Primary helium fan residual life prediction method fusing signal processing and intelligent algorithm

Abstract

The invention discloses a signal processing and intelligent algorithm fused main helium fan residual life prediction method, and relates to the technical field of mechanical equipment state monitoring and maintenance management, and the method comprises the steps: collecting equipment operation data through multiple sensors, carrying out the feature fusion through principal component analysis, and achieving the fault mode recognition through a deep learning algorithm; and the residual life of the equipment is predicted by utilizing transfer learning and an XGBoost algorithm, and a diagnosis and prediction model is integrated into an online monitoring system, so that real-time perception and dynamic prediction of the health state of the equipment are realized, and decision support for maintenance and spare part management is provided. According to the method, the accuracy of fault diagnosis and life prediction of the primary helium fan is effectively improved, and a new thought is provided for safe operation and intelligent maintenance of equipment.

Description

Technical Field

[0001] The present invention relates to the technical field of mechanical equipment status monitoring and maintenance management, and in particular to a method for predicting the remaining life of a main helium blower integrating signal processing and intelligent algorithms. Background Art

[0002] The main helium blower is the core equipment in the helium circulation system. The performance and reliability of the equipment directly affect the safe and stable operation of the system. During long-term operation, the main helium blower is susceptible to faults such as rotor imbalance and blade damage, which lead to increased vibration and reduced efficiency, and even accidents in severe cases. Therefore, accurately diagnosing the failure mode of the main helium blower and predicting the remaining service life are of great significance to the safe operation and maintenance management of the equipment.

[0003] Traditional methods for main helium blower fault diagnosis and life prediction mainly include physical model-based methods and data-driven methods. The physical model-based methods require the establishment of complex mathematical models and are difficult to adapt to changes in equipment status. Although data-driven methods can adaptively model, they often lack interpretability and are difficult to apply to engineering practice. In addition, most existing methods are based on a single data source for modeling, ignoring the correlation between multi-source heterogeneous data, resulting in low diagnostic and prediction accuracy.

[0004] To address the above issues, a new method is needed to integrate multi-source monitoring data, combine physical knowledge and data-driven technology to realize main helium blower fault diagnosis and remaining life prediction, so as to improve the operating reliability and utilization efficiency of the equipment. Summary of the invention

[0005] In view of the above existing problems, the present invention is proposed.

[0006] Therefore, the present invention provides a method for predicting the remaining life of a main helium blower that integrates signal processing and intelligent algorithms. It can achieve comprehensive perception and accurate prediction of the status of the main helium blower through technical means such as multi-source sensor data fusion, fault mode recognition and dynamic prediction of remaining life, provide effective support for equipment management, and solve the problem of lack of targeted remaining life prediction methods in the prior art.

[0007] In order to solve the above technical problems, the present invention provides the following technical solution, a method for predicting the remaining life of a main helium blower integrating signal processing and intelligent algorithm, comprising:

[0008] A sensor is installed on the main helium blower to collect the operating status data of the main helium blower, pre-process the operating status data, and perform principal component analysis, perform feature fusion on the pre-processed multi-source data, and extract a feature vector that comprehensively reflects the health status of the main helium blower;

[0009] Build a fault mode library based on physical models, use deep neural network algorithms to establish a fault mode recognition model, and judge the health status of the current equipment;

[0010] The fault pattern recognition results and feature vectors are used as inputs, and the XGBoost ensemble learning algorithm is used to establish the remaining life prediction model of the main helium blower. In the model training, the transfer learning method is adopted, and the historical data of the equipment is used to assist the training. The fault diagnosis and remaining life prediction models are deployed to the state monitoring system of the main helium blower to achieve real-time monitoring and dynamic prediction of the equipment status.

[0011] Based on the remaining life prediction results, combined with the equipment maintenance cycle and spare parts inventory, the optimal decision for equipment maintenance and spare parts procurement is output.

