A method, device and medium for identifying the operating conditions of a main bearing

Abstract

The present invention discloses a method, device and medium for identifying the working conditions of a main bearing, which are applicable to the technical field of the main bearing of a shield machine. In this method, the influencing factors of working parameters are judged to be divided into absolute judgment standard parameters and relative judgment standard parameters. Then, according to the expert system, a working condition pattern recognition classifier is constructed, avoiding the problem that the existing working condition recognition method is only one-sided and inaccurate due to the change of the working parameters themselves. On the basis of the classification result obtained by the working condition pattern recognition classifier through the absolute judgment standard parameters, for abnormal working conditions, the relative judgment standard parameters are further used to classify and identify through the working condition pattern recognition classifier to obtain the final classification result. In summary, through the double judgments of absolute judgment and relative judgment, combined with the classification and recognition by the working condition pattern recognition classifier, the reliability of the working condition recognition result of the main bearing of the shield machine is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of shield machine main bearings, and particularly to a method, device and medium for identifying the working conditions of a main bearing. Background Art

[0002] The main bearing of the cutter head of a tunnel boring machine is the core component that drives the rotation of the cutter head. It is installed in the main drive housing of the tunnel boring machine. During the construction process, along with different working conditions of the tunneling operation, it always bears the combined action of multi-directional compression, bending and torsion. The local bearing strength will be significantly enhanced and change frequently. The non-uniformity of the bearing temperature field and lubrication flow field further deteriorates the working state of the bearing. In the non-linear and multi-coupled change process, the complex working conditions shorten the remaining life of the main bearing failure, resulting in premature local wear, damage and even failure of the main bearing. Therefore, studying the method for identifying the working conditions of the shield machine main bearing is of crucial significance for predicting the service life of the main bearing and reducing the losses caused by bearing damage.

[0003] Most of the current main bearing identification methods are based on the working condition analysis under a single influencing factor of load signal simulation and vibration signal itself. Due to the lack of analysis combining the actual situation and the influencing relationship between working conditions, the identified working conditions are relatively one-sided, reducing the reliability of the working condition identification results of the shield machine main bearing.

[0004] Therefore, it is urgent for those skilled in the art to seek a method for identifying the working conditions of the main bearing. Summary of the Invention

[0005] The purpose of the present invention is to provide a method, device and medium for identifying the working conditions of a main bearing, so as to improve the reliability of the working condition identification results of the shield machine main bearing.

[0006] To solve the above technical problems, the present invention provides a method for identifying the working conditions of a main bearing, including:

[0007] Obtain the working parameters characterizing the main bearing, where the working parameters are multiple variables;

[0008] Classify the working parameters into absolute judgment standard parameters and relative judgment standard parameters according to the influence factor judgment standard of the main bearing;

[0009] Input the absolute judgment standard parameters into the working condition mode recognition classifier for classification to obtain an initial classification result, where the working condition mode recognition classifier is constructed by an expert system and a clustering analysis method, and the initial classification result includes normal working conditions and abnormal working conditions;

[0010] Input the relative judgment standard parameters into the working condition mode recognition classifier for classification according to the abnormal working conditions of the initial classification result to obtain a final classification result.

[0011] Preferably, the working parameters are divided into absolute judgment standard parameters and relative judgment standard parameters according to the influence factor judgment standard of the main bearing, including:

[0012] Perform priority sorting on the working parameters according to the influence factor judgment standard of the main bearing;

[0013] Take the working parameters corresponding to the first N influencing factors within the priority sorting as absolute judgment standard parameters according to the preset requirements;

[0014] Take the working parameters corresponding to the influencing factors other than the first N influencing factors within the priority sorting as relative judgment standard parameters according to the preset requirements.

[0015] Preferably, the construction process of the working condition mode recognition classifier includes the following steps:

[0016] Obtain the sample parameters representing the main bearing, the description information of multiple working conditions in the expert system, and the corresponding working condition characteristic parameters;

[0017] Construct a relationship network according to the relationship between the description information of multiple working conditions;

[0018] Perform clustering analysis on the sample parameters according to the working condition characteristic parameters to obtain the current clustering result, where the clustering analysis is performed by setting preset conditions on the sample parameters;

[0019] Count the number of times of clustering analysis;

[0020] Judge whether the number of times of clustering analysis corresponding to the current clustering result exceeds the threshold;

[0021] If not, return to the step of performing clustering analysis on the sample parameters to obtain the current clustering result;

[0022] If so, take the current clustering result as the final clustering result;

[0023] Construct a working condition mode recognition classifier according to the corresponding relationship between the relationship network and the final clustering result.

[0024] Preferably, input the absolute judgment standard parameters into the working condition mode recognition classifier for classification to obtain the initial classification result, including:

[0025] Obtain the normal range and warning range of parameters corresponding to multiple classifications of the working condition mode recognition classifier, where the normal range of parameters is lower than the warning range of parameters;

[0026] When the absolute judgment standard parameters exceed the normal range of parameters, it is determined that the initial classification result of the main bearing is an abnormal working condition, where the abnormal working condition includes an abnormal condition and an extreme condition;

[0027] When the absolute judgment standard parameter is within the normal parameter range, the initial classification result of the main bearing is determined to be in the normal working condition;

[0028] Among them, the determination processes of the abnormal working condition and the extreme working condition specifically include:

[0029] When the absolute judgment standard parameter exceeds the normal parameter range and is within the parameter warning range, the abnormal working condition corresponding to the initial classification result of the main bearing is determined to be the abnormal working condition;

[0030] When the absolute judgment standard parameter exceeds the parameter warning range, the abnormal working condition corresponding to the initial classification result of the main bearing is determined to be the extreme working condition.

