Tool holder tightness detection method and device for machine tool tool magazine, computer program product

Abstract

The application discloses a tool apron tightness detection method and device of a machine tool tool magazine, and a computer program product. The method comprises the following steps: acquiring a plurality of tightness detection data between a tool and a tool apron, wherein the tightness detection data is collected by a sensor arranged in the tool apron during a tightness detection process after the tool enters the tool apron; performing feature extraction on the plurality of tightness detection data to obtain target feature data corresponding to each kind of tightness detection data; inputting the target feature data into a tightness state determination model to process the target feature data by using the tightness state determination model, and obtaining the tightness degree between the tool apron and the tool; and determining the tightness state between the tool apron and the tool according to a tightness threshold range in which the tightness degree is located. The application solves the technical problem that the traditional tool tightness detection method in the related art mainly relies on manual inspection or simple mechanical devices, resulting in low inspection efficiency and limited detection precision.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent manufacturing and automation control, in particular to a tool sleeve tightness detection method and device for a machine tool tool magazine, and a computer program product. BACKGROUND

[0002] In modern manufacturing, machine tool tool magazines, as an important tool management system, are widely used in automated machining processes. The tool magazine is responsible for storing and managing different types of cutting tools, and the tightness of the tools directly affects the machining accuracy, efficiency and safety of the machine tool. However, traditional tool tightness detection methods mainly rely on manual inspection or simple mechanical devices, which have some limitations, including low efficiency of manual inspection, limited accuracy of mechanical detection, poor real-time performance, and potential safety hazards.

[0003] To address the issue of low inspection efficiency and limited detection accuracy caused by the traditional tool tightness detection method relying mainly on manual inspection or simple mechanical devices, no effective solution has been proposed yet. SUMMARY

[0004] The embodiments of the present application provide a tool sleeve tightness detection method and device for a machine tool tool magazine, and a computer program product, to at least solve the technical problem of low inspection efficiency and limited detection accuracy caused by the traditional tool tightness detection method relying mainly on manual inspection or simple mechanical devices in the related art.

[0005] According to an aspect of an embodiment of the present application, a tool sleeve tightness detection method for a machine tool tool magazine is provided, comprising: obtaining a plurality of tightness detection data between a tool and a tool sleeve, wherein the tightness detection data is obtained by a sensor deployed in the tool sleeve during a tightness detection process after the tool enters the tool sleeve; extracting features from the plurality of tightness detection data to obtain target feature data corresponding to each tightness detection data; inputting the target feature data into a tightness state determination model to process the target feature data using the tightness state determination model, to obtain the tightness degree between the tool sleeve and the tool, wherein the tightness state determination model is trained using a plurality of training data through deep learning, each of the plurality of training data includes sample target feature data and a sample tightness degree corresponding to the sample target feature data; determining the tightness state between the tool sleeve and the tool according to the tightness threshold range in which the tightness degree is located.

[0006] Optionally, the tightness detection data between the tool and the tool holder is acquired, including at least one of the following: acquiring a spacing distance between the tool and the bottom of the tool holder detected by a photoelectric sensor; acquiring a clamping force between the tool holder and the tool detected by a force sensor, wherein the clamping force is used to reflect the fixing degree between the tool holder and the tool; and acquiring a vibration frequency of the tool holder and the tool in the machine tool processing process detected by a vibration sensor.

[0007] Optionally, the tightness detection data between the tool and the tool holder is acquired, including one of the following: in the case that the current time reaches a predetermined time, receiving the tightness detection data transmitted by the sensor based on a communication channel, wherein the predetermined time is a preset acquisition time, and the communication channel is used for data transmission with the sensor; and in the case that a tightness detection signal is received, sending an acquisition instruction to the sensor to control the sensor to acquire the current tightness detection data, and receiving the tightness detection data through the communication channel.

[0008] Optionally, the tightness detection data is feature extracted to obtain target feature data, including: using a first formula to feature extract the tightness detection data to obtain the target feature data, wherein the first formula is: , i represents the label of the sensor, t represents the current time, f[] represents an activation function, W represents a convolution kernel, b represents a bias, represents the tightness detection data collected by the i-th sensor at the current time t, represents the target feature data corresponding to .

[0009] Optionally, before the target feature data is input into the tightness state determination model to process the target feature data by using the tightness state determination model to obtain the tightness degree between the tool holder and the tool, the tool holder tightness detection method of the machine tool magazine further comprises: iteratively training a convolutional neural network model by using a plurality of sets of sample training data collected by each sensor in a historical time period until an iteration termination condition is reached, to obtain an initial tightness state determination sub-model corresponding to the sensor, wherein each of the plurality of sets of sample training data comprises: the sample target feature data, a sample sub-tightness degree corresponding to the sample target feature data, and the iteration termination condition is at least one of: the number of iterations reaches a preset number of iterations, and the error between the predicted value and the true value of the convolutional neural network model is less than an error threshold; verifying the accuracy of the initial tightness state determination sub-model corresponding to each sensor by using the plurality of sets of sample training data in a cross-validation manner to obtain the accuracy of each tightness state determination sub-model; and determining the initial tightness state determination sub-model as a tightness state determination sub-model when the accuracy is greater than an accuracy threshold.

[0010] Optionally, the tightness state determination model comprises a plurality of tightness state determination sub-models, and inputting the target feature data into the tightness state determination model to process the target feature data by using the tightness state determination model to obtain the tightness degree between the tool holder and the tool comprises: inputting the target feature data corresponding to each sensor into the tightness state determination sub-model to process the target feature data by using the tightness state determination sub-model to obtain a sub-tightness degree corresponding to the target feature data, wherein each tightness state determination sub-model is used to process the data collected by a corresponding sensor; determining an attention weight of each sub-tightness degree by using a second formula according to the accuracy of each tightness state determination sub-model, wherein the second formula is: , , wherein represents the accuracy of the tightness state determination sub-model corresponding to the i-th sensor, and n represents the total number of sensors, , wherein represents the attention weight of the sub-tightness degree corresponding to the i-th sensor, and the attention weight indicates the weight proportion of the sub-tightness degree in the tightness degree; and determining the tightness degree between the tool holder and the tool by using a third formula according to a plurality of sub-tightness degrees and the attention weight corresponding to each sub-tightness degree, wherein the third formula is: , and P(t) represents the tightness degree between the tool holder and the tool at the current time.

[0011] Optionally, the tightness threshold range comprises a first tightness threshold range, a second tightness threshold range, a third tightness threshold range, a fourth tightness threshold range and a fifth tightness threshold range, and the tightness state between the tool holder and the tool is determined according to the tightness threshold range in which the tightness degree is located, comprising: in the case that the tightness degree is located in the first tightness threshold range, determining that the tightness state is a normal state, wherein the first tightness threshold range is a range in which the tightness degree is less than or equal to a first tightness threshold; in the case that the tightness degree is located in the second tightness threshold range, determining that the tightness state is a slight looseness state, wherein the second tightness threshold range is a range in which the tightness degree is greater than the first tightness threshold and less than or equal to a second tightness threshold, and the second tightness threshold is greater than the first tightness threshold; in the case that the tightness degree is located in the third tightness threshold range, determining that the tightness state is a moderate looseness state, wherein the third tightness threshold range is a range in which the tightness degree is greater than the second tightness threshold and less than or equal to a third tightness threshold, and the third tightness threshold is greater than the second tightness threshold; in the case that the tightness degree is located in the fourth tightness threshold range, determining that the tightness state is a severe looseness state, wherein the fourth tightness threshold range is a range in which the tightness degree is greater than the third tightness threshold and less than or equal to a fourth tightness threshold, and the fourth tightness threshold is greater than the third tightness threshold; in the case that the tightness degree is located in the fifth tightness threshold range, determining that the tightness state is a failure state, wherein the fifth tightness threshold range is a range in which the tightness degree is greater than the fourth tightness threshold.

