Adaptive control system and method for a numerically controlled machine tool

Abstract

The application discloses a numerical control machine tool self-adaptive control system and method. The system comprises a numerical control machine tool, a data processing module, a working condition judging module, a self-adaptive control module and an output control module. The data processing module comprises a data acquisition unit and a preprocessing unit. The data acquisition unit is composed of multiple sensors and is used for collecting multiple operation parameters at regular time intervals. The numerical control machine tool is connected with the data acquisition unit in the data processing module. The data acquisition unit is connected with the preprocessing unit. The preprocessing unit is connected with the working condition judging module. The working condition judging module is connected with the self-adaptive control module. The self-adaptive control module is connected with the output control module. According to the embodiment of the application, the cutting parameters and the axial motion control can be automatically adjusted, unnecessary energy consumption and material waste can be reduced, complex geometric shapes and machining requirements can be adapted, and the flexibility makes the system adapt to various complex and changeable machining tasks.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of numerical control machine tool processing monitoring and control technology, and particularly relates to a numerical control machine tool adaptive control system and method. BACKGROUND

[0002] In the manufacture of aircraft parts, as the aircraft structure becomes increasingly large and complex, the processing difficulty of parts is continuously improved. The existing processing machine tools cannot perform adaptive processing of workpieces due to low intelligentization level, and still use fixed processes, so they have been difficult to meet the complex and variable working conditions in the part processing process.

[0003] Adaptive adjustment and compensation of the part processing process is an effective means to solve the above method. The adaptive control system can automatically adjust the processing parameters according to the equipment load, temperature change and other conditions in the processing process, so that the potential of the equipment can be fully utilized, and the production efficiency of the equipment and the service life of the tool are improved. SUMMARY

[0004] Therefore, the present application provides a numerical control machine tool adaptive control system and method to solve the problem that the traditional numerical control machine tool cannot perform adaptive processing of workpieces.

[0005] In a first aspect, the present application provides a numerical control machine tool adaptive control system, which comprises a numerical control machine tool, a data processing module, a working condition judgment module, an adaptive control module and an output control module.

[0006] The data processing module comprises a data acquisition unit and a preprocessing unit. The data acquisition unit is composed of a plurality of sensors and is used to collect a plurality of operating parameters at regular intervals.

[0007] The numerical control machine tool is connected to the data acquisition unit in the data processing module. The data acquisition unit is connected to the preprocessing unit. The preprocessing unit is connected to the working condition judgment module. The working condition judgment module is connected to the adaptive control module. The adaptive control module is connected to the output control module.

[0008] The data processing unit is used to extract features from the collected operating parameters in real time to obtain a plurality of machine tool features.

[0009] The working condition judgment module is used to receive a plurality of machine tool features from the data processing unit and determine the working condition according to a predetermined working condition determination strategy. If the working condition of the operating parameters is determined to be abnormal, the abnormal cutting parameters corresponding to the abnormal operating parameters are obtained and sent to the adaptive control module.

[0010] The adaptive control module is configured to receive the abnormal cutting parameters from the working condition judgment module and to perform adaptive adjustment on the abnormal cutting parameters according to a preset adaptive algorithm.

[0011] The output control module is configured to receive the adjusted cutting parameters from the adaptive control module and to control the axial movement of the machine tool according to the cutting parameters.

[0012] Further, the data acquisition unit comprises a temperature sensor, a position sensor, a force sensor and a speed sensor, wherein the target numerical control machine tool is connected to each sensor of the data acquisition unit.

[0013] The temperature sensor is configured to acquire the machine tool temperature of the target numerical control machine tool based on a time period and to send the machine tool temperature to the working condition judgment module.

[0014] The force sensor is configured to acquire the cutting load of the target numerical control machine tool based on a time period and to send the cutting load to the working condition judgment module.

[0015] The position sensor is configured to receive a coordinate acquisition instruction from the output control module, to acquire the target position coordinates of each axis of the target numerical control machine tool and to send the target position coordinates to the output control module.

