A fault diagnosis method, system, device and medium for a main shaft of a numerical control machine tool

Abstract

Embodiments of the present application relate to the technical field of numerical control machine tools, and disclose a fault diagnosis method, system, device and medium for a main shaft of a numerical control machine tool. The fault diagnosis method for the main shaft of the numerical control machine tool comprises: acquiring a frequency domain signal corresponding to a real-time vibration signal of a main shaft bearing of the numerical control machine tool; extracting the frequency domain signal in the real-time vibration signal; performing feature extraction on the frequency domain signal through a deep belief network to obtain a high-dimensional feature of the frequency domain signal, the high-dimensional feature being used to indicate a target fault mode of the main shaft bearing; selecting a preset fault mode matched with the target fault mode from a pre-constructed main shaft fault knowledge base containing multiple preset fault modes, and taking a fault resolution strategy corresponding to the selected preset fault mode in the main shaft fault knowledge base as a fault resolution strategy corresponding to the target fault mode. The fault diagnosis method for the main shaft of the numerical control machine tool provided by the present application can improve the accuracy of fault diagnosis of the main shaft of the numerical control machine tool and provide a fault resolution strategy in a timely manner.

Description

Technical Field

[0001] The embodiments of the present application relate to the technical field of CNC machine tools, and in particular to a fault diagnosis method, system, device, and medium for a CNC machine tool spindle. Background Art

[0002] CNC machine tools, as key equipment in modern intelligent manufacturing, are the cornerstone of high-precision machining and manufacturing, playing the role of "the mother of industry" in the development of industrial automation. Long-term operation often causes spindle system failures in CNC machine tools, which can affect machine performance, reduce product quality, and even cause the machine to malfunction. The spindle, as the "joint" of the CNC machine tool's mechanical transmission, is the core support component for its smooth operation. Therefore, condition monitoring and fault diagnosis of the machine tool's spindle system are critical to ensuring the reliable operation of the entire CNC machine tool.

[0003] Currently, most spindle systems are monitored and diagnosed manually through regular maintenance and upkeep. This is not only time-consuming and labor-intensive, but the diagnostic results are also subject to the uncertainty of manual experience. Summary of the Invention

[0004] The purpose of the embodiments of the present application is to provide a fault diagnosis method, system, equipment and medium for a CNC machine tool spindle, which can improve the accuracy of CNC machine tool spindle fault diagnosis and provide fault resolution strategies in a timely manner to ensure the reliable operation of the CNC machine tool.

[0005] To solve the above technical problems, an embodiment of the present application provides a fault diagnosis method for a CNC machine tool spindle, comprising the following steps:

[0006] Obtain the frequency domain signal corresponding to the real-time vibration signal of the spindle bearing of the CNC machine tool;

[0007] Performing feature extraction on the frequency domain signal through a deep belief network to obtain high-dimensional features of the frequency domain signal, wherein the high-dimensional features are used to indicate a target fault mode of the spindle bearing;

[0008] The deep belief network includes multiple stacked restricted Boltzmann machines and a BP classifier, each restricted Boltzmann machine is used to extract the features of the frequency domain signal, and the direction from the bottom layer to the top layer of the multiple stacked restricted Boltzmann machines is the feature transfer direction of the deep belief network. The features extracted by each restricted Boltzmann machine are the input features of the next restricted Boltzmann machine to mine the high-dimensional features of the frequency domain signal; the BP classifier is used to correct the network parameters of the deep belief network through back error propagation;

[0009] A preset fault mode that matches the target fault mode is selected from a pre-built spindle fault knowledge base containing multiple preset fault modes, and the fault resolution strategy corresponding to the selected preset fault mode in the spindle fault knowledge base is used as the fault resolution strategy corresponding to the target fault mode.

[0010] In some optional embodiments, obtaining a frequency domain signal corresponding to a real-time vibration signal of a spindle bearing of a CNC machine tool includes:

[0011] Decomposing the real-time vibration signal based on an empirical mode decomposition method to obtain a plurality of intrinsic mode function components of the real-time vibration signal;

[0012] Envelope detection is performed on each eigenmode function component through Hilbert transform to obtain frequency domain signals of different time scales of the real-time vibration signal.

[0013] In some optional embodiments, selecting a preset fault mode that matches the target fault mode from a pre-built spindle fault knowledge base containing multiple preset fault modes includes:

[0014] Establishing a semantic mapping relationship between the target fault mode and the plurality of preset fault modes based on a concept similarity algorithm;

[0015] According to the semantic mapping relationship between the target failure mode and the multiple preset failure modes, a preset failure mode with the highest similarity to the target failure mode is selected from the multiple preset failure modes.

[0016] In some optional embodiments, the spindle fault knowledge base is constructed by the following steps:

[0017] Constructing an ontology class of the spindle fault knowledge base, wherein the ontology class includes preset fault modes and fault resolution strategies of the spindle bearing;

[0018] Defining object properties of all objects in the ontology class to associate objects that have corresponding relationships;

[0019] Define the data attributes of all objects in the ontology class.

[0020] In some optional embodiments, the body class further includes the fault type, fault location, fault phenomenon and fault cause of the main shaft bearing, and the method further includes:

[0021] According to the determined target failure mode and the failure resolution strategy corresponding to the target failure mode, the failure type, failure location, failure phenomenon and failure cause corresponding to the target failure mode are obtained.

[0022] In some optional embodiments, a preset failure mode of the main shaft bearing corresponds to multiple failure causes, and obtaining the failure cause corresponding to the target failure mode according to the target failure mode and the failure resolution strategy corresponding to the target failure mode includes:

[0023] Based on preset SWRL rules, knowledge reasoning is performed on the target failure mode and the failure resolution strategy corresponding to the target failure mode to obtain the failure cause corresponding to the target failure mode.