[0012] According to another aspect of the embodiment of the present application, a tool holder tightness detection device of a machine tool tool magazine is also provided, comprising: a first acquisition unit configured to acquire a plurality of tightness detection data between a tool and a tool holder, wherein the tightness detection data is obtained by a sensor arranged in the tool holder during a tightness detection process after the tool enters the tool holder; a second acquisition unit configured to perform feature extraction on the plurality of tightness detection data to obtain target feature data corresponding to each of the tightness detection data; a third acquisition unit configured to input the target feature data into a tightness state determination model to process the target feature data by using the tightness state determination model to obtain a tightness degree between the tool holder and the tool, wherein the tightness state determination model is obtained by training a plurality of sets of training data by deep learning, and each of the plurality of sets of training data comprises sample target feature data and a sample tightness degree corresponding to the sample target feature data; and a first determination unit configured to determine a tightness state between the tool holder and the tool according to a tightness threshold range in which the tightness degree is located.

[0013] Optionally, the first acquisition unit comprises at least one of the following: a first acquisition module configured to acquire a spacing distance between the tool and the bottom of the tool sleeve detected by the photoelectric sensor; a second acquisition module configured to acquire a clamping force between the tool sleeve and the tool detected by the force sensor, wherein the clamping force is used to reflect the fixing degree between the tool sleeve and the tool; and a third acquisition module configured to acquire a vibration frequency of the tool sleeve and the tool in the machine tool processing process detected by the vibration sensor.

[0014] Optionally, the first acquisition unit comprises one of the following: a first receiving module configured to receive the tightness detection data transmitted by the sensor based on a communication channel in a case where a current time reaches a predetermined time, wherein the predetermined time is a preset acquisition time, and the communication channel is used for data transmission with the sensor; and a second receiving module configured to send an acquisition instruction to the sensor to control the sensor to acquire the current tightness detection data in a case where a tightness detection signal is received, and receive the tightness detection data through the communication channel.

[0015] Optionally, the second acquisition unit comprises a fourth acquisition module configured to perform feature extraction on the tightness detection data by using a first formula to obtain the target feature data, wherein the first formula is: , i represents a label of the sensor, t represents a current time, f[] represents an activation function, W represents a convolution kernel, b represents a bias, represents the tightness detection data collected by the i-th sensor at the current time t, represents the target feature data corresponding to .

[0016] Optionally, the tool holder tightness detection device of the machine tool tool magazine further comprises: a fourth acquisition unit, configured to, before inputting the target feature data into the tightness state determination model to process the target feature data by using the tightness state determination model to obtain the tightness degree between the tool holder and the tool, iteratively train a convolutional neural network model by using a plurality of sets of sample training data collected by each sensor in a historical time period until an iteration termination condition is reached, to obtain an initial tightness state determination sub-model corresponding to the sensor, wherein each of the plurality of sets of sample training data comprises: the sample target feature data, a sample sub-tightness degree corresponding to the sample target feature data, and the iteration termination condition is at least one of: the number of iterations reaches a preset number of iterations, and the error between the predicted value and the true value of the convolutional neural network model is less than an error threshold; a fifth acquisition unit, configured to verify the accuracy of the initial tightness state determination sub-model corresponding to each sensor by using the plurality of sets of sample training data corresponding to each sensor in a cross-validation manner to obtain the accuracy of each tightness state determination sub-model; and a second determination unit, configured to determine the initial tightness state determination sub-model as a tightness state determination sub-model if the accuracy is greater than an accuracy threshold.

[0017] Optionally, the tightness state determination model comprises a plurality of tightness state determination sub-models, and the third acquisition unit comprises: a fifth acquisition module, configured to input the target feature data corresponding to each sensor into the tightness state determination sub-model to process the target feature data by using the tightness state determination sub-model to obtain a sub-tightness degree corresponding to the target feature data, wherein each tightness state determination sub-model is used to process data collected by a corresponding sensor; a first determination module, configured to determine an attention weight of each sub-tightness degree by using a second formula according to the accuracy of each tightness state determination sub-model, wherein the second formula is: , , wherein represents the accuracy of the tightness state determination sub-model corresponding to the i-th sensor, and n represents the total number of sensors, , wherein represents the attention weight of the sub-tightness degree corresponding to the i-th sensor, and the attention weight indicates the proportion of the weight of the sub-tightness degree in the tightness degree; and a second determination module, configured to determine the tightness degree between the tool holder and the tool by using a third formula according to a plurality of sub-tightness degrees and the attention weight corresponding to each sub-tightness degree, wherein the third formula is: , and P(t) represents the tightness degree between the tool holder and the tool at the current time.

[0018] Optionally, the tightness threshold range includes a first tightness threshold range, a second tightness threshold range, a third tightness threshold range, a fourth tightness threshold range and a fifth tightness threshold range, and the first determining unit includes: a third determining module, configured to determine the tightness state as the normal state when the tightness degree is in the first tightness threshold range, wherein the first tightness threshold range is a range in which the tightness degree is less than or equal to a first tightness threshold; a fourth determining module, configured to determine the tightness state as the slight looseness state when the tightness degree is in the second tightness threshold range, wherein the second tightness threshold range is a range in which the tightness degree is greater than the first tightness threshold and less than or equal to a second tightness threshold, and the second tightness threshold is greater than the first tightness threshold; a fifth determining module, configured to determine the tightness state as the moderate looseness state when the tightness degree is in the third tightness threshold range, wherein the third tightness threshold range is a range in which the tightness degree is greater than the second tightness threshold and less than or equal to a third tightness threshold, and the third tightness threshold is greater than the second tightness threshold; a sixth determining module, configured to determine the tightness state as the severe looseness state when the tightness degree is in the fourth tightness threshold range, wherein the fourth tightness threshold range is a range in which the tightness degree is greater than the third tightness threshold and less than or equal to a fourth tightness threshold, and the fourth tightness threshold is greater than the third tightness threshold; and a seventh determining module, configured to determine the tightness state as the fault state when the tightness degree is in the fifth tightness threshold range, wherein the fifth tightness threshold range is a range in which the tightness degree is greater than the fourth tightness threshold.

[0019] According to another aspect of the embodiments of the present application, there is also provided a tool pocket tightness detection system of a machine tool tool magazine, which uses any of the tool pocket tightness detection methods described above.

[0020] According to another aspect of the embodiments of the present application, there is also provided a computer readable storage medium comprising a stored program, wherein the program performs any of the tool pocket tightness detection methods described above.

[0021] According to another aspect of the embodiments of the present application, there is also provided a processor configured to execute a program, wherein the program performs any of the tool pocket tightness detection methods described above when executed.

[0022] According to another aspect of the embodiments of the present application, there is also provided a computer program product comprising computer instructions configured to perform any of the tool pocket tightness detection methods described above when executed by a processor.

[0023] In this embodiment of the invention, various tightness detection data between the cutting tool and the tool holder can be acquired. These tightness detection data are collected by sensors deployed within the tool holder during the tightness detection process after the cutting tool enters the tool holder. Feature extraction is performed on these various tightness detection data to obtain target feature data corresponding to each type of tightness detection data. The target feature data is then input into a tightness state determination model to process the target feature data and obtain the degree of tightness between the tool holder and the cutting tool. The tightness state determination model is trained using multiple sets of training data through deep learning. Each set of training data includes: sample target feature data and the corresponding sample tightness degree. The tightness state between the tool holder and the cutting tool is determined based on the tightness threshold range within which the tightness degree falls. The above technical solution achieves the goal of collecting tightness detection data between the tool holder and the tool during the tightness detection process using sensors, processing the data using a trained deep learning model to obtain the tightness degree between the tool holder and the tool, and finally determining the tightness state of the tool holder based on the threshold range of the tightness degree. This realizes the technical effect of intelligent analysis to determine the tightness state between the tool holder and the tool through automated data collection and analysis, improving detection efficiency and accuracy. It also solves the technical problem that traditional tool tightness detection methods mainly rely on manual inspection or simple mechanical devices, resulting in low inspection efficiency and limited detection accuracy. Attached Figure Description

[0024] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0025] Figure 1 This is a hardware structure block diagram of a mobile terminal for a method of detecting the tightness of a tool holder in a machine tool magazine according to an embodiment of the present invention.

