Bearing machining equipment operation quality detection system and method based on data analysis

Abstract

The invention discloses a bearing machining equipment operation quality detection system and method based on data analysis, and particularly relates to the technical field of industrial equipment.The method comprises the following steps that bearing machining equipment operation data are collected through a fixed time window and preprocessed, and a data set is generated; extracting statistical features and change features, performing stability analysis, and generating a production stability index; performing fault analysis in combination with a historical fault record to generate a fault risk index; the two indexes are input into a pre-training machine learning model, and the equipment machining precision is classified into high-precision machining or low-precision machining; if the machining is low-precision machining, an early warning mechanism is triggered, the sampling frequency is dynamically optimized according to the equipment state, and the monitoring efficiency and the fault prediction accuracy are improved; according to the invention, the operation state of the equipment can be comprehensively monitored, the stability of the equipment can be reflected, the data sampling frequency can be dynamically adjusted, more frequent monitoring can be provided when the risk is high or the stability is unstable, and the acquisition of key data is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial equipment, and more specifically, to a system and method for detecting the operating quality of bearing processing equipment based on data analysis. Background Art

[0002] Bearings are key components in mechanical equipment, and their processing quality directly affects the performance and service life of bearings. In modern industry, bearing processing equipment is widely used in high-precision industries such as automobiles, aerospace, and machine tools, so the requirements for processing quality are extremely strict. However, due to the long-term operation of processing equipment, problems such as component wear, vibration fluctuations, and mechanical deviations may lead to a decrease in processing accuracy, thereby affecting product quality.

[0003] Traditional equipment quality inspection is usually based on the change of a single indicator, but it cannot fully capture the operating status and potential faults of the equipment. The fixed sampling frequency cannot adapt to the changes in the operating status of the equipment, which may cause the abnormal information of high-risk equipment to be missed, or waste sampling resources under low-risk conditions. In addition, traditional methods can only identify equipment after obvious faults occur, making it difficult to predict and prevent the occurrence of faults in a timely manner, resulting in reduced production efficiency or downtime losses. Therefore, a bearing processing equipment operation quality inspection system and method based on data analysis is proposed here to solve the above problems. Summary of the invention

[0004] To achieve the above object, the present invention provides the following technical solutions: The method for detecting the running quality of bearing processing equipment based on data analysis includes the following steps: The operation data of the bearing processing equipment is collected through a fixed time window and preprocessed to obtain a bearing processing equipment data set; Based on the data set of bearing processing equipment, the statistical characteristics and change characteristics describing the working status of the equipment are extracted to perform stability analysis; Conduct fault analysis based on the bearing processing equipment data set and historical fault records of the bearing processing equipment; The stability analysis results and the failure analysis results are input into the pre-trained machine learning model to classify the equipment processing accuracy into high-precision processing and low-precision processing; Based on the classification results of the equipment processing accuracy, decide whether to issue a warning signal and optimize the sampling frequency of the operating data.

[0005] In a preferred embodiment, the stability analysis generates a production stability index, and the failure analysis generates a failure risk index.

[0006] In a preferred embodiment, the preprocessing includes data denoising, standardization and missing value filling to generate structured time series data.

[0007] In a preferred embodiment, the statistical characteristics and change characteristics describing the working state of the equipment are obtained, and the statistical characteristics refer to: obtaining the actual processing coordinates and the preset standard coordinates at each sampling moment of the fixed time window, and then calculating the Euclidean distance value between the actual processing coordinates and the preset standard coordinates, and then respectively calculating the average value of all Euclidean distance values, the standard deviation, and the skewness value; The variation feature refers to: obtaining the vibration signal of each processing equipment component in a fixed time window at each sampling moment, and then performing Fourier transform to obtain the spectrum signal, and obtaining the spectrum slope corresponding to the processing equipment component, summing up all the spectrum slopes at the same sampling moment to obtain the time series data of the fluctuation value, and then respectively calculating the mean value 2, standard deviation 2, and skewness value 2 corresponding to the time series data of the fluctuation value.

[0008] In a preferred embodiment, the logic for obtaining the production stability index is: Calculate the stability influence coefficient based on the mean value, standard deviation and skewness value: ; represents the average value of one, represents a standard deviation of one, represents a skewness value of one, , , are preset proportional factors. represents the stability influence coefficient of one; ; represents the average value 2, represents the standard deviation of two, represents the skewness value two, represents the stability influence coefficient two; The production stability index calculation formula is: ; , Represents the preset mapping coefficient, Represents the production stability index.

[0009] In a preferred embodiment, the logic for obtaining the fault risk index is: From the data set of the bearing processing equipment in the current time window, various preset processing parameters are obtained to obtain processing parameter group 1. From the historical fault records of the bearing processing equipment, multiple processing parameter groups 2 are obtained. The cosine similarity between processing parameter group 1 and each processing parameter group 2 is calculated respectively, and then the maximum cosine similarity is used as the risk value, and then substituted into the fault risk index calculation formula: ; represents the risk value, represents the risk trend function, Indicates the failure risk index.