[0031] Preferably, according to the abnormal working condition of the initial classification result, the relative judgment standard parameter is input into the working condition mode recognition classifier for classification to obtain the final classification result, including:

[0032] When the relative judgment standard parameter is within the normal parameter range or at least one parameter of the relative judgment standard parameter exceeds the normal parameter range and is within the parameter warning range, the abnormal working condition corresponding to the initial classification result of the main bearing is determined to be the abnormal working condition;

[0033] When at least one parameter of the relative judgment standard parameter exceeds the parameter warning range, the abnormal working condition corresponding to the initial classification result of the main bearing is determined to be the extreme working condition.

[0034] Preferably, obtain the working parameters characterizing the main bearing, including:

[0035] Obtain the initial working parameters characterizing the main bearing;

[0036] Preprocess the initial working parameters to obtain the working parameters.

[0037] Preferably, it further includes:

[0038] When the working condition corresponding to the main bearing is the abnormal working condition, output the first prompt information;

[0039] When the working condition corresponding to the main bearing is the extreme working condition, output the second prompt information.

[0040] To solve the above technical problems, the present invention also provides a working condition recognition device for a main bearing, including:

[0041] An acquisition module, configured to acquire the working parameters characterizing the main bearing, where the working parameters are multiple variables;

[0042] A processing module, configured to classify the working parameters into an absolute judgment standard parameter and a relative judgment standard parameter according to the influence factor judgment standard of the main bearing;

[0043] The first classification module is used to input the absolute judgment standard parameters into the working condition mode recognition classifier for classification to obtain an initial classification result, where the working condition mode recognition classifier is constructed by an expert system and a clustering analysis method, and the initial classification result includes normal working conditions and abnormal working conditions;

[0044] The second classification module is used to input the relative judgment standard parameters into the working condition mode recognition classifier for classification according to the abnormal working conditions of the initial classification result to obtain a final classification result.

[0045] To solve the above technical problems, the present invention also provides a working condition recognition device for a main bearing, including:

[0046] A memory for storing a computer program;

[0047] A processor for implementing the steps of the working condition recognition method of the main bearing as described above when executing the computer program.

[0048] To solve the above technical problems, the present invention provides a computer-readable storage medium with a computer program stored thereon, and the computer program, when executed by a processor, implements the steps of the working condition recognition method of the main bearing as described above.

[0049] A working condition recognition method for a main bearing provided by the present invention includes obtaining working parameters characterizing the main bearing, where the working parameters are multiple variables; classifying the working parameters into absolute judgment standard parameters and relative judgment standard parameters according to the influence factor judgment standard of the main bearing; inputting the absolute judgment standard parameters into the working condition mode recognition classifier for classification to obtain an initial classification result, where the working condition mode recognition classifier is constructed by an expert system and a clustering analysis method, and the initial classification result includes normal working conditions and abnormal working conditions; inputting the relative judgment standard parameters into the working condition mode recognition classifier for classification according to the abnormal working conditions of the initial classification result to obtain a final classification result. This method judges the influence factors of the working parameters to be divided into absolute judgment standard parameters and relative judgment standard parameters, and then constructs a working condition mode recognition classifier according to the expert system, avoiding the problem that the existing working condition recognition method is only one-sided and inaccurate due to the change of the working parameters themselves. On the basis of the classification result obtained by the absolute judgment standard parameters through the working condition mode recognition classifier, for abnormal working conditions, the relative judgment standard parameters are further classified and recognized through the working condition mode recognition classifier to obtain the final classification result. In summary, through the double judgments of absolute judgment and relative judgment, combined with the classification and recognition of the working condition mode recognition classifier, the reliability of the working condition recognition result of the main bearing of the shield machine is improved.

[0050] In addition, the present invention also provides a working condition recognition device and medium for a main bearing, which have the same beneficial effects as the working condition recognition method of the main bearing as described above. Description of the Drawings

[0051] To more clearly illustrate the embodiments of the present invention, the following will briefly introduce the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0052] Figure 1 It is a flowchart of a method for identifying the working conditions of a main bearing provided by an embodiment of the present invention;

[0053] Figure 2 It is an application schematic diagram of a method for identifying a main bearing provided by an embodiment of the present invention;

[0054] Figure 3 It is a structural diagram of a device for identifying the working conditions of a main bearing provided by an embodiment of the present invention;

[0055] Figure 4 It is a structural diagram of another device for identifying the working conditions of a main bearing provided by an embodiment of the present invention. Specific embodiments

[0056] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the protection scope of the present invention.

[0057] The core of the present invention is to provide a method, device and medium for identifying the working conditions of a main bearing, so as to improve the reliability of the identification result of the working conditions of the main bearing of a shield machine.

[0058] In order to enable those skilled in the art to better understand the solution of the present invention, the following will further describe the present invention in detail in conjunction with the drawings and specific embodiments.