[0026] Figure 2 This is a flowchart of a method for detecting the tightness of a tool holder in a machine tool magazine according to an embodiment of the present invention;

[0027] Figure 3 This is a schematic diagram of a tool holder tightness detection system for a machine tool magazine according to an embodiment of the present invention;

[0028] Figure 4(a) is a schematic diagram of the barrel-type cutter sleeve before improvement according to an embodiment of the present invention;

[0029] Figure 4(b) is a schematic diagram of the improved barrel-type cutter sleeve according to an embodiment of the present invention;

[0030] Figure 5is a flow chart at a terminal node according to an embodiment of the present application;

[0031] Figure 6 is a flow chart at a coordinator node according to an embodiment of the present application;

[0032] Figure 7 is a schematic diagram of a tool holder tightness detection device of a machine tool tool magazine according to an embodiment of the present application.

[0033] Wherein, the above figures include the following reference signs:

[0034] 102, processor; 104, memory; 106, transmission device; 108, input and output device; A1, force sensor; A2, photoelectric sensor; A3, vibration sensor; B1, information sent by sensor timing; B2, query request sent by coordinator node; C1, query instruction sent at computer serial port; C2, wireless data sent by terminal node timing. DETAILED DESCRIPTION

[0035] In order for those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should be within the scope of protection of the present application.

[0036] It should be noted that the terms "first", "second", and the like in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily indicate a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not necessarily limit to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0037] As introduced in the background, the conventional tool tightness detection method in the related art mainly relies on manual inspection or simple mechanical device, resulting in low inspection efficiency and limited detection accuracy. In view of the above defects, a tool magazine tool holder tightness detection method and device, computer program product are provided in the embodiments of the present application.

[0038] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.

[0039] The methods and embodiments provided in this invention can be executed on a mobile terminal, a computer terminal, or a similar computing device. Taking running on a mobile terminal as an example, Figure 1 This is a hardware structure block diagram of a mobile terminal for a method of detecting the tightness of a tool holder in a machine tool magazine, according to an embodiment of the present invention. Figure 1 As shown, a mobile terminal may include one or more ( Figure 1 Only one is shown in the diagram. A processor 102 (which may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.) and a memory 104 for storing data are also shown. The mobile terminal may further include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the mobile terminal described above. For example, the mobile terminal may also include components that are more... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0040] The memory 104 can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to the machine tool magazine tool sleeve tightness detection method in this embodiment of the invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, thereby implementing the above-described method. The memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of the above-described networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof. The transmission device 106 is used to receive or send data via a network. Specific examples of the above-described networks may include wireless networks provided by the mobile terminal's communication provider. In one example, the transmission device 106 includes a network interface controller (NIC), which can be connected to other network devices via a base station to communicate with the Internet. In one example, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0041] According to the embodiment of the present application, a method embodiment of a tool holder tightness detection method of a machine tool tool magazine is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described herein can be executed in a different order.

[0042] Figure 2 is a flowchart of a tool holder tightness detection method of a machine tool tool magazine according to the embodiment of the present application, as shown in Figure 2 , the method comprises the following steps:

[0043] In step S202, a plurality of tightness detection data between the tool and the tool holder is obtained, wherein the tightness detection data is obtained by the sensor deployed in the tool holder during the tightness detection process after the tool enters the tool holder.

[0044] In this embodiment, a plurality of sensors can be deployed inside the tool holder to collect corresponding data during the tightness detection process by the sensors after the tool enters the tool holder, so as to provide a data basis for subsequent analysis of the tightness state between the tool and the tool holder. The process of tightness detection here can be understood as the process of detection after the tool enters the tool holder.

[0045] The above embodiment of the present application will be described in detail below, Figure 3 , the above embodiment of the present application will be described in detail below, Figure 3 is a schematic diagram of a tool holder tightness detection system of a machine tool tool magazine according to the embodiment of the present application, as shown in Figure 3 , the tool holder tightness detection system can use the tool holder tightness detection method of the machine tool tool magazine based on deep learning provided by the embodiment of the present application, mainly including the following modules: data collection module, data processing module, model training module, model verification module and real-time detection module; The overall implementation process is: the data collection module transmits the sensor information on all tool holders to the computer in real time through the serial port UART, and the remaining modules are completed on the computer.

[0046] According to the above embodiment of the present application, in the above step S202, the tightness detection data between the tool and the tool holder is obtained, including at least one of the following: obtaining the interval distance between the tool and the bottom of the tool holder detected by the photoelectric sensor; obtaining the clamping force between the tool holder and the tool detected by the force sensor, wherein the clamping force is used to reflect the fixing degree between the tool holder and the tool; obtaining the vibration frequency of the tool holder and the tool during the machine tool processing process detected by the vibration sensor.

[0047] The above embodiments of the present invention will be described in detail below with reference to Figures 4(a) and 4(b). Figure 4(a) is a schematic diagram of the improved barrel-type tool holder according to an embodiment of the present invention before the improvement, and Figure 4(b) is a schematic diagram of the improved barrel-type tool holder according to an embodiment of the present invention after the improvement. The improved tool holder structure shown in Figure 4(b) has three additional sensors compared to the improved tool holder shown in Figure 4(a). Among them, A1 is a force sensor, A2 is a photoelectric sensor, and A3 is a vibration sensor. The photoelectric sensor A2 can detect the distance from the tool to the bottom of the tool holder, the force sensor A1 can detect the clamping force between the tool holder and the tool, and the vibration sensor A3 can detect the vibration frequency of the tool holder and the tool in the working state. By collecting corresponding data through these sensors during the tightness detection process, the aim is to effectively improve the accuracy of tool holder tightness detection, real-time monitoring capability, data analysis capability, and overall efficiency.

[0048] According to the above embodiments of the present invention, in step S202, acquiring the tightness detection data between the tool and the tool holder includes one of the following: when the current time reaches a predetermined time, receiving the tightness detection data transmitted by the sensor based on the communication channel, wherein the predetermined time is a pre-set acquisition time, and the communication channel is used for data transmission with the sensor; when a tightness detection signal is received, sending an acquisition command to the sensor to control the sensor to acquire the current tightness detection data, and receiving the tightness detection data through the communication channel.

[0049] Specifically, in Figure 3 The data collection module shown mainly involves the deployment of sensors, the hardware design of terminal nodes and coordinator nodes, and the software design of terminal nodes and coordinator nodes. The information collected by each sensor deployed in the tool holder can be transmitted to an independent terminal node through wires. The hardware design of this node is equivalent to the integration of a main control chip, a wireless communication module, a sensor module, and a voltage regulator chip. Moreover, the main control chip generally needs to have certain computing power and A / D conversion functions in order to control the wireless communication module, the sensor module, and the voltage regulator chip.

[0050] The following is combined with Figure 5 and Figure 6 The embodiments of the present invention will be described in detail below. Figure 5 This is a flowchart at the terminal node according to an embodiment of the present invention. Figure 6 This is a flowchart of the coordinator node according to an embodiment of the present invention.

[0051] In the embodiment provided by the application, ZigBee technology can be used to realize wireless communication between the terminal node and the coordinator node, that is, signals transmitted by the terminal node are received and arranged by the coordinator node, and then transmitted to the computer through the serial port UART, therefore, the hardware design of the coordinator node is similar to that of the terminal node, but does not include the connection of the sensor module, and if the interface of the computer and the coordinator node is inconsistent, an interface conversion module needs to be added in the hardware design of the coordinator node; for the software design of the terminal node and the coordinator node, since wireless communication of multiple sensors is involved, the communication protocol needs to be designed, then the program design of sensor data collection and terminal node information transmission is performed according to the timing or the situation of receiving the query request from the coordinator node, and the program design of the coordinator node information transmission to the computer is performed according to the situation of the computer serial port sending a query instruction or the terminal node sending information at a fixed time, specifically, as shown in Figure 5 , the terminal node can receive information B1 transmitted by each sensor at a fixed time, or control each sensor to collect data to obtain corresponding tightness detection data when receiving the query request B2 from the coordinator node; as shown in Figure 6 , the coordinator node can send a query request to the terminal node according to the query instruction C1 from the computer serial port to control the sensor to collect data, and then receive the tightness detection data from the terminal node, or receive wireless data C2 transmitted by the terminal node at a fixed time to obtain corresponding tightness detection data.

