A method and system for monitoring the operation status of a CNC machine tool for processing hardware

Abstract

The present invention relates to the field of data monitoring technology, and in particular to a method and system for monitoring the operation status of a CNC machine tool for processing hardware. The method comprises the following steps: forming a first data set with multiple similar historical hardware parameter data time series sequences of hardware, forming a second data set with the parameter data time series sequence of the hardware and the similar historical hardware parameter data time series sequence; calculating the degree of deviation of the hardware; recording the area enclosed by the fitting curve of the parameter data time series sequence and the coordinate axis as the first feature of the hardware corresponding to the parameter data time series sequence; calculating the processing stability of the hardware; weighting the degree of deviation of the hardware by the processing stability of the hardware to obtain the smoothing parameter of the hardware; using the smoothing parameter of the hardware in an exponential smoothing algorithm to obtain the CNC machine tool operation status monitoring result corresponding to the hardware, thereby effectively improving the accuracy of the CNC machine tool operation status monitoring.

Description

Technical Field

[0001] The present invention relates to the technical field of data monitoring, and in particular to a method and system for monitoring the operating status of a numerically controlled machine tool used for processing hardware. Background Art

[0002] CNC machine tools are important equipment used for precision processing of hardware and parts in modern manufacturing. They can be used to process hardware in the fields of aerospace, automobile manufacturing, electronics, machinery, etc. In the process of using CNC machine tools, it is necessary to strictly monitor the operating data generated by CNC machine tools in the process of processing hardware to avoid quality problems in the produced hardware and ensure that the equipment in related fields can operate normally.

[0003] The prior art provides a variety of methods for monitoring the operating status of CNC machine tools. For example, a patent application document with publication number CN112381388A discloses a method for monitoring the operation of a spindle motor of a CNC machine tool. The method collects a characteristic parameter set of the operating status of the spindle motor, and removes data sets that do not conform to the value range in the characteristic parameter data set; constructs a topological neural network recognition algorithm for identifying the stability of motor operation, and trains the algorithm using the clustered data set to complete the algorithm training process; collects characteristic parameters in real time, inputs them into the trained topological neural network algorithm, and judges the stability of motor operation.

[0004] The above-mentioned prior art obtains the motor stability data set to train the extension neural network, and obtains a model that can be used to judge the motor operation stability. However, the training performance of the model is highly dependent on the integrity and quality of the data set, and the cost of obtaining and labeling various types of data is high. If some abnormal situations are not covered in the data set, such abnormalities may not be identified. Therefore, it is difficult to cope with scenarios with high real-time requirements, affecting the accuracy of CNC machine tool operation status monitoring.

[0005] Based on this, how to accurately obtain the operating status monitoring results of CNC machine tools is a problem that needs to be solved urgently by technical personnel in this field. Summary of the invention

[0006] In order to solve the technical problem of how to accurately obtain the operating status monitoring result of a CNC machine tool, the present invention provides a CNC machine tool operating status monitoring method and system for processing hardware.

[0007] In a first aspect, the present invention provides a method for monitoring the operating status of a CNC machine tool for processing hardware, which adopts the following technical solution:

[0008] A method for monitoring the operating status of a CNC machine tool for processing hardware parts comprises the following steps:

[0009] Obtain the time series sequence of parameter data generated by the CNC machine tool spindle processing each hardware part; combine multiple similar historical hardware parameter data time series sequences of hardware parts into a first data set, combine the parameter data time series sequence of the hardware part and similar historical hardware parameter data time series sequence into a second data set, and cluster the first data set and the second data set respectively;

[0010] ;

[0011] is the degree of deviation of the hardware, , are the reciprocals of the Euclidean distance and value between the cluster centers of the first and second data sets of the hardware, is the preset hyperparameter; the area enclosed by the fitting curve of the parameter data time series sequence and the coordinate axis is recorded as the first feature of the hardware corresponding to the parameter data time series sequence; the processing stability of the hardware is calculated, and the difference between the processing stability and the first feature of the same type of historical hardware is accumulated and negatively correlated; the deviation degree of the hardware is weighted by the processing stability of the hardware to obtain the smoothing parameter of the hardware; the smoothing parameter of the hardware is used in the exponential smoothing algorithm to obtain the CNC machine tool operation status monitoring result corresponding to the hardware.

