A signal feature extraction method, device, equipment and medium for condition monitoring

Abstract

The application discloses a signal feature extraction method and device for state monitoring, equipment and medium, relates to the numerical control processing technical field, and is used for solving the technical problem that the accuracy of tool state recognition in the existing technology is low in the peck drilling process. The method comprises the following steps: according to target numerical control program instructions, determining the overall machining signal of the overall peck drilling process of the target hole; wherein the overall peck drilling process comprises multiple sub peck drilling processes, the overall machining signal comprises multiple sub machining signals, and one sub peck drilling process corresponds to one sub machining signal; the sliding time window method is used for feature extraction on the overall machining signal, and the signal feature values corresponding to each sub peck drilling process are determined; according to the signal feature values corresponding to each sub peck drilling process, the monitoring feature values of the target hole are determined. Therefore, the application can determine the signal feature values of each sub peck drilling process through the sliding time window method, so that the accuracy of tool state recognition in the peck drilling process is improved.

Description

Technical Field

[0001] This application relates to the field of CNC machining technology, and provides a method, apparatus, equipment and medium for extracting signal features for status monitoring. Background Technology

[0002] As is well known, aircraft structural components are trending towards larger, more integrated, and more complex designs, requiring drilling to create connecting holes to meet subsequent assembly needs. For connecting holes in parts made of difficult-to-machine materials, a pecking drill method is typically used to achieve longer tool life and better machining quality. Furthermore, in metal cutting, cutting tools gradually wear down and may even break or fracture over time. Because the tool is in direct contact with the workpiece, excessive tool wear and breakage will reduce the dimensional accuracy and surface quality of the workpiece, potentially even leading to its scrapping. Therefore, wear on drilling tools also significantly affects the dimensional and positional accuracy of holes.

[0003] Currently, in the machining process, the condition of cutting tools mainly relies on the operator's experience to judge. Operators need to monitor the tool's condition in real time and replace it promptly when it wears down to a certain extent or breaks. However, human factors have a significant impact, making it difficult to respond promptly to some abnormal situations. Furthermore, while commercial tool monitoring systems such as ARTIS and Siemens are maturely applied in the automotive industry, their application in the drilling process of difficult-to-machine materials in aircraft presents challenges. Due to the significant differences in rigidity, thickness, and allowance on the upper and lower surfaces of holes during the drilling process of aircraft structural components, and the large fluctuations in the condition of different batches of parts caused by deformation or assembly errors in large aircraft structural components, the repeatability of drilling signal characteristics is weak. Therefore, the traditional method of learning and comparing monitoring based on statistical values ​​calculated from the original signal has low accuracy and frequently generates false alarms, affecting normal production.

[0004] Therefore, improving the accuracy of tool status recognition during the drilling process has become an urgent problem to be solved. Summary of the Invention

[0005] This application provides a method, apparatus, device, and medium for extracting signal features for condition monitoring, which addresses the technical problem of low accuracy in tool condition identification during the drilling process in the prior art.

[0006] On the one hand, a method for extracting signal features from state monitoring is provided, the method comprising:

[0007] According to the target CNC program instructions, the overall machining signal for the overall pecking and drilling process of the target hole is determined; wherein, the overall pecking and drilling process includes multiple sub-pecking and drilling processes, and the overall machining signal includes multiple sub-machining signals, with one sub-pecking and drilling process corresponding to one sub-machining signal;

[0008] The sliding time window method is used to extract features from the overall processing signal to determine the signal feature values ​​corresponding to each sub-pecking and drilling process.

[0009] Based on the signal characteristic values ​​corresponding to each of the sub-pecking drilling processes, the monitoring characteristic values ​​of the target hole are determined.

[0010] Optionally, the step of determining the overall machining signal for the overall drilling process of the target hole according to the target CNC program instructions includes:

[0011] Based on the G1Fx2 instruction in the target CNC program, the overall machining signal for the overall drilling process of the target hole is determined.

[0012] Optionally, the step of using a sliding time window method to extract features from the overall processing signal and determine the signal feature values ​​corresponding to each sub-pecking drill process includes:

[0013] For any single-stage drilling process, the single-stage drilling process is divided into the initial stage of hole making, the middle stage of hole making, and the final stage of hole making; wherein, the initial stage of hole making is the period when the drill tip has not completely drilled into the workpiece material; the middle stage of hole making is the period when the drill tip has completely drilled into the workpiece material and cut a section before lifting the tool; the final stage of hole making is the period when part of the drill tip has drilled out of the workpiece material but has not completely cut the workpiece material.

[0014] The sliding time window method is used to extract features from any one sub-pecking process to determine the signal feature value corresponding to any one sub-pecking process.