[0052] In step S204, feature extraction is performed on the multiple tightness detection data to obtain target feature data corresponding to each kind of tightness detection data.

[0053] In this embodiment, the data processing module shown in Figure 3 can be used to perform feature extraction on the tightness detection data collected by the multiple sensors to obtain target feature data corresponding to each kind of tightness detection data.

[0054] According to the above embodiment of the application, in step S204, feature extraction is performed on the tightness detection data to obtain target feature data, including: performing feature extraction on the tightness detection data by using a first formula to obtain target feature data, wherein the first formula is: , i represents the label of the sensor, t represents the current time, f[] represents an activation function, W represents a convolution kernel, b represents a bias, represents the tightness detection data collected by the i th sensor at the current time t, represents target feature data corresponding to .

[0055] Specifically, the data processing module mainly includes data preprocessing and feature extraction. Data preprocessing primarily involves denoising and normalizing the signals collected by force, photoelectric, and vibration sensors. Feature extraction utilizes convolutional neural networks to extract statistical features such as peak value, mean, and variance from force sensor data; features such as light intensity change rate and displacement from photoelectric sensors; and features such as vibration frequency and amplitude from vibration sensors. Furthermore, by repeatedly collecting and processing sensor data, a corresponding dataset is formed, providing a foundation for subsequent model training and validation. Assuming the input sensor signals are (i=1, 2, 3, where 1 represents the force sensor signal, 2 represents the photoelectric sensor signal, and 3 represents the vibration sensor signal; all subsequent references to i express the above meanings), denoising can employ a simple low-pass filter, and the filtered signal can be represented as... ,in, Let be the impulse response function of the low-pass filter; the normalization process is as follows: ,in, and These are the maximum and minimum values ​​of the filtered signal, respectively. This is the normalized signal, that is, the processed tightness detection data collected by the i-th sensor at the current time t; using a convolutional neural network to extract features, it can be represented as... ,in, Represents the eigenvector, i.e., with Corresponding target feature data, It is a convolution kernel. It represents the bias, and * indicates the convolution operation. The function represents the activation function, typically the ReLU (Modified Linear Unit) function, which can be used to extract features from the corresponding sensor data.

[0056] Step S206: Input the target feature data into the tightness determination model to process the target feature data and obtain the tightness between the tool holder and the tool. The tightness determination model is trained using multiple sets of training data through deep learning. Each set of training data includes: sample target feature data and the sample tightness corresponding to the sample target feature data.

[0057] In this embodiment, it is possible to utilize Figure 3 The real-time detection module shown processes the target feature data obtained by the data processing module to analyze the degree of analysis between the tool holder and the tool.

[0058] According to the above-mentioned embodiments of the application, before the step S206, that is, before the target feature data is input into the tightness state determination model to process the target feature data by using the tightness state determination model to obtain the tightness degree between the tool sleeve and the tool, the tool sleeve tightness detection method of the machine tool magazine further comprises: iteratively training the convolutional neural network model by using a plurality of sets of sample training data collected by each sensor in a historical time period, until an iteration termination condition is reached, to obtain an initial tightness state determination sub-model corresponding to the sensor, wherein each of the plurality of sets of sample training data comprises: sample target feature data, and a sample sub-tightness degree corresponding to the sample target feature data, and the iteration termination condition is at least one of: the number of iterations reaches a preset number of iterations, and the error between the predicted value and the true value of the convolutional neural network model is less than an error threshold; verifying the accuracy of the corresponding initial tightness state determination sub-model by using the plurality of sets of sample training data corresponding to each sensor in a cross-validation manner to obtain the accuracy of each tightness state determination sub-model; and determining the initial tightness state determination sub-model as a tightness state determination sub-model when the accuracy is greater than an accuracy threshold.

[0059] Specifically, Figure 3 The module training module mainly involves the construction, training and parameter optimization of deep learning models. First, in order to improve the accuracy of the detection results, the application selects to train a corresponding convolutional neural network (CNN) model for each sensor data. This method can fully utilize the unique signal characteristics of each sensor, thereby improving the overall detection performance. In this stage, an independent model is established for each sensor data, so that the model can more accurately capture the key features in different types of data. Then, the cross-validation method is used to evaluate the model performance to prevent overfitting and ensure the generalization ability of the model. By dividing the data set into multiple subsets and alternately using part of them for training and the rest for verification, the performance of the model on unseen data can be fully tested, thereby improving its reliability and practicality. Subsequently, the attention mechanism is used to fuse the features extracted by each model. The attention mechanism can help the model focus on more important features, thereby improving the effective utilization of information. The fused features will be input into the fully connected neural network for final task training. This step ensures that the information obtained from multiple sensors can be utilized comprehensively to achieve more accurate prediction results. Finally, the entire model is optimized and fine-tuned through the backpropagation algorithm. Backpropagation can effectively adjust the model parameters to reduce the loss function, thereby gradually improving the accuracy of the prediction. After this series of training and optimization process, the model not only can effectively identify and predict various states, but also can maintain stable performance in a variable environment, which provides strong support for practical applications.

[0060] In the process of model training, the pre-processed data of each sensor , an independent convolutional neural network model is established , and each model is trained: That is, training the data collected by each sensor can obtain a corresponding tightness state determination sub-model, and the training target of each sensor is to minimize a loss function that measures the difference between the predicted result and the actual label: , wherein, is the output of the convolutional neural network prediction, is the true label. If the mean square error loss is selected as the loss function, then , wherein n represents the number of samples.

[0061] In the preliminary verification of the model, the cross-validation method can be used, assuming that the data set is divided into K subsets , , …, Each time, one subset is selected as the validation set, and the remaining (K-1) subsets are used as the training set. The goal of cross-validation is to average the loss of each validation, that is, to obtain the average loss , which can be expressed as: .

[0062] In addition, the model verification module shown in Figure 3 can be used to evaluate the performance of the fusion model on the validation set, compare the effects of different fusion strategies, and select the best solution. In addition, it is necessary to regularly monitor the performance of the model on new data and retrain or adjust the fusion strategy if necessary to adapt to changes in data. During the monitoring process, if the performance of the model on new data is found to have decreased significantly, retraining may be considered, which involves re-collecting and annotating data to ensure that the training set is representative. In addition, hyperparameter optimization techniques such as grid search or Bayesian optimization can be used to fine-tune existing models to adapt to new data features.

[0063] In a specific embodiment of the present application, the tightness state determination model comprises a plurality of tightness state determination sub-models, and the target feature data is input into the tightness state determination model to process the target feature data by using the tightness state determination model to obtain the tightness degree between the tool sleeve and the tool, comprising: inputting the target feature data corresponding to each sensor into the tightness state determination sub-model to process the target feature data by using the tightness state determination sub-model to obtain the sub-tightness degree corresponding to the target feature data, wherein each tightness state determination sub-model is used to process the data collected by the corresponding sensor; the attention weight of each sub-tightness degree is determined by using a second formula according to the accuracy of each tightness state determination sub-model, wherein the second formula is: , represents the accuracy of the tightness state determination sub-model corresponding to the i th sensor, and n represents the total number of sensors, represents the attention weight of the sub-tightness degree corresponding to the i th sensor, and the attention weight refers to the weight ratio of the sub-tightness degree in the tightness degree; the tightness degree between the tool sleeve and the tool is determined by using a third formula according to the plurality of sub-tightness degrees and the attention weight corresponding to each sub-tightness degree, wherein the third formula is: , P(t) represents the tightness degree between the tool sleeve and the tool at the current time.