[0012] As a preferred solution of the method for predicting the remaining life of a main helium blower integrating signal processing and intelligent algorithm described in the present invention, wherein: the sensor includes an acceleration sensor, a vibration sensor, a pressure sensor, a current sensor and a temperature sensor;

[0013] The principal component analysis includes analyzing the vibration characteristic principal component, the temperature characteristic principal component, the operation parameter principal component, the acoustic emission characteristic principal component, the load characteristic principal component, the environmental factor principal component, the time principal component and the maintenance history principal component;

[0014] The vibration characteristics include amplitude, frequency and phase; the temperature characteristics include temperature level, temperature gradient and temperature fluctuation; the operating parameters include speed, power and efficiency; the acoustic emission characteristics include energy, spectrum and duration; the load characteristics include load level and load fluctuation; the environmental factors include humidity and atmospheric pressure; the time main components include operating time and start-stop frequency; the maintenance history main components include repair frequency and spare parts replacement.

[0015] As a preferred solution of the method for predicting the remaining life of a main helium blower integrating signal processing and intelligent algorithm described in the present invention, the preprocessing includes filtering and normalization, and the filtering adopts a Butterworth bandpass filter, and the transfer function is:

[0016]

[0017] Among them, f c is the cut-off frequency, which is selected according to the vibration frequency characteristics of the main helium blower and has a value range of 10 Hz to 1000 Hz. s is the independent variable in the complex frequency domain, which reflects the dynamic characteristics of the system.

[0018] Normalization uses the maximum and minimum value normalization method to scale the data to the [0, 1] interval:

[0019]

[0020] Among them, X(t) is the original signal, is the normalized signal, min(X) is the minimum value of the original signal, and max(X) is the maximum value of the original signal;

[0021] Perform time domain analysis, frequency domain analysis and time-frequency analysis on the collected original signals to extract the characteristic parameters of the equipment.

[0022] As a preferred solution of the method for predicting the remaining life of a main helium blower integrating signal processing and intelligent algorithm described in the present invention, the feature fusion includes using principal component analysis PCA to perform dimensionality reduction fusion on the features extracted from multi-source sensor data, and assuming that the feature matrix is:

[0023] X = [x1, x2, ... x n ] T

[0024] Among them, x i is the feature vector of the i-th sample, i = 1, 2, ..., n, n is the number of training samples; the goal of PCA is to obtain the transformation matrix P to map the original features to a low-dimensional space:

[0025] Z=P T X

[0026] Among them, X represents the original high-dimensional feature matrix, P represents the transformation matrix obtained by the PCA algorithm, and the covariance matrix of the mapped feature matrix Z is a diagonal matrix, that is, the features are uncorrelated, and redundant information is removed by feature fusion to extract comprehensive features reflecting the normal state of the main helium blower;

[0027] The comprehensive characteristics reflecting the normal state of the main helium blower include vibration spectrum energy, temperature gradient, vibration-temperature correlation, signal waveform entropy and energy field distribution parameters; the fault mode library constructed based on the physical model includes rotor imbalance, blade damage and motor failure.

[0028] As a preferred solution of the method for predicting the remaining life of a main helium blower integrating signal processing and intelligent algorithm described in the present invention, the fault mode recognition model includes, according to the working principle and fault mechanism of the main helium blower, building a physical model library including two typical fault modes of rotor imbalance and blade damage, and using a deep neural network to classify the fused features to realize fault mode recognition, wherein the deep neural network structure includes an input layer, five convolutional layers, a pooling layer and a fully connected layer, and the loss function uses cross entropy:

[0029]

[0030] Among them, ybj is a sample, b is the true label of fault mode j, p bj is the probability predicted by the network, N is the number of samples, K is the number of failure modes, and by minimizing the loss function, the network can identify the failure mode of the main helium fan;

[0031] The remaining service life prediction model includes splicing the fault pattern recognition result with the fusion feature, inputting it into the XGBoost model, and predicting the remaining service life of the main helium blower, wherein XGBoost is a gradient boosting algorithm based on decision tree integration, and the base learner is a CART regression tree. Assuming there are R trees, the XGBoost model is expressed as:

[0032]

[0033] in, is the predicted value of sample a, x a is the eigenvector, f r is the rth tree, F is the function space of CART regression tree, f r (x a ) represents the decision tree for x a The predicted value of

[0034] The model is trained by minimizing the following objective function:

[0035]

[0036] Among them, l is the mean square error loss function, Ω is the complexity penalty term of the tree, n is the number of training samples, is the predicted value of sample a, f r is the rth tree, y a represents the target value of the ath training sample;

[0037] In model training, a transfer learning method is adopted, which includes using historical operation data of the equipment to pre-train the remaining life prediction model.