[0015] Optionally, the step of extracting features from any one sub-pecking process using a sliding time window method and determining the signal feature value corresponding to any one sub-pecking process includes:

[0016] The sliding time window method is used to extract features from any one sub-pecking process to determine the maximum signal value within any one sub-pecking process;

[0017] The target position corresponding to the maximum value of the signal is calculated using a preset position calculation formula;

[0018] Determine whether the target position is within the middle stage of hole making;

[0019] If the target position is determined to be within the middle of the hole-making process, then the maximum signal value is determined as the signal characteristic value corresponding to the middle of the hole-making process, and the maximum signal value is placed into the maximum value set.

[0020] Optionally, the preset position calculation formula is expressed as follows:

[0021]

[0022] in, This is the sequence number corresponding to the initial value of the signal within the sliding time window; This is the index corresponding to the maximum signal value within the sliding time window; This represents the total number of signals within the sliding time window.

[0023] Optionally, the step of determining the monitoring feature value of the target hole based on the signal feature values ​​corresponding to each of the sub-pecking drilling processes includes:

[0024] Based on the thickness of the material being drilled, the height of the drill tip, and the depth of each pecking stroke, the number of times the drill tip cutting edge completely cuts the material during the overall pecking stroke process is obtained.

[0025] Sort the signal feature values ​​in the maximum value set in descending order, and denote the first n signal feature values ​​as the first feature set. At the same time, denote the position of each signal feature value in the first feature set in the maximum value set as the first position set; where n is a positive integer.

[0026] Sort each position in the first position set in descending order, and traverse the sorted first position set to determine whether the sorted positions are consecutive.

[0027] If it is determined that the positions after the arrangement are not consecutive, then the non-consecutive positions are removed from the first position set after the arrangement to obtain the second position set;

[0028] Based on the second location set, the signal feature values ​​in the first feature set are filtered to obtain the second feature set;

[0029] The average value of each signal feature value in the second feature set is used as the monitoring feature value of the target hole.

[0030] Optionally, after determining the monitoring characteristic value of the target hole based on the signal characteristic values ​​corresponding to each of the sub-pecking drilling processes, the method further includes:

[0031] Determine whether the monitoring feature value is within the monitoring threshold range; wherein the monitoring threshold is obtained by learning the monitoring feature values ​​of multiple wells;

[0032] If it is determined that the monitored feature value is not within the monitoring threshold range, an alarm message is sent to the staff.

[0033] On the one hand, a signal feature extraction device for state monitoring is provided, the device comprising:

[0034] The machining signal determination unit is used to determine the overall machining signal of the overall pecking and drilling process of the target hole according to the target CNC program instructions; wherein, the overall pecking and drilling process includes multiple sub-pecking and drilling processes, and the overall machining signal includes multiple sub-machining signals, with one sub-pecking and drilling process corresponding to one sub-machining signal;

[0035] The signal feature value determination unit is used to extract features from the overall processing signal using a sliding time window method, and determine the signal feature values ​​corresponding to each sub-pecking drilling process.

[0036] The monitoring feature value determination unit is used to determine the monitoring feature value of the target hole based on the signal feature value corresponding to each of the sub-pecking drilling processes.

[0037] On one hand, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement any of the methods described above.

[0038] On the one hand, a storage medium is provided that stores computer program instructions thereon, which, when executed by a processor, implement any of the methods described above.

[0039] Compared with the prior art, the beneficial effects of this application are as follows:

[0040] In this application, when extracting signal features from a pecking drilling tool, firstly, the overall machining signal of the overall pecking drilling process of the target hole can be determined according to the target CNC program instructions; wherein, the overall pecking drilling process includes multiple sub-pecking drilling processes, and the overall machining signal includes multiple sub-machining signals, with one sub-pecking drilling process corresponding to one sub-machining signal; then, a sliding time window method can be used to extract features from the overall machining signal to determine the signal feature values ​​corresponding to each sub-pecking drilling process; finally, the monitoring feature values ​​of the target hole can be determined according to the signal feature values ​​corresponding to each sub-pecking drilling process.

[0041] Based on this, in this application, for the pecking drilling process, the "sliding time window method" is used for feature extraction. Therefore, the signal features generated when the drill tip is fully drilled into the workpiece can be accurately located. This not only reduces the interference of factors such as changes in cutting allowance (i.e., reduces the signal fluctuation interference caused by the drill tip not being fully drilled into the workpiece in the early stage of hole making and the drill tip having partially drilled out of the workpiece in the late stage of hole making), but also more accurately locates the influence of the drilling process, improves the accuracy of drilling tool status monitoring, and avoids the interference of hole position differences caused by the allowance on the upper and lower surfaces of the hole and structural deformation. Attached Figure Description

[0042] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the drawings described below are only embodiments of this application. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0043] Figure 1 This is a schematic diagram of an application scenario provided by an embodiment of this application;

[0044] Figure 2 A schematic diagram of a signal feature extraction method for state monitoring provided in an embodiment of this application;

[0045] Figure 3 A schematic diagram illustrating the setting of the drilling process instruction provided in an embodiment of this application;

[0046] Figure 4 A schematic diagram of the overall processing signal for the overall pecking and drilling process provided in an embodiment of this application;

[0047] Figure 5 Another schematic diagram of the overall processing signal for the overall pecking and drilling process provided in the embodiments of this application;

[0048] Figure 6 This is a schematic diagram of a signal feature extraction device for state monitoring provided in an embodiment of this application.