[0059] It should be noted that due to the lack of targeted on-site testing and detection methods for the main bearings of tunnel boring machines at home and abroad, there is a large room for exploration in the working condition simulation experiments of the main bearings of shield machines, showing the phenomenon that theoretical analysis lacks real data support and experimental data lacks reliable analysis methods. The method for identifying the working conditions of the main bearing provided by the present invention is applicable to the identification of different parameters under the working conditions of the main bearing, and also for shield machines in different application scenarios, including but not limited to slurry shield machines, earth pressure balance shield machines, full-face tunnel hard rock boring machines, inclined shaft full-face tunnel boring machines (Tunnel Boring Machine, TBM), vertical shafts, etc.

[0060] Figure 1 The flowchart of a method for identifying the working conditions of a main bearing provided by an embodiment of the present invention is as follows Figure 1 As shown, the method includes:

[0061] S11: Obtain the working parameters characterizing the main bearing, where the working parameters are multiple variables;

[0062] S12: Classify the working parameters into absolute judgment standard parameters and relative judgment standard parameters according to the influence factor judgment standard of the main bearing;

[0063] S13: Input the absolute judgment standard parameters into the working condition mode recognition classifier for classification to obtain an initial classification result, where the working condition mode recognition classifier is constructed by an expert system and a clustering analysis method, and the initial classification result includes normal working conditions and abnormal working conditions;

[0064] S14: Input the relative judgment standard parameters into the working condition mode recognition classifier for classification according to the abnormal working conditions of the initial classification result to obtain a final classification result.

[0065] Specifically, obtaining the working parameters characterizing the main bearing can be any parameter during the working process of the main bearing of a shield machine. For example, the working pressure value of the lubricating pump of the main bearing of a shield machine, the temperature value of internal components, the equipment vibration signal value, the working condition load of the main bearing, the online detection result of oil products, and can also include parameters such as axial load, radial load, and overturning moment that can characterize the main bearing under different working conditions. It should be noted that after the working parameters of the main bearing are collected, preliminary preprocessing and other operations are carried out to ensure that subsequent data processing reduces the interference of non-working condition factors. The preprocessing operation can be to convert the working parameters of different variables into data of the same dimension, or perform frequency screening and noise reduction processing to strip interference information, etc. The embodiment of the present invention does not limit the specific content of the preprocessing, as long as the collected data can be preprocessed to strip interference information.

[0066] In addition, the working parameters are multiple variables. Since the subsequent working condition identification is based on the working parameters under multiple variables, if there is only the working parameter of one variable, the judgment standard for subsequent working condition identification is single, and the problems mentioned in the background art are not solved. Therefore, multiple working parameters are correspondingly adopted, and different judgment parameters are divided according to the working parameters of multiple variables for subsequent classification and identification.

[0067] The working parameters obtained in step S11 are then classified according to the influencing factor judgment criteria of the main bearing, mainly divided into absolute judgment standard parameters and relative judgment standard parameters. The absolute judgment standard parameters and relative judgment standard parameters only explain the influencing factors. For example, the variables of the working parameters are the working pressure value of the main bearing lubrication pump of the shield machine, the internal component temperature value, the equipment vibration signal value, the main bearing working condition load, and the online oil quality detection result. The corresponding influencing factor judgment criteria are sorted according to the weight of the influencing factors. Taking the working pressure value of the main bearing lubrication pump of the shield machine and the internal component temperature value as the absolute judgment standard parameters, the remaining three variables are used as the relative judgment standard parameters. Each of the corresponding judgment standard parameters can also be further divided into different echelons according to the importance of the influencing factors. The more types of variables, the more accurate the working condition identification. There is no requirement for the number of variables within each judgment standard parameter, but any one variable can only exist in one judgment standard parameter, that is, absolute or relative. Here, the parameters with large deviations that will interfere with the results are stripped. Of course, the classification of the working parameters of the main bearing of the shield machine can be divided according to the actual working condition identification content, which is not specifically limited here.

[0068] According to the absolute judgment standard parameters and relative judgment standard parameters in step S12, double judgment and identification are carried out. First, the working parameters under one variable or multiple variables of the absolute judgment standard parameters are initially identified for the working conditions to obtain the initial classification result. The working condition mode recognition classifier provided in this embodiment is constructed by an expert system and a clustering analysis method. The expert system contains a large amount of knowledge and experience related to the main bearing at the expert level in the field of shield machine construction. The clustering analysis method is a multivariate statistical technique, mainly including hierarchical clustering method and iterative clustering method, which is a multivariate statistical method for studying classification.

[0069] An expert system is an artificial intelligence computer program that can solve complex problems by applying a large amount of expert knowledge and reasoning methods in certain specific fields. It belongs to a development branch of artificial intelligence. The research goal of an expert system is to simulate the reasoning thinking process of human experts. Generally, the knowledge and experience of domain experts are stored in the computer in a knowledge expression mode, and the system reasons about the input facts to make judgments and decisions.

[0070] Since the clustering analysis method includes various types, such as partitioning method, hierarchical method, density-based method, grid-based method, model-based method, etc., the clustering analysis method selects the actual clustering method according to the actual working parameters, and the present invention does not make specific limitations. The appropriate clustering analysis method can be selected according to the number of working parameters and the specific presentation method, etc.