[0016] The speed sensor is configured to receive a data acquisition instruction from the working condition judgment module, to acquire the target cutting parameters of the target numerical control machine tool and to send the target cutting parameters to the adaptive control module.

[0017] Further, the working condition judgment module further comprises a temperature abnormality judgment unit and a cutting force abnormality judgment unit.

[0018] The temperature abnormality judgment unit is configured to compare the machine tool temperature of the target numerical control machine tool with a temperature threshold value, to acquire the abnormal cutting parameters under the current abnormal machine tool temperature through the speed sensor in the data acquisition unit when the machine tool temperature data is greater than the temperature threshold value.

[0019] The cutting force abnormality judgment unit is configured to compare the cutting load of the target numerical control machine tool with a load threshold value, to acquire the abnormal cutting parameters under the current abnormal cutting load through the speed sensor in the data acquisition unit when the cutting load is greater than the load threshold value.

[0020] Further, the adaptive control module comprises an adaptive updating unit, an adaptive compensation unit and a cutting parameter adjustment unit.

[0021] The adaptive updating unit is configured to receive the abnormal cutting parameters from the working condition judgment module, to substitute the abnormal cutting parameters into a preset adaptive updating algorithm and to calculate adaptive cutting parameters.

[0022] The adaptive compensation unit is configured to receive new cutting parameters from the cutting parameter adjustment unit, and calculate a cutting compensation amount by substituting the new cutting parameters into a pre-constructed adaptive compensation algorithm.

[0023] The cutting parameter adjustment unit is configured to receive the adaptive cutting parameters from the adaptive update unit and the cutting compensation amount from the adaptive compensation unit, and calculate a sum of the adaptive cutting parameters and the cutting compensation amount to obtain new cutting parameters.

[0024] Further, the output control module further comprises a path planning unit and a servo unit.

[0025] The path planning unit is configured to send a coordinate acquisition instruction to a position sensor after receiving the new cutting parameters from the cutting parameter adjustment unit, receive original target position coordinates of each axis of the target CNC machine tool collected by the position sensor, and obtain new target position coordinates of each axis of the target CNC machine tool according to a pre-set position coordinate and cutting parameter relationship library.

[0026] The servo unit is configured to receive the new target position coordinates of each axis of the target CNC machine tool from the path planning unit, and drive each axis of the machine tool to move according to the new target position coordinates based on the original target position coordinates.

[0027] Further, the system further comprises a reinforcement learning module, wherein the reinforcement learning module is connected to the data processing module, the adaptive control module, and the working condition judgment module.

[0028] The reinforcement learning module is configured to obtain a plurality of running parameters in the preprocessing unit according to a specified period, input the plurality of running parameters into an original machine learning model to obtain a machine tool temperature and cutting parameter relationship library, a cutting load and cutting parameter relationship library, and a position coordinate and cutting parameter relationship library, respectively.

[0029] Meanwhile, the reinforcement learning module is also configured to obtain abnormal cutting parameters in the working condition judgment module according to a specified period, construct an adaptive update algorithm and an adaptive compensation algorithm based on the abnormal cutting parameters and pre-set original cutting parameters, and synchronize the adaptive update algorithm to the adaptive update unit and the adaptive compensation algorithm to the adaptive compensation unit.

[0030] In a second aspect, an embodiment of the present application provides a CNC machine tool adaptive control method, which comprises:

[0031] The data acquisition unit is configured to collect a plurality of running parameters at a specified time.

[0032] The data processing unit is configured to perform feature extraction on the collected plurality of running parameters in real time to obtain a plurality of machine tool features.

[0033] The working condition judgment module receives a plurality of machine tool characteristics from the data processing unit, and judges the working condition state according to a pre-prepared working condition state judgment strategy, and if the working condition state of the running parameter is judged to be abnormal, the abnormal cutting parameter corresponding to the abnormal running parameter is obtained, and the abnormal cutting parameter is sent to the adaptive control module;

[0034] The adaptive control module receives the abnormal cutting parameter transmitted from the working condition judgment module, and performs adaptive adjustment on the abnormal cutting parameter according to a pre-prepared adaptive algorithm.