[0038] As a preferred solution of the method for predicting the remaining life of a main helium blower integrating signal processing and intelligent algorithm described in the present invention, the real-time monitoring and dynamic prediction include integrating the fault diagnosis model and the remaining life prediction model into the state monitoring system of the main helium blower to perform real-time perception and rolling prediction of the equipment state; the state monitoring system collects multi-source sensor signals of the main helium blower, and after preprocessing and feature extraction, inputs them into the fault diagnosis model for fault pattern recognition, and at the same time inputs them into the remaining life prediction model to predict the remaining service life of the equipment, and the prediction results are displayed in real time on the monitoring interface.

[0039] As a preferred solution of the method for predicting the remaining life of a main helium blower integrating signal processing and intelligent algorithms described in the present invention, the decision support includes: the condition monitoring system automatically generates equipment maintenance and spare parts procurement plans based on the remaining life prediction results and in combination with the equipment's maintenance cycle, spare parts inventory, historical failure data, operating condition parameters, maintenance resource availability, production task priority and economic cost-effectiveness; when the predicted remaining life is lower than the set threshold, the system issues an early warning to prompt the operation and maintenance personnel to arrange equipment maintenance in a timely manner; at the same time, based on the predicted remaining life and the equipment's historical failure rate, the spare parts procurement plan is optimized to reduce equipment downtime.

[0040] As a preferred solution of the method for predicting the remaining life of a main helium blower integrating signal processing and intelligent algorithms described in the present invention, the health management system includes intelligent management of the entire life cycle of the main helium blower through fault diagnosis and preventive maintenance function modules, and improves the accuracy of diagnosis and prediction through model optimization and feedback learning.

[0041] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and is characterized in that when the processor executes the computer program, a method for predicting the remaining life of a main helium blower is implemented by integrating signal processing and intelligent algorithms.

[0042] 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 a method for predicting the remaining life of a main helium blower integrating signal processing and intelligent algorithms are implemented.

[0043] The beneficial effects of the present invention are as follows: the accuracy of fault diagnosis and remaining life prediction of the main helium blower is improved. The present invention adopts multi-source data fusion technology, fully mines the fault characteristics in monitoring data such as vibration and temperature, and combines deep learning algorithms to realize accurate identification of typical fault modes of the main helium blower; at the same time, the transfer learning method is introduced, and the historical data of similar equipment is used to assist in modeling, which effectively improves the generalization ability of the remaining life prediction model and realizes real-time monitoring and dynamic prediction of the health status of the main helium blower.

[0044] The present invention integrates fault diagnosis and remaining life prediction models into the condition monitoring system, which can perceive the health status of the equipment in real time and dynamically update the remaining life prediction results according to the status changes, providing a reliable decision-making basis for equipment operation and maintenance, and providing a health management solution for the entire life cycle of the equipment.

[0045] The main helium blower health management system of the present invention not only includes fault diagnosis and life prediction functions, but also provides services such as maintenance decision support and preventive maintenance, which can effectively guide the maintenance and spare parts management of equipment, maximize the availability and operation efficiency of equipment, and reduce operating costs; it has good applicability and promotion value.

[0046] In summary, the present invention provides a new method for main helium blower fault diagnosis and life prediction that integrates multi-source information and takes into account physical knowledge and data-driven, which effectively improves the diagnostic prediction accuracy and equipment operation reliability, and is of great significance for promoting the development and application of industrial predictive maintenance technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0048] Figure 1 A flow chart of a method for predicting the remaining life of a main helium blower by integrating signal processing and intelligent algorithms is provided as an embodiment of the present invention.

[0049] Figure 2 A deep neural network structure diagram for fault mode recognition used in a method for predicting the remaining life of a main helium blower that integrates signal processing and intelligent algorithms provided in accordance with an embodiment of the present invention.

[0050] Figure 3 An architecture diagram of a main helium blower health management system that provides a method for predicting the remaining life of a main helium blower that integrates signal processing and intelligent algorithms, provided in accordance with an embodiment of the present invention. DETAILED DESCRIPTION

[0051] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0052] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and 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.

