Electromechanical data analysis method and system based on digital platform

Abstract

The invention discloses an electromechanical data analysis method and system based on a digital platform. The method comprises the following steps: collecting multi-source data; data processing: analyzing the parameter information of each component to obtain a spindle abnormal coefficient and a motor abnormal coefficient; performing comprehensive processing on the spindle abnormal coefficient and the motor abnormal coefficient to obtain an evaluation coefficient; correlation analysis: acquiring image information of the grinding wheel, and analyzing based on the image information to obtain a grinding wheel coefficient; and performing evaluation processing. According to the method, multi-source data is collected, operation parameters and state information of the grinding machine main shaft, the motor, the grinding wheel and other parts of the electromechanical equipment are comprehensively analyzed, abnormal coefficients and evaluation coefficients are calculated, the operation condition of the equipment can be comprehensively and accurately judged, potential fault hidden dangers are found in time, and corresponding maintenance measures are taken before faults occur; production interruption caused by equipment faults is avoided, stability and high efficiency of production are effectively guaranteed, and production efficiency and economic benefits are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of electromechanical equipment data analysis, and in particular to an electromechanical data analysis method and system based on a digital platform. Background Art

[0002] In modern industrial production, the stable operation of electromechanical equipment such as grinding machines is crucial to ensuring production efficiency and product quality.

[0003] For example, during the operation of a grinder in electromechanical equipment, various components may experience varying degrees of wear and failure. These problems may lead to decreased equipment performance, unstable product quality, and even safety accidents.

[0004] Traditional electromechanical equipment monitoring and analysis methods often rely on manual inspections and simple sensor data, making it difficult to comprehensively and accurately assess the equipment's operating status and potential risks. Existing data analysis methods typically simply compare monitoring data with preset fixed thresholds and issue alerts when the data exceeds the threshold. This approach lacks in-depth data mining and comprehensive analysis, and fails to consider the interrelationships between various parameters and the dynamic changes in equipment operating status. For example, there are inherent connections between parameters such as motor temperature and noise. An abnormality in a single parameter may be caused by multiple factors. Traditional methods are unable to analyze these complex relationships, making them prone to misjudgments or omissions, and unable to accurately assess potential risks to the equipment. Therefore, a more scientific and efficient electromechanical data analysis method and system is needed to achieve real-time monitoring, accurate evaluation and timely warning of electromechanical equipment. Summary of the Invention

[0005] The purpose of the present invention is to solve the above problems and to propose a method and system for electromechanical data analysis based on a digital platform.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions: A method for analyzing electromechanical data based on a digital platform, comprising: Multi-source data collection: Obtain parameter information of each component of the electromechanical equipment grinder during operation, including spindle parameter information and motor parameter information; Data processing: After analyzing the parameter information of each component, the spindle abnormality coefficient and the motor abnormality coefficient are obtained; after comprehensive processing of the spindle abnormality coefficient and the motor abnormality coefficient, the evaluation coefficient is obtained; Correlation analysis: obtain the image information of the grinding wheel and obtain the grinding wheel coefficient based on the image information analysis; Evaluation and processing: respectively compare the evaluation coefficient and the grinding wheel coefficient with their corresponding preset reference thresholds, perform corresponding operations based on the comparison results, and display the analysis results on the interface of the digital platform.

[0007] Preferably, before obtaining the image information of the grinding wheel, the method further includes: The number of all processed parts within a preset time period is obtained, and the inspectors perform quality inspection on each part and count the number of qualified parts. The number of qualified parts is divided by the number of all processed parts within the time period to obtain the part qualification rate. The part qualification rate is compared with the preset qualification rate. If the part qualification rate is less than the preset qualification rate, the image information acquisition operation of the grinding wheel is triggered.