[0012] The present invention processes the time series of parameter data corresponding to the hardware through an exponential smoothing algorithm, and can accurately obtain the operating status monitoring result of the CNC machine tool based on the prediction result. In this process, the present invention takes into account that the fixed smoothing parameters in the exponential smoothing algorithm cannot adapt to the dynamic changes of the parameter data; based on this, the present invention obtains the deviation degree of the current hardware by analyzing the difference before and after adding the parameter sequence of the current hardware to the parameter data set of the same historical hardware, and determines the smoothing coefficient based on the deviation degree, so as to accurately obtain the parameter prediction value, thereby realizing the monitoring of the operating status of the CNC machine tool. On this basis, the present invention also takes into account that the fluctuation of the parameter data set of the same historical hardware itself will affect the calculation of the deviation degree of the current hardware; based on this, the present invention also weights the deviation degree of the current hardware by analyzing the stable state of the parameter data set of the same historical hardware, so that the smoothing parameter can be accurately obtained based on the weighted deviation degree, effectively improving the accuracy of the operating status monitoring of the CNC machine tool.

[0013] According to a method for monitoring the operating status of a CNC machine tool for processing hardware provided by the present invention, the method of obtaining a time series sequence of parameter data generated by the CNC machine tool spindle processing each hardware part also includes: collecting temperature data and vibration data of the spindle during the hardware processing process through sensors in the spindle area of ​​the CNC machine tool, taking the temperature data and vibration data obtained at the same collection time as a data point, and obtaining a time series sequence of parameter data of the hardware after preprocessing.

[0014] The present invention takes into account the possibility of data missing in the originally collected parameter data, and therefore improves the overall quality of the data through preprocessing to facilitate subsequent data processing.

[0015] According to a method for monitoring the operating status of a CNC machine tool for processing hardware provided by the present invention, a first data set and a second data set are clustered by a K-means algorithm.

[0016] According to a method for monitoring the operating status of a CNC machine tool for processing hardware provided by the present invention, a method for obtaining the area enclosed by the fitting curve of the parameter data time series sequence and the coordinate axis includes: taking the start time and end time of the data points in the parameter data time series sequence as the upper and lower limits of the integration of the fitting function to obtain the area enclosed by the fitting curve of the parameter data time series sequence and the coordinate axis.

[0017] The present invention characterizes the cumulative change of the parameter data time series sequence by the area enclosed by the fitting curve of the parameter data time series sequence and the coordinate axis, so that the change of the parameter data time series sequence is more intuitive. By comparing the difference between the areas enclosed by the fitting curves of different parameter data time series sequences and the coordinate axis, the cumulative difference between the two can be accurately obtained.

[0018] According to a method for monitoring the operating status of a CNC machine tool for processing hardware provided by the present invention, the calculation of the processing stability of the hardware includes: obtaining the cumulative sum of the Euclidean distances between the terminal data point in the hardware parameter data time series sequence and the corresponding data point in the similar historical hardware parameter data time series sequence, recording the product of the cumulative sum of the Euclidean distances and the cumulative sum of the differences between the first features of the similar historical hardware of the hardware as the second feature of the hardware; using the negative number of the second feature of the hardware as the exponent of an exponential function with e as the base to obtain the processing stability of the hardware.

[0019] The present invention takes into account that when the current hardware has large fluctuations in similar historical hardware, it will affect the calculation result of the deviation degree of the current hardware. Therefore, the present invention accurately obtains the processing stability of the current hardware by analyzing the differences between the current hardware and similar historical hardware at the same data point and the differences between similar historical hardware.

[0020] According to a method for monitoring the operating status of a CNC machine tool for processing hardware provided by the present invention, the deviation degree of the hardware is weighted by the processing stability of the hardware to obtain the smoothing parameter of the hardware, including: normalizing the product of the processing stability of the hardware and the deviation degree to obtain the smoothing parameter of the hardware.

[0021] According to a method for monitoring the operating status of a CNC machine tool for processing hardware provided by the present invention, the smoothing parameters of the hardware are used in the exponential smoothing algorithm, including: obtaining the temperature mean or vibration mean of three historical data points of the data point in the hardware parameter data time series sequence as the temperature prediction value and vibration prediction value of the data point; substituting the temperature prediction value or vibration prediction value of the data point, the actual temperature value or actual vibration value, and the smoothing parameter into the exponential smoothing formula to obtain the temperature prediction value or vibration prediction value of the next data point.

[0022] The present invention processes the parameter data time series of hardware by using the exponential smoothing method, and can timely and accurately obtain the predicted value of each data point in the parameter data time series of the hardware, thereby accurately obtaining the CNC machine tool operation status monitoring result corresponding to each data point.

[0023] According to a method for monitoring the operating status of a CNC machine tool for processing hardware provided by the present invention, the smoothing parameters of the hardware are used in the exponential smoothing algorithm to obtain the operating status monitoring result of the CNC machine tool corresponding to the hardware, including: if the temperature prediction value and / or vibration prediction value of the next data point is greater than a preset threshold value, the operating status monitoring result of the CNC machine tool corresponding to the hardware is abnormal; otherwise, the operating status monitoring result of the CNC machine tool corresponding to the hardware is normal.