[0010] In a preferred embodiment, the risk trend function refers to: ; Indicates the usage time since the last fault repair. Indicates a preset non-zero adjustment factor.

[0011] In a preferred embodiment, the classification of equipment processing accuracy into high-precision processing and low-precision processing refers to: The fault risk index and production stability index of the current time window are used as input variables of the pre-trained fuzzy logic device, and the equipment processing precision type is used as the output variable. The input variables are fuzzified and the values ​​of the input variables are converted into fuzzy sets. The output variables are fuzzified and the output variables are converted into fuzzy sets. Fuzzy rules are formulated to describe the adaptability of the processing precision types of each equipment under different data type combinations. The fuzzified input variables are inferred through fuzzy rules to obtain the classification type of bearing processing equipment. When the classification type is low-precision processing, the early warning mechanism is activated and a warning signal is issued.

[0012] In a preferred embodiment, optimizing and adjusting the operating data sampling frequency refers to: ; Indicates the preset basic sampling frequency, , are all preset non-zero adjustment coefficients, and , The sum of is one, Indicates the optimized and adjusted operating data sampling frequency, and the application acquires data in the next time window.

[0013] In a preferred embodiment, a bearing processing equipment operation quality detection system based on data analysis includes: Data acquisition module, which collects the operating data of bearing processing equipment through a fixed time window; A data preprocessing module preprocesses the data collected by the data acquisition module to obtain a bearing processing equipment data set; The stability analysis module extracts the statistical characteristics and change characteristics describing the working status of the equipment based on the bearing processing equipment data set, and performs stability analysis; Fault analysis module, which performs fault analysis based on the bearing processing equipment data set and the historical fault records of the bearing processing equipment; The precision classification module inputs the stability analysis results and the fault analysis results into the pre-trained machine learning model to classify the equipment processing accuracy into high-precision processing and low-precision processing; Fault warning module, when the classification type is low-precision processing, activates the warning mechanism and sends out a warning signal; The optimization and adjustment module optimizes and adjusts the sampling frequency of the operating data in the next time window.

[0014] Technical effects and advantages of the present invention: The present invention can comprehensively monitor the operating status of the equipment and reflect its stability by combining statistical features (such as mean, standard deviation, skewness) and change features (such as spectrum slope). The calculation of production stability index (PSI) and failure risk index (FRI) further enhances the comprehensiveness and accuracy of equipment status monitoring.

[0015] Based on the real-time status of the equipment, combined with the production stability index and the fault risk index, the present invention can dynamically adjust the data sampling frequency. The sampling frequency of high-risk equipment or unstable equipment will be automatically increased to obtain more monitoring data, which is helpful to timely discover potential faults; while in the case of low-risk or stable equipment, the sampling frequency will be reduced, thereby saving resources and avoiding unnecessary data processing.

[0016] By combining the stability and risk level of the equipment with the classification of machining accuracy, the present invention can adjust the production process according to the machining accuracy of the equipment to ensure that the machining accuracy of each equipment always meets the production requirements. When the equipment is classified as low-precision machining, the system will automatically start the early warning mechanism to prompt the operator to make adjustments or stop the machine for inspection to prevent production quality problems caused by equipment failure.

[0017] The present invention can provide more frequent monitoring when there is high risk or instability by dynamically adjusting the sampling frequency, ensuring the acquisition of key data. When the equipment is running stably, it reduces resource consumption, improves the efficiency of data collection, and reduces the storage and computing burden. Combining fuzzy logic reasoning and data analysis, the present invention provides smarter and more scientific decision support for equipment management. It can adjust equipment monitoring strategies in real time, helping managers optimize maintenance plans and production arrangements based on the health status of the equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to facilitate understanding by those skilled in the art, the present invention is further described below in conjunction with the accompanying drawings; Figure 1 This is a schematic diagram of the operating quality detection method of bearing processing equipment based on data analysis in the present invention.

[0019] Figure 2This is a schematic diagram of the bearing processing equipment operation quality detection system based on data analysis in the present invention. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0021] Reference Figure 1 - Figure 2 The following embodiments are obtained: Example 1: As the importance of industrial equipment in production lines gradually increases, the stability of equipment operation directly affects product quality and production efficiency. Bearings are core components in mechanical equipment, and the operating status of their processing equipment is crucial to the accuracy and performance of the final product.

[0022] Limitations of traditional monitoring methods: Single monitoring indicator: Traditional monitoring is usually based on a single indicator (such as vibration) and cannot fully capture the operating status of the equipment. Lack of dynamic adjustment: The fixed sampling frequency cannot adapt to the dynamic changes of equipment risks, which can easily lead to resource waste or data omissions. Early warning lag: Traditional methods have difficulty in identifying failure risks at an early stage, and measures can usually be taken only after the equipment has obvious failures.