[0008] Preferably, the process of obtaining the spindle anomaly coefficient includes: Obtain image information of the spindle, and segment the image information of the journal, shaft end, and shaft body from the image information of the spindle. Extract features from the image information of the journal, shaft end, and shaft body in turn, including wear and crack related features. Mark the extracted features as wear areas and crack areas. Obtaining the number of pixels of the marked wear area and crack area, converting the number of pixels of the wear area and crack area into actual area to obtain the wear area and crack area; Obtain the wear area and crack area of the journal, shaft end, and shaft body in sequence, and divide the wear areas of the journal, shaft end, and shaft body by the total area of the journal, shaft end, and shaft body to obtain the journal wear ratio, shaft end wear ratio, and shaft body wear ratio; Divide the crack areas of the journal, shaft end, and shaft body by the total area of the journal, shaft end, and shaft body to obtain the journal crack ratio, shaft end crack ratio, and shaft body crack ratio; The wear ratio and crack ratio of the journal, shaft end and shaft body are processed comprehensively to obtain the journal abnormal value, shaft end abnormal value and shaft body abnormal value; The spindle anomaly coefficient is obtained by calculating the journal anomaly value, shaft end anomaly value and shaft body anomaly value.

[0009] Preferably, the process of obtaining the motor abnormality coefficient includes: Obtain the current value monitored at each monitoring time point during the motor's working period; preset a current rated value, compare the current value monitored at each time point with the preset current rated value, and record the current value exceeding the preset current rated value as an exceedance value; After accumulating the various exceedance values, the average is calculated to obtain the exceedance mean; The motor is divided into regions according to the preset area, and the motor temperature value of each region at each monitoring time point is obtained in turn; Preset temperature tolerance range, compare the motor temperature value of each area at each monitoring time point with the preset temperature operating range, and record the temperature that is not within the preset temperature tolerance range as abnormal temperature; In the time series, among the monitoring time points corresponding to all motor temperature values, the difference between the monitoring time points corresponding to adjacent abnormal temperatures is calculated to obtain the abnormal duration, and all abnormal durations are accumulated to obtain the duration. Obtain the duration of each area in turn, and perform comprehensive processing on the duration of each area to obtain the different temperature duration; Obtain the noise decibels of the motor at each monitoring time point, preset a standard noise decibel, accumulate the noise decibels that are greater than the preset standard noise decibels, and calculate the average to obtain the excess decibel average; The motor abnormality coefficient is obtained by comprehensively processing the exceedance mean, duration, and excess decibel mean.

[0010] Preferably, the evaluation coefficient is obtained after comprehensive processing of the main shaft abnormality coefficient and the motor abnormality coefficient, specifically including: normalizing the main shaft abnormality coefficient and the motor abnormality coefficient, constructing an ellipse with the main shaft abnormality coefficient and the motor abnormality coefficient as the major semi-axis and minor semi-axis of the ellipse respectively, and calculating the area of the ellipse and recording it as the evaluation coefficient.

[0011] Preferably, the process of obtaining the image information of the grinding wheel and obtaining the grinding wheel coefficient based on the image information analysis is as follows: Obtaining a preset number of grinding wheel side image information, and obtaining a side profile image of each grinding wheel image after preprocessing the image; From the side profile, take the upper contour line of the grinding wheel as the starting point, draw a preset number of distance segments perpendicular to the lower contour line of the grinding wheel, and extract the maximum distance segment and the minimum distance segment from each distance segment; The maximum distance line segment and the minimum distance line segment in each side profile of the grinding wheel are obtained in sequence, and arranged in descending order according to the value. The maximum distance line segment and the minimum distance line segment are extracted, and the wear extreme difference value is obtained by calculating the difference between the maximum distance line segment and the minimum distance line segment. Obtain images of the front and back sides of the grinding wheel, and divide the front and back sides of the grinding wheel into regions with preset areas in turn. Use a brightness measurement tool to measure the brightness of each region on the front and back sides of the grinding wheel. Each region is measured for a preset number of times, and the average value is recorded as the brightness value. Thus, the brightness values of each area on the front and back sides of the grinding wheel are obtained; the areas corresponding to the maximum brightness value and the minimum brightness value are extracted; and the difference between the maximum brightness value and the minimum brightness value is recorded as the deviation value; Marking the areas corresponding to the maximum brightness value and the minimum brightness value as the maximum brightness area and the minimum brightness area respectively; and obtaining the area value after analyzing and processing the maximum brightness area and the minimum brightness area; The grinding wheel coefficient is obtained by weighted calculation of the wear extreme value, deviation value and area value.

[0012] Preferably, the evaluation coefficient and the grinding wheel coefficient are respectively compared with their corresponding preset reference thresholds. If both the evaluation coefficient and the grinding wheel coefficient are smaller than the corresponding preset reference thresholds, a prediction analysis of the evaluation coefficient is triggered to obtain a prediction coefficient. The corresponding risk levels are matched according to the differences between the evaluation coefficient and the grinding wheel coefficient and their corresponding preset reference thresholds.