[0049] The diagram is labeled as follows: 10-Signal feature extraction device for status monitoring, 101-Processor, 102-Memory, 103-I / O interface, 104-Database, 60-Signal feature extraction device for status monitoring, 601-Processing signal determination unit, 602-Signal feature value determination unit, 603-Monitoring feature value determination unit, 604-Alarm determination unit. Detailed Implementation

[0050] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application. Unless otherwise specified, the embodiments and features in the embodiments of this application can be arbitrarily combined with each other. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than that shown here.

[0051] As is well known, aircraft structural components are trending towards larger, more integrated, and more complex designs, requiring drilling to create connecting holes to meet subsequent assembly needs. For connecting holes in parts made of difficult-to-machine materials, a pecking drill method is typically used to achieve longer tool life and better machining quality. Furthermore, in metal cutting, cutting tools gradually wear down and may even break or fracture over time. Because the tool is in direct contact with the workpiece, excessive tool wear and breakage will reduce the dimensional accuracy and surface quality of the workpiece, potentially even leading to its scrapping. Therefore, wear on drilling tools also significantly affects the dimensional and positional accuracy of holes.

[0052] Currently, in the machining process, the condition of cutting tools mainly relies on the operator's experience to judge. Operators need to monitor the tool's condition in real time and replace it promptly when it wears down to a certain extent or breaks. However, human factors have a significant impact, making it difficult to respond promptly to some abnormal situations. Furthermore, while commercial tool monitoring systems such as ARTIS and Siemens are maturely applied in the automotive industry, their application in the drilling process of difficult-to-machine materials in aircraft presents challenges. Due to the significant differences in rigidity, thickness, and allowance on the upper and lower surfaces of holes during the drilling process of aircraft structural components, and the large fluctuations in the condition of different batches of parts caused by deformation or assembly errors in large aircraft structural components, the repeatability of drilling signal characteristics is weak. Therefore, the traditional method of learning and comparing monitoring based on statistical values ​​calculated from the original signal has low accuracy and frequently generates false alarms, affecting normal production.

[0053] Based on this, this application provides a signal feature extraction method for state monitoring. In this method, firstly, the overall machining signal of the overall pecking and drilling process of the target hole can be determined according to the target CNC program instructions; wherein, the overall pecking and drilling process includes multiple sub-pecking and drilling processes, and the overall machining signal includes multiple sub-machining signals, with one sub-pecking and drilling process corresponding to one sub-machining signal; then, the sliding time window method can be used to extract features from the overall machining signal to determine the signal feature values ​​corresponding to each sub-pecking and drilling process; finally, the monitoring feature values ​​of the target hole can be determined according to the signal feature values ​​corresponding to each sub-pecking and drilling process. Based on this, in this application, for the pecking drilling process, the "sliding time window method" is used for feature extraction. Therefore, the signal features generated when the drill tip is fully drilled into the workpiece can be accurately located. This not only reduces the interference of factors such as changes in cutting allowance (i.e., reduces the signal fluctuation interference caused by the drill tip not being fully drilled into the workpiece in the early stage of hole making and the drill tip having partially drilled out of the workpiece in the late stage of hole making), but also more accurately locates the influence of the drilling process, improves the accuracy of drilling tool status monitoring, and avoids the interference of hole position differences caused by the allowance on the upper and lower surfaces of the hole and structural deformation.

[0054] After introducing the design concept of the embodiments of this application, the following is a brief introduction to the application scenarios to which the technical solutions of the embodiments of this application can be applied. It should be noted that the application scenarios described below are only for illustrating the embodiments of this application and are not intended to limit the scope. In specific implementation, the technical solutions provided by the embodiments of this application can be flexibly applied according to actual needs.

[0055] like Figure 1 The diagram shown illustrates an application scenario provided by an embodiment of this application. This application scenario may include a signal feature extraction device 10 for status monitoring.

[0056] The signal feature extraction device 10 for status monitoring can be used to extract signal features from drilling tools. For example, it can be an in-vehicle computer, a personal computer (PC), a server, or a laptop. The signal feature extraction device 10 for status monitoring may include one or more processors 101, memory 102, I / O interfaces 103, and a database 104. Specifically, the processor 101 can be a central processing unit (CPU) or a digital processing unit, etc. The memory 102 can be volatile memory, such as random-access memory (RAM); the memory 102 can also be non-volatile memory, such as read-only memory, flash memory, hard disk drive (HDD), or solid-state drive (SSD); or the memory 102 can be any other medium capable of carrying or storing desired program code in the form of instructions or data structures that can be accessed by a computer, but is not limited thereto. The memory 102 can be a combination of the above-mentioned memories. The memory 102 can store some program instructions of the signal feature extraction method for state monitoring provided in the embodiments of this application. When these program instructions are executed by the processor 101, they can be used to implement the steps of the signal feature extraction method for state monitoring provided in the embodiments of this application, so as to solve the technical problem of low accuracy of tool state identification in the prior art during the drilling process. The database 104 can be used to store data such as target CNC program instructions, overall machining signals, signal feature values, and monitoring feature values ​​involved in the solution provided in the embodiments of this application.