[0023] Potential of data-driven methods: With the advancement of industrial equipment monitoring technology, more and more operating data can be collected and stored in real time. Data-driven analysis methods can combine historical fault records and use machine learning models to predict faults and classify processing accuracy.

[0024] The purpose of the present invention is to comprehensively monitor the equipment status through data analysis and improve the stability and reliability of equipment operation. The present invention calculates the fault risk index by combining the current operation data with the historical fault records, realizes the early prediction of faults, and thus reduces the risk of unplanned equipment downtime. Dynamic adjustment of the sampling frequency can effectively reduce the consumption of monitoring resources during the operation of the equipment, while ensuring the density of data collection under high-risk conditions. The present invention comprehensively quantifies the equipment operation status by combining the production stability index (PSI) and the fault risk index (FRI), and uses a machine learning model to classify high-precision processing and low-precision processing, thereby optimizing the decision-making process. In the industrial context, intelligent monitoring and predictive maintenance have become the core needs of modern industry. The present invention is proposed to meet this demand and improve the level of intelligence of equipment management through data-driven monitoring methods.

[0025] The present invention proposes a method for detecting the running quality of bearing processing equipment based on data analysis, comprising the following steps: The operation data of bearing processing equipment is collected and preprocessed through a fixed time window to obtain a bearing processing equipment data set; the operation data is the core basis for detecting and analyzing the working status of the equipment. Data preprocessing (such as denoising, standardization, and missing value completion) ensures the integrity, accuracy, and consistency of the data, providing a high-quality data set for subsequent analysis. Dividing the data by time window can capture the status characteristics of the equipment in a specific time period, which is helpful for dynamic monitoring.

[0026] Based on the data set of bearing processing equipment, the statistical characteristics and variation characteristics describing the working status of the equipment are extracted to perform stability analysis; the stability of equipment operation is evaluated through statistical characteristics (such as mean, standard deviation, and skewness value). Variation characteristics (such as the spectrum slope of the vibration signal) can capture the dynamic changes in the equipment status. Combining statistical characteristics with variation characteristics, a production stability index (PSI) is generated to intuitively quantify the operating stability of the equipment and help identify potential problems.

[0027] Based on the bearing processing equipment data set and the historical fault records of the bearing processing equipment, the fault analysis is performed; the fault analysis combines the current state with the historical fault records, and by calculating the similarity, it identifies whether the current operating state is close to the historical fault state. Generate a fault risk index (FRI) to evaluate the current fault risk level of the equipment. Through the historical fault trend function, the cumulative effect of the use time on the fault risk is considered to ensure a more accurate risk prediction.

[0028] The stability analysis results and the fault analysis results are input into the pre-trained machine learning model to classify the equipment processing accuracy into high-precision processing and low-precision processing; by combining PSI and FRI, the pre-trained model can classify the equipment processing accuracy and provide a more scientific basis for decision-making. High-precision processing equipment can continue to operate, while low-precision processing equipment will trigger an early warning mechanism to help detect problems in a timely manner and prevent further damage.

[0029] According to the classification results of the equipment processing accuracy, decide whether to issue an early warning signal and optimize the sampling frequency of the operation data. By reminding the operation and maintenance personnel through early warning signals, early prevention of faults can be achieved, reducing production downtime and maintenance costs. Sampling frequency optimization adjustment dynamically adjusts the sampling frequency according to the real-time risk status of the equipment (combined with PSI and FRI), ensuring more intensive data collection in high-risk situations, and reducing the sampling frequency in low-risk situations to reduce resource waste.

[0030] Stability analysis generates a production stability index, and failure analysis generates a failure risk index. The production stability index (PSI) is calculated by analyzing the statistical characteristics and change characteristics of the equipment during operation, and is used to quantitatively measure the stability of the equipment's operating status. The following is the specific significance of generating PSI: Quantifying equipment operation stability: Through the statistical characteristics of mean, standard deviation and skewness value, PSI can reflect the overall volatility and regularity of the equipment's operating status. A high PSI value indicates that the equipment's operating status is volatile and unstable; a low PSI value indicates that the equipment is running relatively smoothly. Early identification of potential anomalies: When the equipment's operating status begins to fluctuate but has not yet reached the level of failure, PSI can provide early warning to help maintenance personnel take measures before the problem spreads. For example, the change trend of PSI can indicate that the equipment may gradually enter an unstable stage. Improving processing quality: Equipment operation stability is the basis of high-precision processing. Generating PSI through stability analysis can provide an important basis for the classification of equipment processing accuracy, ensuring that the equipment operates in a stable state to meet processing quality requirements. Assisting dynamic monitoring and decision-making: As a dynamic monitoring indicator, PSI can help factory managers understand the operating status of equipment in real time.