[0013] Preferably, the process of obtaining the prediction coefficient includes: Get the evaluation coefficients of a preset number within a preset time period before the current time point; Obtain each group of evaluation coefficients corresponding to the electromechanical equipment, thereby constructing a line graph of the changes in the evaluation coefficients of the electromechanical equipment. Based on the time order of each group of evaluation coefficients, plot the numerical points corresponding to each group of evaluation coefficients in the line graph, connect adjacent numerical points to obtain risk lines, and calculate the slope of each risk line and the angle with the horizontal line. When the angle between the risk line and the horizontal line is obtuse, it is recorded as an ascending line. When the angle between the risk line and the horizontal line is acute, it is recorded as a descending line. Calculate the slope of each ascending and descending line; All rising slopes and falling slopes are accumulated respectively to obtain the total rising value and the total falling value of the electromechanical equipment, and the total rising value is divided by the total falling value to obtain the imbalance ratio; Mark the highest value point and the lowest value point in the constructed evaluation coefficient change line graph, construct a vertical line segment between the two sets of marked points, calculate the length of the vertical line segment, and record it as the distance value; The imbalance ratio and the distance value are comprehensively processed to obtain a prediction coefficient; a prediction coefficient threshold is preset, and the prediction coefficient is compared with the prediction coefficient threshold. If the prediction coefficient is greater than the prediction coefficient threshold, an early warning signal is triggered and sent to the mobile terminal of the manager.

[0014] A digital platform-based electromechanical data analysis system, comprising: Data collection module: This module obtains parameter information of each component of the electromechanical equipment grinder during operation, including spindle parameter information, motor parameter information, and image information of the grinding wheel; and pre-processes the data before uploading it to the digital platform for storage; Data processing module: obtains spindle parameter information and motor parameter information from the digital platform, analyzes them and obtains the spindle abnormality coefficient and motor abnormality coefficient; comprehensively processes the spindle abnormality coefficient and motor abnormality coefficient to obtain the evaluation coefficient; and analyzes the image information of the grinding wheel to obtain the grinding wheel coefficient; Risk assessment module: matches risk levels based on assessment coefficient and grinding wheel coefficient respectively; Prediction module: Analyzes the preset number of evaluation coefficients before the current time point to obtain the prediction coefficient.

[0015] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are: 1. The present invention collects multi-source data, comprehensively analyzes the operating parameters and status information of the electromechanical equipment grinder spindle, motor, grinding wheel and other components, calculates the abnormality coefficient and evaluation coefficient, and can comprehensively and accurately judge the equipment operation status, timely discover potential fault hazards, and take corresponding maintenance measures before the fault occurs, avoiding production interruptions caused by equipment failure, effectively ensuring the stability and efficiency of production, and improving production efficiency and economic benefits.

[0016] 2. Based on data analysis results, the present invention can not only match risk levels in real time, but also perform predictive analysis when the assessment coefficient and grinding wheel coefficient meet specific conditions. Once the prediction coefficient exceeds the threshold, an early warning signal is triggered to prevent production interruptions and safety accidents caused by equipment failures in advance and reduce losses. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Further details, features and advantages of the present application are disclosed in the following description of exemplary embodiments in conjunction with the accompanying drawings, in which: Figure 1 is a flow chart of the present invention; DETAILED DESCRIPTION

[0018] Several embodiments of the present application will be described in more detail below with reference to the accompanying drawings so that those skilled in the art can implement the present application. The present application can be embodied in many different forms and for many different purposes and should not be limited to the embodiments described herein. These embodiments are provided to make the present application comprehensive and complete and to fully convey the scope of the present application to those skilled in the art. The embodiments do not limit the present application.

[0019] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. It will be further understood that terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the relevant art and / or the context of this specification, and will not be interpreted in an idealized or overly formal sense unless expressly defined as such herein.

