An intelligent monitoring method, system and device for grinding machines

Abstract

The present application relates to the field of industrial manufacturing equipment monitoring technology, and specifically to an intelligent monitoring method, system and device for grinders, the method comprising: obtaining each grinder processing parameter at each moment; determining the chain state trend characteristic value of each grinder processing parameter based on the trend change and distribution between each grinder processing parameter; determining the comprehensive state monitoring weight of each grinder processing parameter based on the chain state trend characteristic value; determining the deviation monitoring parameter of each grinder processing parameter at the current moment based on the abnormal changes of each grinder processing parameter at all moments; determining the grinder state deviation coefficient, and intelligently monitoring the grinder processing state. The present application analyzes the chain changes of different grinder processing parameters, which can improve the accuracy of intelligent monitoring of grinders.

Description

Technical Field

[0001] The present application relates to the technical field of industrial manufacturing equipment monitoring, and in particular to an intelligent monitoring method, system and device for a grinder. Background Art

[0002] With the rapid development of the manufacturing industry, CNC tool grinders, as high-precision processing equipment, have become the focus of industry attention for their technological innovation and development trends. With the continuous advancement of manufacturing technology, the processing accuracy of CNC tool grinders is also continuously improving. Intelligence and automation are one of the important directions for the development of CNC tool grinder technology. By introducing sensors, control systems and intelligent algorithms, automatic monitoring, automatic adjustment and optimization of the processing process of CNC tool grinders are realized, which improves the stability and reliability of CNC tool grinder processing. With the continuous development of artificial intelligence technology, the intelligent monitoring level of CNC tool grinders will continue to improve.

[0003] However, in the monitoring process of the processing of CNC tool grinders, the error of grinder monitoring may be large due to the complex processing environment of the equipment and the random interference of the environment during the processing. For example, the error analysis process of each monitoring data of the grinder using the traditional anomaly detection method does not take into account the overall state deviation of the grinder, which leads to a large monitoring error of the grinder state. Therefore, the monitoring result of the grinder state is directly obtained by performing an anomaly analysis on the parameters of different aspects during the grinding process, which ignores the correlation and change characteristics between different parameters of the CNC tool grinder in a complex environment, making the accuracy of the intelligent monitoring results for the grinder generally low. Summary of the invention

[0004] In order to solve the above technical problems, an intelligent monitoring method, system and device for a grinder are provided to solve the existing problems.

[0005] The solution to the technical problem of the present application is to provide an intelligent monitoring method, system and device for a grinder, comprising the following steps:

[0006] In a first aspect, an embodiment of the present application provides an intelligent monitoring method for a grinding machine, the method comprising the following steps:

[0007] Obtain each grinding machine processing parameter at each moment;

[0008] According to the trend change and distribution of each grinding machine processing parameter, the linkage state trend characteristic value of each grinding machine processing parameter is determined;

[0009] Determining the comprehensive state monitoring weight of each grinding machine processing parameter based on the chain state trend characteristic value;

[0010] According to the abnormal changes of each grinding machine processing parameter at all times, the deviation monitoring parameters of each grinding machine processing parameter at the current moment are determined;

[0011] Based on the deviation monitoring parameters and the comprehensive state monitoring weight of each grinding machine processing parameter at the current moment, the grinding machine state deviation coefficient at the current moment is determined, and the grinding machine processing state is intelligently monitored.

[0012] Preferably, the determining of the linkage state trend characteristic value of each grinding machine processing parameter includes:

[0013] Any one of the grinding machine processing parameters is recorded as the target processing parameter; and the remaining grinding machine processing parameters are recorded as each reference processing parameter;

[0014] Using a mutation point detection algorithm for the target processing parameters, obtaining each target parameter subsequence and each control parameter subsequence for each control processing parameter;

[0015] Analyze the trend differences and discreteness between each target parameter subsequence to obtain the time series state feature vector of the target processing parameter;

[0016] For each control parameter subsequence of each control processing parameter, the same method as the time sequence state feature vector of the target processing parameter is adopted to obtain the time sequence state feature vector of each control processing parameter;

[0017] The similarity of the time series state feature vector between each control processing parameter and the target processing parameter is respectively used as the linkage state coefficient;

[0018] The mean value of all the linkage state coefficients is used as the linkage state trend characteristic value of the target processing parameter;

[0019] The same method as the chain state trend characteristic value of the target processing parameter is adopted to obtain the chain state trend characteristic value of each grinding machine processing parameter.