[0053] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0054] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0055] At the same time, in the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the directions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0056] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0057] Example 1, reference Figure 1-Figure 3 , which is the first embodiment of the present invention, provides a method for predicting the remaining life of a main helium blower by integrating signal processing and intelligent algorithms, comprising:

[0058] 1. Multi-source data collection and preprocessing

[0059] Acceleration sensors, vibration sensors and temperature sensors are installed on the main helium blower to collect the operating status data of the equipment in real time. The collected raw signals are pre-processed, including filtering and normalization.

[0060] The Butterworth bandpass filter is used for filtering, and the transfer function is:

[0061]

[0062] Among them, f cis the cut-off frequency, which can be selected according to the vibration frequency characteristics of the main helium blower, and the value range is 10Hz~1000Hz. s is the independent variable in the complex frequency domain, which reflects the dynamic characteristics of the system.

[0063] Normalization uses the maximum and minimum value normalization method to scale the data to the [0, 1] interval:

[0064]

[0065] Among them, X(t) is the original signal, is the normalized signal, min(X) is the minimum value of the original signal, and max(X) is the maximum value of the original signal;

[0066] Preprocessing also includes time domain, frequency domain and time-frequency domain analysis of the collected original signals to extract characteristic parameters about the health status of the equipment, such as mean, variance, peak value, kurtosis, etc. These characteristics can reflect the vibration and temperature characteristics of the main helium blower under different fault modes.

[0067] 2. Feature Fusion

[0068] The principal component analysis (PCA) is used to reduce the dimension of the features extracted from multi-source sensor data. Assume that the feature matrix is: X = [x1, x2, ... x n ] T

[0069] Among them, x i is the feature vector of the i-th sample, i = 1, 2, ..., n, n is the number of training samples; the goal of PCA is to find the transformation matrix P to map the original features to a low-dimensional space:

[0070] Z=P T X

[0071] X represents the original high-dimensional feature matrix, P represents the transformation matrix found by the PCA algorithm, and the covariance matrix of the mapped feature matrix Z is a diagonal matrix, that is, the features are uncorrelated and redundant information is removed through feature fusion, and comprehensive features reflecting the health status of the main helium blower are extracted;

[0072] Among them, the comprehensive features include vibration spectrum energy, temperature gradient, vibration-temperature correlation, signal waveform entropy and energy field distribution parameters;

[0073] Among them, the fault mode library based on the physical model includes rotor imbalance, blade damage and motor failure.

[0074] 3. Failure mode identification

[0075] According to the working principle and failure mechanism of the main helium blower, a physical model library containing two typical failure modes, rotor imbalance and blade damage, is constructed. A deep neural network is used to classify the fusion features and realize fault mode recognition. The network structure is as follows: Figure 2 As shown, it includes an input layer, five convolutional layers, a pooling layer, and a fully connected layer. The loss function uses cross entropy:

[0076]

[0077] Among them, y bj is a sample, b is the true label of fault mode j, p bj is the probability predicted by the network, N is the number of samples, K is the number of failure modes, and by minimizing the loss function, the network can identify the failure mode of the main helium fan.

[0078] 4. Remaining life prediction

[0079] The fault pattern recognition results are spliced ​​with the fusion features and input into the XGBoost model to predict the remaining service life of the main helium blower. XGBoost is a gradient boosting algorithm based on decision tree ensemble. The base learner is the CART regression tree. Assuming there are R trees, the XGBoost model is expressed as:

[0080]

[0081] in, is the predicted value of sample a, x a is the eigenvector, f r is the rth tree, F is the function space of CART regression tree, f r (x a ) represents the decision tree for x a The predicted value of

[0082] The model is trained by minimizing the following objective function:

[0083]

[0084] Among them, l is the mean square error loss function, Ω is the complexity penalty term of the tree, n is the number of training samples, is the predicted value of sample a, f r is the rth tree, y a represents the target value of the ath training sample; through the optimization of the objective function, the model can accurately predict the remaining service life of the main helium blower;

[0085] During the model training process, the transfer learning method was used to pre-train the XGBoost model using the historical operating data of similar models of main helium blowers to improve the generalization ability of the model. Specifically, the model was first trained on the source device, and then fine-tuned on the target device so that the model could better adapt to the characteristics of the target device.