[0024] In some optional embodiments, the target failure mode is obtained by classifying the high-dimensional features based on a random forest algorithm.

[0025] The embodiment of the present application further provides a fault diagnosis system for a CNC machine tool spindle, comprising:

[0026] A signal acquisition module is used to obtain the frequency domain signal corresponding to the real-time vibration signal of the spindle bearing of the CNC machine tool;

[0027] a feature extraction module, configured to extract features from the frequency domain signal using a deep belief network to obtain high-dimensional features of the frequency domain signal, wherein the high-dimensional features are used to indicate a target fault mode of the spindle bearing;

[0028] The deep belief network includes multiple stacked restricted Boltzmann machines and a BP classifier, each restricted Boltzmann machine is used to extract the features of the frequency domain signal, and the direction from the bottom layer to the top layer of the multiple stacked restricted Boltzmann machines is the feature transfer direction of the deep belief network. The features extracted by each restricted Boltzmann machine are the input features of the next restricted Boltzmann machine to mine the high-dimensional features of the frequency domain signal; the BP classifier is used to correct the network parameters of the deep belief network through back error propagation;

[0029] A fault diagnosis module is used to select a preset fault mode that matches the target fault mode from a pre-built spindle fault knowledge base containing multiple preset fault modes, and use the fault solution strategy corresponding to the selected preset fault mode in the spindle fault knowledge base as the fault solution strategy corresponding to the target fault mode.

[0030] An embodiment of the present application also provides a computer device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the above-mentioned CNC machine tool spindle fault diagnosis method.

[0031] An embodiment of the present application further provides a computer-readable storage medium storing a computer program, which implements the above-mentioned CNC machine tool spindle fault diagnosis method when executed by a processor.

[0032] The fault diagnosis method for a CNC machine tool spindle provided by the embodiments of the present application has at least the following beneficial effects:

[0033] Since the most prone to failure and the most difficult to detect failure in the spindle system of a CNC machine tool often comes from the bearing part, this application collects the real-time vibration signal of the spindle bearing of the CNC machine tool, extracts the frequency domain signal that accurately reflects the spindle vibration failure, and performs feature extraction on the frequency domain signal through a deep confidence network, which can fully exploit the high-dimensional features of the spindle bearing failure, and the high-dimensional features are used to indicate the target failure mode of the spindle bearing. A preset failure mode that matches the target failure mode can be selected from a pre-built spindle failure knowledge base containing multiple preset failure modes, and the fault solution strategy corresponding to the selected preset failure mode in the spindle fault knowledge base is used as the fault solution strategy corresponding to the target failure mode.

[0034] The deep belief network includes multiple stacked restricted Boltzmann machines, each restricted Boltzmann machine is used to extract the features of the frequency domain signal, and the direction from the bottom layer to the top layer of the multiple stacked restricted Boltzmann machines is the feature transmission direction of the deep belief network. The extracted features of each restricted Boltzmann machine are the input features of the next restricted Boltzmann machine, so that the high-dimensional features of the spindle bearing fault can be fully mined. The BP classifier can correct the network parameters of the deep belief network through reverse error propagation, further improving the accuracy of the extracted high-dimensional features, with high efficiency and accuracy. At the same time, it can also determine the fault resolution strategy corresponding to the fault mode, so as to timely deal with the spindle bearing fault of the CNC machine tool and ensure the stable operation of the CNC machine tool. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] One or more embodiments are exemplarily described by the figures in the corresponding drawings, and these exemplified descriptions do not constitute limitations on the embodiments.

[0036] Figure 1 This is a flow chart of a method for diagnosing a spindle fault of a CNC machine tool provided according to one embodiment of the present application;

[0037] Figure 2 1 is a schematic diagram of a DBN model structure provided according to an embodiment of the present application;

[0038] Figure 3 This is a flowchart for constructing a spindle fault knowledge base according to an embodiment of the present application;

[0039] Figure 4 This is a schematic diagram of an ontology class of a spindle fault knowledge base provided according to an embodiment of the present application;

[0040] Figure 5 is a characteristic diagram of a statistical parameter provided according to an embodiment of the present application;

[0041] Figure 6 is a schematic diagram of a model output result provided according to an embodiment of the present application;

[0042] Figure 7 This is a schematic diagram of a fault diagnosis system for a CNC machine tool spindle provided according to one embodiment of the present application;

[0043] Figure 8 It is a structural diagram of a computer device provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0044] In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, each embodiment of the present application will be described in detail below with reference to the accompanying drawings. However, it will be understood by those skilled in the art that in each embodiment of the present application, many technical details are proposed to enable the reader to better understand the present application. However, even without these technical details and various changes and modifications based on the following embodiments, the technical solutions claimed in the present application can be implemented. The division of the following embodiments is for convenience of description and should not constitute any limitation on the specific implementation of the present application. The various embodiments can be combined and referenced with each other under the premise of no contradiction.

[0045] To avoid downtime caused by spindle failures in CNC machine tools and the resulting impact on product quality, condition monitoring and early fault diagnosis of CNC machine tool spindle systems are crucial. With the development of intelligent sensing technology and artificial intelligence theory, precise and intelligent fault diagnosis through monitoring and analyzing machine tool spindle status data has become a research hotspot. For example, data-driven quantitative analysis methods use sensors to collect relevant information and data representing the machine tool's fault status. These data are analyzed and processed through mechanism analysis, signal processing, and mathematical statistics to extract key fault characteristics and identify the fault type. Qualitative analysis methods based on knowledge modeling can achieve efficient semantic mapping and knowledge reasoning while enabling domain knowledge sharing. Based on data-driven analysis of machine tool spindle fault types, they infer underlying implicit knowledge, thereby identifying the cause of the fault, repair methods, and maintenance measures, thereby reducing the probability of failure.