[0020] Preferably, the method for obtaining each target parameter subsequence and each control parameter subsequence of each control processing parameter is:

[0021] The target processing parameters at all times are divided through each mutation point in the target processing parameters to form each target parameter subsequence;

[0022] Based on the acquisition moments corresponding to all mutation points of the target processing parameters, each control processing parameter at all moments is divided to form control parameter subsequences of each control processing parameter.

[0023] Preferably, the step of obtaining the time series state feature vector of the target processing parameter includes:

[0024] The trend verification algorithm is used to obtain the trend statistics of each target parameter subsequence;

[0025] Calculate the discrete degree of each target parameter subsequence;

[0026] Record the difference of the trend statistic between each target parameter subsequence and the remaining target parameter subsequences as the first time series analysis difference;

[0027] The difference in the discreteness between each target parameter subsequence and the remaining target parameter subsequences is recorded as a second time series analysis difference;

[0028] Merging the first timing analysis difference and the second timing analysis difference, and recording the result as a timing deviation index;

[0029] Taking the average of all the timing deviation indices as the timing state deviation value of each target parameter subsequence;

[0030] The time sequence state deviation values ​​of all target parameter subsequences are combined to form a time sequence state feature vector of the target processing parameter.

[0031] Preferably, the step of determining the comprehensive state monitoring weight of each grinding machine processing parameter comprises:

[0032] The sum of the chain state trend characteristic values ​​of all grinding machine processing parameters is recorded as the first sum value;

[0033] The ratio of the chain state trend characteristic value of each grinding machine processing parameter to the first sum value is used as the comprehensive state monitoring weight of each grinding machine processing parameter.

[0034] Preferably, the step of determining the deviation monitoring parameters of each grinding machine processing parameter at the current moment includes:

[0035] Anomaly detection algorithm is used for each grinding machine processing parameter at all times to obtain the abnormal probability of each grinding machine processing parameter at each time;

[0036] The abnormal probability of each grinding machine processing parameter at the current moment is used as the deviation monitoring parameter of each grinding machine processing parameter at the current moment.

[0037] Preferably, the determining of the grinding machine state deviation coefficient at the current moment includes:

[0038] The deviation monitoring parameter of each grinding machine processing parameter at the current moment and the comprehensive state monitoring weight are integrated to determine the state deviation factor of each grinding machine processing parameter at the current moment;

[0039] The state deviation factors of all kinds of grinding machine processing parameters are merged to serve as the grinding machine state deviation coefficient at the current moment.

[0040] Preferably, the intelligent monitoring of the grinding machine processing state includes: when the grinding machine state deviation coefficient is greater than a preset stability threshold, the grinding machine operation state is abnormal, otherwise, the grinding machine operation state is normal.

[0041] In a second aspect, the embodiment of the present application further provides an intelligent monitoring system for a grinding machine, the system comprising:

[0042] Processing parameter acquisition module: obtain the processing parameters of each grinder at each moment;

[0043] Grinding machine state analysis module: determine the interlocking state trend characteristic value of each grinding machine processing parameter according to the trend change and distribution between each grinding machine processing parameter; determine the comprehensive state monitoring weight of each grinding machine processing parameter based on the interlocking state trend characteristic value; determine the deviation monitoring parameter of each grinding machine processing parameter at the current moment according to the abnormal change of each grinding machine processing parameter at all times; determine the grinding machine state deviation coefficient at the current moment based on the deviation monitoring parameter and the comprehensive state monitoring weight of each grinding machine processing parameter at the current moment;

[0044] Grinding machine state monitoring module: based on the grinding machine state deviation coefficient, intelligently monitors the grinding machine processing state.

[0045] In a third aspect, an embodiment of the present application further provides an intelligent monitoring device for a grinder, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein when the processor executes the computer program, the steps of any one of the above-mentioned intelligent monitoring methods for a grinder are implemented.