[0086] 5. Real-time monitoring and dynamic prediction

[0087] The trained fault diagnosis model and remaining life prediction model are integrated into the condition monitoring system of the main helium blower to achieve real-time perception and rolling prediction of the equipment status, such as Figure 3 As shown in the figure, the condition monitoring system collects multi-source sensor signals from the main helium blower. After preprocessing and feature extraction, the signals are input into the fault diagnosis model for fault pattern recognition. At the same time, they are input into the remaining life prediction model to estimate the remaining service life of the equipment. The prediction results can be displayed in real time on the monitoring interface, providing intuitive decision support for operation and maintenance personnel.

[0088] 6. Decision support

[0089] The condition monitoring system automatically generates equipment maintenance and spare parts procurement plans based on the remaining life prediction results, combined with factors such as the equipment's maintenance cycle and spare parts inventory, to provide continuous decision-making support for equipment management. Specifically, when the predicted remaining life is lower than the set threshold, the system will issue an early warning to prompt operation and maintenance personnel to arrange equipment maintenance in a timely manner. At the same time, based on the predicted remaining life and the equipment's historical failure rate, the spare parts procurement plan is optimized to ensure an adequate supply of key spare parts and reduce equipment downtime.

[0090] 7. Model Optimization

[0091] The condition monitoring system has self-learning capabilities. It can continuously collect equipment operation data and use incremental learning methods to update the fault diagnosis and remaining life prediction models online, thereby continuously improving the accuracy of diagnosis and prediction. Specifically, when new equipment operation data is collected, it is added to the original training set, and the model is fine-tuned using the new training set so that the model can adapt to changes in equipment status. At the same time, the system will regularly evaluate the model offline, evaluate the generalization performance of the model through methods such as cross-validation, and optimize the model structure and hyperparameters based on the evaluation results to further improve the prediction accuracy of the model.

[0092] To sum up, the remaining life prediction method of the main helium blower provided by the present invention, which integrates signal processing and intelligent algorithms, realizes accurate diagnosis and prediction of the health status of the main helium blower through multi-source data fusion, fault pattern recognition, and transfer learning technology. It can provide reliable decision support for equipment operation and maintenance, effectively improve the operating reliability and utilization efficiency of the main helium blower, and has significant technical advantages and application value.

[0093] Example 2, reference Figure 1-Figure 3 , which is an embodiment of the present invention, provides a method for predicting the remaining life of a main helium blower by integrating signal processing and intelligent algorithms. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through experiments.

[0094] In order to verify the effectiveness of the method of the present invention, an application test was carried out on the main helium blower test bench. Acceleration sensors, vibration displacement sensors and temperature sensors were installed at key parts of the blower. At the same time, the historical operation data of the main helium blower test bench was used as the source domain data for transfer learning.

[0095] In the data preprocessing stage, the collected vibration signals were bandpass filtered to remove noise components below 10 Hz and above 1000 Hz, and the data were normalized using the maximum and minimum normalization method. 20 time domain and frequency domain features were extracted, including mean, root mean square value, peak value, pulse factor, etc. These 20 features were reduced to a 5-dimensional space using principal component analysis technology, and a low-dimensional feature vector that comprehensively reflects the health status of the equipment was obtained.

[0096] In the fault diagnosis module, a physical model library containing five typical fault modes, including rotor imbalance, blade cracks, and blade deformation, was constructed, and a five-layer convolutional neural network was used to classify the fused features. The input of the network is a five-dimensional feature vector, and the output is the probability distribution of the five fault modes. The network was trained using the cross entropy loss function and the Adam optimization algorithm, and the fault classification accuracy on the test set reached more than 95%.

[0097] In the remaining life prediction module, a regression prediction model was constructed using the XGBoost algorithm. The input of the model is the fault pattern recognition result and the fused feature vector, and the output is the remaining service life of the equipment. The model was first pre-trained on the source domain data, and then fine-tuned using the operating data of the target equipment. Through transfer learning, the prediction accuracy and generalization performance of the model on the target equipment have been significantly improved; on a set of independent test samples, the average relative error between the remaining life predicted by the model and the actual life is less than 10%.