[0035] The output control module receives the cutting parameter adjusted by the adaptive control module, and controls the axial movement of the machine tool according to the cutting parameter.

[0036] The technical scheme of the embodiment of the application periodically collects and processes the running parameter data in the machining process of the numerical control machine tool, monitors the running state of the target numerical control machine tool, and when the data is abnormal, the cutting parameter at the abnormal moment is adaptively adjusted, and the axial movement displacement of the machine tool is controlled according to the adjusted cutting parameter, so that adaptive control is realized. By automatically adjusting the cutting parameter and the axial movement control, unnecessary energy consumption and material waste can be reduced, and complex geometric shapes and machining requirements can be adapted. This flexibility enables the system to adapt to various complex and variable machining tasks.

[0037] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the application, nor is it intended to limit the scope of the application. Other features of the application will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0038] In order to more clearly illustrate the technical solutions in the embodiments of the application, the following will briefly introduce the drawings needed to be used in the embodiment description. Obviously, the drawings in the following description are only some embodiments of the application, and other drawings can be obtained by those skilled in the art without creative labor.

[0039] Figure 1 It is a schematic diagram of the overall connection relationship of a numerical control machine tool adaptive control system provided by the first embodiment of the application;

[0040] Figure 2 It is a flowchart of a numerical control machine tool adaptive control method provided by the second embodiment of the application;

[0041] Figure 3 It is a schematic diagram of the connection relationship between a reinforcement learning module and other functional modules suitable for the embodiment of the application;

[0042] Figure 4It is a kind of numerical control machine tool self-adaptive control system's each functional module internal development schematic view suitable for the embodiment of the application

[0043] Figure 5 It is the internal subunit connection relationship schematic view of a kind of output control module suitable for the embodiment of the application. DETAILED DESCRIPTION

[0044] In order to make the person in this technical field better understand the present application scheme, the technical scheme in the embodiment of the present application will be described clearly and completely in the following with the drawings in the embodiment of the present application, obviously, the described embodiment is only a part of the embodiment of the present application, not all. Based on the embodiment in the present application, all other embodiments obtained by the person skilled in the art without making creative labor should belong to the scope of the present application.

[0045] 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 describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than those 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.

[0046] Embodiment one

[0047] Figure 1 A schematic diagram of a numerical control machine tool self-adaptive control system is provided for the first embodiment of the present application, the system comprises:

[0048] Numerical control machine tool (S1), data processing module (S2), working condition judgment module (S3), adaptive control module (S4) and output control module (S5);

[0049] The data processing module (S2) comprises a data acquisition unit (S21) and a preprocessing unit (S22), the data acquisition unit is composed of a plurality of sensors, for collecting a plurality of operating parameters at regular intervals;

[0050] Among them, the numerical control machine tool (S1) is connected with the data acquisition unit in the data processing module, the data acquisition unit is connected with the preprocessing unit, the preprocessing unit is connected with the working condition judgment module, the working condition judgment module is connected with the adaptive control module, and the adaptive control module is connected with the output control module;

[0051] The data processing unit is configured to perform feature extraction on the collected multiple operating parameters in real time to obtain multiple machine tool features.

[0052] The working condition judgment module is configured to receive the multiple machine tool features from the data processing unit, and perform working condition state judgment according to a pre-prepared working condition state judgment strategy, and if it is judged that the working condition state of the operating parameters is abnormal, acquire abnormal cutting parameters corresponding to the abnormal operating parameters, and send the abnormal cutting parameters to the adaptive control module.

[0053] The adaptive control module is configured to receive the abnormal cutting parameters transmitted from the working condition judgment module, and perform adaptive adjustment on the abnormal cutting parameters according to a pre-prepared adaptive algorithm.

[0054] The output control module is configured to receive the cutting parameters adjusted by the adaptive control module, and control the axial movement of the machine tool according to the cutting parameters.