[0031] The Failure Risk Index (FRI) is calculated by the similarity between the equipment operating parameters in the current time window and the historical fault records and the trend function of the equipment operation time, and is used to quantify the failure risk of the equipment. The following is the specific significance of generating FRI: Evaluate the risk of equipment failure: FRI can measure the closeness of the current equipment status to the historical fault status. The higher the similarity, the greater the risk value. The larger the FRI, the higher the failure risk of the current operating status of the equipment. Predict equipment failure trends: By combining the influence of equipment usage time (such as risk trend function), FRI can dynamically reflect the risk accumulation of equipment after long-term operation. The longer the equipment runs, the higher the FRI will be with the increase of usage time, providing a scientific basis for equipment maintenance. Support preventive maintenance: Through real-time monitoring of FRI, managers can identify potential failures in advance and arrange preventive maintenance to avoid equipment downtime or product scrapping due to sudden failures. This greatly reduces equipment maintenance costs and production losses. Ensure the continuity of the production line: In the manufacturing industry, equipment failures usually lead to the shutdown of the entire production line. By monitoring FRI in real time, managers can formulate maintenance plans to ensure the stable operation of the production line. Data-driven intelligent decision-making: FRI provides a data-based intelligent fault prediction method by comparing current operating data with historical fault records, providing a scientific basis for the traditional empirical maintenance model.

[0032] The synergistic significance of the production stability index (PSI) and the failure risk index (FRI): Comprehensive evaluation of equipment operation status: PSI evaluates the stability of the equipment, and FRI evaluates the failure risk of the equipment. The combination of the two can fully reflect the operation status of the equipment. For example, when the equipment is stable but the FRI is high, it may indicate that the equipment is about to fail; when the equipment is unstable and the FRI is high, it indicates that the risk of failure is higher. Intelligent classification and maintenance: PSI and FRI are input into the machine learning model as input variables to intelligently classify the equipment processing accuracy (high-precision processing or low-precision processing). According to the classification results, managers can perform targeted maintenance or adjustments on the equipment. Optimization of production and equipment management: Combining PSI and FRI can optimize production planning and equipment management. For example, reduce the load of unstable equipment or arrange preventive maintenance to avoid greater losses caused by failures. Dynamic adjustment of sampling frequency: Adjust the data sampling frequency through the changing trends of PSI and FRI, sample more intensively for high-risk equipment, and reduce the sampling of low-risk equipment, so as to achieve efficient use of resources.

[0033] Preprocessing includes data denoising, standardization, and missing value completion to generate structured time series data. Data denoising is to eliminate random noise or outliers in the original data and retain key information that reflects the true operating status of the equipment. The collected original data may be affected by sensor errors, electromagnetic interference, or environmental changes, and may contain noise. Denoising can remove these irrelevant interferences and make the data more accurate. Undenoised data may lead to misjudgment, and the noise may be mistakenly regarded as abnormal equipment status. Denoising can reduce misjudgment and improve the reliability of fault analysis and stability analysis. Noise can mask the actual change trend in the data. After denoising, the real characteristics of equipment operation can be extracted more clearly to provide support for subsequent feature analysis.

[0034] Data standardization is the process of unifying data of different dimensions or ranges so that they have the same scale, thereby eliminating the dimensional differences between different features. The data may contain features of different dimensions (such as the acceleration of a vibration signal). Standardization can eliminate dimensional differences and make these features comparable when analyzed.

[0035] Filling missing values ​​is to fill in missing data caused by sensor failure, communication interruption or other reasons in data collection. Missing values ​​in time series data will lead to discontinuity during analysis. Filling missing values ​​can ensure the integrity of time series data and avoid information loss. Missing values ​​will lead to deviations when calculating characteristic values ​​(such as mean, standard deviation, etc.), affecting the accuracy of analysis results. Filling missing values ​​can reduce these effects. Equipment operation data has the characteristics of continuity. Filling missing values ​​can retain the dynamic characteristics of data, making subsequent status analysis more realistic. Time series data is structured data arranged in chronological order, which can reflect the changes in equipment operation status over time. After generating structured time series data, statistical characteristics (mean, standard deviation, skewness) and dynamic change characteristics (vibration spectrum, fluctuation value, etc.) of equipment operation can be extracted from it. Time series data can help identify trends and patterns in equipment operation status, support real-time monitoring and fault trend prediction. Structured time series data is easy to compare with historical fault records, identify the similarity between the current state and historical fault patterns, and support fault analysis. Structured time series data is consistent and standardized, and can be directly used as input for machine learning models, improving model training efficiency and prediction accuracy.

[0036] Obtain the statistical characteristics and change characteristics that describe the working status of the equipment. The statistical characteristics refer to: obtaining the actual processing coordinates and the preset standard coordinates at each sampling moment in the fixed time window, and then calculating the Euclidean distance value between the actual processing coordinates and the preset standard coordinates, and then respectively obtaining the average value, standard deviation, and skewness value of all Euclidean distance values; the statistical characteristics are the characteristic values ​​calculated by analyzing the degree of deviation between the actual processing coordinates of the equipment and the preset standard coordinates in the fixed time window, including: average value (μ1): indicates the average level of deviation in the processing process. Standard deviation (σ1): reflects the volatility of the processing process. Skewness value (γ1): reflects the symmetry of the distribution of processing deviations.