[0057] In this embodiment, the signal feature extraction device 10 for status monitoring can acquire video rendering instructions through the I / O interface 103. Then, the processor 101 of the signal feature extraction device 10 for status monitoring will solve the technical problem of low accuracy in tool status recognition during the drilling process in the prior art by following the program instructions of the signal feature extraction method for status monitoring provided in this embodiment in the memory 102. In addition, the target CNC program instructions, overall machining signals, signal feature values, and monitoring feature values ​​can be stored in the database 104.

[0058] Of course, the methods provided in the embodiments of this application are not limited to... Figure 1 The application scenarios shown can also be used in other possible scenarios, and this application embodiment does not impose any limitations. Figure 1The functions that the various devices in the application scenarios shown can achieve will be described in subsequent method embodiments, and will not be elaborated on here. Below, the methods of the embodiments of this application will be described in conjunction with the accompanying drawings.

[0059] like Figure 2 The diagram shown is a flowchart illustrating a signal feature extraction method for state monitoring provided in this application embodiment. This method can... Figure 1 The signal feature extraction device 10 for status monitoring is used to perform the operation. Specifically, the process of this method is described as follows.

[0060] Step 201: Determine the overall machining signals for the overall drilling process of the target hole according to the target CNC program instructions.

[0061] In this application, the drilling program can be set up according to the standard G-instruction method. Specifically, since the drilling process for each hole is divided into three stages: rapid traverse, rapid feed, and cutting feed, as follows... Figure 3 The diagram illustrates a setting of drilling process instructions provided in an embodiment of this application. Therefore, this application can use CNC program instructions G0, G1Fx1, and G1Fx2 to set the three stages of rapid traverse, rapid feed, and cutting feed, respectively. For example, G1Fx1 can be set to G1F1000, and G1Fx2 to G1F100. Specifically, the G0 instruction corresponds to the rapid traverse portion between holes, where no material cutting occurs; that is, the G0 instruction corresponds to the rapid traverse stage. The G1Fx1 instruction corresponds to the rapid feed portion approaching or moving away from the hole machining position, where no material cutting occurs; that is, the G1Fx1 instruction corresponds to the rapid feed stage. The G1Fx2 instruction corresponds to the portion where hole-making material is removed; that is, the G1Fx2 instruction corresponds to the cutting feed stage.

[0062] In practical applications, the G1Fx2 stage is also the part where each hole is repeatedly machined using the peck-drill method. The number of repetitions is calculated based on the hole depth and the feed per revolution. Figure 4 The diagram shows a schematic of the overall machining signal for the overall pecking and drilling process provided in this application embodiment. Each peak of the signal curve corresponds to a G1Fx2 stage (i.e., a sub-pecking and drilling process). Furthermore, in this application, the overall pecking and drilling process includes multiple sub-pecking and drilling processes, and the overall machining signal includes multiple sub-machining signals. Each sub-pecking and drilling process corresponds to one sub-machining signal. Since changes in the pecking and drilling tool state can cause differences in signal characteristics during material cutting, G1Fx2 is the key monitoring target for the pecking and drilling process in this application. When using the pecking and drilling method, the pecking depth f can be set relatively small each time (e.g., setting the pecking depth f to 0.5mm), and the two stages corresponding to the G1Fx1 and G1Fx2 commands can be repeated.

[0063] Based on this, during the signal feature learning and monitoring process, for each hole-making step, the G1Fx2 instruction in the target Numerical Control (NC) program can be used as a marker to screen the processing signals of the hole-making material removal process, thereby determining the overall processing signals of the overall drilling process of the target hole.

[0064] Step 202: Use the sliding time window method to extract features from the overall processing signal and determine the signal feature values ​​corresponding to each sub-pecking and drilling process.

[0065] In this application, depending on the cutting parameters, each sub-pecking process can be divided into the following three stages:

[0066] (1) In the early stage of hole making, when the drill tip has not fully penetrated the material being processed, the tool is lifted.

[0067] (2) The middle stage of hole making, the period after the drill tip has fully penetrated the material and cut for a period of time and then the tool is lifted.

[0068] (3) The period at the end of hole making, when the drill tip has drilled out of the workpiece material but has not completely cut the workpiece material.

[0069] In this process, the machining signal amplitude varies significantly due to different drilling amounts at different stages. Furthermore, deviations in the blank allowance or form / position deviations for each part result in different hole machining positions. Consequently, the machining allowance of the drill bit at the beginning and end of hole making differs considerably from that of the previous part, leading to poor signal repeatability. However, during the middle stage of hole making, the cutting allowance after the drill tip has fully penetrated the workpiece is the same as that of the previous part, eliminating interference from allowance changes on tool monitoring. Therefore, in this application, the signal characteristics of the middle stage of hole making during the sub-pecking drilling process can be extracted for tool monitoring learning and real-time monitoring.