[0046] This application has at least the following beneficial effects:

[0047] The present application obtains the time series state deviation value and determines the chain state trend characteristic value of each grinder processing parameter by analyzing the trend change and distribution of each grinder processing parameter. The beneficial effect of the present application is that when the processing state deviates during the processing of the CNC grinder, there are differences in the chain state trend changes of different processing parameters of the grinder. The chain synchronization changes of other processing parameters caused by the change of one processing parameter are analyzed according to the trend differences of the changes between different grinder processing parameters, and the degree of correlation change between different grinder processing parameters is considered. According to the abnormal changes of each grinder processing parameter at all times and the chain state trend characteristic value, the grinder state deviation coefficient at the current moment is determined, and the grinder processing state is intelligently monitored. The beneficial effect of the present application is that based on the chain change degree caused by different grinder processing parameters and combined with the abnormal characteristics of the parameters, the grinder processing state is analyzed to improve the precision and accuracy of the intelligent monitoring of the grinder. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] The following is a further detailed description of an intelligent monitoring method for a grinder of the present application in conjunction with the accompanying drawings.

[0049] Figure 1 A flowchart of the steps of an intelligent monitoring method for a grinder provided in this application;

[0050] Figure 2 A flowchart of the steps of the method for obtaining the time sequence state characteristic vector of the grinding wheel rotation speed provided in the present application;

[0051] Figure 3 A flowchart of the steps of the method for obtaining the grinding machine state deviation coefficient provided in this application;

[0052] Figure 4 A flowchart of the steps of an intelligent monitoring system for a grinder provided in this application. DETAILED DESCRIPTION

[0053] In order to make the purpose, technical solution and advantages of the present application more clear, the following is a further detailed description of an intelligent monitoring method, system and device for a grinder proposed in the present application in combination with the accompanying drawings and implementation examples. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0054] Unless defined otherwise, all 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.

[0055] See also Figure 1 , which shows a flowchart of a method for intelligent monitoring of a grinder provided by an embodiment of the present application, the method comprising the following steps:

[0056] Step 1, obtaining each grinding machine processing parameter at each moment.

[0057] During the CNC grinder processing, vibration sensors, speed sensors, temperature sensors and displacement sensors are used to collect each processing parameter of the CNC grinder. Due to the complex processing environment of the CNC grinder, the process of collecting the various processing parameters of the CNC grinder is easily disturbed by environmental noise. The grinding machine processing parameters at all times are subjected to noise reduction processing. According to the collection time of the sensor, each grinding machine processing parameter at each moment is obtained, including vibration frequency, grinding wheel speed, grinding machine temperature and feed speed.

[0058] Preferably, as an embodiment of the present application, a median filter is used to perform noise reduction processing on the grinding machine processing parameters. As other implementation methods, the implementer can adopt other noise reduction methods, which are not limited in this embodiment. The median filter is a well-known technology and will not be described in detail.

[0059] At this point, each grinding machine processing parameter at each moment is obtained.

[0060] Step 2: Determine the linkage state trend characteristic value of each grinding machine processing parameter according to the trend change and distribution between each grinding machine processing parameter.

[0061] Normally, during the operation of the CNC grinder, the machine tool runs stably, the material and surface condition of the workpiece are normal, and the processing parameters of the CNC grinder are within a stable range of change. The change characteristics of different parameters of the CNC grinder are basically the same. However, during the grinding process of the CNC grinder, factors such as grinding roughness and grinding wheel passivation may cause the processing state of the CNC grinder to be disordered, resulting in CNC grinder processing overload, irregular vibration between the grinding wheel and the workpiece, and feed speed deviation.

[0062] As for the state characteristics of the CNC grinder during processing, due to the possible differences in the quality of the workpiece and the roughness of the workpiece surface, the grinding wheel speed or vibration frequency data may change instantaneously at different operating times. This change is not caused by the change of the CNC grinder state. Therefore, the instantaneous change characteristics of a single parameter of the CNC grinder cannot accurately reflect the state deviation characteristics of the CNC grinder.

[0063] Furthermore, considering the synchronous change trend of different state parameters caused by the disorder of the CNC grinder processing state, the grinding machine processing parameters are used to reflect the comprehensive sensitive state of the CNC grinder state characteristics. Specifically, for example, the grinding wheel speed is analyzed. If harder particles are encountered on the surface of the workpiece during the grinding process, the speed may drop, causing irregular vibration frequency. The continuous influence of the particles within a certain time range will further lead to unstable changes in the feed speed and may cause power overload of the CNC grinder and temperature increase of the grinder. The above are only the chain synchronous change trend characteristics of different state parameters that may be caused by the surface roughness of the workpiece in the CNC grinder processing process.