[0037] Significance: Quantifying machining accuracy: Euclidean distance calculation reflects the degree to which the machining coordinates deviate from the standard coordinates. The average value can intuitively evaluate the overall level of machining accuracy. Capturing the stability of equipment operation: The standard deviation reflects the stability of the equipment's operating status by evaluating the volatility of the machining coordinates. Large fluctuations may indicate that the equipment is abnormal, and the equipment runs more stably when the fluctuations are small. Diagnosing deviation patterns: The skewness value can reveal the tendency of the machining coordinates to deviate from the direction. For example, positive skewness may indicate that the machining results systematically deviate from the positive direction, while negative skewness indicates deviation from the negative direction, providing a basis for failure mode analysis. Evaluating long-term stability: The time series of statistical characteristics can reveal changes in the stability of the equipment's long-term operation, providing support for predictive maintenance and process improvements.

[0038] The change feature refers to: obtaining the vibration signal of each processing equipment component in a fixed time window at each sampling moment, then performing Fourier transform to obtain the spectrum signal, and obtaining the spectrum slope corresponding to the processing equipment component, summing up all the spectrum slopes at the same sampling moment, and obtaining the time series data of the fluctuation value, and then respectively calculating the mean value 2, standard deviation 2, and skewness value 2 corresponding to the time series data of the fluctuation value. Mean value 2 (μ2): reflects the overall level of vibration fluctuation. Standard deviation 2 (σ2): measures the amplitude of change in vibration fluctuation. Skewness value 2 (γ2): describes the symmetry of the distribution of vibration fluctuations.

[0039] Significance: Revealing the dynamic operating status: Vibration signals can reflect the dynamic characteristics of equipment components in operation. Extracting slopes through spectrum analysis can capture the rapidly changing characteristics of equipment operation. Detecting potential faults: Significant changes in vibration fluctuations are often early signs of equipment abnormalities or failures. The potential risk of equipment failure can be identified by the changing trends of mean value 2 and standard deviation 2. Evaluating the smoothness of equipment operation: Mean value 2 and standard deviation 2 can comprehensively reflect the smoothness of equipment operation. For example, when the vibration fluctuation is small, the equipment runs more smoothly, otherwise it indicates that the equipment is not in good operating condition. Analyzing the synergy of mechanical components: The slopes of vibration signals of different components comprehensively reflect the synergistic relationship between mechanical components. If the spectrum slopes of certain components change significantly, it may indicate that the operating status of these components is inconsistent with other components, indicating potential problems.

[0040] The logic for obtaining the production stability index is: Calculate the stability influence coefficient based on the mean value, standard deviation and skewness value: ; It represents the average value, which indicates the average level of deviation of the machining coordinates from the standard coordinates within a fixed time window, reflecting the overall situation of machining accuracy. The larger the mean value, the more serious the deviation. It represents the standard deviation of 1, which indicates the fluctuation range of the processing coordinates and reflects the stability of the equipment operation status. The larger the standard deviation, the greater the fluctuation of the equipment operation. Indicates a skewness value of one, indicating the asymmetry of the distribution of machining coordinate deviations. A large skewness value indicates that the deviations may have a systematic tendency (such as continuous positive or negative bias). , , are preset proportional factors. represents the stability influence coefficient of one; Clamping the skewness values ​​to the range of -1 to 1 ensures smooth effects of skewness on stability.

[0041] ; It represents the average value 2, which represents the average spectrum slope of the vibration signal, reflecting the overall vibration level of the equipment. The larger the average value, the more unstable the equipment operation state. It represents the standard deviation 2, which indicates the fluctuation amplitude of the slope of the vibration signal spectrum, reflecting the degree of change of the vibration state of the equipment. A larger standard deviation indicates the unsteadiness of the equipment operation. It indicates the skewness value 2, which indicates the asymmetry of the spectrum slope distribution and describes whether the vibration signal has bias. The abnormal change of the skewness value may indicate a fault trend in a specific direction. represents the stability influence coefficient two; The production stability index calculation formula is: ; , Represents the preset mapping coefficient, which is used to map the parameter value to a standardized value range. Represents the production stability index. Stability influence coefficients 1 (WD1) and 2 (WD2) start from statistical characteristics and change characteristics respectively, and balance the contribution between characteristics through nonlinear transformation (logarithm, hyperbolic function, etc.) to avoid excessive influence of a certain feature. Through the square and nonlinear processing of the spectral characteristics in WD2, the dynamic change characteristics of equipment operation are captured more sensitively. The final PSI formula uses the tangent function (tan) to further amplify the combined effect of stability influence coefficients WD1 and WD2, making the instability characteristics more significant.