[0024] According to a method for monitoring the operating status of a CNC machine tool for processing hardware provided by the present invention, the method further comprises: in response to the CNC machine tool operating status monitoring result corresponding to the hardware being abnormal, issuing an abnormal alarm.

[0025] In a second aspect, the present invention provides a CNC machine tool operation status monitoring system for processing hardware, which adopts the following technical solution:

[0026] A CNC machine tool operation status monitoring system for processing hardware parts comprises: a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the above-mentioned CNC machine tool operation status monitoring method for processing hardware parts is implemented.

[0027] By adopting the above technical solution, the above-mentioned method for monitoring the operating status of a CNC machine tool for processing hardware is generated into a computer program and stored in a memory to be loaded and executed by a processor, so that a terminal device is made based on the memory and the processor for easy use.

[0028] The present invention has the following technical effects:

[0029] Based on the above technical scheme, the present invention provides a method and system for monitoring the operation status of a CNC machine tool for processing hardware. When obtaining the monitoring result of the operation status of the CNC machine tool, the time series of parameter data corresponding to the hardware is processed by an exponential smoothing algorithm, and the monitoring result of the operation status of the CNC machine tool can be accurately obtained based on the prediction result. In this process, the present invention takes into account that the fixed smoothing parameter in the exponential smoothing algorithm cannot adapt to the dynamic changes of the parameter data; based on this, the present invention obtains the deviation degree of the current hardware by analyzing the difference before and after adding the parameter sequence of the current hardware to the parameter data set of the same historical hardware, and determines the smoothing coefficient based on the deviation degree, so as to accurately obtain the parameter prediction value, thereby realizing the monitoring of the operation status of the CNC machine tool. On this basis, the present invention also takes into account that the fluctuation of the parameter data set of the same historical hardware itself will affect the calculation of the deviation degree of the current hardware; based on this, the present invention also weights the deviation degree of the current hardware by analyzing the stable state of the parameter data set of the same historical hardware, so that the smoothing parameter can be accurately obtained based on the weighted deviation degree, effectively improving the accuracy of the monitoring of the operation status of the CNC machine tool. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 A schematic flow chart of a method for monitoring the operating status of a CNC machine tool for machining hardware provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0031] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments.

[0032] It should be understood that when the terms "first", "second", etc. are used in the claims, description and drawings of the present invention, they are only used to distinguish different objects rather than to describe a specific order.

[0033] In order to ensure the quality of hardware, it is necessary to strictly monitor the operating data generated by CNC machine tools during the processing of hardware.

[0034] The exponential smoothing algorithm is an algorithm used for time series data prediction. By setting fixed smoothing parameters, the algorithm can dynamically adjust according to the latest data and timely capture abnormal data in the time series data. Therefore, the exponential smoothing algorithm can be used to process the real-time collected CNC machine tool operation status monitoring data, so as to accurately obtain the monitoring results.

[0035] Based on this, an embodiment of the present invention discloses a method for monitoring the operating status of a CNC machine tool for processing hardware. The method processes the operating data of the CNC machine tool during the processing of hardware by an exponential smoothing algorithm, thereby accurately screening out potential abnormal data.

[0036] Please refer to Figure 1 As shown, Figure 1 A flow chart of a method for monitoring the operating status of a CNC machine tool for machining hardware provided in an embodiment of the present invention, the method specifically comprises the following steps.

[0037] S1: Obtain the time series of parameter data generated by the CNC machine tool spindle processing each hardware part.

[0038] Among them, the parameters generated by the CNC machine tool spindle each time processing hardware can be temperature data, vibration data, etc., which can be set according to actual needs.

[0039] It should be noted that during the CNC machine tool processing, the high-speed rotating spindle drives the clamped tool to cut the hardware. During this process, the coolant forms a lubricating film between the tool and the workpiece, thereby reducing the temperature of the machine tool, workpiece and tool to prevent deformation or damage caused by overheating.

[0040] However, long-term cutting operations of CNC machine tools will cause the coolant level to drop, and a large amount of heat will be generated between the components. If the heat generated between the components cannot be effectively controlled, it will cause thermal expansion of the spindle components, thereby aggravating the wear of the mechanical components and causing obvious vibration in the spindle area. Therefore, by using sensors to monitor the vibration and temperature parameters of the spindle area in real time, the health status of the machine tool can be obtained in real time.