[0071] The initial classification results are mainly divided into two types, normal operating conditions and abnormal operating conditions. No further identification is performed for normal operating conditions. For abnormal operating conditions, classification and identification are continued through relative judgment standard parameters to facilitate double identification and accurate identification and classification of abnormal operating conditions.

[0072] The relative judgment standard parameters are further input into the operating condition pattern recognition classifier for classification and identification. Since the classification and identification is mainly performed on data under abnormal operating conditions, the corresponding final classification result is an abnormal operating condition. Only further identification is performed based on other working parameters (relative judgment standard parameters) to improve the recognition accuracy of the current main bearing operating condition identification.

[0073] The present invention provides a method for identifying the working condition of a main bearing, comprising obtaining working parameters characterizing the main bearing, wherein the working parameters are multiple variables; dividing the working parameters into absolute judgment standard parameters and relative judgment standard parameters according to the judgment standard of the influencing factors of the main bearing; inputting the absolute judgment standard parameters into a working condition pattern recognition classifier for classification to obtain an initial classification result, wherein the working condition pattern recognition classifier is constructed by an expert system and a cluster analysis method, and the initial classification result includes normal working conditions and abnormal working conditions; inputting the relative judgment standard parameters into the working condition pattern recognition classifier for classification according to the abnormal working conditions of the initial classification result to obtain a final classification result. The method divides the working parameters into absolute judgment standard parameters and relative judgment standard parameters by judging the influencing factors, and then constructs a working condition pattern recognition classifier according to the expert system, avoiding the problem that the existing working condition recognition method is only one-sided and inaccurate due to the change of the working parameters themselves, and on the basis of the classification result obtained by the absolute judgment standard parameters through the working condition pattern recognition classifier, the abnormal working conditions are further classified and identified through the working condition pattern recognition classifier through the relative judgment standard parameters to obtain the final classification result. In summary, after the dual judgment of absolute judgment and relative judgment, combined with the working condition pattern recognition classifier for classification, the reliability of the working condition identification results of the shield machine main bearing is improved.

[0074] On the basis of the above embodiment, the working parameters are divided into absolute judgment standard parameters and relative judgment standard parameters according to the judgment standard of the influencing factors of the main bearing in step S12, including:

[0075] Prioritize the operating parameters according to the criteria for the factors affecting the main bearing;

[0076] According to preset requirements, the working parameters corresponding to the top N influencing factors in the priority ranking are used as absolute judgment standard parameters;

[0077] According to preset requirements, the working parameters corresponding to the influencing factors except the first N influencing factors in the priority sorting are used as relative judgment standard parameters.

[0078] It should be noted that the judgment criterion for the influencing factors of the main bearing is determined according to the influence degree of the variables of the working parameters on the normal operation of the main bearing. Therefore, it is necessary to sort the obtained working parameters by priority.

[0079] Correspondingly, the judgment criterion for the influencing factors of the main bearing can be the standard list tested and produced by the manufacturer or summarized by experienced personnel, or the sorting rule can be automatically set according to the currently collected working parameters according to the actual working conditions. Sort the variables involved in the currently collected working parameters. For example, a standard list of 20 influencing factors generated by sorting according to the size of the influencing factors, where the first 5 are used as the absolute judgment standard parameters for the influencing factors, and the subsequent 15 influencing factors are used as the relative judgment standard parameters. There are currently 5 influencing factors collected, and the influencing factors of 2 variables are in the list of absolute judgment standard parameters. Then, the working parameters corresponding to these 2 variables can be used as the absolute judgment standard parameters, that is, N is 2, and the influencing factors of the subsequent 3 variables are used as the relative judgment standard parameters.

[0080] If there are currently 5 influencing factors collected and all 5 are in the absolute judgment standard parameters, some variables of the absolute standard parameters can be set in the relative judgment standard parameters, but the priority sorting cannot be disrupted. When the sorting rule is automatically set according to the actual working conditions, the first N can be selected as the absolute judgment standard parameters, and the subsequent ones are used as the relative judgment standard parameters. This embodiment does not make specific limitations, as long as the collected working parameters can be completely distinguished and distinguished according to the judgment criterion of the influencing factors.

[0081] In the embodiment of the present invention, the working parameters are divided into absolute judgment standard parameters and relative judgment standard parameters according to the judgment criterion of the influencing factors of the main bearing, which is convenient for subsequent dual judgment to ensure the reliability of the recognition result.

[0082] On the basis of the above embodiment, the construction process of the working condition mode recognition classifier in step S13 includes the following steps:

[0083] Obtain the sample parameters characterizing the main bearing, the description information of multiple working conditions in the expert system, and the corresponding working condition characteristic parameters;

[0084] Construct a relationship network according to the relationship between the description information of multiple working conditions;

[0085] Perform clustering analysis on the sample parameters according to the working condition characteristic parameters to obtain the current clustering result, where the clustering analysis is performed by setting preset conditions on the sample parameters;

[0086] Count the number of times of clustering analysis;

[0087] Determine whether the number of clustering analyses corresponding to the current clustering result exceeds the threshold;

[0088] If not, return to the step of performing clustering analysis on the sample parameters to obtain the current clustering result;

[0089] If so, use the current clustering result as the final clustering result;

[0090] Construct a working condition pattern recognition classifier according to the correspondence between the relationship network and the final clustering result.