[0042] The logic for obtaining the fault risk index is: From the data set of the bearing processing equipment in the current time window, various preset processing parameters are obtained to obtain processing parameter group 1. From the historical fault records of the bearing processing equipment, multiple processing parameter groups 2 are obtained. The cosine similarity between processing parameter group 1 and each processing parameter group 2 is calculated respectively, and then the maximum cosine similarity is used as the risk value, and then substituted into the fault risk index calculation formula: ; Indicates the risk value, which indicates the similarity between the current processing parameter group and the historical fault record. It is calculated by cosine similarity. The higher the similarity, the closer the current equipment status is to the historical fault status. It represents the risk trend function, which indicates the impact of equipment operation time on failure risk. The longer the time, the higher the failure risk. Represents the failure risk index. FRI combines the dynamic characteristics of equipment operation data with historical failure records, and can quantify the current failure risk of the equipment in a numerical way. By calculating the similarity between the current processing parameters and the historical failure parameters, it is accurately evaluated whether the equipment state is close to the known failure mode. The maximum similarity of the risk value in the historical data can be used to determine whether the equipment has potential failures. Even if the equipment has not yet shown obvious signs of failure, if the risk value is high, FRI can provide early warnings in time to help operation and maintenance personnel take measures in advance. The risk trend function takes into account the cumulative effect of equipment usage time, indicating that the longer the equipment is in operation, the greater the possibility of failure. This design conforms to the actual law of equipment failure and provides a scientific basis for equipment maintenance. FRI can dynamically monitor the risk of equipment failure. As an important indicator of predictive maintenance, it helps managers repair equipment in time before failure and reduce downtime. The higher the FRI value, the more it is necessary to focus on monitoring the equipment or arrange maintenance plans.

[0043] The risk trend function is: ; Indicates the usage time since the last fault repair. Represents a preset non-zero adjustment factor. T represents the time that the equipment has been running continuously since the last repair was completed. As the equipment running time T increases, the aging and wear of various parts of the equipment will gradually accumulate, and the risk of failure will also increase. As a time variable, T directly reflects the cumulative state of equipment operation and is the core driving factor of the risk trend function. λ is a constant used to adjust the degree of influence of equipment running time on the risk of failure. The size of λ determines the speed of risk growth: when λ is large, the risk increases exponentially with time. When λ is small, the risk increases slowly with time. Under different equipment or working conditions, the value of λ can be adjusted according to the actual situation to ensure the adaptability of the function. The exponential function simulates the nonlinear cumulative effect of risk over time, that is, the speed of risk growth will continue to accelerate over time. This design conforms to the actual law of equipment failure: the risk of equipment is low in the early stage of operation, but as the running time increases, the risk shows an accelerating upward trend. Equipment that has been running for a long time usually experiences problems such as component wear, fatigue aging, etc. These problems will accumulate over time, resulting in a gradual increase in the risk of failure. By associating the running time T with the risk index, the contribution of the time accumulation effect to the risk of equipment failure is quantified. The risk trend function provides dynamic adjustment capabilities for the calculation of the FRI. Even if the current state of the equipment is not very similar to the historical fault records, if the operating time T is long, the risk trend function will amplify the risk index, thereby indicating potential risks.

[0044] The classification of equipment processing accuracy into high-precision processing and low-precision processing refers to: The fault risk index and production stability index of the current time window are used as input variables of the pre-trained fuzzy logic device, and the equipment processing precision type is used as the output variable. The input variables are fuzzified and the values ​​of the input variables are converted into fuzzy sets. The output variables are fuzzified and the output variables are converted into fuzzy sets. Fuzzy rules are formulated to describe the adaptability of the processing precision types of each equipment under different data type combinations. The fuzzified input variables are inferred through fuzzy rules to obtain the classification type of bearing processing equipment. When the classification type is low-precision processing, the early warning mechanism is activated and a warning signal is issued.

[0045] When using the pre-trained fuzzy logic, define the input variables, including: Fault risk index: quantifies the similarity between the current operating state of the equipment and the historical fault records and the time accumulation risk. Production stability index: quantifies the stability of the equipment operation process, reflecting the equipment processing coordinate deviation and dynamic vibration characteristics.

[0046] The specific values ​​of the input variables are converted into fuzzy sets, which are expressed in the form of linguistic variables, such as "low", "medium", etc.: Failure risk index: low risk, medium risk, high risk; production stability index: stable, medium stable, unstable. Through the membership function, the value of the input variable is mapped to the membership degree in the fuzzy set, and the membership degree ranges from 0 to 1, indicating the degree of belonging of the input value to each fuzzy set.

[0047] Define output variables: The output variable is the type of equipment processing accuracy, expressed as a language variable: High-precision processing: The equipment is in good operating condition, and the processing results meet the high-precision requirements. Low-precision processing: The equipment is in poor operating condition, and the processing results may not meet the accuracy requirements. Fuzzy processing: Similar to the input variables, the classification results of the output variables are also expressed by fuzzy sets: high precision, medium precision, and low precision. The fuzzy results of the output variables are used for comprehensive reasoning, and ultimately provide the degree of membership of the equipment processing accuracy classification.