[0041] For example, in an embodiment of the present invention, a time series sequence of parameter data generated by a CNC machine tool spindle processing each hardware part is obtained, which also includes: collecting temperature data and vibration data of the spindle during the hardware processing process through sensors in the spindle area of ​​the CNC machine tool, taking the temperature data and vibration data obtained at the same collection time as a data point, and obtaining a time series sequence of parameter data of the hardware after preprocessing.

[0042] Among them, the preprocessing can be missing data interpolation, data denoising, etc.; it can be specifically set according to actual needs, and the embodiment of the present invention does not impose too many restrictions here.

[0043] Specifically, high-precision vibration sensors and temperature sensors are arranged in the spindle area of ​​the CNC machine tool, temperature data and vibration data are collected based on a preset collection frequency, and the temperature data and vibration data are associated with corresponding hardware types and stored in a database.

[0044] For example, the collection frequency may be set to once every 5 seconds; the collection frequency may be set specifically according to actual needs, and the embodiment of the present invention does not impose too many limitations on this.

[0045] It is understandable that the CNC machine tool processes the same type of hardware for the same length of time and collects data at the same frequency each time. Therefore, the length of the parameter data timing sequence of the same type of hardware that has completed cutting is the same.

[0046] It should be noted that in the exponential smoothing algorithm, the smoothing parameter determines the weight distribution of the algorithm to historical data and the latest data. If it is set too large, it may cause the algorithm to over-rely on the latest data, and if it is set too small, it may cause the algorithm to over-rely on historical data. The setting of the smoothing parameter directly affects the smoothing effect. Therefore, the exponential smoothing algorithm using fixed smoothing parameters cannot quickly respond to the real-time change trend of parameter data during the cutting process, which leads to a lag in the parameter prediction results of the CNC machine tool, affecting the accuracy of the monitoring results.

[0047] Based on this, the embodiment of the present invention analyzes the degree of deviation between the parameter data of the currently processed hardware and the parameter data of similar historical hardware, and obtains the smoothing parameters of the current hardware based on the degree of deviation, so as to accurately identify potential abnormalities in the current hardware processing process, that is, execute the following steps.

[0048] It can be understood that in the subsequent steps, the embodiment of the present invention uses the parameter data generated by the CNC machine tool spindle processing the hardware as the parameter data of the hardware. Therefore, the parameter data timing sequence of the hardware mentioned in the subsequent steps refers to the parameter data timing sequence generated by the CNC machine tool spindle processing the hardware, rather than the parameter data of the hardware itself.

[0049] S2: Combining multiple similar historical hardware parameter data time series sequences of hardware into a first data set, combining the parameter data time series sequence of the hardware and similar historical hardware parameter data time series sequence into a second data set, clustering the first data set and the second data set respectively to obtain the deviation degree of the hardware.

[0050] Among them, the algorithm for clustering the first data set and the second data set can be a K-means algorithm (K-means clustering algorithm, referred to as K-means), a density-based clustering algorithm, etc. The type of clustering algorithm can be set according to actual needs, and the embodiment of the present invention does not impose too many restrictions on this.

[0051] The specific steps of obtaining the cluster center through the clustering algorithm can be implemented through the existing technology, and the embodiment of the present invention will not be described in detail here.

[0052] It can be understood that the embodiment of the present invention obtains the parameter data timing sequence of the current hardware during the current hardware production process, and the parameter data timing sequence of the same type of historical hardware is a complete parameter data timing sequence that has completed the production process. Therefore, the number of data points in the current hardware parameter data timing sequence is less than or equal to the number of data points in each parameter data timing sequence of the same type of historical hardware.

[0053] For example, when obtaining the time series sequence of similar historical hardware parameter data of the current hardware, the number of similar historical hardware can be preset, and the number of similar historical hardware parameter data time series sequence can be obtained based on the preset number of similar historical hardware.

[0054] Among them, the number of similar historical hardware can be set to 10; the number of similar historical hardware can be set according to actual needs, and the embodiment of the present invention does not impose too many restrictions on this.

[0055] It can be understood that the second data set obtained based on the above steps includes the first data set.

[0056] It should be noted that if the internal machinery of the CNC machine tool is worn out during the production of hardware, the difference between the parameter data timing sequence of the spindle area and the historical parameter data timing sequence will be large.

[0057] Based on this, the embodiment of the present invention obtains the current hardware parameter data time series sequence and the same historical hardware parameter data set, and analyzes the difference between the cluster center distances before and after the current hardware parameter data time series sequence is added to the same historical hardware parameter data set. If the addition of the current hardware parameter data increases the difference between the cluster center distances, it means that the current hardware parameter data time series sequence deviates greatly from the same historical data, and the possibility of anomalies is also greater.