[0091] It should be noted that the construction of the working condition pattern recognition classifier requires repeated training and testing. Therefore, in addition to obtaining the sample parameters characterizing the main bearing, it is also necessary to obtain the description information of the working conditions in the expert system and the corresponding working condition characteristic parameters. The description information of the working conditions mainly characterizes the parameters of the main bearing under different working conditions, which can be the same as or different from the working condition characteristic parameters. The working condition characteristic parameters mainly distinguish the characteristics under different working conditions and are obtained by extracting the parameters of the main bearing under different working conditions. In order to facilitate the establishment of the authority and fairness of the working condition pattern recognition classifier, it is necessary to obtain the description information of multiple working conditions in the expert system and construct a feature relationship network through the relationship between the description information of multiple working conditions.

[0092] Based on the expert system, use the working condition characteristic parameters under different working conditions as the values of the clustering model, and different sample parameters as input variables, and use the clustering analysis algorithm to train the model. Each cluster in the clustering result represents a working condition state, and the same state corresponds to the same working condition pattern. Since the clustering effect between clusters is continuously improved after each clustering analysis, it is necessary to train and test this model to obtain the working condition pattern recognition classifier.

[0093] Perform clustering analysis on the sample parameters to obtain the current clustering result. It should be noted that clustering analysis clusters the samples by setting preset conditions. The preset conditions can be, for example, the number of categories into which the clustering parameters are finally divided, or the screening relationship, screening conditions, screening times of the categories, or the similarity between samples, the similarity between classes, etc. as preset conditions to obtain the clustering result. In this embodiment, the setting of the preset conditions is not specifically limited and can be set according to the actual situation.

[0094] After clustering is completed once, count the number of current and past clustering analyses. If the current number does not exceed the threshold, it means that the number of training and testing has not reached the requirement, and training and testing need to continue. If the current number exceeds the threshold, it means that the parameters of the current clustering have been tested and trained to the corresponding number of times, and the clustering result can be used as the final clustering result, that is, the classification situation of the working condition pattern recognition classifier. For example, if the clustering result is divided into three categories: normal working condition, abnormal working condition, and extreme working condition, the classification situation of the working condition pattern recognition classifier is the same.

[0095] Combine the final clustering results with the constructed relationship network to obtain a working condition pattern recognition classifier under the current working condition. In this embodiment, the constructed working condition pattern recognition classifier can establish corresponding expert systems for shield machines in different application scenarios, set different working condition pattern recognition classifiers, and increase or decrease the relationship network for tracing the reasons of working condition features.

[0096] The construction process of the working condition pattern recognition classifier provided by the embodiment of the present invention, combined with the relationship network of the expert system, effectively solves the problem of shortage of main bearing working condition test data and construction data of existing shield machines, and can identify the working conditions of the main bearing of shield machines under complex conditions, and has strong expansibility. For different working condition pattern recognition classifiers and expert experience system networks, the relationship network structure of working condition features can be increased or decreased. Combining the actual situation and the influence relationship between working conditions is convenient for subsequent working condition recognition and classification.

[0097] Based on the above embodiment, inputting the absolute judgment standard parameters into the working condition pattern recognition classifier for classification to obtain the initial classification result in step S13 includes:

[0098] Obtain the normal range and warning range of parameters corresponding to multiple classifications of the working condition pattern recognition classifier, where the normal range of parameters is lower than the warning range of parameters;

[0099] When the absolute judgment standard parameter exceeds the normal range of parameters, it is determined that the initial classification result of the main bearing is an abnormal working condition, where the abnormal working condition includes an abnormal condition and an extreme condition;

[0100] When the absolute judgment standard parameter is within the normal range of parameters, it is determined that the initial classification result of the main bearing is a normal working condition;

[0101] Among them, the determination process of the abnormal condition and the extreme condition specifically includes:

[0102] When the absolute judgment standard parameter exceeds the normal range of parameters and is within the warning range of parameters, it is determined that the abnormal working condition corresponding to the initial classification result of the main bearing is an abnormal condition;

[0103] When the absolute judgment standard parameter exceeds the warning range of parameters, it is determined that the abnormal working condition corresponding to the initial classification result of the main bearing is an extreme condition.

[0104] Specifically, since the working condition pattern recognition classifier is divided into three categories, normal working condition, abnormal working condition and extreme condition, it is actually two major categories, normal working condition and abnormal working condition. Corresponding to different working conditions, the normal range and warning range of parameters are adopted. When the absolute judgment standard parameter is greater than the normal threshold, it is determined that the current working condition of the main bearing is an abnormal working condition. When the absolute judgment standard parameter is within the normal range of parameters, it is determined that the current working condition of the main bearing is a normal working condition.

[0105] Correspondingly, the determination process of abnormal conditions and extreme conditions specifically includes:

[0106] When the absolute judgment standard parameter exceeds the normal parameter range and is within the parameter warning range, it is determined as an abnormal condition.

[0107] When the absolute judgment standard parameter exceeds the parameter warning range, it is determined as an extreme condition. The specific parameter range is set according to the actual situation. It should be noted that the normal parameter range is lower than the parameter warning range.