[0046] Based on the above, by associating the data-driven fault type identification results with the instances in the constructed CNC machine tool spindle fault knowledge base, we can further explore the underlying causes of the fault and provide specific fault maintenance strategies through knowledge reasoning. Therefore, the embodiments of this application combine data-driven quantitative analysis methods with qualitative analysis methods based on knowledge modeling to achieve in-depth and comprehensive intelligent fault diagnosis and health management of CNC machine tool spindle systems.

[0047] An embodiment of the present application relates to a fault diagnosis method for a CNC machine tool spindle. The implementation details of the fault diagnosis method for a CNC machine tool spindle of this embodiment are described in detail below. The following content is only the implementation details provided for ease of understanding and is not necessary for implementing this solution.

[0048] The specific process of the fault diagnosis method of the CNC machine tool spindle of this embodiment can be as follows: Figure 1 As shown, including:

[0049] Step 101: Acquire a frequency domain signal corresponding to a real-time vibration signal of a spindle bearing of a CNC machine tool.

[0050] Specifically, the spindle, as a fundamental component of CNC machine tools, plays a crucial role in part machining. Its operating condition directly impacts machining efficiency and quality. The spindle system generally consists of a rotating shaft, bearings, broaching system, rotor, stator, and spindle housing. Mechanical failures in the spindle system are often caused by wear and tear of these components, as well as structural changes caused by improper use. The most common and difficult-to-detect faults in the spindle system often occur in the rolling bearings. Bearing failures occur frequently and are difficult to diagnose using the machine tool's self-diagnostic systems. Long-term high-speed operation of the spindle causes wear and tear in the bearings, which in turn increases bearing clearance and deformation. Furthermore, if bearing components are not properly maintained, defects such as pitting and cracks can develop on the inner and outer rings, rolling elements, and other surfaces due to poor lubrication and excessive loads. Therefore, the quality of the bearings directly determines the service life and proper operation of the machine tool spindle system and impacts the overall performance of the CNC machine tool.

[0051] In practice, when a machine tool spindle bearing fails, it's often accompanied by highly random vibration signals. These nonlinear vibration signals contain a wealth of fault information and characteristics. Therefore, to fully understand and grasp the type of bearing failure, this embodiment installs a vibration sensor module on the machine tool spindle to obtain real-time vibration signals that fully reflect the bearing failure characteristics.

[0052] By performing signal analysis and processing on the collected real-time vibration signals, we can further obtain sensitive characteristic information (i.e., frequency domain signals) in the real-time vibration signals, laying a data foundation for subsequent fault type identification research.

[0053] In one example, based on the empirical mode decomposition method, a real-time vibration signal is decomposed to obtain multiple intrinsic mode function components of the real-time vibration signal; each intrinsic mode function component is subjected to envelope detection through Hilbert transform to obtain frequency domain signals of different time scales of the real-time vibration signal. Because the vibration signal collected by the sensor of the CNC machine tool spindle system contains a lot of noise and exhibits nonlinear properties such as frequent oscillations and instability when a fault occurs, conventional signal processing methods cannot adapt to this complexity. Therefore, this embodiment uses empirical mode decomposition (EMD) to achieve the decomposition of nonlinear multidimensional data (real-time vibration signals of spindle bearings) and the extraction of frequency domain signals.

[0054] EMD is an analysis method that can adaptively process non-stationary and nonlinear signals. Without specifying basis functions, EMD can flexibly decompose the signal into frequency band components of different scales and extract its intrinsic mode function from the time domain signal itself. The specific decomposition process is as follows:

[0055]

[0056] Where x(t) represents the real-time vibration signal, t represents the sampling time of the real-time vibration signal, I represents the kth IMF component containing different time scales, and r(t) represents the residual trend term of the signal.

[0057] In the processing of CNC machine tool spindle vibration signals, EMD is used to obtain the intrinsic mode function (IMF) components, and then envelope detection is performed through Hilbert transform to obtain frequency domains at different time scales. These information components can more accurately characterize the spindle fault characteristics. The specific implementation process of EMD mainly includes the following steps: (1) decomposing the vibration signal into local extreme value lines of different scales; (2) constructing envelope detection lines through local extreme value lines; (3) averaging the envelope lines to obtain IMF components; (4) repeating the iteration until only the trend term is retained in the signal, thereby extracting the vibration intrinsic mode components of the original signal and reconstructing them to obtain the vibration signal frequency domain signal.

[0058] Step 102 : extracting features from the frequency domain signal through a deep belief network to obtain high-dimensional features of the frequency domain signal. The high-dimensional features are used to indicate a target fault mode of the spindle bearing.

[0059] Specifically, deep belief networks (DBNs) are deep learning networks capable of fully exploiting data features. They are multi-layer neural network generation models formed by stacking multiple restricted Boltzmann machines (RBMs). Starting from the underlying raw data, DBNs train and optimize the weight parameters of the deep neural network through a layer-by-layer greedy learning algorithm. This achieves a complex mapping from low-dimensional input to high-dimensional feature data output, effectively discovering the essential characteristics of faults in the raw vibration signal data.

[0060] In the specific implementation, the DBN learning process mainly consists of unsupervised forward stacking RBM learning and supervised backward fine-tuning RBM parameter training. The model structure and training process of DBN are as follows: Figure 2 As shown, the deep belief network includes multiple stacked restricted Boltzmann machines and a BP classifier. Each restricted Boltzmann machine is used to extract the features of the frequency domain signal, and the direction from the bottom layer to the top layer of the multiple stacked restricted Boltzmann machines is the feature transfer direction of the deep belief network. The features extracted by each restricted Boltzmann machine are the input features of the next restricted Boltzmann machine to mine the high-dimensional features of the frequency domain signal; the BP classifier is used to correct the network parameters of the deep belief network through back error propagation.

