the time series monitoring data of building equipment components X n Perform initial clustering to obtain the initial cluster center set of building equipment component failures;

[0091] Based on the initial clustering center set of construction equipment component failures, retain the first half of the initial clustering center set of construction equipment component failures, and randomly generate several backtracking points near the second half of the initial clustering center set of construction equipment component failures to obtain the fluctuating clustering center set of construction equipment component failures; arbitrarily combine the first half of the initial clustering center set of construction equipment component failures and the fluctuating clustering center set of construction equipment component failures to obtain E different individual cluster fault center point partitions F e ;

[0092] Based on the individual cluster fault center point partition F e Simulate the division of the time-series monitoring data X of construction equipment components n to obtain simulated data division blocks; calculate the similarity between different simulated data division blocks to obtain the corresponding average similarity; take the reciprocal of the average similarity as the fitness R of the individual cluster fault center point partition F e ; e ;

[0093] When the maximum number of iterations is reached, output the individual cluster fault center point partition corresponding to the maximum current fitness, which is the optimal individual cluster fault center point partition; perform data cutting based on the optimal individual cluster fault center point partition to obtain the construction equipment component fault backtracking points H a , a = 1, 2,..., A;

[0094] Through the improved adaptive clustering algorithm, the time-series monitoring data of construction equipment components can be accurately divided into reasonable data blocks. This data cutting method can more precisely identify the changing trend of equipment failures. Especially through the reasonable setting of backtracking points, the accurate identification of equipment failures is ensured; during the clustering process, after generating the initial fault clustering centers using the K-means clustering algorithm, it is optimized by combining the fluctuating clustering centers and randomly generated backtracking points to ensure that the clustering centers can adapt to the fluctuations of the equipment operation state. This adaptive adjustment improves the adaptability of the clustering process to different fault modes; by setting the maximum number of iterations and optimizing according to the fitness of the cluster fault center points, it is ensured that the clustering process gradually converges to the best solution in multiple iterations. This iterative optimization process makes the final clustering result more accurate and effectively avoids the situation of local optimal solutions; by accurately dividing the data blocks and calculating their similarities, clearer and more structured data can be provided for subsequent fault analysis. These data blocks help improve the understanding and processing ability of the fault diagnosis model for the time-series data of equipment components;

[0095] The specific steps for fault diagnosis in the comprehensive fault diagnosis layer include:

[0096] The comprehensive fault diagnosis layer includes a component fault identification layer and a comprehensive fault result analysis layer;

[0097] In the component fault identification layer, based on the building equipment component time slice data block G a and the building equipment component B n fault diagnosis is carried out to obtain the building equipment component fault diagnosis result C na ;

[0098] Among them, the comprehensive fault result analysis layer includes a result matrix analysis unit and a feature analysis unit;

[0099] In the result matrix analysis unit, all the building equipment component fault diagnosis results C na are combined to obtain the building equipment fault diagnosis matrix;

[0100] In the feature analysis unit, feature extraction is carried out based on the building equipment fault diagnosis matrix to obtain the building equipment fault diagnosis matrix feature; feature recognition is carried out on the building equipment fault diagnosis matrix feature to obtain the building equipment comprehensive fault diagnosis result;

[0101] The function of the result matrix analysis unit is to combine the fault diagnosis results of all building equipment components to form a fault diagnosis matrix; first, collect the fault diagnosis results of each component. For example, the fault diagnosis result of each component is calculated based on historical data, sensor data, etc. Combine the fault diagnosis results of all components according to the time sequence and component number to form a diagnosis matrix; a machine learning model can be used to analyze the matrix and train a classifier or regression model for generating the fault diagnosis matrix under future input data; the function of the feature analysis unit is to extract features based on the fault diagnosis matrix and then carry out fault identification. The process of feature extraction includes identifying the key patterns or relationships affecting the equipment state from the original matrix, and then analyzing these features to obtain a comprehensive fault diagnosis result; in this step, data preprocessing and feature extraction techniques such as principal component analysis, convolutional neural network or autoencoder can be used to transform the fault diagnosis matrix into a more concise and representative feature vector; input the extracted features into a deep neural network classifier for training to learn how to identify and predict equipment faults according to different feature patterns;

[0102] Through the component fault identification layer, independent fault diagnosis is carried out using the time-slice data blocks and component information of construction equipment components, which can accurately identify the fault types and fault states of each equipment component. This provides detailed component-level information for the overall equipment fault diagnosis and ensures the accuracy of the diagnosis results. In the comprehensive fault result analysis layer, by combining all component fault diagnosis results into a fault diagnosis matrix, the overall state of the construction equipment can be comprehensively analyzed. This global perspective helps to reveal the associations and mutual influences between multiple component faults, thereby improving the comprehensiveness and accuracy of fault diagnosis. The feature analysis unit can effectively screen out the most diagnostically valuable information by extracting key features from the fault diagnosis matrix and performing feature recognition. This process helps to improve the intelligent level of the fault diagnosis model, enabling it to automatically extract useful diagnostic features from complex diagnostic data. Through the analysis of the fault diagnosis matrix and feature recognition, reliable comprehensive fault diagnosis results can be obtained in a short time. This efficient diagnostic process not only improves the speed of fault identification but also enhances the reliability of fault prediction, avoiding the situation of missed diagnosis or misdiagnosis.