[0108] In the embodiment of the present invention, the absolute judgment standard parameter is input into the working condition mode recognition classifier for classification to obtain the initial classification result. Through the absolute judgment standard for preliminary judgment and input into the working condition mode recognition classifier to analyze the overall situation, the absolute standard judgment is used to identify the working condition.

[0109] On the basis of the above embodiment, inputting the relative judgment standard parameter into the working condition mode recognition classifier for classification according to the abnormal working condition of the initial classification result in step S14 to obtain the final classification result includes:

[0110] When the relative judgment standard parameter is within the normal parameter range or at least one of the relative judgment standard parameters exceeds the normal parameter range and is within the parameter warning range, it is determined that the abnormal working condition corresponding to the initial classification result of the main bearing is an abnormal condition;

[0111] When at least one of the relative judgment standard parameters exceeds the parameter warning range, it is determined that the abnormal working condition corresponding to the initial classification result of the main bearing is an extreme condition.

[0112] Figure 2 It is a schematic application diagram of a method for identifying a main bearing provided by an embodiment of the present invention. As Figure 2 shown, in the case of abnormal conditions and extreme conditions, continue to input the relative judgment standard parameter into the working condition mode recognition classifier for classification to obtain the final classification result. Since there are multiple parameters, when the relative judgment standard parameter is within the normal parameter range or at least one of the relative judgment standard parameters exceeds the normal parameter range and is within the parameter warning range, it can be determined as an abnormal condition. The abnormal condition provided in this embodiment is identified based on the abnormal working condition within the initial classification result. Therefore, when in the normal line situation, there is no abnormality, and its working parameters all meet the standard range, which is also classified as an abnormal condition.

[0113] When at least one of the relative judgment standard parameters exceeds the parameter warning range, it is determined that the abnormal working condition corresponding to the initial classification result of the main bearing is an extreme condition. As Figure 2As shown, when any one of the multiple relative judgment standard parameters, that is, the working parameter reaches the danger line, which means it exceeds the parameter warning range, it is an extreme working condition.

[0114] As Figure 2 shown, pressure and temperature are absolute judgment standard parameters. Combining with an expert system for classification and identification, when in abnormal working conditions and extreme working conditions, which are non-normal working conditions, vibration signals, loads, and oil products are used as relative judgment standard parameters. Combining with an expert system for classification and identification.

[0115] The present invention provides an embodiment in which the relative judgment standard parameters are input into a working condition mode recognition classifier according to the non-normal working conditions of the initial classification result to obtain a final classification result. For the situation under non-abnormal working conditions, the relative judgment standard parameters are further combined for working condition recognition. Compared with the recognition of working conditions with a single influencing factor, it has stronger reliability.

[0116] Based on the above embodiment, obtaining the working parameters characterizing the main bearing in step S11 includes:

[0117] Obtaining the initial working parameters characterizing the main bearing;

[0118] Preprocessing the initial working parameters to obtain working parameters.

[0119] It should be noted that after the acquisition process of the working parameters of the main bearing, preliminary preprocessing and other operations are carried out to ensure that subsequent data processing reduces the interference of non-working condition factors. The preprocessing operation can be to convert the working parameters of different variables into data of the same dimension, or perform frequency screening and noise reduction processing to strip interference information, etc.

[0120] The present invention provides an embodiment of obtaining the initial working parameters characterizing the main bearing; preprocessing the initial working parameters to obtain working parameters and stripping interference information for subsequent identification.

[0121] Based on the above embodiment, the method further includes:

[0122] When the working condition corresponding to the main bearing is an abnormal working condition, a first prompt message is output;

[0123] When the working condition corresponding to the main bearing is an extreme working condition, a second prompt message is output.

[0124] Specifically, when the operating condition category is an abnormal operating condition, a prompt message is output. It should be noted that the emergency levels of abnormal operating conditions and extreme operating conditions are different. An abnormal operating condition can continue to maintain the current operation, but an extreme operating condition may directly cause damage to other equipment. Therefore, the output prompt messages can be the same or different. As a preferred embodiment, the two prompt messages are different, and the output frequency of the prompt message for the extreme operating condition is higher than that of the abnormal operating condition, the loudness or the prompt sound is louder, etc.

[0125] When the operating condition corresponding to the main bearing in the embodiment of the present invention is an abnormal operating condition, a first prompt message is output; when the operating condition corresponding to the main bearing is an extreme operating condition, a second prompt message is output, timely reminding the staff to perform maintenance.

[0126] The above has described in detail each embodiment corresponding to the method for identifying the operating condition of the main bearing. On this basis, the present invention also discloses an operating condition identification device for the main bearing corresponding to the above method. Figure 3 It is a structural diagram of an operating condition identification device for a main bearing provided by an embodiment of the present invention. As Figure 3 shown, the operating condition identification device for the main bearing includes:

[0127] An acquisition module 11, configured to acquire working parameters characterizing the main bearing, where the working parameters are multiple variables;

[0128] A processing module 12, configured to classify the working parameters into absolute judgment standard parameters and relative judgment standard parameters according to the influence factor judgment standard of the main bearing;

[0129] A first classification module 13, configured to input the absolute judgment standard parameters into a working condition mode recognition classifier for classification to obtain an initial classification result, where the working condition mode recognition classifier is constructed by an expert system and a clustering analysis method, and the initial classification result includes a normal operating condition and an abnormal operating condition;

[0130] A second classification module 14, configured to input the relative judgment standard parameters into the working condition mode recognition classifier for classification according to the abnormal operating condition of the initial classification result to obtain a final classification result. Since the embodiments of the device part correspond to the above embodiments, the embodiments of the device part are described with reference to the above embodiments of the device part and will not be repeated here.