[0064] Specifically, the core of the attention mechanism is to calculate the importance weight of each sensor feature, and then perform weighted fusion. After the training of each sensor model (i.e. the tightness state determination sub-model corresponding to each sensor) is completed, the model is evaluated using the validation set, and the importance of each sensor is measured according to the accuracy of the model, and the conversion formula is as follows: wherein, represents the accuracy of the tightness state determination sub-model corresponding to the i th sensor, and n represents the total number of sensors, represents the attention weight of the sub-tightness degree corresponding to the i th sensor, and the attention weight refers to the weight ratio of the sub-tightness degree in the tightness degree; before inputting into the fully connected neural network, the features of each sensor are weighted and fused into a new feature vector by using the attention weight, , P(t) represents the tightness degree between the tool sleeve and the tool at the current time.

[0065] Step S208, determining the tightness state between the tool sleeve and the tool according to the tightness threshold range in which the tightness degree is located.

[0066] In this embodiment, the specific tightness state between the tool sleeve and the tool can be determined according to the tightness threshold range in which the tightness degree obtained by analyzing in the above steps is located.

[0067] According to the above embodiment of the present application, in the step S208, the tightness threshold range includes a first tightness threshold range, a second tightness threshold range, a third tightness threshold range, a fourth tightness threshold range and a fifth tightness threshold range, and the tightness state between the tool holder and the tool is determined according to the tightness threshold range in which the tightness degree is located, including: in the case that the tightness degree is located in the first tightness threshold range, determining that the tightness state is a normal state, wherein the first tightness threshold range is a range in which the tightness degree is less than or equal to a first tightness threshold value; in the case that the tightness degree is located in the second tightness threshold range, determining that the tightness state is a slight looseness state, wherein the second tightness threshold range is a range in which the tightness degree is greater than the first tightness threshold value and less than or equal to a second tightness threshold value, and the second tightness threshold value is greater than the first tightness threshold value; in the case that the tightness degree is located in the third tightness threshold range, determining that the tightness state is a moderate looseness state, wherein the third tightness threshold range is a range in which the tightness degree is greater than the second tightness threshold value and less than or equal to a third tightness threshold value, and the third tightness threshold value is greater than the second tightness threshold value; in the case that the tightness degree is located in the fourth tightness threshold range, determining that the tightness state is a severe looseness state, wherein the fourth tightness threshold range is a range in which the tightness degree is greater than the third tightness threshold value and less than or equal to a fourth tightness threshold value, and the fourth tightness threshold value is greater than the third tightness threshold value; in the case that the tightness degree is located in the fifth tightness threshold range, determining that the tightness state is a failure state, wherein the fifth tightness threshold range is a range in which the tightness degree is greater than the fourth tightness threshold value.

[0068] Specifically, five loose-tight threshold ranges can be roughly divided (of course, other numbers of threshold ranges can be divided according to actual conditions, which are not specifically limited here), which correspond to several specific states usually included in the tool management of the machine tool magazine one by one: 1) the first loose-tight threshold range corresponds to the normal state: the tool is firmly clamped by the tool holder, and there is no sign of loosening, at this time the contact force, vibration and position between the tool and the tool holder are all within the preset normal range; 2) the second loose-tight threshold range corresponds to the slight loosening state: the contact force or vibration between the tool and the tool holder slightly exceeds the normal range, but has not yet caused obvious influence on the machining precision or equipment safety, this state may indicate that the tool is about to loosen, and the operator needs to pay close attention; 3) the third loose-tight threshold range corresponds to the moderate loosening state: the tool clamping force significantly decreases or the vibration significantly increases, the machining precision begins to be affected, and there is a certain safety hazard, at this time, the tool should be immediately checked and adjusted to prevent further loosening; 4) the fourth loose-tight threshold range corresponds to the severe loosening state: the tool is almost completely loosened, and cannot guarantee the processing, which may pose a serious threat to the equipment and the operator, and the processing must be stopped immediately for emergency treatment and repair; 5) the fifth loose-tight threshold range corresponds to the fault state: the tool and the tool holder cannot work normally due to excessive wear, damage or other reasons, and the tool or the tool holder needs to be replaced for repair; through real-time monitoring and accurate identification of these states, accidents in processing can be effectively prevented, processing efficiency can be improved, and the safety of equipment and operators can be ensured, in actual application, through real-time data acquisition of sensors and analysis of deep learning models, it can be quickly judged which state the tool is in, so that corresponding measures can be taken.

[0069] In addition, in the real-time detection module, a visual interface and detection report output are also included. The visual interface should display the data from various sensors in real time, including temperature, pressure, and vibration information, in the form of charts or dashboards, so that users can quickly understand the current equipment status. Meanwhile, a reasonable data refresh frequency will ensure timely information updates, helping users make quick decisions. In addition, the interface should clearly display the tightness status between the tool holder and the tool, using color coding or graphical icons, such as green for normal status, yellow for warning, and red for failure. Even a 3D model or animation effect can be used to visually display the relative position of the tool and tool holder. In terms of detection report output, the system should be able to automatically generate real-time reports containing detection time, tool holder status, and sensor data, supporting multiple formats (such as PDF, Excel) to meet the needs of different users. The report should include data trend analysis, showing the changing trend of tool tightness status through line charts, and using various visualization charts such as pie charts and bar charts to enhance report readability. In addition, users should be able to customize the content and format of the report as needed, select the required data items, and provide the function of regularly generating reports, such as daily, weekly, or monthly reports, to help users systematically summarize and analyze equipment status.

[0070] As can be seen from the above, through the technical solutions provided by the above embodiments of the present application, the tightness detection data between the tool and the tool holder can be obtained, wherein the tightness detection data is obtained by the sensor deployed in the tool holder during the tightness detection process after the tool enters the tool holder; the target feature data corresponding to each type of tightness detection data is obtained by feature extraction on the multiple types of tightness detection data; the target feature data is input into the tightness state determination model to process the target feature data using the tightness state determination model, and the tightness degree between the tool holder and the tool is obtained, wherein the tightness state determination model is obtained by training multiple sets of training data using deep learning, and each set of training data includes sample target feature data and sample tightness degree corresponding to the sample target feature data; the tightness state between the tool holder and the tool is determined according to the tightness threshold range in which the tightness degree is located, which achieves the technical effect of collecting the tightness detection data between the tool holder and the tool during the tightness detection process using the sensor, processing the tightness detection data using the trained deep learning model to obtain the tightness degree between the tool holder and the tool, and finally determining the tool holder tightness state according to the threshold range in which the tightness degree is located, realizing the technical effect of automatically collecting and analyzing data using an automated system to intelligently analyze and determine the tightness state between the tool holder and the tool, and improving the detection efficiency and accuracy.

[0071] Therefore, through the technical scheme provided by the above-mentioned embodiments of the present application, the technical problem that the traditional tool tightness detection method in the related art mainly relies on manual inspection or simple mechanical devices, resulting in low inspection efficiency and limited detection accuracy, is solved.

[0072] It should be noted that, for the foregoing method embodiments, in order to simply describe, they are all expressed as a series of action combinations, but those skilled in the art should know that the present application is not limited to the action sequence described, because according to the present application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should know that the embodiments described in the specification all belong to preferred embodiments, and the actions and modules involved are not necessarily essential to the present application.

[0073] From the above description of the embodiments, those skilled in the art can clearly understand that the method according to the above-mentioned embodiments can be realized by means of software and the necessary general hardware platform, of course, it can also be realized by hardware, but in many cases, the former is a better embodiment. Based on such understanding, the technical solutions of the present application can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes a plurality of instructions for causing a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the method described in each embodiment of the present application.

[0074] According to the embodiments of the present application, a tool sleeve tightness detection device of a tool magazine of a machine tool is also provided, Figure 7 is a schematic diagram of the tool sleeve tightness detection device of the tool magazine of the machine tool according to the embodiments of the present application, as Figure 7 shown, the device comprises a first acquisition unit 71, a second acquisition unit 73, a third acquisition unit 75 and a first determination unit 77. The tool sleeve tightness detection device of the machine tool will be described in detail below.

[0075] The first acquisition unit 71 is configured to acquire a plurality of tightness detection data between the tool and the tool sleeve, wherein the tightness detection data is obtained by a sensor arranged in the tool sleeve during the tightness detection process after the tool enters the tool sleeve.