[0103] Embodiment 2, an intelligent fault diagnosis system for construction equipment, see Figure 1 as shown, including:

[0104] A faulty component determination module, including a data acquisition unit and a data processing unit;

[0105] The data acquisition unit is used to record the current monitoring time point when receiving a construction equipment fault signal; identify the construction equipment to which the construction equipment fault signal belongs as the faulty construction equipment; among them, for the faulty construction equipment, extract the corresponding construction equipment fault diagnosis digital model; the construction equipment fault diagnosis digital model is constructed by the digital twin method; the construction equipment fault diagnosis digital model includes N construction equipment components B n , n = 1, 2,..., N, where N is the total number of construction equipment components included in the faulty construction equipment; obtain the construction equipment monitoring data D m of the faulty construction equipment including the first M monitoring time points L m where m = 1, 2,..., M; the monitoring time point L M corresponds to the current monitoring time point; combine the first M pieces of construction equipment monitoring data D m to obtain the faulty construction equipment monitoring data set; where D m ={D mi |i = 1, 2,..., I}; D mi represents the multi-modal monitoring data from different sensors in the construction equipment monitoring data D m , and I represents the total number of different sensors;

[0106] The data processing unit is used to perform analysis based on the monitoring data set of faulty construction equipment and the construction equipment data matching model to obtain an updated digital model Z of equipment faulty components n and the time-series monitoring data X of construction equipment components n ;

[0107] The fault comprehensive diagnosis module includes a comprehensive diagnosis unit and a model update unit;

[0108] The comprehensive diagnosis unit is used to perform fault analysis by using the time-series monitoring data X of construction equipment components n and the intelligent fault diagnosis model of construction equipment to obtain the comprehensive fault diagnosis result of construction equipment; according to the comprehensive fault diagnosis result of construction equipment and the new digital model of construction equipment fault diagnosis, maintenance operations are performed on the faulty construction equipment;

[0109] The model update unit is used to update the digital model of construction equipment fault diagnosis of the faulty construction equipment by combining all the updated digital models Z of equipment faulty components n to obtain a new digital model of construction equipment fault diagnosis.

[0110] It should be understood that those of ordinary skill in the art can make improvements or transformations according to the above description, and all such improvements and transformations shall fall within the protection scope of the appended claims of the present invention. The parts not described in detail in this specification belong to the prior art well known to those of ordinary skill in the art.