[0020] See also Figure 1 As shown, the present invention provides a technical solution: A method for analyzing electromechanical data based on a digital platform, comprising: Multi-source data collection: Obtain parameter information of each component of the electromechanical equipment grinder during operation, including spindle parameter information and motor parameter information; clean the data to remove outliers and supplement missing values, and store the data in the database of the digital platform; Data processing: After analyzing the parameter information of each component, the spindle abnormality coefficient and the motor abnormality coefficient are obtained; after comprehensive processing of the spindle abnormality coefficient and the motor abnormality coefficient, the evaluation coefficient is obtained; The process of obtaining the spindle anomaly coefficient includes: Obtain image information of the spindle, and segment the image information of the journal, shaft end, and shaft body from the image information of the spindle. Extract features from the image information of the journal, shaft end, and shaft body in turn, including wear and crack related features. Mark the extracted features as wear areas and crack areas. Obtain the number of pixels of the marked wear area and crack area, and convert the number of pixels of the wear area and crack area into actual area based on the resolution of the image to obtain the wear area and crack area; Obtain the wear area and crack area of the journal, shaft end, and shaft body in sequence, and divide the wear areas of the journal, shaft end, and shaft body by the total area of the journal, shaft end, and shaft body to obtain the journal wear ratio, shaft end wear ratio, and shaft body wear ratio; Divide the crack areas of the journal, shaft end, and shaft body by the total areas of the journal, shaft end, and shaft body to obtain the journal crack ratio, shaft end crack ratio, and shaft body crack ratio; The wear ratio and crack ratio of the journal, shaft end and shaft body are processed comprehensively to obtain the journal abnormal value, shaft end abnormal value and shaft body abnormal value; Preset weight factors for the wear ratio and crack ratio of the journal, multiply the wear ratio and crack ratio of the journal by the corresponding weight factors, and then sum them to obtain the journal abnormal value; based on the analysis and acquisition process of the journal abnormal value, perform corresponding analysis on the wear ratio and crack ratio of the shaft end and shaft body, and then obtain the shaft end abnormal value and shaft body abnormal value; The spindle abnormality coefficient is obtained by calculating the journal abnormality, shaft end abnormality and shaft body abnormality. Calculation process: Mark the journal abnormal value, shaft end abnormal value, and shaft body abnormal value as 、 、 The subsequent entry formula: ; Get the spindle anomaly coefficient ; in 、 、 They are the maximum allowable value of journal abnormality, the reference value of shaft end abnormality, and the threshold value of shaft body abnormality; 、 、 are the weight factors corresponding to the journal abnormal value, shaft end abnormal value and shaft body abnormal value respectively; The process of obtaining the motor abnormality coefficient includes: Obtain the current value monitored at each monitoring time point during the motor's working period; preset a current rated value, compare the current value monitored at each time point with the preset current rated value, and record the current value exceeding the preset current rated value as an exceedance value; After accumulating the various exceedance values, the average is calculated to obtain the exceedance mean; The motor is divided into regions according to the preset area, and the motor temperature value of each region at each monitoring time point is obtained in turn; Preset temperature tolerance range, compare the motor temperature value of each area at each monitoring time point with the preset temperature operating range, and record the temperature that is not within the preset temperature tolerance range as abnormal temperature; In the time series, among the monitoring time points corresponding to all motor temperature values, the difference between the monitoring time points corresponding to adjacent abnormal temperatures is calculated to obtain the abnormal duration, and all abnormal durations are accumulated to obtain the duration. Obtain the duration of each area in turn, and perform comprehensive processing on the duration of each area to obtain the different temperature duration; Assign a corresponding weight factor to each area of the motor, multiply the duration of each area with its corresponding weight factor in turn, and then sum them up to obtain the temperature difference duration; Obtain the noise decibels of the motor at each monitoring time point, preset a standard noise decibel, accumulate the noise decibels that are greater than the preset standard noise decibels, and calculate the average to obtain the excess decibel average; The motor abnormality coefficient is obtained by comprehensively processing the exceedance mean, duration, and excess decibel mean; Specifically, the method includes: normalizing the mean value, duration, and mean value of excess decibels, using the mean value and duration as the two right-angled sides of a right triangle, and connecting the remaining side to form a complete triangle; using the mean value of excess decibels as