[0048] Formulation of fuzzy rules: Fuzzy rules describe the adaptability of different input variable combinations to output variables. For example: if the failure risk index is "low risk" and the production stability index is "stable", the equipment processing accuracy is "high precision". If the failure risk index is "high risk" and the production stability index is "unstable", the equipment processing accuracy is "low precision". Fuzzy rules are usually generated by expert experience or data training, covering all possible input combinations.

[0049] Fuzzy reasoning: Rule matching: According to the fuzzy set and membership of the input variable, the fuzzy logic device matches the rules that match it. The contribution of each rule to the output variable is determined by the membership of the input variable. Membership synthesis: The fuzzy logic device synthesizes the results of multiple rules to obtain the membership of the output variable in each fuzzy set. The synthesis method often uses the "maximum minimum method" or "weighted average method".

[0050] Defuzzification: Defuzzification: Convert the results of fuzzy reasoning (fuzzy sets and membership of output variables) into specific values. Defuzzification methods include "center of gravity method" or "maximum membership method". The defuzzification results are used for final classification. Output classification: According to the results of defuzzification, the equipment processing accuracy is divided into: High-precision processing: The equipment runs stably, the risk is low, and the processing results meet the requirements. Low-precision processing: The equipment runs with large fluctuations, the risk is high, and the processing results do not meet the requirements.

[0051] Optimizing the sampling frequency of operating data means: ; Indicates the preset basic sampling frequency, that is, the sampling frequency required by the device in normal operation. , are preset non-zero adjustment coefficients to control the influence of the production stability index (PSI) and the failure risk index (FRI) on the sampling frequency, and , The sum of is one, Indicates the sampling frequency of the optimized and adjusted operation data, which is applied to the next time window for data acquisition. The production stability index reflects the stability of the equipment operation. The higher the PSI, the greater the fluctuation of the equipment and the stronger the instability. The fault risk index quantifies the fault risk level of the current operation state of the equipment. The higher the FRI, the closer the equipment is to the potential fault state. The formula incorporates the production stability index (PSI) and the fault risk index (FRI) into the calculation of the sampling frequency, so that the sampling frequency can be dynamically adjusted according to the changes in the equipment operation state: When the equipment volatility is high (higher PSI): the sampling frequency is increased to capture subtle changes in the equipment operation with a higher sampling density. When the fault risk is high (higher FRI): the sampling frequency is increased to monitor the equipment status in real time to avoid the expansion of faults. When the equipment status is stable and the fault risk is low: the sampling frequency is appropriately reduced to reduce unnecessary data collection and processing costs. High sampling frequency can provide more intensive operation data, which helps to capture subtle anomalies in equipment operation and improve the accuracy of fault detection and status monitoring. Through dynamic sampling, the drastic fluctuations and potential risks of equipment status can be captured more timely. When the equipment is stable, the sampling frequency is reduced, the amount of data collected is reduced, and the storage and processing costs are reduced. Dynamic allocation of resources improves the efficiency of the monitoring system and focuses monitoring resources on high-risk equipment or high-volatility periods. Dynamic adjustment of the sampling frequency can help operation and maintenance personnel grasp the changes in equipment status in real time and provide accurate data support for predictive maintenance. When the sampling frequency is increased, potential faults can be discovered earlier and the probability of sudden failures can be reduced.

[0052] Embodiment 2: A bearing processing equipment operation quality detection system based on data analysis, comprising: Data acquisition module, which collects the operating data of bearing processing equipment through a fixed time window; A data preprocessing module preprocesses the data collected by the data acquisition module to obtain a bearing processing equipment data set; The stability analysis module extracts the statistical characteristics and change characteristics describing the working status of the equipment based on the bearing processing equipment data set, and performs stability analysis; Fault analysis module, which performs fault analysis based on the bearing processing equipment data set and the historical fault records of the bearing processing equipment; The precision classification module inputs the stability analysis results and the fault analysis results into the pre-trained machine learning model to classify the equipment processing accuracy into high-precision processing and low-precision processing; Fault warning module, when the classification type is low-precision processing, activates the warning mechanism and sends out a warning signal; The optimization and adjustment module optimizes and adjusts the sampling frequency of the operating data in the next time window.

[0053] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0054] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0055] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0056] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0057] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for detecting the operation quality of bearing processing equipment based on data analysis, characterized in that: The following steps are involved: The operation data of the bearing processing equipment is collected through a fixed time window and preprocessed to obtain a bearing processing equipment data set; Based on the data set of bearing processing equipment, the statistical characteristics and change characteristics describing the working status of the equipment are extracted to perform stability analysis; Conduct fault analysis based on the bearing processing equipment data set and historical fault records of the bearing processing equipment; The stability analysis results and the failure analysis results are input into the pre-trained machine learning model to classify the equipment processing accuracy into high-precision processing and low-precision processing; Based on the classification results of the equipment processing accuracy, decide whether to issue a warning signal and optimize the sampling frequency of the operating data.