[0070] Furthermore, for any single-stage drilling process, the single-stage drilling process can be divided into the initial stage of hole making, the middle stage of hole making, and the final stage of hole making. Among them, the initial stage of hole making is the period when the drill tip has not completely drilled into the workpiece material; the middle stage of hole making is the period when the drill tip has completely drilled into the workpiece material and cut a section before lifting the tool; the final stage of hole making is the period when part of the drill tip has drilled out of the workpiece material but has not completely cut the workpiece material.

[0071] Then, the sliding time window method can be used to extract features from any given sub-pecking process to determine the signal feature values ​​corresponding to that sub-pecking process. The time span parameter of the sliding time window is... Set the machining time corresponding to the G1Fx2 instruction in each pecking drill NC program, and the sampling frequency of the machining signal is [value missing]. The total number of samples within the sliding time window .

[0072] Furthermore, when using the sliding time window method to extract features from any sub-pecking process and determine the signal feature value corresponding to any sub-pecking process, firstly, the sliding time window method can be used to extract features from any sub-pecking process and determine the maximum signal value m within any sub-pecking process.

[0073] Then, the target position corresponding to the maximum value m of the signal can be calculated using a preset position calculation formula. In this application, the preset position calculation formula can be expressed as follows:

[0074]

[0075] in, This is the sequence number corresponding to the initial value of the signal within the sliding time window; This is the index corresponding to the maximum signal value within the sliding time window; This represents the total number of signals within the sliding time window.

[0076] Next, since the area with the largest amount of material removal is located in the middle of the hole making process during each sub-pecking drill, in order to improve data processing efficiency, reduce interference from factors such as changes in cutting allowance, and improve the accuracy of drilling tool status monitoring, it is possible to determine whether the target position is within the middle of the hole making process.

[0077] If the target location is determined to be within the middle stage of hole drilling, the maximum signal value is defined as the signal characteristic value corresponding to the middle stage of hole drilling, and this maximum signal value is placed into the maximum value set. Here, the maximum value set M is the set of signal maximum values ​​generated by each sub-drilling process within the overall drilling process of the target hole (the corresponding CNC program segment between two GO instructions). For example, the fluctuation range during the middle stage of hole drilling can be set to... ~ ,like Then, the maximum value m of the acquired signal is considered to be the signal characteristic generated during the middle stage of hole making corresponding to this sub-pecking drilling process, where, It can be set to 0.45. It can be set to 0.55. The maximum value m of the acquired signal is placed into the maximum value set M.

[0078] After finding the signal characteristic value corresponding to the secondary drilling process, it is possible to set... This allows the time window to slide to the next region to calculate the next sub-pecking process.

[0079] Conversely, if the maximum value m of the signal is not a characteristic signal generated during the middle stage of hole making, then the maximum value m of the signal can be marked as an abnormal signal.

[0080] Step 203: Determine the monitoring characteristic value of the target hole based on the signal characteristic value corresponding to each sub-pecking drilling process.

[0081] In practical applications, for drilling complex structural components with multiple holes, the calculated number of times (n) the drill tip completely cuts the material varies due to the different thicknesses of each hole. Furthermore, for parts with different drawing numbers or parts from different batches of the same drawing number, differences in the allowance on the upper and lower surfaces of the holes and the hole's location due to structural deformation lead to variations in the stage of the overall drilling process where the drill tip completely cuts the material. For example... Figure 5 The diagram shown is another schematic representation of the overall machining signal during the drilling process provided in this application embodiment. Compared to the learning data, the drill tip in the monitoring data for drilling at the same location enters the stage of complete material cutting earlier, and also enters the stage of material extraction without complete material cutting earlier. Therefore, when using the entire drilling process data for learning and comparative monitoring, the following will occur... Figure 3 The examples shown illustrate false alarms exceeding the upper and lower limits. The impact of such margins or structural deformations is widespread and unavoidable; therefore, feature extraction is necessary to prevent such false alarms.

[0082] Therefore, to avoid interference from differences in hole position caused by the allowance on the upper and lower surfaces of the hole location and structural deformation, this application employs "adaptive identification of signals generated by the drill tip fully penetrating the material during the drilling process" to more accurately locate the impact of the drilling process, thereby improving the accuracy of drilling tool condition monitoring.

[0083] Specifically, firstly, it can be based on the thickness of the material being drilled. Drill tip height of drilling tools and the depth of each peck The number of times, n, the cutting edge of the drill tip completely cuts the material during the overall pecking drill process is obtained. That is, the number of times n can be determined using the following formula:

[0084]

[0085] in, Since it is a floor function, the degree n is less than 1. The largest integer. For example, material thickness. 3mm, drill tip height If the value is 1.1 mm, then the number of calculations n = 3.