[0061] Here, h represents the hidden layer and v represents the visual layer. The two are connected by the weight parameter w. The input raw data passes through the first visual layer and forms a low-level RBM with the first hidden layer. The output of this layer serves as the visual layer input of the second RBM, and forms a second RBM with the second hidden layer h2. This stacking process forms a DBN deep learning network. The DBN network parameters are initialized through forward training layer by layer. Then, the BP (Back Propagation) classifier is used to fine-tune the parameters through back error propagation. This continuously trains the model to obtain more representative high-dimensional features from the low-level data.

[0062] In one example, the target fault mode is determined by classifying high-dimensional features using a random forest algorithm. After extracting the high-dimensional features of the frequency domain signal using a DBN, the resulting high-dimensional feature set is randomly sampled and grouped to construct a training sample set. This is then fed into the random forest algorithm model, which then outputs the fault mode identification result (i.e., the target fault mode) through majority voting.

[0063] The Random Forest algorithm (RF) is a supervised machine learning algorithm used to solve classification or regression problems. The algorithm uses decision trees as the basic learner and uses decision tree voting to establish the results. The main principle is to randomly sample k sample sets with replacement from the N sample training sets, and randomly select features from these sample sets to generate decision trees to form a random forest. Each decision tree is used to perform pattern discrimination on the new sample to be tested, and the discrimination results of all decision trees are combined to determine the final classification result through selection voting. The implementation process of the random forest algorithm model mainly includes the following steps: (1) m samples are randomly sampled with replacement from the original N training sample data set using the bootstrap method as the sampling subset, and the sampling is repeated multiple times. (2) A decision tree is established in the sampling subset for training, and attribute features are randomly selected from the feature set to calculate the optimal feature as the tree node. (3) Each decision tree grows by node splitting until it can no longer be divided, thereby generating n classification and regression decision trees. (4) The test set is input into the random forest model composed of n decision trees to obtain n results, and the final result is determined by majority voting.

[0064] Step 103 , selecting a preset fault mode that matches the target fault mode from a pre-built spindle fault knowledge base containing multiple preset fault modes, and using the fault resolution strategy corresponding to the selected preset fault mode in the spindle fault knowledge base as the fault resolution strategy corresponding to the target fault mode.

[0065] Specifically, this embodiment uses the ontology knowledge modeling method to construct a spindle fault knowledge base. The spindle fault knowledge base contains a variety of preset fault modes of spindle bearings and corresponding fault resolution strategies. By matching the target fault mode with these multiple preset fault modes, a preset fault mode that matches the target fault mode can be obtained, and then the fault resolution strategy corresponding to the target fault mode can be determined.

[0066] In one example, a preset fault mode that matches a target fault mode is obtained in the following manner: based on a concept similarity algorithm, a semantic mapping relationship between the target fault mode and multiple preset fault modes is established; and according to the semantic mapping relationship between the target fault mode and multiple preset fault modes, a preset fault mode with the highest similarity to the target fault mode is selected from the multiple preset fault modes.

[0067] The construction process of the spindle fault knowledge base is as follows: Figure 3As shown in the figure, this knowledge base is applied to CNC machine tool spindle fault diagnosis. The ontology is constructed primarily around knowledge of spindle component structure and fault mechanisms. First, knowledge in the field of CNC machine tool spindle bearings is acquired through literature, expert experience, and fault cases. An information dictionary is established based on the ontology formal language, laying the corpus foundation for ontology construction. The protege ontology construction tool is then used to construct a spindle fault diagnosis ontology model. This involves defining ontology concept classes and their subclasses, defining object and data attributes of ontology classes, defining attribute constraint scopes and class relationships, creating class instances, and constructing diagnostic reasoning rules. Consistency checks and evaluation of the ontology are then performed using instances. If the consistency check fails, feedback is provided to improve the ontology. The ontology is stored and shared as an OWL file. Instance semantic mapping is used to form a knowledge base, enabling fault diagnosis based on knowledge reasoning.

[0068] Therefore, the construction of the spindle fault knowledge base mainly includes the following parts:

[0069] (1) Construct the ontology class of the spindle fault knowledge base, which includes the preset failure modes and fault resolution strategies of the spindle bearings.

[0070] Ontology construction includes five basic primitives, namely, class, class attributes, axioms, relations, and instances. By analyzing the structural characteristics and fault mechanisms of machine tool spindle bearings, the Fault Diagnosis Ontology (FDO) is defined.<C,A,R,I,X> , where C represents the set of concept classes, A represents the set of attributes, R represents the set of relationships between classes, I represents the set of class instances, and X represents the set of axioms.

[0071] The structural characteristics and failure mechanisms of bearings were analyzed and summarized into top-level parent categories: fault location, fault characteristics, fault phenomenon, fault cause, fault type, and fault diagnosis and maintenance strategy. The fault location refers to the specific location in the bearing where the fault phenomenon occurs and the fault repair is performed; the fault phenomenon refers to the description of the external manifestation of the bearing failure; the fault cause refers to the cause of the specific failure of the machine tool spindle bearing; the fault type refers to the classification of the occurred fault; the fault diagnosis and maintenance strategy refers to the specific and effective measures taken to solve the fault (equivalent to the fault resolution strategy); the fault characteristics refer to the main characteristics of each component that characterize the bearing fault (equivalent to the fault mode) extracted after analyzing the fault signal collected by the sensor. Based on the above core elements, the top-level parent category of the spindle bearing fault domain ontology was determined, and the ontology construction tool Protege was used to manually construct the parent category hierarchy. The parent category can contain subcategories, and its subcategories are further determined based on the above five top-level categories. Figure 4 A schematic diagram showing an ontology class and the relationship between ontology classes.