[0076] The second acquisition unit 73 is configured to perform feature extraction on the plurality of tightness detection data to obtain target feature data corresponding to each type of tightness detection data.

[0077] The third acquisition unit 75 is configured to input the target feature data into a tightness state determination model, and process the target feature data by using the tightness state determination model to obtain the tightness degree between the tool holder and the tool. The tightness state determination model is obtained by using a plurality of sets of training data through deep learning. Each of the plurality of sets of training data includes sample target feature data and a sample tightness degree corresponding to the sample target feature data.

[0078] The first determination unit 77 is configured to determine the tightness state between the tool holder and the tool according to the tightness threshold range in which the tightness degree is located.

[0079] It should be noted that the first acquisition unit 71, the second acquisition unit 73, the third acquisition unit 75 and the first determination unit 77 correspond to steps S202 to S208 in the above embodiment, and the four units have the same instances and application scenarios as the corresponding steps, but are not limited to the content disclosed in the above embodiment.

[0080] As can be seen from the above, in the scheme described in the above embodiment, the first acquisition unit is used to acquire a plurality of tightness detection data between the tool and the tool holder. The tightness detection data is obtained by a sensor arranged in the tool holder during the tightness detection process after the tool enters the tool holder. The second acquisition unit is used to extract features from the plurality of tightness detection data to obtain target feature data corresponding to each kind of tightness detection data. The third acquisition unit is used to input the target feature data into a tightness state determination model to process the target feature data by using the tightness state determination model to obtain the tightness degree between the tool holder and the tool. The tightness state determination model is obtained by using a plurality of sets of training data through deep learning. Each of the plurality of sets of training data includes sample target feature data and a sample tightness degree corresponding to the sample target feature data. The first determination unit is used to determine the tightness state between the tool holder and the tool according to the tightness threshold range in which the tightness degree is located. The technical effect of automatically collecting and analyzing data by an automatic system to intelligently analyze and determine the tightness state between the tool holder and the tool is achieved. The detection efficiency and accuracy are improved.

[0081] Therefore, the technical scheme provided in the above embodiment of the present application solves the technical problem that the traditional tool tightness detection method in the related art mainly relies on manual inspection or simple mechanical devices, resulting in low inspection efficiency and limited detection accuracy.

[0082] In an optional embodiment of the present application, the first acquisition unit comprises at least one of the following: a first acquisition module configured to acquire the interval distance between the tool and the bottom of the tool sleeve detected by the photoelectric sensor; a second acquisition module configured to acquire the clamping force between the tool sleeve and the tool detected by the force sensor, wherein the clamping force is used to reflect the fixing degree between the tool sleeve and the tool; and a third acquisition module configured to acquire the vibration frequency of the tool sleeve and the tool during the machining process of the machine tool detected by the vibration sensor.

[0083] In an optional embodiment of the present application, the first acquisition unit comprises one of the following: a first receiving module configured to receive the tightness detection data transmitted by the sensor based on the communication channel in the case that the current time reaches the predetermined time, wherein the predetermined time is a preset acquisition time, and the communication channel is used for data transmission with the sensor; and a second receiving module configured to send an acquisition instruction to the sensor to control the sensor to collect the current tightness detection data in the case that the tightness detection signal is received, and receive the tightness detection data through the communication channel.

[0084] In an optional embodiment of the present application, the second acquisition unit comprises a fourth acquisition module configured to perform feature extraction on the tightness detection data by using a first formula to obtain target feature data, wherein the first formula is: , wherein i represents the label of the sensor, t represents the current time, f[] represents an activation function, W represents a convolution kernel, b represents a bias, represents the tightness detection data collected by the i-th sensor at the current time t, represents the target feature data corresponding to .

[0085] In an optional embodiment of the present application, the tool holder tightness detection device of the machine tool tool magazine further comprises: a fourth obtaining unit, configured to, before the target feature data is input into the tightness state determination model and the tightness state determination model is used to process the target feature data to obtain the tightness degree between the tool holder and the tool, iteratively train the convolutional neural network model using a plurality of sets of sample training data collected by each sensor in a historical time period until an iteration termination condition is reached, to obtain an initial tightness state determination sub-model corresponding to the sensor, wherein each of the plurality of sets of sample training data comprises: sample target feature data, sample sub-tightness degree corresponding to the sample target feature data, and the iteration termination condition is at least one of: the number of iterations reaches a preset number of iterations, and the error between the predicted value and the true value of the convolutional neural network model is less than an error threshold; a fifth obtaining unit, configured to verify the accuracy of the initial tightness state determination sub-model corresponding to each sensor using a plurality of sets of sample training data corresponding to each sensor in a cross-validation manner to obtain the accuracy of each tightness state determination sub-model; and a second determining unit, configured to determine the initial tightness state determination sub-model as a tightness state determination sub-model if the accuracy is greater than an accuracy threshold.

[0086] In an optional embodiment of the present application, the tightness state determination model comprises a plurality of tightness state determination sub-models, and the third obtaining unit comprises: a fifth obtaining module, configured to input the target feature data corresponding to each sensor into the tightness state determination sub-model to process the target feature data using the tightness state determination sub-model to obtain a sub-tightness degree corresponding to the target feature data, wherein each tightness state determination sub-model is used to process the data collected by a corresponding sensor; a first determining module, configured to determine the attention weight of each sub-tightness degree using a second formula according to the accuracy of each tightness state determination sub-model, wherein the second formula is: , wherein represents the accuracy of the tightness state determination sub-model corresponding to the i-th sensor, and n represents the total number of sensors, wherein represents the attention weight of the sub-tightness degree corresponding to the i-th sensor, and the attention weight refers to the weight proportion of the sub-tightness degree in the tightness degree; and a second determining module, configured to determine the tightness degree between the tool holder and the tool using a third formula according to the plurality of sub-tightness degrees and the attention weight corresponding to each sub-tightness degree, wherein the third formula is: wherein P(t) represents the tightness degree between the tool holder and the tool at the current time.

[0087] In an optional embodiment of the present application, the tightness threshold range comprises a first tightness threshold range, a second tightness threshold range, a third tightness threshold range, a fourth tightness threshold range and a fifth tightness threshold range, and the first determining unit comprises: a third determining module configured to determine the tightness state as the normal state when the tightness degree is within the first tightness threshold range, wherein the first tightness threshold range is a range in which the tightness degree is less than or equal to a first tightness threshold value; a fourth determining module configured to determine the tightness state as the slight looseness state when the tightness degree is within the second tightness threshold range, wherein the second tightness threshold range is a range in which the tightness degree is greater than the first tightness threshold value and less than or equal to a second tightness threshold value, and the second tightness threshold value is greater than the first tightness threshold value; a fifth determining module configured to determine the tightness state as the moderate looseness state when the tightness degree is within the third tightness threshold range, wherein the third tightness threshold range is a range in which the tightness degree is greater than the second tightness threshold value and less than or equal to a third tightness threshold value, and the third tightness threshold value is greater than the second tightness threshold value; a sixth determining module configured to determine the tightness state as the severe looseness state when the tightness degree is within the fourth tightness threshold range, wherein the fourth tightness threshold range is a range in which the tightness degree is greater than the third tightness threshold value and less than or equal to a fourth tightness threshold value, and the fourth tightness threshold value is greater than the third tightness threshold value; and a seventh determining module configured to determine the tightness state as the failure state when the tightness degree is within the fifth tightness threshold range, wherein the fifth tightness threshold range is a range in which the tightness degree is greater than the fourth tightness threshold value.

[0088] According to another aspect of the embodiments of the present application, there is also provided a tool holder tightness detection system of a machine tool tool magazine, which uses any of the tool holder tightness detection methods of the machine tool tool magazine.

[0089] According to another aspect of the embodiments of the present application, there is also provided a computer readable storage medium comprising a stored program, wherein the program performs any of the tool holder tightness detection methods of the machine tool tool magazine.