[0131] For the introduction of an operating condition identification device for a main bearing provided by the present invention, please refer to the above method embodiments. The present invention will not repeat it here, and it has the same beneficial effects as the above method for identifying the operating condition of the main bearing.

[0132] Figure 4 It is a structural diagram of another operating condition identification device for a main bearing provided by an embodiment of the present invention. As Figure 4 shown, the device includes:

[0133] A memory 21 for storing a computer program;

[0134] A processor 22 for implementing the steps of the working condition identification method of the main bearing when executing the computer program.

[0135] The working condition identification device of the main bearing provided in this embodiment may include, but is not limited to, a slurry balance shield machine, an earth pressure balance shield machine, a full-face tunnel hard rock boring machine, an inclined shaft TBM, a vertical shaft, etc.

[0136] Among them, the processor 22 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 22 may be implemented in at least one hardware form of a digital signal processor (DSP), a field-programmable gate array (FPGA), or a programmable logic array (PLA). The processor 22 may also include a main processor and a coprocessor. The main processor is a processor for processing data in the wake state, also known as a central processing unit (CPU); the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor 22 may be integrated with a graphics processing unit (GPU), and the GPU is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 22 may further include an artificial intelligence (AI) processor, and the AI processor is used to process computational operations related to machine learning.

[0137] The memory 21 may include one or more computer-readable storage media, and the computer-readable storage media may be non-transitory. The memory 21 may further include high-speed random access memory and non-volatile memory, such as one or more disk storage devices and flash storage devices. In this embodiment, the memory 21 is at least used to store the following computer program 211. After the computer program is loaded and executed by the processor 22, it can implement the relevant steps of the working condition identification method of the main bearing disclosed in any of the foregoing embodiments. In addition, the resources stored in the memory 21 may further include an operating system 212 and data 213, etc., and the storage method may be temporary storage or permanent storage. Among them, the operating system 212 may include Windows, Unix, Linux, etc. The data 213 may include, but is not limited to, the data involved in the working condition identification method of the main bearing, etc.

[0138] In some embodiments, the working condition recognition device of the main bearing may further include a display screen 23, an input / output interface 24, a communication interface 25, a power supply 26, and a communication bus 27.

[0139] Those skilled in the art can understand that Figure 4 the structure shown in does not constitute a limitation on the working condition recognition device of the main bearing, and may include more or fewer components than those shown in the figure.

[0140] The processor 22 realizes the working condition recognition method of the main bearing provided in any of the above embodiments by calling the instructions stored in the memory 21.

[0141] For the introduction of a working condition recognition device of a main bearing provided by the present invention, please refer to the above method embodiments. The present invention will not be elaborated herein, and it has the same beneficial effects as the above working condition recognition method of the main bearing.

[0142] Furthermore, the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by the processor 22, the steps of the working condition recognition method of the main bearing as described above are realized.

[0143] It can be understood that if the method in the above embodiments is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and executes all or part of the steps of the methods described in various embodiments of the present invention. And the aforementioned storage media include: USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks, or optical disks and other various media that can store program codes.

[0144] For the introduction of a computer-readable storage medium provided by the present invention, please refer to the above method embodiments. The present invention will not be elaborated herein, and it has the same beneficial effects as the above working condition recognition method of the main bearing.

[0145] The above has introduced in detail a method for identifying the working conditions of a main bearing, a device for identifying the working conditions of a main bearing, and a medium provided by the present invention. The various embodiments in the specification are described in a progressive manner. Each embodiment focuses on the differences from other embodiments. For the same or similar parts between the various embodiments, reference can be made to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple. For the relevant parts, reference can be made to the description in the method part. It should be noted that for those of ordinary skill in the art in the technical field, without departing from the principle of the present invention, several improvements and modifications can be made to the present invention, and these improvements and modifications also fall within the protection scope of the claims of the present invention.

[0146] It should also be noted that in this specification, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "including one..." does not exclude the existence of another identical element in the process, method, article or device including the said element.

Claims

1. A method for identifying the operating conditions of a main bearing, characterized in that, it includes: Obtain the operating parameters characterizing the main bearing, where the operating parameters are multiple variables; According to the influence factor judgment criteria of the main bearing, divide the operating parameters into absolute judgment standard parameters and relative judgment standard parameters; Input the absolute judgment standard parameters into the operating condition pattern recognition classifier for classification to obtain an initial classification result, where the operating condition pattern recognition classifier is constructed by an expert system and a clustering analysis method, and the initial classification result includes normal operating conditions and abnormal operating conditions; According to the abnormal operating conditions in the initial classification result, input the relative judgment standard parameters into the operating condition pattern recognition classifier for classification to obtain a final classification result; Among them, the step of dividing the operating parameters into absolute judgment standard parameters and relative judgment standard parameters according to the influence factor judgment criteria of the main bearing includes: Perform a priority ranking on the operating parameters according to the influence factor judgment criteria of the main bearing; According to preset requirements, use the operating parameters corresponding to the first N influence factors in the priority ranking as the absolute judgment standard parameters; According to the preset requirements, use the operating parameters corresponding to the influence factors other than the first N influence factors in the priority ranking as the relative judgment standard parameters.