[0072] In an example, the ontology class also includes the fault type, fault location, fault phenomenon and fault cause of the spindle bearing. After determining the target fault mode and the fault solution strategy corresponding to the target fault mode, the fault type, fault location, fault phenomenon and fault cause corresponding to the target fault mode can also be obtained based on the determined target fault mode and the fault solution strategy of the target fault mode.

[0073] In one example, a preset failure mode of a spindle bearing corresponds to multiple failure causes. In this case, to determine the failure cause corresponding to the target failure mode, it is necessary to perform knowledge reasoning on the target failure mode and the fault resolution strategy corresponding to the target failure mode based on the preset SWRL rules to obtain the failure cause corresponding to the target failure mode.

[0074] (2) Define the object properties of all objects in the ontology class to associate the ontology classes that have corresponding relationships, and define the data properties of all objects in the ontology class.

[0075] Specifically, the semantic relationships and instance properties between ontology classes need to be described by defining class attributes. Attributes are mainly constrained by axioms, domains, and ranges. In the bearing fault diagnosis ontology, object attributes and data attributes are defined to express the associations between classes and the data characteristics of class instances. For example, the object attribute "has_Cause" is used to associate the fault phenomenon with the fault cause. For example, the attribute definition domain of "pitting corrosion has_Cause poor lubrication in the main bearing" is the fault phenomenon class, and the range is the fault cause class. In addition, data attributes are added in protege through the DataTypeProperties option to describe the data constraints of the instance. For example, "has_temperature" indicates that the bearing seat has temperature data characteristics, its definition domain is "fault location", and its range is "float".

[0076] To implement knowledge reasoning, the constructed ontology class must be instantiated to complete the transformation into a knowledge base. A specific instance of a class not only possesses all of the class's attributes but can also semantically associate with other instances through object properties to enable knowledge reasoning. The knowledge base of the instantiated spindle fault ontology may contain semantic conflicts and errors. This requires consistency checking using the Protege tool's built-in reasoning engine to ensure the logical consistency of the knowledge base structure and the correctness of the knowledge description. If the bearing inner ring diameter damage generally exceeds 0.17mm, pitting corrosion is considered a fault. Once pitting corrosion occurs, it is considered an inner ring fault.

[0077] The following is a consistency test of the knowledge base for a bearing fault instance: The test instance "testInstance1," the inner ring component instance "Inner_Ring1," and the pitting fault phenomenon instance "Pitting_phenomenon1" were constructed. The inner ring component of "testInstance1" is inner_Ring1, i.e., "testInstance1 has_Componentinner_Ring1," and the pitting fault phenomenon "has_Cause Pitting_phenomenon1" occurs. Using the "Euwntfo" button, an equivalence class "(has_Component someInner_Ring)and(has_Cause some Pitting)" is added to the inner ring fault class (Inner_RingFault). After selecting the HemiT reasoner and clicking "Start Reasoner" to begin reasoning on the instance, the test instance is automatically attributed to an instance of the Inner_RingFault class, which is consistent with the expected result. The applicable fault resolution action is "Maintenance1," proving the semantic logic of the knowledge base correct and passing the consistency test. After verification, the knowledge base can be saved as an OWL file for cross-platform sharing.

[0078] In this embodiment, a semantic mapping method is used to semantically associate the results of signal processing, feature extraction, and fault identification with the fault phenomenon instances in the ontology knowledge base, and establish a mapping between them. The semantic mapping process can be expressed as: f = map(,R,[instance,},(result,}). Here, f represents the mapping relationship between I and R, instance represents the set of fault phenomenon instances, and rusult represents the set of fault identification results in the data-driven diagnosis method. A concept similarity algorithm is used to establish a semantic mapping relationship between the two, and the constructed SWRL rules are combined to perform ontology knowledge reasoning to obtain the fault cause and maintenance solution (fault resolution strategy) that matches the fault diagnosis instance (preset fault mode).

[0079] In this embodiment, since the most prone to failure and the most difficult to detect failure in the spindle system of a CNC machine tool often comes from the bearing part, the real-time vibration signal of the spindle bearing of the CNC machine tool is collected in this application, and the frequency domain signal that accurately reflects the spindle vibration failure is extracted. The frequency domain signal is subjected to feature extraction through a deep confidence network, which can fully exploit the high-dimensional features of the spindle bearing failure. The high-dimensional features are used to indicate the target failure mode of the spindle bearing. A preset failure mode that matches the target failure mode can be selected from a pre-built spindle failure knowledge base containing multiple preset failure modes, and the fault solution strategy corresponding to the selected preset failure mode in the spindle fault knowledge base is used as the fault solution strategy corresponding to the target failure mode. The deep belief network includes multiple stacked restricted Boltzmann machines, each restricted Boltzmann machine is used to extract the features of the frequency domain signal, and the direction from the bottom layer to the top layer of the multiple stacked restricted Boltzmann machines is the feature transmission direction of the deep belief network. The extracted features of each restricted Boltzmann machine are the input features of the next restricted Boltzmann machine, so that the high-dimensional features of the spindle bearing fault can be fully mined. The BP classifier can correct the network parameters of the deep belief network through reverse error propagation, further improving the accuracy of the extracted high-dimensional features, with high efficiency and accuracy. At the same time, it can also determine the fault resolution strategy corresponding to the fault mode, so as to timely deal with the spindle bearing fault of the CNC machine tool and ensure the stable operation of the CNC machine tool.