[0090] Optionally, in the present embodiment, the above computer readable storage medium can be located in any one of the computer terminals in a computer terminal group in a computer network, or in any one of the communication devices in a communication device group.

[0091] Optionally, in the embodiment, the computer readable storage medium is configured to store program code for performing the following steps: obtaining a plurality of tightness detection data between the tool and the tool holder, wherein the tightness detection data is obtained by the sensor arranged in the tool holder during the tightness detection process after the tool enters the tool holder; performing feature extraction on the plurality of tightness detection data to obtain target feature data corresponding to each tightness detection data; inputting the target feature data into the tightness state determination model to process the target feature data by using the tightness state determination model to obtain the tightness degree between the tool holder and the tool, wherein the tightness state determination model is obtained by training a plurality of training data by deep learning, and each of the plurality of training data includes sample target feature data and a sample tightness degree corresponding to the sample target feature data; determining the tightness state between the tool holder and the tool according to the tightness threshold range in which the tightness degree is located.

[0092] Optionally, in the embodiment, the computer readable storage medium is configured to store program code for performing the following steps: obtaining the interval distance between the tool and the bottom of the tool holder detected by the photoelectric sensor; obtaining the clamping force between the tool holder and the tool detected by the force sensor, wherein the clamping force is used to reflect the fixing degree between the tool holder and the tool; obtaining the vibration frequency of the tool holder and the tool during the machining process of the machine tool detected by the vibration sensor.

[0093] Optionally, in the embodiment, the computer readable storage medium is configured to store program code for performing the following steps: in the case that the current time reaches a predetermined time, receiving the tightness detection data transmitted by the sensor based on the communication channel, wherein the predetermined time is a preset collection time, and the communication channel is used for data transmission with the sensor; in the case that the tightness detection signal is received, sending a collection instruction to the sensor to control the sensor to collect the current tightness detection data, and receiving the tightness detection data through the communication channel.

[0094] Optionally, in the embodiment, the computer readable storage medium is configured to store program code for performing the following steps: performing feature extraction on the tightness detection data by using a first formula to obtain target feature data, wherein the first formula is: , i represents the label of the sensor, t represents the current time, f[] represents the activation function, W represents the convolution kernel, b represents the bias, represents the tightness detection data collected by the i-th sensor at the current time t, represents the target feature data corresponding to .

[0095] Optionally, in the embodiment, the computer readable storage medium is configured to store program code for performing the following steps: iteratively training the convolutional neural network model using a plurality of sets of sample training data collected by each sensor in a historical time period, until an iteration termination condition is reached, to obtain an initial tightness state determination sub-model corresponding to the sensor, wherein each of the plurality of sets of sample training data comprises: sample target feature data, and a sample sub-tightness degree corresponding to the sample target feature data, and the iteration termination condition is at least one of: the number of iterations reaches a preset number of iterations, and an error between a predicted value and an actual value of the convolutional neural network model is less than an error threshold; verifying the accuracy of the initial tightness state determination sub-model corresponding to each sensor using a plurality of sets of sample training data corresponding to the sensor in a cross-validation manner, to obtain the accuracy of each tightness state determination sub-model; and determining the initial tightness state determination sub-model as a tightness state determination sub-model if the accuracy is greater than an accuracy threshold.

[0096] Optionally, in the embodiment, the computer readable storage medium is configured to store program code for performing the following steps: inputting target feature data corresponding to each sensor into the tightness state determination sub-model, to process the target feature data using the tightness state determination sub-model, to obtain a sub-tightness degree corresponding to the target feature data, wherein each tightness state determination sub-model is used to process data collected by a corresponding sensor; determining an attention weight of each sub-tightness degree using a second formula according to the accuracy of each tightness state determination sub-model, wherein the second formula is: , wherein represents the accuracy of the tightness state determination sub-model corresponding to the i-th sensor, and n represents the total number of sensors, wherein represents the attention weight of the sub-tightness degree corresponding to the i-th sensor, and the attention weight refers to the proportion of the weight of the sub-tightness degree in the tightness degree; determining the tightness degree between the tool holder and the tool using a third formula according to a plurality of sub-tightness degrees and the attention weight corresponding to each sub-tightness degree, wherein the third formula is: , and P(t) represents the tightness degree between the tool holder and the tool at the current time.

[0097] Optionally, in the embodiment, the computer readable storage medium is configured to store program code for performing the following steps: determining that the tightness state is a normal state when the tightness degree is in a first tightness threshold range, wherein the first tightness threshold range is a range in which the tightness degree is less than or equal to a first tightness threshold; determining that the tightness state is a slight looseness state when the tightness degree is in a second tightness threshold range, wherein the second tightness threshold range is a range in which the tightness degree is greater than the first tightness threshold and less than or equal to a second tightness threshold, and the second tightness threshold is greater than the first tightness threshold; determining that the tightness state is a moderate looseness state when the tightness degree is in a third tightness threshold range, wherein the third tightness threshold range is a range in which the tightness degree is greater than the second tightness threshold and less than or equal to a third tightness threshold, and the third tightness threshold is greater than the second tightness threshold; determining that the tightness state is a severe looseness state when the tightness degree is in a fourth tightness threshold range, wherein the fourth tightness threshold range is a range in which the tightness degree is greater than the third tightness threshold and less than or equal to a fourth tightness threshold, and the fourth tightness threshold is greater than the third tightness threshold; and determining that the tightness state is a failure state when the tightness degree is in a fifth tightness threshold range, wherein the fifth tightness threshold range is a range in which the tightness degree is greater than the fourth tightness threshold.

[0098] According to another aspect of the embodiments of the present application, a processor is also provided, which is configured to run a program, wherein the program is configured to perform any of the tool holder tightness detection methods of the tool magazine of the machine tool when the program is running.

[0099] According to another aspect of the embodiments of the present application, a computer program product is also provided, which comprises computer instructions configured to perform any of the tool holder tightness detection methods of the tool magazine of the machine tool when the computer instructions are executed by a processor.

[0100] The above-mentioned sequence numbers of the embodiments of the present application are only for description, and do not represent the advantages or disadvantages of the embodiments.

[0101] In the above-mentioned embodiments of the present application, the description of each embodiment has its own focus, and the parts not described in detail in a certain embodiment can be referred to the relevant description of other embodiments.

[0102] In several embodiments provided in the present application, it should be understood that the disclosed technical contents can be implemented by other ways. Among them, the above-mentioned device embodiments are only schematic, for example, the division of the units can be a logical function division, and in actual implementation, there can be another division way, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units or modules shown or discussed can be indirect coupling or communication connection through some interfaces, and can be electrical or other forms.

[0103] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., may be located in one place, or may be distributed to multiple units. Part or all of the units may be selected according to actual needs to achieve the purpose of the embodiment.

[0104] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0105] The integrated unit, if realized in the form of a software functional unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application, essentially or the part that contributes to the prior art, or all or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, including a number of instructions to make a computer device (which can be a personal computer, a server or a network device, etc.) execute all or part of the steps of the method described in each embodiment of the present application. The foregoing storage medium includes: a U disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a mobile hard disk, a magnetic disk or an optical disk, and various program code storage media.

[0106] The above is only the preferred embodiment of the present application, and it should be noted that for those skilled in the art, without departing from the principles of the present application, a number of improvements and refinements can be made, and these improvements and refinements should be considered as the protection scope of the present application.