[0058] For example, in the embodiment of the present invention, the degree of deviation of the hardware is calculated, and the specific formula may be referred to as follows:

[0059] ;

[0060] is the degree of deviation of the hardware, is the reciprocal of the sum of the Euclidean distances between the cluster centers of the first data set of hardware. is the reciprocal of the sum of the Euclidean distances between the cluster centers of the second data set of hardware. Preset hyperparameters.

[0061] in, It can be set to 0.1; it can be set specifically according to actual needs, and the embodiment of the present invention does not impose too many restrictions here.

[0062] The Euclidean distance between cluster centers can be obtained by an existing formula, which will not be described in detail in the embodiment of the present invention.

[0063] In the above formula, It indicates the concentration degree of the first data set. The smaller the value is, the smaller the Euclidean distance between the cluster centers of the first data set is as a whole. The data distribution in the first data set is more concentrated as a whole. The parameter data of the same historical hardware production process of the current hardware fluctuates less, and the possibility of abnormal fluctuations is also smaller.

[0064] It indicates the concentration degree of the second data set. The smaller the value is, the smaller the Euclidean distance between the cluster centers of the second data set is as a whole. The data distribution in the second data set is more concentrated as a whole. The overall distribution of the parameter data time series sequence in the current hardware production process is similar to that of the parameter data time series sequence in the similar historical hardware production process. The corresponding possibility of abnormal fluctuations is also smaller.

[0065] It means that the concentration of the first data set of the current hardware is greater than that of the second data set. This situation shows that after adding the current hardware parameter data time series sequence to the first data set, the concentration of the second data set obtained becomes smaller and the discreteness becomes larger. The larger the value is, the greater the difference between the concentration of the first data set and the concentration of the second data set is, and the greater the deviation of the corresponding current hardware is.

[0066] It means that the concentration of the first data set of the current hardware is less than or equal to the concentration of the second data set. This situation shows that after adding the current hardware parameter data time series sequence to the first data set, the concentration of the second data set becomes larger and the discreteness becomes smaller. The closer the distribution of the current hardware parameter data time series sequence is to the distribution of the similar historical hardware parameter data time series sequence, the smaller the deviation of the corresponding current hardware is.

[0067] After obtaining the degree of deviation of the parameter data of each hardware during the production process based on the above steps, continue to perform the following steps.

[0068] S3: Record the area enclosed by the fitting curve of the parameter data time series sequence and the coordinate axis as the first feature of the hardware corresponding to the parameter data time series sequence, and calculate the processing stability of the hardware.

[0069] Among them, the processing stability of hardware is negatively correlated with the cumulative difference of the first feature between similar historical hardware of the same hardware.

[0070] The fitting curve of the parameter data time series can be obtained by the least square method. When constructing the fitting curve, the temperature data of the data point can be used as the horizontal coordinate and the vibration data can be used as the vertical coordinate; or the vibration data of the data point can be used as the horizontal coordinate and the temperature data can be used as the vertical coordinate. The specific setting can be based on actual needs, and the embodiment of the present invention does not impose too many restrictions on this.

[0071] It should be noted that, based on the above steps, the difference between the cluster center distances before and after adding the current hardware parameter data time series sequence to the same historical hardware parameter data set can be analyzed to obtain the difference between the current hardware and the same historical hardware. During the processing, each time a piece of hardware is cut, the CNC machine tool will be recalibrated and initialized before cutting the next piece of hardware. Therefore, the processing conditions of the same type of hardware are usually kept consistent, and the normal parameter data time series sequence of the hardware will be relatively stable.

[0072] However, if there are abnormal data in the time series of parameter data of similar historical hardware, the stability of the parameter data change of the similar historical hardware itself will be lower. Therefore, the deviation degree of hardware obtained based on the above steps may also be affected by the abnormal parameter data of the similar historical hardware itself.

[0073] Based on this, the embodiment of the present invention can also obtain the stability of the parameter data of similar historical hardware of the current hardware. If the parameter data of similar historical hardware is more stable, it means that the credibility of the deviation degree of the current hardware is also higher.

[0074] By way of example, in an embodiment of the present invention, a method for obtaining the area enclosed by the fitting curve of the parameter data time series sequence and the coordinate axis includes: taking the start time and end time of the data points in the parameter data time series sequence as the upper and lower limits of the integration of the fitting function, and obtaining the area enclosed by the fitting curve of the parameter data time series sequence and the coordinate axis.

[0075] The area enclosed by the fitting curve of the hardware parameter data time series and the coordinate axis is the first feature of the hardware. The size of the area is used to characterize the cumulative amount of parameter changes during the processing of the hardware.