[0080] In one embodiment, the present application provides an experimental scheme for verifying the effectiveness and adaptability of the above-mentioned CNC machine tool spindle fault diagnosis method, as described below:

[0081] This embodiment uses an acceleration sensor to collect experimental sample data based on the SQI-MFS mechanical comprehensive fault simulation experimental platform. The experimental sample is a bearing, model MB ER-16K, which can simulate the working status of a healthy bearing or a bearing with different degrees of fault under different working conditions. In order to reflect the fault phenomena occurring in the actual operation of the bearing as comprehensively as possible, experimental data of three types of faults (inner ring, outer ring, rolling element) and fault diameters of 0.1778mm, 0.335mm, and 0.554mm were collected to form a sample data set corresponding to 10 working conditions. On this basis, bearing vibration signal collection tasks at speeds of 1000r / min, 1400r / min, and 1800r / min were set. Each task collects 100 groups of samples at a sampling frequency of 15kHz, which are divided into a model training set and a test set according to a ratio of 7:3, with each group of samples having 2000 data points. The experimental data sets of the three tasks are shown in Table 1:

[0082] Table 1

[0083]

[0084]

[0085] (1) After obtaining the original vibration signal data set according to the above requirements, the training sample signals in Task 1 to Task 3 are decomposed using EMD. The time domain signals of the first four IMF components, the Hilbert envelope spectrum of the four IMF components, and the Hilbert marginal spectrum are used to calculate 18 statistical parameters (range, mean, standard deviation, kurtosis, energy, energy entropy, kurtosis, crest factor, pulse factor, shape factor, skewness, power spectrum entropy, singular spectrum entropy, approximate entropy, sample entropy, fuzzy entropy, permutation entropy and envelope entropy). A total of 162 statistical features are obtained. Taking the inner ring fault sample data at 1000 r / min as an example, the 162 statistical features extracted are as follows: Figure 5 shown.

[0086] (2) Each set of original statistical feature data sets is input into the DBN network for iterative training to achieve adaptive mining of deep features. The network's hidden layer is set to 5 layers, the number of nodes in the first layer is 10, the second layer is 8, the third layer is 5, and the RBM learning rate is set to 0.001. After setting the parameters, the model finally extracts 100 deep features that can better reflect bearing faults through iterative optimization. The training output results are as follows: Figure 6 As shown in the figure, it can be seen that the feature discrimination and distribution characteristics are good.

[0087] (3) The deep features mined by the DBN network are input into RF for fault mode classification. First, the number of random forest decision trees is set to 80, the maximum depth of the decision tree is 12, and the number of optimization iterations of RF hyperparameter cross-validation is 5. Then, 40% of each working condition and its fault state are randomly selected as training data for RF training. After the training is completed, the actual fault label classification of the test samples is performed.

[0088] In addition to the RF classification method, classic machine learning classifiers (SVM, KNN, Softmax) are selected to perform fault state recognition and classification on Task 1, Task 2, and Task 3, respectively. The diagnosis results of each model under different working conditions are obtained, as shown in Table 2. The experimental results show that the fault diagnosis models constructed based on the four classifiers can all achieve effective fault pattern recognition and classification. Among them, the model constructed based on the RF classifier can achieve fault diagnosis performance that is significantly better than the models constructed by other classifiers. The fault diagnosis accuracy rates in Tasks 1-3 can reach 92.75%, 91.25%, and 94.79%, respectively.

[0089] Table 2

[0090]

[0091] To further verify the effectiveness of this embodiment's CNC machine tool spindle fault diagnosis method, this embodiment conducted a bearing fault diagnosis experiment based on an actual CNC machine tool. Using an accelerometer and a high-speed data acquisition card to collect raw data, four bearing states (normal, inner race fault, outer race fault, and rolling element fault) were set. The proposed fault diagnosis method, used to identify the fault state, achieved an average fault diagnosis accuracy of 92%.

[0092] In addition, the above-mentioned fault diagnosis results are semantically mapped with instances in the spindle fault knowledge base of this embodiment, and instance matching is performed using concept similarity. Taking the data-driven fault diagnosis "outer ring fault result (outer ring malfunction)" as an example, the concept similarity Sim(cg2c1) with the instance "quter_ringdefect" constructed in the knowledge base is 0.87, so it is determined that a semantic mapping relationship exists between the two. Next, the relevant attributes of the fault instance are edited and input into the ontology knowledge base for knowledge reasoning. Here, a custom SWRL rule is constructed, that is, the "Pitting" class in the fault phenomenon and the "Maintenance2" class in the fault resolution strategy class are defined to include the same fault cause "Fault_Cause". Therefore, the two can be semantically associated through "hasMaintenance". After constructing the class instance and editing the rules, the protege reasoning engine is launched to perform knowledge reasoning, which can realize fault diagnosis, maintenance and strategy guidance for the fault phenomenon. After reasoning, the pitting corrosion phenomenon of the bearing outer ring "hasMaintenance" has maintenance strategy 2. The specific content of maintenance strategy 2 is to improve the bearing processing quality, control the load, ensure lubrication and heat dissipation, and in summary, it realizes the maintenance strategy support for specific faults.

[0093] Based on the above, the embodiment of the present application also uses C# language, WPF form application framework, and SqlSever database technology to develop a CNC machine tool spindle fault diagnosis and health service management service system. The system mainly includes three modules: the first is to monitor and diagnose the machine tool bearing status based on data collected by various sensors, referred to as the data-driven monitoring and fault identification module, which mainly completes data storage, abnormal data alarm, dynamic display data, fault data processing and analysis, fault diagnosis and other functions. The second is based on the CNC machine tool spindle fault ontology and rule reasoning knowledge base, which mainly includes instance input, fault knowledge query and retrieval and other functions. The third is to combine the data-driven machine tool spindle bearing fault state identification results with ontology semantics to improve the knowledge service base for healthy operation management, mainly including linkage with the protege software background, iterating and improving the previously constructed ontology knowledge base, and also providing knowledge retrieval services based on fault phenomena, giving possible fault cause analysis and fault maintenance strategy decision references, and providing guarantees for the healthy operation of CNC machine tool spindle equipment.