Claims

1. A tool holder tightness detection method of a machine tool tool magazine, characterized by, The method comprises the following steps: obtaining a plurality of tightness detection data between the tool and the tool holder, wherein the tightness detection data is obtained by the sensor arranged in the tool holder during the tightness detection process after the tool enters the tool holder; extracting features from a plurality of tightness detection data to obtain target feature data corresponding to each tightness detection data; inputting the target feature data into a tightness state determination model to process the target feature data using the tightness state determination model to obtain the tightness degree between the tool holder and the tool, wherein the tightness state determination model is obtained by training a plurality of training data using deep learning, and each of the plurality of training data comprises sample target feature data and sample tightness degree corresponding to the sample target feature data; determining the tightness state between the tool holder and the tool according to the tightness threshold range in which the tightness degree is located, The tightness detection data is subjected to feature extraction to obtain target feature data, including: the tightness detection data is subjected to feature extraction by using a first formula to obtain the target feature data, wherein the first formula is: , i represents a label of the sensor, t represents a current time, f[] represents an activation function, W represents a convolution kernel, b represents a bias, represents the tightness detection data collected by the i-th sensor at the current time t, represents the target feature data corresponding to , The tightness state determination model comprises a plurality of tightness state determination sub-models, the target feature data is input into the tightness state determination model, the target feature data is processed by using the tightness state determination model, and the tightness degree between the tool sleeve and the tool is obtained, comprising: the target feature data corresponding to each sensor is input into the tightness state determination sub-model respectively, the target feature data is processed by using the tightness state determination sub-model, and the sub-tightness degree corresponding to the target feature data is obtained, wherein each tightness state determination sub-model is used for processing the data collected by the corresponding sensor; the attention weight of each sub-tightness degree is determined by using a second formula according to the accuracy of each tightness state determination sub-model, wherein the second formula is: , represents the accuracy of the tightness state determination sub-model corresponding to the i th sensor, n represents the total number of sensors, represents the attention weight of the sub-tightness degree corresponding to the i th sensor, the attention weight refers to the weight proportion of the sub-tightness degree in the tightness degree; the tightness degree between the tool sleeve and the tool is determined by using a third formula according to a plurality of sub-tightness degrees and the attention weight corresponding to each sub-tightness degree, wherein the third formula is: , P(t) represents the tightness degree between the tool sleeve and the tool at the current moment.

2. The tool holder tightness detection method of a machine tool tool magazine according to claim 1, characterized in that, obtaining the tightness detection data between the tool and the tool holder, comprising one of the following: in the case that the current time reaches a predetermined time, receiving the tightness detection data transmitted by the sensor based on the communication channel, wherein the predetermined time is a preset collection time, and the communication channel is used for data transmission with the sensor; in the case that the tightness detection signal is received, sending a collection instruction to the sensor to control the sensor to collect the current tightness detection data, and receiving the tightness detection data through the communication channel.

3. The tool holder tightness detection method of a machine tool tool magazine according to claim 1, characterized in that, Obtaining the tightness detection data between the tool and the tool holder comprises at least one of the following: obtaining the interval distance between the tool and the bottom of the tool holder detected by the photoelectric sensor; obtaining the clamping force between the tool holder and the tool detected by the force sensor, wherein the clamping force reflects the fixing degree between the tool holder and the tool; obtaining the vibration frequency of the tool holder and the tool during the machining process of the machine tool detected by the vibration sensor.

4. The tool holder tightness detection method of a machine tool tool magazine according to claim 1, characterized in that, Before inputting the target feature data into the tightness state determination model to process the target feature data using the tightness state determination model to obtain the tightness degree between the tool holder and the tool, it further comprises the following steps: iteratively training a convolutional neural network model using a plurality of sample training data collected by each sensor in a historical time period until an iteration termination condition is reached to obtain an initial tightness state determination sub-model corresponding to the sensor, wherein each of the plurality of sample training data comprises the sample target feature data and the sample sub-tightness degree corresponding to the sample target feature data, and the iteration termination condition is at least one of the following: the number of iterations reaches a preset iteration number, and the error between the predicted value and the true value of the convolutional neural network model is less than an error threshold; verifying the accuracy of the initial tightness state determination sub-model corresponding to each sensor using the plurality of sample training data in a cross-validation manner to obtain the accuracy of each tightness state determination sub-model. In a case where the accuracy is greater than an accuracy threshold, it is determined that the initial tightness state determination sub-model is a tightness state determination sub-model.

5. The tool holder tightness detection method of a machine tool tool magazine according to claim 1, characterized in that, The tightness threshold range includes a first tightness threshold range, a second tightness threshold range, a third tightness threshold range, a fourth tightness threshold range, and a fifth tightness threshold range. The tightness state between the tool holder and the tool is determined according to the tightness threshold range in which the tightness degree is located, including: In a case where the tightness degree is in the first tightness threshold range, it is determined that the tightness state is a normal state, wherein the first tightness threshold range is a range in which the tightness degree is less than or equal to a first tightness threshold; In a case where the tightness degree is in the second tightness threshold range, it is determined that the tightness state is a slight looseness state, wherein the second tightness threshold range is a range in which the tightness degree is greater than the first tightness threshold and less than or equal to a second tightness threshold, and the second tightness threshold is greater than the first tightness threshold; In a case where the tightness degree is in the third tightness threshold range, it is determined that the tightness state is a moderate looseness state, wherein the third tightness threshold range is a range in which the tightness degree is greater than the second tightness threshold and less than or equal to a third tightness threshold, and the third tightness threshold is greater than the second tightness threshold; In a case where the tightness degree is in the fourth tightness threshold range, it is determined that the tightness state is a severe looseness state, wherein the fourth tightness threshold range is a range in which the tightness degree is greater than the third tightness threshold and less than or equal to a fourth tightness threshold, and the fourth tightness threshold is greater than the third tightness threshold; In a case where the tightness degree is in the fifth tightness threshold range, it is determined that the tightness state is a failure state, wherein the fifth tightness threshold range is a range in which the tightness degree is greater than the fourth tightness threshold.

6. A tool holder tightness detecting device of a machine tool tool magazine, characterized by, including: A first acquisition unit is configured to acquire a plurality of tightness detection data between a tool and a tool holder, wherein the tightness detection data is obtained by a sensor deployed in the tool holder during a tightness detection process after the tool enters the tool holder; A second acquisition unit is configured to perform feature extraction on a plurality of the tightness detection data to obtain target feature data corresponding to each of the tightness detection data; A third acquisition unit is configured to input the target feature data into a tightness state determination model to process the target feature data by using the tightness state determination model to obtain a tightness degree between the tool holder and the tool, wherein the tightness state determination model is obtained by training a plurality of training data by deep learning, and each of the plurality of training data includes sample target feature data and a sample tightness degree corresponding to the sample target feature data; A first determination unit is configured to determine a tightness state between the tool holder and the tool according to a tightness threshold range in which the tightness degree is located, The second acquisition unit comprises a fourth acquisition module configured to perform feature extraction on the tightness detection data by using a first formula to obtain the target feature data, wherein the first formula is: , i represents a label of the sensor, t represents a current time, f[] represents an activation function, W represents a convolution kernel, and b represents a bias, represents the tightness detection data collected by the i th sensor at the current time t, represents the target feature data corresponding to ​ The tightness state determination model comprises a plurality of tightness state determination sub-models, and the third acquisition unit comprises: a fifth acquisition module, configured to input the target feature data corresponding to each sensor into the tightness state determination sub-model respectively, to process the target feature data by using the tightness state determination sub-model, and obtain a sub-tightness degree corresponding to the target feature data, wherein each tightness state determination sub-model is configured to process the data collected by a corresponding sensor; a first determination module, configured to determine an attention weight of each sub-tightness degree according to the accuracy of each tightness state determination sub-model by using a second formula, wherein the second formula is: , denotes the accuracy of the tightness state determination sub-model corresponding to the i th sensor, n denotes the total number of sensors, denotes the attention weight of the sub-tightness degree corresponding to the i th sensor, and the attention weight indicates the proportion of the weight of the sub-tightness degree in the tightness degree; and a second determination module, configured to determine the tightness degree between the tool holder and the tool according to a plurality of sub-tightness degrees and the attention weight corresponding to each sub-tightness degree by using a third formula, wherein the third formula is: , and P(t) denotes the tightness degree between the tool holder and the tool at the current moment.

7. A computer-readable storage medium, characterized in that, The computer readable storage medium includes a stored program, wherein the program performs the tool holder tightness detection method of the machine tool tool magazine according to any one of claims 1 to 5.

8. A computer program product comprising computer instructions, characterized in that, The computer instructions, when executed by a processor, perform the tool holder tightness detection method of the machine tool tool magazine according to any one of claims 1 to 5.

Images