[0064] If one of the machining parameters of the CNC grinder has a disordered change characteristic, and the machining state of the CNC grinder also has a disordered operation state characteristic, then the interval characteristics of the disordered change of the machining parameter currently analyzed are similar to the parameter interval disordered change characteristics of other machining parameters. Based on this characteristic, a relative analysis of different machining parameters is performed, specifically:

[0065] In the embodiment, the grinding wheel speed is taken as an example for analysis, specifically:

[0066] A mutation point detection algorithm is used for the grinding wheel speed at all times. Based on all mutation points of the grinding wheel speed, the grinding wheel speed at all times is divided into various speed subsequences.

[0067] Preferably, as an embodiment of the present application, a Bayesian mutation point detection algorithm is used to obtain mutation points. As other implementation methods, implementers can adopt other methods of the prior art, such as Pelt mutation detection algorithm, Pettitt mutation point detection algorithm, etc. This embodiment does not impose any special restrictions on this.

[0068] It should be noted that when partitioning is performed based on mutation points, each mutation point is partitioned into the previous subsequence.

[0069] The trend verification algorithm is used to obtain the trend statistics of each speed subsequence;

[0070] Calculate the discrete degree of each speed subsequence;

[0071] Preferably, as an embodiment of the present application, the Mann-Kendall trend test algorithm is used to obtain trend statistics; secondly, the degree of discreteness of each speed subsequence is obtained by calculating the coefficient of variation of each speed subsequence, wherein the Mann-Kendall trend test algorithm and the coefficient of variation are well-known technologies and will not be described in detail here.

[0072] It can be understood that this embodiment adopts the Mann-Kendall trend test algorithm to obtain trend statistics, and measures the degree of dispersion by the coefficient of variation. As other implementation methods, the implementer can adopt other methods of the prior art, for example, the KPSS test algorithm, the Sen's slope trend test algorithm, etc. to obtain trend statistics. The method for measuring the degree of dispersion can be through variance, standard deviation and information entropy, etc., and this embodiment does not impose any special restrictions on this.

[0073] It should be noted that, the larger the trend statistics and the discreteness, the more significant the trend change characteristics and fluctuation change characteristics of the divided subsequences are, and the CNC grinding machine may have a state deviation change in a shorter period of time.

[0074] Furthermore, by analyzing the fluctuation differences of each subsequence of the grinding wheel speed, the changing trend of the grinding wheel speed of the grinder can be reflected, specifically:

[0075] The difference of the trend statistic between each speed subsequence and the remaining speed subsequences is recorded as a first time series analysis difference;

[0076] The difference in the discreteness between each speed subsequence and the remaining speed subsequences is recorded as a second time series analysis difference;

[0077] Merging the first timing analysis difference and the second timing analysis difference, and recording the result as a timing deviation index;

[0078] Taking the average value of all the timing deviation indexes as the timing state deviation value of each speed subsequence;

[0079] It is understandable that the fusion relationship can be specifically expressed as a multiplication relationship, an addition relationship, and the idempotence of an exponential function, and the present application does not impose any special limitation on this.

[0080] Preferably, as an embodiment of the present application, the absolute value of the difference in the trend statistic between each speed subsequence and the remaining speed subsequences is recorded as the first timing analysis difference; the absolute value of the difference in the degree of discreteness between each speed subsequence and the remaining speed subsequences is recorded as the second timing analysis difference; and the product of the first timing analysis difference and the second timing analysis difference is recorded as the timing deviation index.

[0081] It should be noted that the larger the timing state deviation value is, the more differences in timing relative trends and fluctuation states may occur in different periods during the CNC grinding process.

[0082] Furthermore, based on the time series state deviation value of the speed subsequence, the trend change of other grinding machine processing parameters is analyzed, specifically:

[0083] The time sequence state deviation values ​​of all speed subsequences are used to form a time sequence state feature vector of the grinding wheel speed;

[0084] Further, the step flow chart of the method for obtaining the time sequence state characteristic vector of the grinding wheel speed provided by the present application is as follows: Figure 2 shown.