Claims

1. An intelligent diagnostic method for construction equipment faults, characterized in that, It includes the following steps: When receiving a building equipment failure signal, record the current monitoring time point; Identify the construction equipment to which the construction equipment fault signal belongs as the faulty construction equipment; among them, for the faulty construction equipment, extract the corresponding construction equipment fault diagnosis digital model; the construction equipment fault diagnosis digital model is constructed by the digital twin method; the construction equipment fault diagnosis digital model includes N construction equipment components B n , where n = 1, 2, …, N, and N is the total number of construction equipment components included in the faulty construction equipment; Obtain the construction equipment with faults, including the construction equipment monitoring data D of the first M monitoring time points L where the current monitoring time point is located m where m = 1, 2, …, M; the monitoring time point L m corresponds to the current monitoring time point M ​ Combine the first M pieces of construction equipment monitoring data D m to obtain a monitoring data set of faulty construction equipment; where D m ={D mi |i = 1, 2, …, I}; D mi represents the multi-modal monitoring data from different sensors in the construction equipment monitoring data D m , and I represents the total number of different sensors; Analyze based on the monitoring data set of faulty construction equipment and the construction equipment data matching model to obtain the updated digital model Z of equipment faulty components n and the time-series monitoring data X of construction equipment components n ; Combine all updated digital models Z of faulty components of equipment n Update the digital model for diagnosing building equipment faults of faulty building equipment to obtain a new digital model for diagnosing building equipment faults; utilize the time-series monitoring data X of building equipment components n and the intelligent diagnostic model for building equipment faults to conduct fault analysis and obtain the comprehensive diagnostic results of building equipment faults; According to the comprehensive diagnosis result of building equipment failure and the new digital model for building equipment failure diagnosis, perform maintenance operations on the faulty building equipment; The intelligent diagnosis model for building equipment failure includes a time-series data diagnosis layer, a comprehensive failure diagnosis layer, and a diagnosis result output layer; The time-series data diagnosis layer is used to perform data cutting on the basis of the time-series monitoring data X of building equipment components n by using the improved adaptive clustering algorithm to obtain the fault backtracking points H of building equipment components a , a = 1, 2, …, A; based on the fault backtracking points H of building equipment components a perform data segmentation on the time-series monitoring data X of building equipment components n to obtain the time-slice data blocks G of building equipment components a ; The specific steps for data cutting using the improved adaptive clustering algorithm in the time-series data diagnosis layer include: Construct E clustering fault center points to divide the individual F e , e = 1, 2, …, E; each clustering fault center point divides the individual F e Contains a set of backtracking points for dividing the time-series monitoring data X of construction equipment components n Perform the division; combine the E clustering fault center point divided individuals F e to obtain a clustering fault center point division iterative population; set the maximum number of iterations; Construct the individual F for dividing the central points of different clustering faults e The specific steps include: Using the K-means clustering algorithm to perform primary clustering on the time-series monitoring data X of building equipment components n to obtain the initial clustering center set of building equipment component failures; Based on the initial clustering center set of construction equipment component failures, retain the first half of the initial clustering center set of construction equipment component failures, and randomly generate several backtracking points near the second half of the initial clustering center set of construction equipment component failures to obtain a fluctuating clustering center set of construction equipment component failures; arbitrarily combine the first half of the initial clustering center set of construction equipment component failures and the fluctuating clustering center set of construction equipment component failures to obtain E different individual F of clustering fault center point divisions e ; Dividing individual F based on the clustering fault center point e For the time-series monitoring data X of building equipment components n Perform simulation division to obtain simulation data division blocks; calculate the similarity between different simulation data division blocks to obtain the corresponding average similarity; take the reciprocal of the average similarity as the fitness R of the individual F divided by the clustering fault center point e ; e ; When the maximum number of iterations is reached, output the individual corresponding to the maximum current fitness as the optimal clustering fault center point division individual; perform data cutting based on the optimal clustering fault center point division individual to obtain the building equipment component fault backtracking point H a , a = 1, 2, …, A.

2. The intelligent fault diagnosis method for a construction device according to claim 1, wherein The building equipment data matching model includes a monitoring data processing layer, a component feature matching layer, and an analysis result output layer; The monitoring data processing layer is used to normalize the multi-modal monitoring data D m in the building equipment monitoring data mi to obtain preprocessed multi-modal monitoring data D mi '; perform feature matching on all preprocessed multi-modal monitoring data D mi ' to obtain the building equipment matching label Q mi ; At monitoring time point L m the preprocessed multi-modal monitoring data D mi corresponding to the same construction equipment matching label Q mi are combined to obtain the construction equipment component monitoring data J mn ; the construction equipment component monitoring data J m at all monitoring time points L mn are combined to obtain the construction equipment component time-series monitoring data X n ; The component feature matching layer is used to perform model update processing based on the digital model for building equipment fault diagnosis and the time-series monitoring data X of building equipment components n to obtain an updated digital model Z of the faulty components of the equipment n ; The analysis result output layer is used to output the updated digital model Z of the faulty components of the device n .

3. The intelligent fault diagnosis method for a construction device according to claim 2, characterized in that, The specific steps for model update processing in the component feature matching layer include: The component feature matching layer includes a feature extraction layer and a model update layer; among them, the feature extraction layer includes a text data processing unit and an image data processing unit; Extract the sequential monitoring data X of building equipment components n from the text data to obtain the sequential text change data T of building equipment components n ; In the text data processing unit, convert the sequential text change data T of building equipment components n into the sequential text data vector T' of building equipment components n ; Use the pre-trained dynamic time attention mechanism to reconstruct the sequential text data vector T' of building equipment components n to obtain the sequential text data feature W of building equipment components n ; Extract the time-series monitoring data X of the construction equipment components n from the image data therein to obtain the time-series image change data P of the construction equipment components n ; In the image data processing unit, for the time-series image change data P of the construction equipment components n extract the frequency-domain features and time-domain features respectively to obtain the time-domain feature component P of the time-series image of the construction equipment components n1 and the frequency-domain feature component P of the time-series image of the construction equipment components n2 ; Combine the time-domain feature component P of the time-series image of the construction equipment components n1 and the frequency-domain feature component P of the time-series image of the construction equipment components n2 using the pre-trained dynamic time attention mechanism to obtain the time-series image data feature U of the construction equipment components n ; In the model update layer, based on the time-series text data feature W of the construction equipment components n and the time-series image data feature U of the construction equipment components n predictions are made to obtain the transformation factor of the digital twin model of the construction equipment; according to the transformation factor of the digital twin model of the construction equipment, the construction equipment component B in the construction equipment fault diagnosis digital model of the faulty construction equipment n is updated to obtain the updated equipment fault component digital model Z n .