[0076] By way of example, in an embodiment of the present invention, calculating the processing stability of hardware includes: obtaining the cumulative sum of the Euclidean distances between the end data points in the hardware parameter data time series sequence and the corresponding data points in the similar historical hardware parameter data time series sequence, recording the product of the cumulative sum of the Euclidean distances and the cumulative sum of the differences between the first features of the similar historical hardware as the second feature of the hardware; using the negative number of the second feature of the hardware as the exponent of an exponential function with base e to obtain the processing stability of the hardware.

[0077] For example, to calculate the processing stability of hardware, please refer to the following relationship:

[0078] ;

[0079] For the processing stability of hardware, is the number of similar historical hardware of the hardware. For the hardware and The parameter data time series of the same historical hardware The Euclidean distance between data points is is the maximum ordinal number in the hardware parameter data time series sequence, is the maximum ordinal number in the time series of parameter data of the same historical hardware. is the minimum ordinal number in the time series of parameter data of the same historical hardware. For the The fitting curve of the same historical hardware, For the The fitting curve of the same historical hardware, is the integral symbol, is the differential symbol, is an exponential function with base e.

[0080] In the above formula, the parameter data timing sequence of the current hardware is The data point is the end data point in the parameter data time series.

[0081] Indicates The first characteristic of the same kind of historical hardware, Indicates The first characteristic of a similar historical hardware.

[0082] It represents the cumulative sum of the Euclidean distances between the terminal data point in the current hardware parameter data time series and the corresponding data point in the similar historical hardware parameter data time series. The larger the value, the greater the difference between the current hardware processing data and the similar historical hardware processing data, the greater the possibility of abnormality, and the worse the corresponding processing stability.

[0083] It represents the cumulative sum of the differences in the first features of the current hardware with similar historical hardware. The larger the value, the more consistent the parameter data changes during the processing of the current hardware with similar historical hardware, the less likely the CNC machine tool will experience a decrease in coolant effect or wear, and the higher the corresponding processing stability.

[0084] After obtaining the processing stability of each hardware based on the above steps, continue to perform the following steps.

[0085] S4: The deviation degree of the hardware is weighted by the processing stability of the hardware to obtain the smoothing parameter of the hardware.

[0086] It should be noted that if the parameter data time series of the current hardware is more stable than that of the historical hardware of the same type, it means that the parameter changes in the CNC machine tool operation process are relatively stable. At this time, if the parameter deviation degree generated by the current hardware processing process is high, the credibility of the parameter deviation degree generated by the current hardware processing process is also higher, which means that the current hardware processing process may be abnormal due to factors such as poor coolant effect or wear of machine tool parts.

[0087] Similarly, when the fluctuation of the time series of parameter data of the current hardware of the same type in history is greater, the credibility of the parameter deviation degree generated by the current hardware processing process in representing the abnormal state of the CNC machine tool will be lower.

[0088] Based on this, the embodiment of the present invention weights the deviation degree of the hardware by the processing stability of the hardware to obtain the actual deviation degree of the current hardware, and obtains its smoothing parameter based on the actual deviation degree of the current hardware.

[0089] It should be noted that the higher the deviation of the weighted spindle area parameter data currently collected, the greater the overall change between the current hardware and its corresponding similar historical hardware. There may be increased wear of components or abnormal mechanical failures in the current hardware production process. Abnormalities in CNC machine tools will gradually increase, and the recent data changes of the current hardware will be more important. Therefore, a larger smoothing parameter value can be set to increase the sensitivity of the exponential smoothing algorithm to recent data changes, so as to reflect these abnormal changes more quickly and predict potential abnormalities in a timely manner.

[0090] On the contrary, the lower the deviation of the weighted spindle area parameter data currently collected, the more consistent the overall changes of the current hardware processing data and the historical data of similar hardware processing are, the machine tool continues to operate well and stably during the production of different hardware, and is less sensitive to recent data changes. Therefore, a smaller smoothing parameter value can be set to make the algorithm pay more attention to long-term data changes, thereby accurately obtaining prediction results.

[0091] For example, in an embodiment of the present invention, the degree of deviation of the hardware is weighted by the processing stability of the hardware to obtain the smoothing parameter of the hardware, including: normalizing the product of the processing stability of the hardware and the degree of deviation to obtain the smoothing parameter of the hardware.

[0092] After obtaining the smoothing parameters of each hardware based on the above steps, the smoothing parameters of the hardware can be used for prediction in the exponential smoothing algorithm, that is, continue to perform the following steps.

[0093] S5: Use the smoothing parameter of the hardware in the exponential smoothing algorithm to obtain the CNC machine tool operation status monitoring result corresponding to the hardware.