[0085] Based on the corresponding acquisition moments of all mutation points of the grinding wheel speed, the other grinding machine processing parameters are divided into vibration subsequences, temperature subsequences and feed speed subsequences;

[0086] For each vibration subsequence, each temperature subsequence and each feed speed subsequence, the same method as the time series state feature vector is adopted to obtain the time series state feature vectors of the vibration frequency, the grinding machine temperature and the feed speed respectively;

[0087] It should be noted that the time sequence state characteristic vector reflects the time sequence state difference of each grinding machine processing parameter during the grinding machine processing.

[0088] Furthermore, considering the timing state difference based on the grinding wheel speed, the timing state difference of other grinding machine processing parameters is analyzed for relative linkage trend characteristics, specifically:

[0089] The similarity of the time series state characteristic vectors between the grinding wheel speed and the vibration frequency, the grinding machine temperature and the feed speed are used as the linkage state coefficients respectively;

[0090] The mean value of all the interlocking state coefficients is used as the interlocking state trend characteristic value of the grinding wheel speed;

[0091] Preferably, as an embodiment of the present application, the cosine similarity of the time series state feature vector between the grinding wheel speed and the vibration frequency is calculated as the linkage state coefficient between the grinding wheel speed and the vibration frequency; accordingly, the linkage state coefficient between the grinding wheel speed and the grinding machine temperature and the linkage state coefficient between the grinding wheel speed and the feed speed are calculated respectively.

[0092] The above analysis is based on the grinding wheel speed of each grinding machine processing parameter. For other grinding machine processing parameters, the same analysis method as the grinding wheel speed is used to analyze the chain state trend characteristic value of each grinding machine processing parameter, specifically:

[0093] The same method as the interlocking state trend characteristic value of the grinding wheel speed is adopted to obtain the interlocking state trend characteristic value of the vibration frequency, the interlocking state trend characteristic value of the grinding machine temperature and the interlocking state trend characteristic value of the feed speed.

[0094] At this point, the chain state trend characteristic value of each grinding machine processing parameter is obtained.

[0095] Step 3: Determine the comprehensive state monitoring weight of each grinding machine processing parameter based on the chain state trend characteristic value.

[0096] According to the chain synchronous change trend between different processing parameters caused by the state change in the CNC grinder processing process, a relative characteristic analysis is performed on different processing parameters, and the state deviation monitoring weight of each grinder processing parameter is obtained based on the analysis results. The state monitoring deviation weight comprehensively reflects the relative change trend difference of different state parameters, and can accurately characterize the state parameters for analyzing the accuracy of the CNC grinder state.

[0097] Furthermore, the weight of the chain state trend characteristic value of each grinding machine processing parameter among all grinding machine processing parameters is analyzed to reflect the influence of each grinding machine processing parameter on the grinding machine state, specifically:

[0098] The sum of the chain state trend characteristic values ​​of all grinding machine processing parameters is recorded as the first sum value;

[0099] The ratio of the chain state trend characteristic value of each grinding machine processing parameter to the first sum value is used as the comprehensive state monitoring weight of each grinding machine processing parameter;

[0100] It should be noted that the larger the weight of comprehensive state monitoring is, the higher the consistency of the change of state characteristic deviation of CNC grinder and the change characteristics of state parameter linkage state trend is based on the change characteristic analysis of each grinder processing parameter.

[0101] Step 4: Determine the deviation monitoring parameter of each grinding machine processing parameter at the current moment according to the abnormal changes of each grinding machine processing parameter at all moments.

[0102] Furthermore, each grinding machine processing parameter at all times is detected to reflect the deviation of the grinding machine state at the current time, specifically:

[0103] Anomaly detection algorithm is used for each grinding machine processing parameter at all times to obtain the abnormal probability of each grinding machine processing parameter at each time;

[0104] Using the abnormal probability of each grinding machine processing parameter at the current moment as a deviation monitoring parameter of each grinding machine processing parameter at the current moment;

[0105] Preferably, as an embodiment of the present application, the LOF anomaly detection algorithm is used for anomaly detection. As other implementations, the implementer can adopt other methods of the prior art, such as isolation forest, etc., among which the LOF anomaly detection algorithm is a well-known technology and will not be described in detail here.

[0106] Step 5: Based on the deviation monitoring parameter and the comprehensive state monitoring weight of each grinding machine processing parameter at the current moment, determine the grinding machine state deviation coefficient at the current moment, and perform intelligent monitoring on the grinding machine processing state.