4. The intelligent fault diagnosis method for a construction device according to claim 3, wherein, The comprehensive fault diagnosis layer is used to perform fault diagnosis based on the time slice data block G of the building equipment component a and the building equipment component B n to obtain the fault diagnosis result C of the building equipment component na ; Combine all the fault diagnosis results C of the building equipment components na to obtain a building equipment fault diagnosis matrix; Conduct comprehensive failure diagnosis according to the building equipment failure diagnosis matrix to obtain the comprehensive diagnosis result of building equipment failure; The diagnosis result output layer is used to output the comprehensive diagnosis result of building equipment failure.

5. The intelligent fault diagnosis method for a construction device according to claim 4, characterized in that, The specific steps for failure diagnosis in the comprehensive failure diagnosis layer include: The comprehensive failure diagnosis layer includes a component failure identification layer and a comprehensive failure result analysis layer; In the component fault identification layer, based on the building equipment component time slice data block G a and the building equipment component B n fault diagnosis is performed to obtain the building equipment component fault diagnosis result C na ; Among them, the comprehensive failure result analysis layer includes a result matrix analysis unit and a feature analysis unit; In the result matrix analysis unit, all the building equipment component fault diagnosis results C na are combined to obtain the building equipment fault diagnosis matrix; In the feature analysis unit, based on the building equipment failure diagnosis matrix, perform feature extraction to obtain the building equipment failure diagnosis matrix feature; perform feature recognition on the building equipment failure diagnosis matrix feature to obtain the comprehensive diagnosis result of building equipment failure.

6. The intelligent fault diagnosis method for a construction device according to claim 5, wherein, The specific steps for training the model update layer in the component feature matching layer include: Collect several groups of digital model change prediction training samples; each group of digital model change prediction training samples contains a verified model transformation factor and corresponding data features; combine several groups of digital model change prediction training samples to obtain a digital model change prediction training set; Use the digital model change prediction training set for model training to obtain an initial model update layer; perform model evaluation on the initial model update layer. If the initial model update layer passes the model evaluation, use the initial model update layer as the model update layer in the component feature matching layer; otherwise, continue model training using the digital model change prediction training set.

7. An intelligent fault diagnosis system for construction equipment, characterized in that, The system applies an intelligent diagnosis method for building equipment failure as described in any one of claims 1-6, including: A faulty component determination module, including a data acquisition unit and a data processing unit; The data acquisition unit is used to record the current monitoring time point when a building equipment failure signal is received; identify the building equipment to which the building equipment failure signal belongs as the faulty building equipment; among them, for the faulty building equipment, extract the corresponding building equipment fault diagnosis digital model; the building equipment fault diagnosis digital model is constructed by the digital twin method; the building equipment fault diagnosis digital model includes N building equipment components B n , n = 1, 2, …, N, where N is the total number of building equipment components included in the faulty building equipment; obtain the building equipment monitoring data D m of the faulty building equipment including the first M monitoring time points L m where m = 1, 2, …, M; the monitoring time point L M corresponds to the current monitoring time point; combine the first M building equipment monitoring data D m to obtain the faulty building equipment monitoring data set; among them, D m = {D mi |i = 1, 2, …, I}; D mi represents the multi-modal monitoring data from different sensors in the building equipment monitoring data D m , and I represents the total number of different sensors; The data processing unit is used to analyze based on the monitoring data set of faulty construction equipment and the construction equipment data matching model to obtain the updated digital model Z of equipment faulty components n and the time-series monitoring data X of construction equipment components n ; A comprehensive failure diagnosis module, including a comprehensive diagnosis unit and a model update unit; The comprehensive diagnosis unit is used to utilize the time-series monitoring data X of construction equipment components n and the intelligent fault diagnosis model of construction equipment to conduct fault analysis and obtain the comprehensive diagnosis result of construction equipment faults; according to the comprehensive diagnosis result of construction equipment faults and the new digital model for diagnosing construction equipment faults, perform maintenance operations on the faulty construction equipment; The model update unit is used to combine all the updated digital models of the faulty components of the equipment Z n to update the digital model for diagnosing building equipment faults of the faulty building equipment, and obtain a new digital model for diagnosing building equipment faults.

Images