[0055] In the process of manufacturing an airplane, most of the parts of the airplane have the characteristics of complex structure, large profile size and high machining precision requirement, which puts high requirements on the selection and use of the numerical control machine tool. With the rapid development of modern aviation manufacturing industry, the numerical control machine tool has initially formed a key technical advantage represented by the manufacturing of large and complex structural parts of the airplane in the aviation manufacturing industry, and especially in the machining and manufacturing of typical parts of the airplane, adaptive machining control of the numerical control machine tool helps to promote the development of the numerical control machine tool in terms of machining reliability and tool cutting efficiency.

[0056] Specifically, in the adaptive control system of the numerical control machine tool designed in the embodiment of the application, the running state of the numerical control machine tool is monitored by periodically collecting multiple machine tool operating parameters of the numerical control machine tool (S1). Each machine tool operating parameter is obtained depending on a specific sensor, multiple sensors constitute a data acquisition unit (S21), different types of operating parameters collected are sent to a preprocessing unit (S22) for filtering, normalization and other processing to ensure the quality and consistency of the operating parameters, and then frequency domain features or time domain features are extracted to describe the key information in the machining process to obtain multiple machine tool features.

[0057] In practical application, the working condition state determination strategy is to determine whether the current state of the target machine tool is normal according to the value of the running parameter obtained in advance according to prior knowledge, for example, when the value of a running parameter exceeds the normal threshold value specified in the working condition state determination strategy, the machine tool needs to be adaptively regulated and controlled at this time. The cutting parameters can refer to the spindle speed and the feed speed, and when the running parameters of the target machine tool are at different values, the corresponding spindle speed and feed speed are different, so when it is determined that the running parameter is abnormal, the cutting parameters under the abnormal running parameter are also abnormal, that is, the speed and the feed speed are abnormal.

[0058] And the pre-set adaptive algorithm refers to the adaptive adjustment of the abnormal cutting parameters, so as to restore the normal speed and feed speed of the target machine tool, and when the cutting parameters return to normal, the working condition state of the target machine tool returns to normal, that is, each running parameter returns to normal.

[0059] In the embodiment of the application, by periodically collecting and processing the running parameter data in the machining process of the numerical control machine tool, the running state of the target numerical control machine tool is monitored, when the data is abnormal, the cutting parameters at the abnormal time can be adaptively adjusted, and the movement displacement of each axis of the machine tool is controlled according to the adjusted cutting parameters, so as to realize adaptive control. By automatically adjusting the cutting parameters and the axial movement control, not only unnecessary energy consumption and material waste can be reduced, but also complex geometric shapes and machining requirements can be adapted, and such flexibility enables the system to adapt to various complex and variable machining tasks.

[0060] Optionally, the data acquisition unit comprises a temperature sensor, a position sensor, a force sensor and a speed sensor, wherein the target numerical control machine tool is connected with each sensor of the data acquisition unit respectively;

[0061] The temperature sensor is used for collecting the machine tool temperature of the target numerical control machine tool based on a time period, and sending the machine tool temperature to the working condition judgment module through the preprocessing unit;

[0062] The force sensor is used for collecting the cutting load of the target numerical control machine tool based on a time period, and sending the cutting load to the working condition judgment module through the preprocessing unit;

[0063] The position sensor is used for receiving the coordinate acquisition instruction from the output control module, collecting the target position coordinates of each axis of the target numerical control machine tool, and sending the target position coordinates to the output control module through the preprocessing unit;

[0064] The speed sensor is used for receiving the data acquisition instruction issued by the working condition judgment module, collecting the target cutting parameters of the target numerical control machine tool, and sending the target cutting parameters to the adaptive control module through the preprocessing unit.

[0065] The temperature sensor can be used to measure the temperature of the machine tool and the tool to avoid the influence of overheating and thermal deformation on the machining precision; the force sensor can be used to measure the cutting load to monitor the mechanical properties of the cutting process in real time; the position sensor can be used to measure the position and motion state of each axis of the machine tool, such as grating ruler and encoder; the speed sensor can be used to collect the current spindle speed and feed speed of the target machine tool.