[0094] It can be understood that by analyzing the current hardware parameter data time series sequence based on the above steps, the smoothing parameter of the current hardware parameter data time series sequence can be obtained, and the smoothing parameter is the smoothing parameter of the terminal data point in the current hardware parameter data time series sequence.

[0095] By way of example, in an embodiment of the present invention, smoothing parameters of hardware are used in an exponential smoothing algorithm, including: obtaining the temperature mean or vibration mean of three historical data points of a data point in a time series sequence of hardware parameter data as the temperature prediction value and vibration prediction value of the data point; substituting the temperature prediction value or vibration prediction value of the data point, the actual temperature value or actual vibration value, and the smoothing parameter into the exponential smoothing formula to obtain the temperature prediction value or vibration prediction value of the next data point.

[0096] Among them, when obtaining three historical data points of a data point, the left adjacent data point of the data point can be used as the starting point to obtain three consecutive historical data points including the left data point; the exponential smoothing formula is a prior art and the embodiment of the present invention will not be described in detail here.

[0097] By way of example, in an embodiment of the present invention, the smoothing parameters of the hardware are used in the exponential smoothing algorithm to obtain the CNC machine tool operating status monitoring result corresponding to the hardware, including: if the temperature prediction value and / or vibration prediction value of the next data point is greater than a preset threshold, then the CNC machine tool operating status monitoring result corresponding to the hardware is abnormal; otherwise, the CNC machine tool operating status monitoring result corresponding to the hardware is normal.

[0098] Among them, the threshold of the temperature prediction value can be set to 70 degrees Celsius, and the threshold of the vibration prediction value can be set to 18 mm / s; the threshold can be set specifically according to actual needs.

[0099] It should be noted that after the CNC machine tool operating status monitoring is obtained based on the above steps, different levels of early warning can be issued based on the abnormal monitoring results of the CNC machine tool operating status, so that the staff can handle it in time.

[0100] For example, in an embodiment of the present invention, the operating status monitoring result of the CNC machine tool corresponding to the hardware is obtained, and then the method further includes: in response to the operating status monitoring result of the CNC machine tool corresponding to the hardware being abnormal, issuing an abnormal alarm.

[0101] For example, in an embodiment of the present invention, when an alarm is issued for abnormal monitoring results of the operating status of a CNC machine tool, if the CNC machine tool operating status monitoring results corresponding to the temperature prediction value and the vibration prediction value of the data point are both abnormal, a first-level alarm is triggered; if the CNC machine tool operating status monitoring results corresponding to the temperature prediction value or the vibration prediction value of the data point are abnormal, a second-level alarm is triggered.

[0102] Among them, the warning intensity and priority of the first-level warning are greater than those of the second-level warning; the warning prompt method can be set according to actual needs, and the embodiment of the present invention does not impose too many restrictions on this.

[0103] It can be seen that in the embodiment of the present invention, when the operating status monitoring result of the CNC machine tool used to process the hardware is obtained, the time series sequence of parameter data generated by the CNC machine tool spindle processing each hardware can be obtained; multiple similar historical hardware parameter data time series sequences of the hardware are combined into a first data set, the parameter data time series sequence of the hardware and the similar historical hardware parameter data time series sequence are combined into a second data set, and the first data set and the second data set are clustered respectively;

[0104] ;

[0105] is the degree of deviation of the hardware, , are the reciprocals of the Euclidean distance and value between the cluster centers of the first and second data sets of the hardware, is a preset hyperparameter; the area enclosed by the fitting curve of the parameter data time series sequence and the coordinate axis is recorded as the first feature of the hardware corresponding to the parameter data time series sequence; the processing stability of the hardware is calculated, and the difference between the processing stability and the first feature of the same type of historical hardware is accumulated and negatively correlated; the deviation degree of the hardware is weighted by the processing stability of the hardware to obtain the smoothing parameter of the hardware; the smoothing parameter of the hardware is used in the exponential smoothing algorithm to obtain the CNC machine tool operation status monitoring result corresponding to the hardware, which effectively improves the accuracy of CNC machine tool operation status monitoring.

[0106] An embodiment of the present invention also discloses a CNC machine tool operation status monitoring system for processing hardware, including a processor and a memory, wherein the memory stores computer program instructions. When the computer program instructions are executed by the processor, a CNC machine tool operation status monitoring method for processing hardware provided by the present invention is implemented.

[0107] The above system also includes other components well known to those skilled in the art, such as a communication bus and a communication interface, and their configuration and functions are known in the art, so they will not be described in detail here.

[0108] In the present invention, the aforementioned memory may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, a computer-readable storage medium may be any suitable magnetic storage medium or magneto-optical storage medium, or any other medium that can be used to store the required information and can be accessed by an application, module, or both. Any such computer storage medium may be part of the device or accessible or connectable to the device.