[0094] The steps of the various methods above are divided only for the purpose of clear description. During implementation, they can be combined into one step or some steps can be split and decomposed into multiple steps. As long as they include the same logical relationship, they are all within the scope of protection of this patent. Adding insignificant modifications or introducing insignificant designs to the algorithm or process without changing the core design of the algorithm and process are all within the scope of protection of this patent.

[0095] Another embodiment of the present application relates to a fault diagnosis system for a CNC machine tool spindle. The implementation details of the fault diagnosis system for the CNC machine tool spindle of this embodiment are specifically described below. The following content is only for the convenience of understanding the implementation details and is not necessary for the implementation of this solution. The schematic diagram of the fault diagnosis system for the CNC machine tool spindle of this embodiment can be as follows: Figure 7 As shown, it includes: a signal acquisition module 701, a feature extraction module 702 and a fault diagnosis module 703.

[0096] Specifically, the signal acquisition module 701 is used to obtain a frequency domain signal corresponding to a real-time vibration signal of a spindle bearing of a CNC machine tool.

[0097] A feature extraction module 702 is configured to extract features from the frequency domain signal using a deep belief network to obtain high-dimensional features of the frequency domain signal. The high-dimensional features are used to indicate a target fault mode of the spindle bearing.

[0098] Among them, the deep belief network includes multiple stacked restricted Boltzmann machines and a BP classifier. Each restricted Boltzmann machine is used to extract the features of the frequency domain signal, and the direction from the bottom layer to the top layer of the multiple stacked restricted Boltzmann machines is the feature transfer direction of the deep belief network. The features extracted by each restricted Boltzmann machine are the input features of the next restricted Boltzmann machine to obtain the high-dimensional features of the frequency domain signal; the BP classifier is used to correct the network parameters of the deep belief network through reverse error propagation.

[0099] The fault diagnosis module 703 is used to select a preset fault mode that matches the target fault mode from a pre-built spindle fault knowledge base containing multiple preset fault modes, and use the fault solution strategy corresponding to the selected preset fault mode in the spindle fault knowledge base as the fault solution strategy corresponding to the target fault mode.

[0100] In one example, the signal acquisition module 701 is also used to decompose the real-time vibration signal based on the empirical mode decomposition method to obtain multiple intrinsic mode function components of the real-time vibration signal; and perform envelope detection on each intrinsic mode function component through Hilbert transform to obtain frequency domain signals of different time scales of the real-time vibration signal.

[0101] In one example, the fault diagnosis module 703 is also used to establish a semantic mapping relationship between the target fault mode and multiple preset fault modes based on a concept similarity algorithm; according to the semantic mapping relationship between the target fault mode and multiple preset fault modes, select the preset fault mode with the highest similarity to the target fault mode from the multiple preset fault modes.

[0102] It is not difficult to find that this embodiment is a system embodiment corresponding to the above-mentioned method embodiment, and this embodiment can be implemented in conjunction with the above-mentioned method embodiment. The relevant technical details and technical effects mentioned in the above-mentioned embodiment are still valid in this embodiment, and to reduce repetition, they are not repeated here. Accordingly, the relevant technical details mentioned in this embodiment can also be applied to the above-mentioned embodiment.

[0103] It is worth mentioning that all modules involved in this embodiment are logical modules. In actual applications, a logical unit can be a physical unit, a part of a physical unit, or a combination of multiple physical units. In addition, to highlight the innovation of this application, this embodiment does not include units that are not closely related to solving the technical problem proposed by this application. However, this does not mean that other units do not exist in this embodiment.

[0104] Another embodiment of the present application relates to a computer device, such as Figure 8As shown, it includes: at least one processor 801; and a memory 802 that is communicatively connected to the at least one processor 801; wherein the memory 802 stores instructions that can be executed by the at least one processor 801, and the instructions are executed by the at least one processor 801 to enable the at least one processor 801 to execute the fault diagnosis method of the CNC machine tool spindle in the above-mentioned embodiments.

[0105] The memory and processor are connected using a bus, which can include any number of interconnected buses and bridges. The bus connects various circuits of one or more processors and memories. The bus can also connect various other circuits such as peripheral devices, voltage regulators, and power management circuits. These are all well known in the art and are therefore not described further herein. The bus interface provides an interface between the bus and the transceiver. The transceiver can be a single component or multiple components, such as multiple receivers and transmitters, providing a unit for communicating with various other devices over a transmission medium. Data processed by the processor is transmitted over a wireless medium via an antenna. Furthermore, the antenna receives data and transmits it to the processor.

[0106] The processor is responsible for managing the bus and general processing, and can also provide various functions, including timing, peripheral interfaces, voltage regulation, power management, and other control functions. Memory can be used to store data used by the processor when performing operations.

[0107] Another embodiment of the present application relates to a computer-readable storage medium storing a computer program, which implements the above method embodiment when executed by a processor.

[0108] That is, those skilled in the art will understand that all or part of the steps in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a program, which is stored in a storage medium and includes a number of instructions for causing a device (which may be a single-chip microcomputer, chip, etc.) or a processor to execute all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, etc., various media that can store program code.

[0109] Those skilled in the art will appreciate that the above embodiments are specific embodiments for implementing the present application, and that in actual applications, various changes may be made thereto in form and detail without departing from the spirit and scope of the present application.