2. The method for detecting the operation quality of bearing processing equipment based on data analysis according to claim 1 is characterized in that: Stability analysis generates a production stability index, and failure analysis generates a failure risk index.

3. The method for detecting the operation quality of bearing processing equipment based on data analysis according to claim 2 is characterized in that: Preprocessing includes data denoising, standardization, and missing value filling to generate structured time series data.

4. The method for detecting the running quality of bearing processing equipment based on data analysis according to claim 3 is characterized in that: Obtain statistical features and change features that describe the working status of the equipment. The statistical features refer to: obtaining the actual processing coordinates and the preset standard coordinates at each sampling moment in a fixed time window, then calculating the Euclidean distance value between the actual processing coordinates and the preset standard coordinates, and then respectively calculating the average value, standard deviation, and skewness value of all Euclidean distance values; The variation feature refers to: obtaining the vibration signal of each processing equipment component in a fixed time window at each sampling moment, and then performing Fourier transform to obtain the spectrum signal, and obtaining the spectrum slope corresponding to the processing equipment component, summing up all the spectrum slopes at the same sampling moment to obtain the time series data of the fluctuation value, and then respectively calculating the mean value 2, standard deviation 2, and skewness value 2 corresponding to the time series data of the fluctuation value.

5. The method for detecting the running quality of bearing processing equipment based on data analysis according to claim 4 is characterized in that: The logic for obtaining the production stability index is: Calculate the stability influence coefficient based on the mean value, standard deviation and skewness value: ; represents the average value of one, represents a standard deviation of one, represents a skewness value of one, , , are preset proportional factors. represents the stability influence coefficient of one; ; represents the average value 2, represents the standard deviation of two, represents the skewness value two, represents the stability influence coefficient two; The calculation formula of production stability index is: ; , Represents the preset mapping coefficient, Represents the production stability index.

6. The method for detecting the running quality of bearing processing equipment based on data analysis according to claim 5 is characterized in that: The logic for obtaining the fault risk index is: From the data set of the bearing processing equipment in the current time window, various preset processing parameters are obtained to obtain processing parameter group 1. From the historical fault records of the bearing processing equipment, multiple processing parameter groups 2 are obtained. The cosine similarity between processing parameter group 1 and each processing parameter group 2 is calculated respectively, and then the maximum cosine similarity is used as the risk value, and then substituted into the fault risk index calculation formula: ; represents the risk value, represents the risk trend function, Indicates the failure risk index.

7. The method for detecting the running quality of bearing processing equipment based on data analysis according to claim 6 is characterized in that: The risk trend function is: ; Indicates the usage time since the last fault repair. Indicates a preset non-zero adjustment factor.

8. The method for detecting the running quality of bearing processing equipment based on data analysis according to claim 7 is characterized in that: The classification of equipment processing accuracy into high-precision processing and low-precision processing refers to: The fault risk index and production stability index of the current time window are used as input variables of the pre-trained fuzzy logic device, and the equipment processing precision type is used as the output variable. The input variables are fuzzified and the values ​​of the input variables are converted into fuzzy sets. The output variables are fuzzified and the output variables are converted into fuzzy sets. Fuzzy rules are formulated to describe the adaptability of the processing precision types of each equipment under different data type combinations. The fuzzified input variables are inferred through fuzzy rules to obtain the classification type of bearing processing equipment. When the classification type is low-precision processing, the early warning mechanism is activated and a warning signal is issued.

9. The method for detecting the running quality of bearing processing equipment based on data analysis according to claim 8 is characterized in that: Optimizing the sampling frequency of operating data means: ; Indicates the preset basic sampling frequency, , are all preset non-zero adjustment coefficients, and , The sum of is one, Indicates the optimized and adjusted operating data sampling frequency, and the application acquires data in the next time window.

10. A bearing processing equipment operation quality detection system based on data analysis, used to implement the bearing processing equipment operation quality detection method based on data analysis according to any one of claims 1 to 9, characterized in that: include: Data acquisition module, which collects the operating data of bearing processing equipment through a fixed time window; A data preprocessing module preprocesses the data collected by the data acquisition module to obtain a bearing processing equipment data set; The stability analysis module extracts the statistical characteristics and change characteristics describing the working status of the equipment based on the bearing processing equipment data set, and performs stability analysis; Fault analysis module, which performs fault analysis based on the bearing processing equipment data set and the historical fault records of the bearing processing equipment; The precision classification module inputs the stability analysis results and the fault analysis results into the pre-trained machine learning model to classify the equipment processing accuracy into high-precision processing and low-precision processing; Fault warning module, when the classification type is low-precision processing, activates the warning mechanism and sends out a warning signal; The optimization and adjustment module optimizes and adjusts the sampling frequency of the operating data in the next time window.

Images