[0109] The above are all preferred embodiments of the present invention, and are not intended to limit the protection scope of the present invention. Therefore, any equivalent changes made based on the structure, shape, and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for monitoring the operating status of a CNC machine tool for processing hardware, characterized in that: include: Obtain the time series of parameter data generated by the CNC machine tool spindle processing each hardware part; Combining multiple similar historical hardware parameter data time series sequences of hardware into a first data set, combining the hardware parameter data time series sequence and similar historical hardware parameter data time series sequence into a second data set, and clustering the first data set and the second data set respectively; ； is the degree of deviation of the hardware, , are the reciprocals of the Euclidean distance and value between the cluster centers of the first and second data sets of the hardware, To preset hyperparameters; The area enclosed by the fitting curve of the parameter data time series sequence and the coordinate axis is recorded as the first feature of the hardware corresponding to the parameter data time series sequence; Calculate the processing stability of hardware, including: Obtain the cumulative sum of the Euclidean distances between the terminal data point in the hardware parameter data time series and the corresponding data point in the similar historical hardware parameter data time series, and record the product of the cumulative sum of the Euclidean distances and the cumulative sum of the differences between the first features of the similar historical hardware as the second feature of the hardware; use the negative number of the second feature of the hardware as the exponent of the exponential function with e as the base to obtain the processing stability of the hardware, and the processing stability is negatively correlated with the cumulative sum of the differences between the first features of the similar historical hardware; The deviation degree of the hardware is weighted by the processing stability of the hardware to obtain the smoothing parameter of the hardware; the smoothing parameter of the hardware is used in the exponential smoothing algorithm to obtain the CNC machine tool operation status monitoring result corresponding to the hardware.

2. A method for monitoring the operating status of a CNC machine tool for processing hardware according to claim 1, characterized in that: The method of obtaining the time series of parameter data generated by the CNC machine tool spindle processing each hardware part also includes: The temperature data and vibration data of the spindle during the hardware processing are collected through sensors in the spindle area of ​​the CNC machine tool. The temperature data and vibration data obtained at the same collection time are taken as a data point, and the parameter data time series sequence of the hardware is obtained after preprocessing.

3. The method for monitoring the operating status of a CNC machine tool for processing hardware according to claim 1, characterized in that: The first data set and the second data set are clustered using the K-means algorithm.

4. A method for monitoring the operating status of a CNC machine tool for processing hardware according to claim 2, characterized in that: Methods for obtaining the area enclosed by the fitting curve of the parameter data time series and the coordinate axis include: The start time and end time of the data points in the parameter data time series are used as the upper and lower limits of the integration of the fitting function to obtain the area enclosed by the fitting curve of the parameter data time series and the coordinate axis.

5. The method for monitoring the operating status of a CNC machine tool for processing hardware according to claim 1, characterized in that: The method of weighting the deviation degree of the hardware by the processing stability of the hardware to obtain the smoothing parameter of the hardware includes: The product of the processing stability and the deviation degree of the hardware is normalized to obtain the smoothing parameter of the hardware.

6. The method for monitoring the operating status of a CNC machine tool for processing hardware according to claim 2, characterized in that: The smoothing parameters of the hardware used in the exponential smoothing algorithm include: Obtain the temperature mean or vibration mean of three historical data points of a data point in the hardware parameter data time series as the temperature prediction value and vibration prediction value of the data point; The temperature prediction value or vibration prediction value, the actual temperature value or actual vibration value, and the smoothing parameter of the data point are substituted into the exponential smoothing formula to obtain the temperature prediction value or vibration prediction value of the next data point.

7. A method for monitoring the operating status of a CNC machine tool for processing hardware according to claim 6, characterized in that: The method of using the smoothing parameter of the hardware in the exponential smoothing algorithm to obtain the CNC machine tool operation status monitoring result corresponding to the hardware includes: If the temperature prediction value and / or vibration prediction value of the next data point is greater than the preset threshold, the operating status monitoring result of the CNC machine tool corresponding to the hardware is abnormal; otherwise, the operating status monitoring result of the CNC machine tool corresponding to the hardware is normal.

8. The method for monitoring the operating status of a CNC machine tool for processing hardware according to claim 7, characterized in that: The step of obtaining the CNC machine tool operation status monitoring result corresponding to the hardware also includes: In response to the CNC machine tool operation status monitoring result corresponding to the hardware being abnormal, an abnormal alarm is issued.

9. A CNC machine tool operation status monitoring system for processing hardware, characterized in that: include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a method for monitoring the operating status of a CNC machine tool for processing hardware according to any one of claims 1 to 8 is implemented.

Images