Claims

1. A method for diagnosing a spindle fault of a CNC machine tool, characterized in that: The method comprises: Obtain the frequency domain signal corresponding to the real-time vibration signal of the spindle bearing of the CNC machine tool; Performing feature extraction on the frequency domain signal through a deep belief network to obtain high-dimensional features of the frequency domain signal, wherein the high-dimensional features are used to indicate a target fault mode of the spindle bearing; The deep belief network includes multiple stacked restricted Boltzmann machines and a BP classifier, each restricted Boltzmann machine is used to extract the features of the frequency domain signal, and the direction from the bottom layer to the top layer of the multiple stacked restricted Boltzmann machines is the feature transfer direction of the deep belief network. The features extracted by each restricted Boltzmann machine are the input features of the next restricted Boltzmann machine to mine the high-dimensional features of the frequency domain signal; the BP classifier is used to correct the network parameters of the deep belief network through back error propagation; Selecting a preset fault mode that matches the target fault mode from a pre-built spindle fault knowledge base containing multiple preset fault modes, and using the fault resolution strategy corresponding to the selected preset fault mode in the spindle fault knowledge base as the fault resolution strategy corresponding to the target fault mode; The selecting of a preset fault mode that matches the target fault mode from a pre-built spindle fault knowledge base containing multiple preset fault modes includes: Establishing a semantic mapping relationship between the target fault mode and the multiple preset fault modes based on a concept similarity algorithm; selecting a preset fault mode with the highest similarity to the target fault mode from the multiple preset fault modes according to the semantic mapping relationship between the target fault mode and the multiple preset fault modes; The spindle fault knowledge base is constructed by the following steps: Constructing an ontology class of the spindle fault knowledge base, wherein the ontology class includes preset fault modes and fault resolution strategies of the spindle bearing; defining object properties of all objects in the ontology class to associate objects with corresponding relationships; and defining data properties of all objects in the ontology class; The entity class also includes the fault type, fault location, fault phenomenon and fault cause of the main shaft bearing, and the method further includes: According to the determined target failure mode and the failure resolution strategy corresponding to the target failure mode, the failure type, failure location, failure phenomenon and failure cause corresponding to the target failure mode are obtained.

2. The fault diagnosis method for a CNC machine tool spindle according to claim 1, wherein: The obtaining of a frequency domain signal corresponding to a real-time vibration signal of a spindle bearing of a CNC machine tool comprises: Decomposing the real-time vibration signal based on an empirical mode decomposition method to obtain a plurality of intrinsic mode function components of the real-time vibration signal; Envelope detection is performed on each eigenmode function component through Hilbert transform to obtain frequency domain signals of different time scales of the real-time vibration signal.

3. The fault diagnosis method for a CNC machine tool spindle according to claim 1, wherein: A preset failure mode of the main shaft bearing corresponds to multiple failure causes, and obtaining the failure cause corresponding to the target failure mode according to the target failure mode and the failure solution strategy corresponding to the target failure mode includes: Based on preset SWRL rules, knowledge reasoning is performed on the target failure mode and the failure resolution strategy corresponding to the target failure mode to obtain the failure cause corresponding to the target failure mode.

4. The fault diagnosis method for a CNC machine tool spindle according to any one of claims 1 to 3, characterized in that: The target failure mode is obtained by classifying the high-dimensional features based on a random forest algorithm.

5. A fault diagnosis system for a CNC machine tool spindle, characterized in that: The system comprises: A signal acquisition module is used to obtain the frequency domain signal corresponding to the real-time vibration signal of the spindle bearing of the CNC machine tool; a feature extraction module, configured to extract features from the frequency domain signal using a deep belief network to obtain high-dimensional features of the frequency domain signal, wherein the high-dimensional features are used to indicate a target fault mode of the spindle bearing; The deep belief network includes multiple stacked restricted Boltzmann machines and a BP classifier, each restricted Boltzmann machine is used to extract the features of the frequency domain signal, and the direction from the bottom layer to the top layer of the multiple stacked restricted Boltzmann machines is the feature transfer direction of the deep belief network. The features extracted by each restricted Boltzmann machine are the input features of the next restricted Boltzmann machine to mine the high-dimensional features of the frequency domain signal; the BP classifier is used to correct the network parameters of the deep belief network through back error propagation; a fault diagnosis module, configured to select a preset fault mode that matches the target fault mode from a pre-built spindle fault knowledge base containing multiple preset fault modes, and use the fault resolution strategy corresponding to the selected preset fault mode in the spindle fault knowledge base as the fault resolution strategy corresponding to the target fault mode; The fault diagnosis module is further configured to establish a semantic mapping relationship between the target fault mode and the multiple preset fault modes based on a concept similarity algorithm; and select, from the multiple preset fault modes, a preset fault mode having the highest similarity to the target fault mode based on the semantic mapping relationship between the target fault mode and the multiple preset fault modes; The spindle fault knowledge base is constructed by the following steps: constructing an ontology class of the spindle fault knowledge base, wherein the ontology class includes preset fault modes and fault resolution strategies of the spindle bearings; defining object properties of all objects in the ontology class to associate objects with corresponding relationships; and defining data properties of all objects in the ontology class; The ontology class also includes the fault type, fault location, fault phenomenon and fault cause of the main shaft bearing. The fault diagnosis module is also used to obtain the fault type, fault location, fault phenomenon and fault cause corresponding to the target fault mode based on the determined target fault mode and the fault solution strategy corresponding to the target fault mode.

6. A computer device, characterized in that: include: at least one processor; And, a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the fault diagnosis method for the CNC machine tool spindle as described in any one of claims 1 to 4.

7. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the fault diagnosis method for a CNC machine tool spindle according to any one of claims 1 to 4 is implemented.

Images