[0107] Furthermore, the deviation degree of the processing state of the grinder is analyzed through the deviation monitoring parameters and the grinding machine processing parameters, and the grinding machine processing state is intelligently monitored, specifically:

[0108] The deviation monitoring parameter of each grinding machine processing parameter at the current moment and the comprehensive state monitoring weight are integrated to determine the state deviation factor of each grinding machine processing parameter at the current moment;

[0109] The state deviation factors of all kinds of grinding machine processing parameters are integrated to serve as the grinding machine state deviation coefficient at the current moment;

[0110] Preferably, as an embodiment of the present application, the product of the deviation monitoring parameter of each grinder processing parameter at the current moment and the comprehensive state monitoring weight is used as the state deviation factor of each grinder processing parameter at the current moment; secondly, the sum of the state deviation factors of all grinder processing parameters is used as the grinder state deviation coefficient at the current moment.

[0111] It should be noted that if the grinder state deviation coefficient at the current moment is larger, it means that the CNC grinder processing state may deviate based on the comprehensive analysis of the chain trend change characteristics of various grinder processing parameters during the operation of the CNC grinder.

[0112] Further, the step flow chart of the method for obtaining the grinding machine state deviation coefficient provided in the present application is as follows: Figure 3 shown.

[0113] Furthermore, based on the grinder state deviation coefficient, the current grinding machine processing state is intelligently monitored, specifically:

[0114] If the grinder state deviation coefficient at the current moment is less than the preset stability threshold, the grinder is in normal operation. If the grinder state deviation coefficient at the current moment is greater than the preset stability threshold, the grinder operation state is abnormal and the processing process needs to be terminated in time and the grinder needs to be repaired.

[0115] The embodiment of the present application also provides an intelligent monitoring system for a grinding machine, the system comprising:

[0116] Processing parameter acquisition module: obtain the processing parameters of each grinder at each moment;

[0117] Grinding machine state analysis module: determine the interlocking state trend characteristic value of each grinding machine processing parameter according to the trend change and distribution between each grinding machine processing parameter; determine the comprehensive state monitoring weight of each grinding machine processing parameter based on the interlocking state trend characteristic value; determine the deviation monitoring parameter of each grinding machine processing parameter at the current moment according to the abnormal change of each grinding machine processing parameter at all times; determine the grinding machine state deviation coefficient at the current moment based on the deviation monitoring parameter and the comprehensive state monitoring weight of each grinding machine processing parameter at the current moment;

[0118] Grinding machine state monitoring module: monitors the grinding machine processing state based on the grinding machine state deviation coefficient.

[0119] Furthermore, the present application provides a flowchart of a step of an intelligent monitoring system for a grinder as shown in FIG. Figure 4 shown.

[0120] Based on the same inventive concept as the above method, an embodiment of the present application also provides an intelligent monitoring device for a grinder, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of any one of the above-mentioned intelligent monitoring methods for a grinder when executing the computer program.

[0121] It should be understood that although Figure 1 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 1At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0122] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0123] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the present application. It should be pointed out that, for those of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present application. Therefore, any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present application without departing from the content of the technical solution of the present application, shall fall within the protection scope of the technical solution of the present application.

Claims

1. An intelligent monitoring method for a grinding machine, characterized in that: The method comprises the following steps: Obtain each grinding machine processing parameter at each moment; According to the trend change and distribution of each grinding machine processing parameter, the linkage state trend characteristic value of each grinding machine processing parameter is determined; Determining the comprehensive state monitoring weight of each grinding machine processing parameter based on the chain state trend characteristic value; According to the abnormal changes of each grinding machine processing parameter at all times, the deviation monitoring parameters of each grinding machine processing parameter at the current moment are determined; Based on the deviation monitoring parameters and the comprehensive state monitoring weight of each grinding machine processing parameter at the current moment, determine the grinding machine state deviation coefficient at the current moment, and perform intelligent monitoring on the grinding machine processing state; The step of determining the linkage state trend characteristic value of each grinding machine processing parameter includes: Any one of the grinding machine processing parameters is recorded as the target processing parameter; and the remaining grinding machine processing parameters are recorded as each reference processing parameter; Using a mutation point detection algorithm for the target processing parameters, obtaining each target parameter subsequence and each control parameter subsequence for each control processing parameter; Analyze the trend differences and discreteness between each target parameter subsequence to obtain the time series state feature vector of the target processing parameter; For each control parameter subsequence of each control processing parameter, the same method as the time sequence state feature vector of the target processing parameter is adopted to obtain the time sequence state feature vector of each control processing parameter; The similarity of the time series state feature vector between each control processing parameter and the target processing parameter is respectively used as the linkage state coefficient; The mean value of all the linkage state coefficients is used as the linkage state trend characteristic value of the target processing parameter; The same method as the linkage state trend characteristic value of the target processing parameter is used to obtain the linkage state trend characteristic value of each grinding machine processing parameter; Determining the grinding machine state deviation coefficient at the current moment includes: The deviation monitoring parameter of each grinding machine processing parameter at the current moment and the comprehensive state monitoring weight are integrated to determine the state deviation factor of each grinding machine processing parameter at the current moment; The state deviation factors of all kinds of grinding machine processing parameters are merged to serve as the grinding machine state deviation coefficient at the current moment.