the height of the triangle, constructing a triangular pyramid model, and calculating the volume of the triangular pyramid and recording it as the motor abnormality coefficient; The main shaft abnormality coefficient and the motor abnormality coefficient are comprehensively processed to obtain an evaluation coefficient, specifically including: normalizing the main shaft abnormality coefficient and the motor abnormality coefficient, constructing an ellipse by using the main shaft abnormality coefficient and the motor abnormality coefficient as the major semi-axis and the minor semi-axis of the ellipse respectively, and calculating the area of the ellipse and recording it as the evaluation coefficient; Correlation analysis: obtain the image information of the grinding wheel and obtain the grinding wheel coefficient based on the image information analysis; Before obtaining the image information of the grinding wheel, the following steps are also required: The number of all processed parts within a preset time period is obtained. Inspectors perform quality inspections on each part and count the number of qualified parts. The number of qualified parts is divided by the total number of processed parts within the time period to obtain the part qualification rate. The part qualification rate is compared with the preset qualification rate. If the part qualification rate is lower than the preset qualification rate, the image information acquisition operation of the grinding wheel is triggered. Inspectors conduct quality inspections on each part: Inspectors inspect parts according to product quality standards and inspection specifications. Inspectors use more precise measuring equipment, such as coordinate measuring machines, to accurately measure the size, shape, and position accuracy of parts. They also use professional testing tools, such as roughness meters to test surface roughness and hardness testers to test hardness. The image information of the grinding wheel is obtained, and the grinding wheel coefficient is obtained based on the image information analysis. The process is as follows: Obtaining a preset number of grinding wheel side image information, and obtaining a side profile image of each grinding wheel image after preprocessing the image; From the side profile, take the upper contour line of the grinding wheel as the starting point, draw a preset number of distance segments perpendicular to the lower contour line of the grinding wheel, and extract the maximum distance segment and the minimum distance segment from each distance segment; The maximum distance line segment and the minimum distance line segment in each side profile of the grinding wheel are obtained in sequence, and arranged in descending order according to the value. The maximum distance line segment and the minimum distance line segment are extracted, and the wear extreme difference value is obtained by calculating the difference between the maximum distance line segment and the minimum distance line segment. Obtain images of the front and back sides of the grinding wheel, and divide the front and back sides of the grinding wheel into regions with preset areas in turn. Use a brightness measurement tool to measure the brightness of each region on the front and back sides of the grinding wheel. Each region is measured for a preset number of times, and the average value is recorded as the brightness value. Thus, the brightness values of each area on the front and back sides of the grinding wheel are obtained; the areas corresponding to the maximum brightness value and the minimum brightness value are extracted; and the difference between the maximum brightness value and the minimum brightness value is recorded as the deviation value; Marking the areas corresponding to the maximum brightness value and the minimum brightness value as the maximum brightness area and the minimum brightness area respectively; and obtaining the area value after analyzing and processing the maximum brightness area and the minimum brightness area; The grinding wheel coefficient is obtained by weighted calculation of the wear extreme value, deviation value and area value; Preset weight factors for wear extreme value, deviation value, and area value, respectively multiply the wear extreme value, deviation value, and area value with their corresponding weight factors and then sum them to obtain the grinding wheel coefficient; The process of obtaining the region value includes: dividing the maximum brightness region into predetermined triangular areas to obtain respective maximum brightness subregions; obtaining the brightness values between each maximum brightness subregion, recording them as first region brightness values; arranging the respective first region brightness values in descending order, and extracting the maximum first region brightness value and the minimum first region brightness value therefrom; Obtain the sub-region centers corresponding to the maximum first region brightness value and the minimum first region brightness value, respectively, connect them with a straight line, and calculate the length of the straight line, which is recorded as the first span value; Based on the above process of analyzing the maximum brightness area to obtain the first span value, the same analysis is performed on the minimum brightness area to obtain the second span value; Preset weight factors for the first span value and the second span value, multiply the first span value and the second span value by their corresponding weight factors, and