[0086] Then, the signal feature values ​​in the maximum value set M can be sorted in descending order, and the first n signal feature values ​​are denoted as the first feature set. and simultaneously the first feature set The position of each signal feature value in the maximum value set M is denoted as the first position set. Where n is a positive integer. For example, such as Figure 5 As shown, by taking the first three signal feature values ​​to form a set, the learning feature set of the entire pecking process is obtained. The set of monitoring features is (0.7984, 0.8392, 0.7936). The values ​​are (0.7520, 0.7814, 0.7860). By comparison, it can be seen that the drill tip fully penetrates the material cutting stage of the machining process corresponding to the learning process and the monitoring process are not at the same position.

[0087] Next, we can work on the first set of positions. Sort each position in descending order, and then iterate through the first set of positions after the sorting to determine whether the positions after the sorting are consecutive.

[0088] Then, if it is determined that the positions after the arrangement are not consecutive, the non-consecutive positions are removed from the first set of positions after the arrangement to obtain the second set of positions. That is, interference from occasional abnormal signal maximum values ​​can be eliminated to identify the position of the drill tip cutting edge in the material-pecking stage. Conversely, if all positions are determined to be continuous after arrangement, it indicates that there are no occasional abnormal signal maximum values. For example, continuing with the above example... It can be seen that the first set of positions in the learning process and the monitoring process The values ​​in the array are all continuous, therefore, there is no need to remove the maximum signal value corresponding to a non-continuous position.

[0089] Next, we can use the second position set At each position of the first feature set The signal feature values ​​in the sample are filtered to obtain the second feature set. .

[0090] Finally, the second feature set can be... The average value of each signal feature in As a monitoring characteristic value of the target aperture. For example, continuing with the above example. It can be seen that the learning feature value of the learning process is calculated to be 0.8104, and the monitoring feature value of the monitoring process is calculated to be 0.7721.

[0091] In one possible implementation, during the learning process of the pecking drill, the upper and lower limits of the monitoring threshold can be set based on the calculated learning feature value corresponding to each hole (the process for determining the learning feature value is exactly the same as the process for determining the monitoring feature value), thereby determining the monitoring threshold range. Based on this, monitoring can be performed during the next pecking drill. For example, based on the learning feature value corresponding to each hole in the learning process, the upper and lower limits of the monitoring threshold can be set to 0.9725 and 0.6483, respectively.

[0092] Step 204: If it is determined that the monitored characteristic value exceeds the monitoring threshold range, an alarm message is sent to the staff.

[0093] Specifically, firstly, it can be determined whether the monitoring feature value is within the monitoring threshold range; whereby the monitoring threshold is obtained by learning the monitoring feature values ​​of multiple wells.

[0094] Then, if it is determined that the monitored characteristic value is not within the monitoring threshold range, an alarm message is sent to the staff. Conversely, if it is determined that the monitored characteristic value is within the monitoring threshold range, the status of the drilling tool can be monitored based on that monitored characteristic value. For example, continuing with the above example, since the monitored characteristic value is calculated to be 0.7721, the upper and lower limits of the monitoring threshold are 0.9725 and 0.6483, respectively. Therefore, no alarm was required during the processing of the target hole, which greatly avoided false alarms during signal feature extraction.

[0095] In summary, this application proposes a signal feature extraction method for condition monitoring of drilling tools. For the process of machining each hole using a pecking drilling method, a sliding time window method is used to find the maximum signal value corresponding to a single pecking drilling process. Then, signal data showing complete material cutting by the drill tip are further filtered and feature values ​​are calculated. Based on this, this application can effectively and adaptively identify signals generated by the drill tip completely penetrating the material during the middle stage of hole drilling, reducing signal fluctuation interference in the early and late stages of hole drilling, and more accurately locating the impact of the drilling process, thereby improving the accuracy of drilling tool condition monitoring. Furthermore, it can avoid interference from differences in hole position caused by the allowance on the upper and lower surfaces of the hole and structural deformation.

[0096] Based on the same inventive concept, embodiments of this application provide a signal feature extraction device 60 for state monitoring, such as... Figure 6 As shown, the signal feature extraction device 60 for state monitoring includes:

[0097] The machining signal determination unit 601 is used to determine the overall machining signal of the overall pecking and drilling process of the target hole according to the target CNC program instructions; wherein, the overall pecking and drilling process includes multiple sub-pecking and drilling processes, the overall machining signal includes multiple sub-machining signals, and one sub-pecking and drilling process corresponds to one sub-machining signal;

[0098] The signal feature value determination unit 602 is used to extract features from the overall processing signal using a sliding time window method, and determine the signal feature values ​​corresponding to each sub-pecking drilling process.

[0099] The monitoring feature value determination unit 603 is used to determine the monitoring feature value of the target hole based on the signal feature value corresponding to each sub-pecking drilling process.