[0098] The trained fault diagnosis and life prediction models were deployed in the online monitoring system of the main helium blower, enabling real-time assessment and prediction of the equipment health status. When the system detects an abnormality in the equipment, it automatically triggers the fault diagnosis process, identifies the most likely failure mode and issues an alarm. At the same time, the system dynamically updates the remaining life prediction value of the equipment and automatically generates a maintenance plan and spare parts requirement list based on the prediction results.

[0099] This application example fully demonstrates the effectiveness and advancement of the method of the present invention in actual engineering. By integrating multi-source monitoring data, physical modeling and machine learning technology, the present invention provides an effective health management solution for main helium blowers, which can significantly improve the reliability and economy of equipment operation and has broad prospects for promotion and application.

[0100] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. 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.

[0101] Embodiment 3, the third embodiment of the present invention, is different from the first two embodiments in that:

[0102] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0103] 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 generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. 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.

[0104] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate 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 A function specified in one or more boxes.

[0105] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0106] Although the preferred embodiments of the present application have been described, those skilled in the art may make other 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 falling within the scope of the present application.

[0107] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A method for predicting the remaining life of a main helium blower by integrating signal processing and intelligent algorithms. Features: include, A sensor is installed on the main helium blower to collect the operating status data of the main helium blower, pre-process the operating status data, and perform principal component analysis, perform feature fusion on the pre-processed multi-source data, and extract a feature vector that comprehensively reflects the health status of the main helium blower; Build a fault mode library based on physical models, use deep neural network algorithms to establish a fault mode recognition model, and judge the health status of the current equipment; The fault pattern recognition results and feature vectors are used as inputs, and the XGBoost ensemble learning algorithm is used to establish the remaining life prediction model of the main helium blower. In the model training, the transfer learning method is adopted, and the historical data of the equipment is used to assist the training. The fault diagnosis and remaining life prediction model is deployed to the state monitoring system of the main helium blower to realize real-time monitoring and dynamic prediction of the equipment status. Based on the remaining life prediction results, combined with the equipment maintenance cycle and spare parts inventory, the optimal decision for equipment maintenance and spare parts procurement is output.

2. A method for predicting the remaining life of a main helium blower by integrating signal processing and intelligent algorithm as claimed in claim 1, Features: The sensors include acceleration sensors, vibration sensors, pressure sensors, current sensors and temperature sensors; The principal component analysis includes analyzing the vibration characteristic principal component, the temperature characteristic principal component, the operation parameter principal component, the acoustic emission characteristic principal component, the load characteristic principal component, the environmental factor principal component, the time principal component and the maintenance history principal component; The vibration characteristics include amplitude, frequency and phase; the temperature characteristics include temperature level, temperature gradient and temperature fluctuation; the operating parameters include speed, power and efficiency; the acoustic emission characteristics include energy, spectrum and duration; the load characteristics include load level and load fluctuation; the environmental factors include humidity and atmospheric pressure; the time main components include operating time and start-stop frequency; the maintenance history main components include repair frequency and spare parts replacement.

3. A method for predicting the remaining life of a main helium blower by integrating signal processing and intelligent algorithm as claimed in claim 2, Features: The preprocessing includes filtering and normalization. The filtering adopts a Butterworth bandpass filter, and the transfer function is: Among them, f c is the cut-off frequency, which is selected according to the vibration frequency characteristics of the main helium blower and has a value range of 10 Hz to 1000 Hz. s is the independent variable in the complex frequency domain, which reflects the dynamic characteristics of the system. Normalization uses the maximum and minimum value normalization method to scale the data to the [0, 1] interval: Among them, X(t) is the original signal, is the normalized signal, min(X) is the minimum value of the original signal, and max(X) is the maximum value of the original signal; Perform time domain analysis, frequency domain analysis and time-frequency analysis on the collected original signals to extract the characteristic parameters of the equipment.