sum them to obtain the area value; Evaluation and processing: comparing the evaluation coefficient and grinding wheel coefficient with their corresponding preset reference thresholds, performing corresponding operations based on the comparison results, and displaying the analysis results on the interface of the digital platform; The evaluation coefficient and the grinding wheel coefficient are respectively compared with their corresponding preset reference thresholds. If both the evaluation coefficient and the grinding wheel coefficient are less than the corresponding preset reference thresholds, a prediction analysis of the evaluation coefficient is triggered to obtain a prediction coefficient. Matching corresponding risk levels according to the differences between the assessment coefficient and the grinding wheel coefficient and their corresponding preset reference thresholds; Specifically include: If the assessment coefficient is greater than the preset reference threshold, the assessment coefficient is calculated with its corresponding preset reference threshold to obtain the risk difference; three sets of value ranges corresponding to the risk differences are preset, each set of risk differences corresponds to a risk level, and the risk difference is matched with the value ranges corresponding to the three sets of risk differences to obtain the risk level corresponding to the risk difference; the risk levels include mild assessment risk, moderate assessment risk and severe assessment risk; Based on the above process of matching the assessment coefficient to the risk level, the same analysis is performed on the grinding wheel coefficient to obtain the difference between the grinding wheel coefficient and the corresponding preset reference threshold value. The corresponding risk level includes mild grinding wheel risk, moderate grinding wheel risk and severe grinding wheel risk. The process of obtaining the prediction coefficient includes: Get the evaluation coefficients of a preset number within a preset time period before the current time point; Obtain each group of evaluation coefficients corresponding to the electromechanical equipment, thereby constructing a line graph of the changes in the evaluation coefficients of the electromechanical equipment. Based on the time order of each group of evaluation coefficients, plot the numerical points corresponding to each group of evaluation coefficients in the line graph, connect adjacent numerical points to obtain risk lines, and calculate the slope of each risk line and the angle with the horizontal line. When the angle between the risk line and the horizontal line is obtuse, it is recorded as an ascending line. When the angle between the risk line and the horizontal line is acute, it is recorded as a descending line. Calculate the slope of each ascending and descending line; All rising slopes and falling slopes are accumulated respectively to obtain the total rising value and the total falling value of the electromechanical equipment, and the total rising value is divided by the total falling value to obtain the imbalance ratio; Mark the highest value point and the lowest value point in the constructed evaluation coefficient change line graph, construct a vertical line segment between the two sets of marked points, calculate the length of the vertical line segment, and record it as the distance value; The imbalance ratio and the distance value are comprehensively processed to obtain a prediction coefficient; a prediction coefficient threshold is preset, and the prediction coefficient is compared with the prediction coefficient threshold. If the prediction coefficient is greater than the prediction coefficient threshold, an early warning signal is triggered and sent to the mobile terminal of the manager; The calculation process of the prediction coefficient is: The imbalance ratio and distance value are marked as and , substitute into the formula , and obtain the prediction coefficient of electromechanical equipment ;in and are the weighting factors for the imbalance ratio and distance value, respectively; A digital platform-based electromechanical data analysis system, comprising: Data collection module: This module obtains parameter information of each component of the electromechanical equipment grinder during operation, including spindle parameter information, motor parameter information, and image information of the grinding wheel; and pre-processes the data before uploading it to the digital platform for storage; Data processing module: obtains spindle parameter information and motor parameter information from the digital platform, analyzes them and obtains the spindle abnormality coefficient and motor abnormality coefficient; comprehensively processes the spindle abnormality coefficient and motor abnormality coefficient to obtain the evaluation coefficient; and analyzes the image information of the grinding wheel to obtain the grinding wheel coefficient; Risk assessment module: matches risk levels based on assessment coefficient and grinding wheel coefficient respectively; Prediction module: Analyze the preset number of evaluation coefficients before the current time point to obtain the prediction coefficient; preset the prediction coefficient threshold, compare the prediction coefficient with the prediction coefficient threshold, and if the prediction coefficient is greater than the prediction coefficient threshold, trigger the early warning signal and send the early warning signal to the manager's mobile terminal.