[0100] Optionally, the processing signal determination unit 601 is also used for:

[0101] Based on the G1Fx2 instruction in the target CNC program, determine the overall machining signal for the overall drilling process of the target hole.

[0102] Optionally, the signal feature value determination unit 602 is also used for:

[0103] For any single-stage drilling process, the single-stage drilling process is divided into the initial stage of hole making, the middle stage of hole making, and the final stage of hole making. Among them, the initial stage of hole making is the period when the drill tip has not completely drilled into the workpiece material; the middle stage of hole making is the period when the drill tip has completely drilled into the workpiece material and cut a section before lifting the tool; the final stage of hole making is the period when part of the drill tip has drilled out of the workpiece material but has not completely cut the workpiece material.

[0104] The sliding time window method is used to extract features from any one sub-pecking process to determine the signal feature value corresponding to any one sub-pecking process.

[0105] Optionally, the signal feature value determination unit 602 is also used for:

[0106] The sliding time window method is used to extract features from any one sub-pecking process to determine the maximum signal value within any one sub-pecking process;

[0107] The target position corresponding to the maximum signal value is calculated using a preset position calculation formula;

[0108] Determine if the target location is within the middle stage of hole making;

[0109] If the target location is determined to be within the middle of the hole-making process, the maximum signal value is determined as the signal characteristic value corresponding to the middle of the hole-making process, and the maximum signal value is placed into the maximum value set.

[0110] Optionally, the monitoring feature value determination unit 603 is also used for:

[0111] Based on the thickness of the material being drilled, the height of the drill tip, and the depth of each pecking stroke, the number of times the drill tip cutting edge completely cuts the material during the overall pecking stroke process is obtained.

[0112] Sort the signal feature values ​​in the maximum value set in descending order, and denote the first n signal feature values ​​as the first feature set. At the same time, denote the position of each signal feature value in the first feature set in the maximum value set as the first position set; where n is a positive integer.

[0113] Sort each position in the first position set in descending order, and traverse the sorted first position set to determine whether the positions are consecutive.

[0114] If it is determined that the positions after the arrangement are not consecutive, then the non-consecutive positions are removed from the first position set after the arrangement to obtain the second position set;

[0115] Based on the second location set, the signal feature values ​​in the first feature set are filtered to obtain the second feature set;

[0116] The average value of each signal feature value in the second feature set is used as the monitoring feature value of the target hole.

[0117] Optionally, the status monitoring signal feature extraction device 60 further includes an alarm determination unit 604, used for:

[0118] Determine whether the monitoring feature value is within the monitoring threshold range; wherein, the monitoring threshold is obtained by learning the monitoring feature values ​​of multiple wells;

[0119] If it is determined that the monitored characteristic value is not within the monitoring threshold range, an alarm message will be sent to the staff.

[0120] The signal feature extraction device 60 for this status monitoring can be used to perform... Figure 2 The method performed by the signal feature extraction device for state monitoring in the illustrated embodiment is described above. Therefore, the functions that each functional module of the signal feature extraction device 60 for state monitoring can achieve can be found by referring to [the relevant documentation / reference]. Figure 2 The embodiments shown are described in detail below.

[0121] In some possible implementations, various aspects of the methods provided in this application can also be implemented as a program product comprising program code that, when run on a computer device, causes the computer device to perform the steps of the methods according to the various exemplary embodiments of this application described above. For example, the computer device may perform actions such as... Figure 2 The method performed by the signal feature extraction device for state monitoring in the illustrated embodiment.

[0122] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks. Alternatively, if the integrated units of this application are implemented as software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of this application, or the parts that contribute to the prior art, can be embodied in the form of software products. These computer software products are stored in a storage medium and include several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, ROM, RAM, magnetic disks, or optical disks.

[0123] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.

[0124] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A method for extracting signal features from state monitoring, characterized in that, The method includes: According to the target CNC program instructions, the overall machining signal for the overall pecking and drilling process of the target hole is determined; wherein, the overall pecking and drilling process includes multiple sub-pecking and drilling processes, and the overall machining signal includes multiple sub-machining signals, with one sub-pecking and drilling process corresponding to one sub-machining signal; The sliding time window method is used to extract features from the overall processing signal to determine the signal feature values ​​corresponding to each sub-pecking and drilling process. Based on the signal characteristic values ​​corresponding to each of the sub-pecking drilling processes, the monitoring characteristic value of the target hole is determined; wherein, the step of determining the monitoring characteristic value of the target hole based on the signal characteristic values ​​corresponding to each of the sub-pecking drilling processes includes: Based on the thickness of the material being drilled, the height of the drill tip, and the depth of each pecking stroke, the number of times the drill tip cutting edge completely cuts the material during the overall pecking stroke process is obtained. The signal feature values ​​in the maximum value set are sorted in descending order, and the first n signal feature values ​​are denoted as the first feature set. At the same time, the position of each signal feature value in the first feature set in the maximum value set is denoted as the first position set; where n is a positive integer; the maximum value set M is the set of signal maximum values ​​generated by each sub-pecking process in the overall pecking process of the target hole. Sort each position in the first position set in descending order, and traverse the sorted first position set to determine whether the sorted positions are consecutive. If it is determined that the positions after the arrangement are not consecutive, then the non-consecutive positions are removed from the first position set after the arrangement to obtain the second position set; Based on the second location set, the signal feature values ​​in the first feature set are filtered to obtain the second feature set; The average value of each signal feature value in the second feature set is used as the monitoring feature value of the target hole.