2. The method for identifying the operating conditions of a main bearing according to claim 1, characterized in that, The construction process of the operating condition pattern recognition classifier includes the following steps: Obtain the sample parameters characterizing the main bearing, the description information of multiple operating conditions in the expert system, and the corresponding operating condition characteristic parameters; Construct a relationship network according to the relationship between the description information of multiple operating conditions; Perform clustering analysis on the sample parameters according to the operating condition characteristic parameters to obtain the current clustering result, where the clustering analysis is performed by setting preset conditions on the operating parameters; Count the number of times of clustering analysis; Judge whether the number of times of clustering analysis corresponding to the current clustering result exceeds the threshold; If not, return to the step of performing clustering analysis on the sample parameters to obtain the current clustering result; If so, use the current clustering result as the final clustering result; Construct the operating condition pattern recognition classifier according to the corresponding relationship between the relationship network and the final clustering result.

3. The method for identifying the operating conditions of a main bearing according to claim 2, characterized in that, The step of inputting the absolute judgment standard parameters into the operating condition pattern recognition classifier for classification to obtain an initial classification result includes: Obtain the normal range and warning range of parameters corresponding to multiple classifications of the operating condition pattern recognition classifier, where the normal range of parameters is lower than the warning range of parameters; When the absolute judgment standard parameter exceeds the normal range of parameters, determine that the initial classification result of the main bearing is the abnormal operating condition, where the abnormal operating condition includes abnormal conditions and extreme conditions; When the absolute judgment standard parameter is within the normal range of parameters, determine that the initial classification result of the main bearing is the normal operating condition; Among them, the determination process of the abnormal condition and the extreme condition specifically includes: When the absolute judgment standard parameter exceeds the normal range of the parameter and is within the warning range of the parameter, it is determined that the abnormal working condition corresponding to the initial classification result of the main bearing is the abnormal working condition; When the absolute judgment standard parameter exceeds the warning range of the parameter, it is determined that the abnormal working condition corresponding to the initial classification result of the main bearing is the extreme working condition.

4. The working condition identification method of the main bearing according to claim 3, characterized in that, inputting the relative judgment standard parameter into the working condition mode recognition classifier according to the abnormal working condition of the initial classification result for classification to obtain a final classification result, including: When the relative judgment standard parameter is within the normal range of the parameter or at least one of the relative judgment standard parameters exceeds the normal range of the parameter and is within the warning range of the parameter, it is determined that the abnormal working condition corresponding to the initial classification result of the main bearing is the abnormal working condition; When at least one of the relative judgment standard parameters exceeds the warning range of the parameter, it is determined that the abnormal working condition corresponding to the initial classification result of the main bearing is the extreme working condition.

5. The working condition identification method of the main bearing according to claim 1, characterized in that, obtaining the working parameters characterizing the main bearing, including: obtaining the initial working parameters characterizing the main bearing; preprocessing the initial working parameters to obtain the working parameters.

6. The working condition identification method of the main bearing according to any one of claims 1 to 5, characterized in that, further comprising: when the working condition corresponding to the main bearing is an abnormal working condition, outputting a first prompt message; when the working condition corresponding to the main bearing is an extreme working condition, outputting a second prompt message.

7. A working condition identification device for a main bearing, characterized in that, comprising: an acquisition module for acquiring working parameters characterizing the main bearing, wherein the working parameters are multiple variables; a processing module for classifying the working parameters into absolute judgment standard parameters and relative judgment standard parameters according to the influence factor judgment standard of the main bearing; a first classification module for inputting the absolute judgment standard parameter into a working condition mode recognition classifier for classification to obtain an initial classification result, wherein the working condition mode recognition classifier is constructed by an expert system and a clustering analysis method, and the initial classification result includes a normal working condition and an abnormal working condition; a second classification module for inputting the relative judgment standard parameter into the working condition mode recognition classifier according to the abnormal working condition of the initial classification result for classification to obtain a final classification result; wherein, classifying the working parameters into absolute judgment standard parameters and relative judgment standard parameters according to the influence factor judgment standard of the main bearing includes: sorting the working parameters according to the influence factor judgment standard of the main bearing; taking the working parameters corresponding to the first N influence factors within the priority sorting as the absolute judgment standard parameters according to preset requirements; The working parameters corresponding to the influencing factors other than the top N influencing factors within the priority ranking are used as the relative judgment standard parameters according to the preset requirements.

8. A device for identifying the working conditions of a main bearing, characterized in that, it includes: a memory for storing a computer program; a processor for implementing the steps of the method for identifying the working conditions of the main bearing according to any one of claims 1 to 6 when executing the computer program.

9. A computer-readable storage medium, characterized in that, a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps of the method for identifying the working conditions of the main bearing according to any one of claims 1 to 6 are implemented.

Images