2. The intelligent monitoring method for a grinding machine according to claim 1, characterized in that: The method for obtaining each target parameter subsequence and each control parameter subsequence of each control processing parameter is as follows: The target processing parameters at all times are divided through each mutation point in the target processing parameters to form each target parameter subsequence; Based on the acquisition moments corresponding to all mutation points of the target processing parameters, each control processing parameter at all moments is divided to form control parameter subsequences of each control processing parameter.

3. The intelligent monitoring method for a grinding machine according to claim 1, characterized in that: The step of obtaining the time series state feature vector of the target processing parameter comprises: The trend verification algorithm is used to obtain the trend statistics of each target parameter subsequence; Calculate the discrete degree of each target parameter subsequence; Record the difference of the trend statistic between each target parameter subsequence and the remaining target parameter subsequences as the first time series analysis difference; The difference in the discreteness between each target parameter subsequence and the remaining target parameter subsequences is recorded as a second time series analysis difference; Merging the first timing analysis difference and the second timing analysis difference, and recording the result as a timing deviation index; Taking the average of all the timing deviation indices as the timing state deviation value of each target parameter subsequence; The time sequence state deviation values ​​of all target parameter subsequences are combined to form a time sequence state feature vector of the target processing parameter.

4. The intelligent monitoring method for a grinding machine according to claim 1, characterized in that: The method of determining the comprehensive state monitoring weight of each grinding machine processing parameter includes: The sum of the chain state trend characteristic values ​​of all grinding machine processing parameters is recorded as the first sum value; The ratio of the chain state trend characteristic value of each grinding machine processing parameter to the first sum value is used as the comprehensive state monitoring weight of each grinding machine processing parameter.

5. The intelligent monitoring method for a grinding machine according to claim 1, characterized in that: The method of determining the deviation monitoring parameters of each grinding machine processing parameter at the current moment includes: Anomaly detection algorithm is used for each grinding machine processing parameter at all times to obtain the abnormal probability of each grinding machine processing parameter at each time; The abnormal probability of each grinding machine processing parameter at the current moment is used as the deviation monitoring parameter of each grinding machine processing parameter at the current moment.

6. The intelligent monitoring method for a grinding machine according to claim 1, characterized in that: The intelligent monitoring of the grinding machine processing state includes: when the grinding machine state deviation coefficient is greater than a preset stability threshold, the grinding machine operation state is abnormal, otherwise, the grinding machine operation state is normal.

7. An intelligent monitoring system for a grinding machine, implementing the method as claimed in claim 1, characterized in that: The system comprises: Processing parameter acquisition module: obtain the processing parameters of each grinder at each moment; Grinding machine state analysis module: determine the interlocking state trend characteristic value of each grinding machine processing parameter according to the trend change and distribution between each grinding machine processing parameter; determine the comprehensive state monitoring weight of each grinding machine processing parameter based on the interlocking state trend characteristic value; determine the deviation monitoring parameter of each grinding machine processing parameter at the current moment according to the abnormal change of each grinding machine processing parameter at all times; determine the grinding machine state deviation coefficient at the current moment based on the deviation monitoring parameter and the comprehensive state monitoring weight of each grinding machine processing parameter at the current moment; Grinding machine state monitoring module: based on the grinding machine state deviation coefficient, intelligently monitors the grinding machine processing state.

8. An intelligent monitoring device for a grinding machine, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the processor implements the steps of the intelligent monitoring method for a grinder as described in any one of claims 1 to 6.

Images