[0021] The above formulas are obtained by collecting a large amount of data and performing software simulation, and a formula close to the actual value is selected. The influencing weight factors and specific coefficient values in the formula are set by technical personnel in this field according to actual conditions, and can be adjusted and modified later.

[0022] The above description of the embodiments is intended to enable one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not limited to the embodiments shown herein but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for analyzing electromechanical data based on a digital platform, characterized in that: include: Multi-source data collection: Obtain parameter information of each component of the electromechanical equipment grinder during operation, including spindle parameter information and motor parameter information; Data processing: After analyzing the parameter information of each component, the spindle abnormality coefficient and the motor abnormality coefficient are obtained; after comprehensive processing of the spindle abnormality coefficient and the motor abnormality coefficient, the evaluation coefficient is obtained; Correlation analysis: obtain the image information of the grinding wheel and obtain the grinding wheel coefficient based on the image information analysis; Assessment and processing; The evaluation coefficient and grinding wheel coefficient are compared with their corresponding preset reference thresholds respectively, and corresponding operations are performed according to the comparison results. The analysis results are displayed on the interface of the digital platform.

2. The electromechanical data analysis method based on a digital platform according to claim 1, characterized in that: Before obtaining the image information of the grinding wheel, the following steps are also required: The number of all processed parts within a preset time period is obtained, and the inspectors perform quality inspection on each part and count the number of qualified parts. The number of qualified parts is divided by the number of all processed parts within the time period to obtain the part qualification rate. The part qualification rate is compared with the preset qualification rate. If the part qualification rate is less than the preset qualification rate, the image information acquisition operation of the grinding wheel is triggered.

3. The electromechanical data analysis method based on a digital platform according to claim 1, characterized in that: The process of obtaining the spindle anomaly coefficient includes: Obtain image information of the spindle, and segment the image information of the journal, shaft end, and shaft body from the image information of the spindle. Extract features from the image information of the journal, shaft end, and shaft body in turn, including wear and crack related features. Mark the extracted features as wear areas and crack areas. Obtaining the number of pixels of the marked wear area and crack area, converting the number of pixels of the wear area and crack area into actual area to obtain the wear area and crack area; Obtain the wear area and crack area of the journal, shaft end, and shaft body in sequence, and divide the wear areas of the journal, shaft end, and shaft body by the total area of the journal, shaft end, and shaft body to obtain the journal wear ratio, shaft end wear ratio, and shaft body wear ratio; Divide the crack areas of the journal, shaft end, and shaft body by the total areas of the journal, shaft end, and shaft body to obtain the journal crack ratio, shaft end crack ratio, and shaft body crack ratio; The wear ratio and crack ratio of the journal, shaft end and shaft body are processed comprehensively to obtain the journal abnormal value, shaft end abnormal value and shaft body abnormal value; The spindle anomaly coefficient is obtained by calculating the journal anomaly value, shaft end anomaly value and shaft body anomaly value.

4. The electromechanical data analysis method based on a digital platform according to claim 1, characterized in that: The process of obtaining the motor abnormality coefficient includes: Obtain the current value monitored at each monitoring time point during the motor's working period; preset a current rated value, compare the current value monitored at each time point with the preset current rated value, and record the current value exceeding the preset current rated value as an exceedance value; After accumulating the various exceedance values, the average is calculated to obtain the exceedance mean; The motor is divided into regions according to the preset area, and the motor temperature value of each region at each monitoring time point is obtained in turn; Preset temperature tolerance range, compare the motor temperature value of each area at each monitoring time point with the preset temperature operating range, and record the temperature that is not within the preset temperature tolerance range as abnormal temperature; In the time series, among the monitoring time points corresponding to all motor temperature values, the difference between the monitoring time points corresponding to adjacent abnormal temperatures is calculated to obtain the abnormal duration, and all abnormal durations are accumulated to obtain the duration. Obtain the duration of each area in turn, and perform comprehensive processing on the duration of each area to obtain the different temperature duration; Obtain the noise decibels of the motor at each monitoring time point, preset a standard noise decibel, accumulate the noise decibels that are greater than the preset standard noise decibels, and calculate the average to obtain the excess decibel average; The motor abnormality coefficient is obtained by comprehensively processing the exceedance mean, duration, and excess decibel mean.

5. The electromechanical data analysis method based on a digital platform according to claim 4, characterized in that: The evaluation coefficient is obtained after comprehensive processing of the main shaft abnormality coefficient and the motor abnormality coefficient, specifically including: normalizing the main shaft abnormality coefficient and the motor abnormality coefficient, constructing an ellipse by using the main shaft abnormality coefficient and the motor abnormality coefficient as the major semi-axis and minor semi-axis of the ellipse respectively, and calculating the area of the ellipse and recording it as the evaluation coefficient.