4. A method for predicting the remaining life of a main helium blower by integrating signal processing and intelligent algorithm as claimed in claim 3, Features: The feature fusion includes using principal component analysis PCA to reduce the dimension of the features extracted from multi-source sensor data. The feature matrix is: X=[x 1 ,x 2 ,…x n ] T Among them, x i is the feature vector of the i-th sample, i = 1, 2, ..., n, n is the number of training samples; the goal of PCA is to obtain the transformation matrix P to map the original features to a low-dimensional space: Z=P T X Among them, X represents the original high-dimensional feature matrix, P represents the transformation matrix obtained by the PCA algorithm, and the covariance matrix of the mapped feature matrix Z is a diagonal matrix, that is, the features are uncorrelated, and redundant information is removed by feature fusion to extract comprehensive features reflecting the normal state of the main helium blower; The comprehensive characteristics reflecting the normal state of the main helium blower include vibration spectrum energy, temperature gradient, vibration-temperature correlation, signal waveform entropy and energy field distribution parameters; the fault mode library constructed based on the physical model includes rotor imbalance, blade damage and motor failure.

5. A method for predicting the remaining life of a main helium blower by integrating signal processing and intelligent algorithm as claimed in claim 4, Features: The fault mode recognition model includes, according to the working principle and fault mechanism of the main helium blower, building a physical model library including two typical fault modes of rotor imbalance and blade damage, using a deep neural network to classify the fusion features to realize fault mode recognition, wherein the deep neural network structure includes an input layer, five convolutional layers, a pooling layer and a fully connected layer, and the loss function uses cross entropy: Among them, y bj is a sample, b is the true label of fault mode j, p bj is the probability predicted by the network, N is the number of samples, K is the number of failure modes, and by minimizing the loss function, the network can identify the failure mode of the main helium fan; The remaining service life prediction model includes splicing the fault pattern recognition result with the fusion feature, inputting it into the XGBoost model, and predicting the remaining service life of the main helium blower, wherein XGBoost is a gradient boosting algorithm based on decision tree integration, and the base learner is a CART regression tree. Assuming there are R trees, the XGBoost model is expressed as: in, is the predicted value of sample a, x a is the eigenvector, f r is the rth tree, F is the function space of CART regression tree, f r (x a ) represents the decision tree for x a The predicted value of The model is trained by minimizing the following objective function: Among them, l is the mean square error loss function, Ω is the complexity penalty term of the tree, n is the number of training samples, is the predicted value of sample a, f r is the rth tree, y a represents the target value of the ath training sample; In model training, a transfer learning method is adopted, which includes using historical operation data of the equipment to pre-train the remaining life prediction model.

6. A method for predicting the remaining life of a main helium blower by integrating signal processing and intelligent algorithm as claimed in claim 5, Features: The real-time monitoring and dynamic prediction include integrating the fault diagnosis model and the remaining life prediction model into the state monitoring system of the main helium blower to perform real-time perception and rolling prediction of the equipment state; The condition monitoring system collects multi-source sensor signals from the main helium blower, and after preprocessing and feature extraction, inputs them into the fault diagnosis model for fault pattern recognition. At the same time, it inputs them into the remaining life prediction model to predict the remaining service life of the equipment. The prediction results are displayed in real time on the monitoring interface.

7. A method for predicting the remaining life of a main helium blower by integrating signal processing and intelligent algorithm as claimed in claim 6, Features: The decision support includes: the condition monitoring system automatically generates equipment maintenance and spare parts procurement plans based on the remaining life prediction results and combines the equipment's maintenance cycle, spare parts inventory, historical failure data, operating condition parameters, maintenance resource availability, production task priority and economic cost-effectiveness for analysis; when the predicted remaining life is lower than the set threshold, the system issues an early warning to prompt the operation and maintenance personnel to arrange equipment maintenance in a timely manner; at the same time, based on the predicted remaining life and the equipment's historical failure rate, the spare parts procurement plan is optimized to reduce equipment downtime.

8. A method for predicting the remaining life of a main helium blower by integrating signal processing and intelligent algorithm as claimed in claim 7, Features: The health management system includes intelligent management of the entire life cycle of the main helium blower through fault diagnosis and preventive maintenance function modules, and improves the accuracy of diagnosis and prediction through model optimization and feedback learning.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program. It is characterized in that When the processor executes the computer program, the steps of the method according to any one of claims 1 to 8 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

Images