2. The method as described in claim 1, characterized in that, The step of determining the overall machining signals for the overall drilling process of the target hole according to the target CNC program instructions includes: Based on the G1Fx2 instruction in the target CNC program, the overall machining signal for the overall drilling process of the target hole is determined.

3. The method as described in claim 1, characterized in that, The step of extracting features from the overall processing signal using a sliding time window method to determine the signal feature values ​​corresponding to each sub-pecking drill process includes: For any single-stage drilling process, the single-stage drilling process is divided into the initial stage of hole making, the middle stage of hole making, and the final stage of hole making; wherein, the initial stage of hole making is the period when the drill tip has not completely drilled into the workpiece material; the middle stage of hole making is the period when the drill tip has completely drilled into the workpiece material and cut a section before lifting the tool; the final stage of hole making is the period when part of the drill tip has drilled out of the workpiece material but has not completely cut the workpiece material. The sliding time window method is used to extract features from any one sub-pecking process to determine the signal feature value corresponding to any one sub-pecking process.

4. The method as described in claim 3, characterized in that, The step of extracting features from any one sub-pecking process using a sliding time window method and determining the signal feature value corresponding to any one sub-pecking process includes: The sliding time window method is used to extract features from any one sub-pecking process to determine the maximum signal value within any one sub-pecking process; The target position corresponding to the maximum value of the signal is calculated using a preset position calculation formula; Determine whether the target position is within the middle stage of hole making; If the target position is determined to be within the middle of the hole-making process, then the maximum signal value is determined as the signal characteristic value corresponding to the middle of the hole-making process, and the maximum signal value is placed into the maximum value set.

5. The method as described in claim 4, characterized in that, The preset position calculation formula is expressed as follows: in, This is the sequence number corresponding to the initial value of the signal within the sliding time window; This is the index corresponding to the maximum signal value within the sliding time window; This represents the total number of signals within the sliding time window.

6. The method as described in claim 1, characterized in that, After determining the monitoring characteristic value of the target hole based on the signal characteristic values ​​corresponding to each of the sub-pecking drilling processes, the method further includes: Determine whether the monitoring feature value is within the monitoring threshold range; wherein the monitoring threshold is obtained by learning the monitoring feature values ​​of multiple wells; If it is determined that the monitored feature value is not within the monitoring threshold range, an alarm message is sent to the staff.

7. A signal feature extraction device for state monitoring, characterized in that, The device includes: The machining signal determination unit is used to determine the overall machining signal of the overall pecking and drilling process of the target hole according to the target CNC program instructions; wherein, the overall pecking and drilling process includes multiple sub-pecking and drilling processes, and the overall machining signal includes multiple sub-machining signals, with one sub-pecking and drilling process corresponding to one sub-machining signal; The signal feature value determination unit is used to extract features from the overall processing signal using a sliding time window method, and determine the signal feature values ​​corresponding to each sub-pecking drilling process. The monitoring feature value determination unit is used to determine the monitoring feature value of the target hole based on the signal feature values ​​corresponding to each of the sub-pecking drilling processes. The step of determining the monitoring feature value of the target hole based on the signal feature values ​​corresponding to each of the sub-pecking drilling processes includes: obtaining the number of times the drill tip cutting edge completely cuts the material during the overall pecking drilling process based on the thickness of the drilling material, the drill tip height of the drilling tool, and the depth of each pecking operation; sorting the signal feature values ​​in the maximum value set in descending order, recording the first n signal feature values ​​as the first feature set, and simultaneously recording the position of each signal feature value in the first feature set within the maximum value set as the first position. The set of values ​​is M, where n is a positive integer; the maximum value set M is the set of signal maximum values ​​generated by each sub-pecking process in the overall pecking process of the target hole; the positions in the first position set are sorted in descending order, and the sorted first position set is traversed to determine whether the positions are continuous; if it is determined that the positions are not continuous, the discontinuous positions are removed from the sorted first position set to obtain the second position set; based on the second position set, the signal feature values ​​in the first feature set are filtered to obtain the second feature set; the average value of each signal feature value in the second feature set is used as the monitoring feature value of the target hole.

8. An electronic device, characterized in that, The device includes: Memory, used to store program instructions; A processor is configured to invoke program instructions stored in the memory and execute the method described in any one of claims 1-6 according to the obtained program instructions.

9. A storage medium, characterized in that, The storage medium stores computer-executable instructions for causing a computer to perform the method described in any one of claims 1-6.

Images