6. The electromechanical data analysis method based on a digital platform according to claim 1, characterized in that: The process of obtaining the image information of the grinding wheel and obtaining the grinding wheel coefficient based on the image information analysis is as follows: Obtaining a preset number of grinding wheel side image information, and obtaining a side profile image of each grinding wheel image after preprocessing the image; From the side profile, take the upper contour line of the grinding wheel as the starting point, draw a preset number of distance segments perpendicular to the lower contour line of the grinding wheel, and extract the maximum distance segment and the minimum distance segment from each distance segment; The maximum distance line segment and the minimum distance line segment in each side profile of the grinding wheel are obtained in sequence, and arranged in descending order according to the value. The maximum distance line segment and the minimum distance line segment are extracted, and the wear extreme difference value is obtained by calculating the difference between the maximum distance line segment and the minimum distance line segment. Obtain images of the front and back sides of the grinding wheel, and divide the front and back sides of the grinding wheel into regions with preset areas in turn. Use a brightness measurement tool to measure the brightness of each region on the front and back sides of the grinding wheel. Each region is measured for a preset number of times, and the average value is recorded as the brightness value. Thus, the brightness values of each area on the front and back sides of the grinding wheel are obtained; the areas corresponding to the maximum brightness value and the minimum brightness value are extracted; and the difference between the maximum brightness value and the minimum brightness value is recorded as the deviation value; Mark the areas corresponding to the maximum brightness value and the minimum brightness value as the maximum brightness area and the minimum brightness area respectively; After analyzing and processing the maximum brightness area and the minimum brightness area, the area value is obtained; The grinding wheel coefficient is obtained by weighted calculation of the wear extreme value, deviation value and area value.

7. The electromechanical data analysis method based on a digital platform according to claim 6, characterized in that: The evaluation coefficient and the grinding wheel coefficient are respectively compared with their corresponding preset reference thresholds. If both the evaluation coefficient and the grinding wheel coefficient are less than the corresponding preset reference thresholds, a prediction analysis of the evaluation coefficient is triggered to obtain a prediction coefficient. The corresponding risk levels are matched according to the differences between the evaluation coefficient and the grinding wheel coefficient and their corresponding preset reference thresholds.

8. The electromechanical data analysis method based on a digital platform according to claim 7, characterized in that: The process of obtaining the prediction coefficient includes: Get the evaluation coefficients of a preset number within a preset time period before the current time point; Obtain each group of evaluation coefficients corresponding to the electromechanical equipment, thereby constructing a line graph of the changes in the evaluation coefficients of the electromechanical equipment. Based on the time order of each group of evaluation coefficients, plot the numerical points corresponding to each group of evaluation coefficients in the line graph, connect adjacent numerical points to obtain risk lines, and calculate the slope of each risk line and the angle with the horizontal line. When the angle between the risk line and the horizontal line is obtuse, it is recorded as an ascending line. When the angle between the risk line and the horizontal line is acute, it is recorded as a descending line. Calculate the slope of each ascending and descending line; All rising slopes and falling slopes are accumulated respectively to obtain the total rising value and the total falling value of the electromechanical equipment, and the total rising value is divided by the total falling value to obtain the imbalance ratio; Mark the highest value point and the lowest value point in the constructed evaluation coefficient change line graph, construct a vertical line segment between the two sets of marked points, calculate the length of the vertical line segment, and record it as the distance value; The imbalance ratio and the distance value are comprehensively processed to obtain a prediction coefficient; a prediction coefficient threshold is preset, and the prediction coefficient is compared with the prediction coefficient threshold. If the prediction coefficient is greater than the prediction coefficient threshold, an early warning signal is triggered and sent to the mobile terminal of the manager.

9. A digital platform-based electromechanical data analysis system, using the digital platform-based electromechanical data analysis method according to any one of claims 1 to 8, characterized in that: include: Data collection module: obtains parameter information of each component of the electromechanical equipment grinder during operation, including spindle parameter information and motor parameter information; and image information of the grinding wheel; The data is pre-processed and uploaded to the digital platform for storage; Data processing module: obtains spindle parameter information and motor parameter information from the digital platform, analyzes them and obtains the spindle abnormality coefficient and motor abnormality coefficient; comprehensively processes the spindle abnormality coefficient and motor abnormality coefficient to obtain the evaluation coefficient; and analyzes the image information of the grinding wheel to obtain the grinding wheel coefficient; Risk assessment module: matches risk levels based on assessment coefficient and grinding wheel coefficient respectively; Prediction module: Analyzes the preset number of evaluation coefficients before the current time point to obtain the prediction coefficient.

Images