[0066] Optionally, the working condition judgment module further comprises a temperature abnormality judgment unit and a cutting force abnormality judgment unit.

[0067] The temperature abnormality judgment unit is configured to compare the machine tool temperature of the target numerical control machine tool with a temperature threshold value, and when the machine tool temperature data is greater than the temperature threshold value, the abnormal cutting parameter under the current abnormal machine tool temperature is obtained through the speed sensor in the data acquisition unit.

[0068] The cutting force abnormality judgment unit is configured to compare the cutting load of the target numerical control machine tool with a load threshold value, and when the cutting load is greater than the load threshold value, the abnormal cutting parameter under the current abnormal cutting load is obtained through the speed sensor in the data acquisition unit.

[0069] In the working condition state judgment strategy, the basic threshold values of various operating parameters are preset, when the temperature operating parameter collected by the temperature sensor or the cutting load operating parameter collected by the force sensor exceeds the corresponding basic threshold value, the working condition judgment module sends a data acquisition signal to the speed sensor, and the speed sensor receives the data acquisition signal, collects the cutting parameter under the current working condition state of the target machine tool, and sends it to the adaptive updating unit for adaptive adjustment.

[0070] Optionally, the adaptive control module comprises an adaptive updating unit, an adaptive compensation unit, and a cutting parameter adjustment unit.

[0071] The adaptive updating unit is configured to receive the abnormal cutting parameter sent by the working condition judgment module, and calculate the control error and the new cutting parameter by substituting the abnormal cutting parameter into the pre-constructed adaptive updating algorithm.

[0072] The adaptive compensation unit is configured to receive the control error sent by the cutting parameter adjustment unit, and calculate the cutting compensation amount by substituting the control error into the pre-constructed adaptive compensation algorithm; the cutting parameter adjustment unit is configured to receive the new cutting parameter in the adaptive updating unit and the cutting compensation amount in the adaptive compensation unit, and calculate the sum of the new cutting parameter and the cutting compensation amount to obtain the adaptive cutting parameter.

[0073] Specifically, in the adaptive updating algorithm, an initial cutting parameter μ0 and an expected output r(k) are preset, the expected output r(k) is each standard operation parameter corresponding to the initial cutting parameter μ0, each abnormal operation parameter is an actual output y(k), and a control error between the expected output and the actual output can be obtained, and a specific calculation formula is e(k) = r(k) - y(k).

[0074] Wherein, e(k) represents the control error at k time, the cutting adjustment amount of the cutting parameter is calculated according to the control error, and the algorithm formula is Δu(k) = K·e(k).

[0075] Δu(k) = K·e(k).

[0076] Wherein, K is a preset gain matrix, and Δu(k) is the cutting parameter adjustment amount, the new cutting parameter u(k) is obtained by adding the cutting parameter adjustment amount and the initial cutting parameter, that is, u(k) = u0 + Δu(k).

[0077] In the adaptive compensation unit, the required cutting compensation amount is calculated through the control error to correct the error in the machining process, and the specific algorithm formula is C(k) = K c ·e(k).

[0078] Wherein, C(k) represents the cutting compensation amount at k time, and K c represents a compensation coefficient.

[0079] Finally, in the cutting parameter adjustment unit, the adaptive cutting parameter U k is obtained by summing the new cutting parameter u(k) and the cutting compensation amount C(k), and the specific algorithm formula is U k = Δu(k) + C(k).

[0080] Optionally, the output control module further comprises a path planning unit and a servo unit.

[0081] The path planning unit is configured to send a coordinate acquisition instruction to a position sensor after receiving the adaptive cutting parameter from the cutting parameter adjustment unit, receive original target position coordinates of each axis of the target numerical control machine tool collected by the position sensor, and obtain new target position coordinates of each axis of the target numerical control machine tool according to a preset position coordinate and cutting parameter relationship library.

[0082] The servo unit is configured to receive the new target position coordinates of each axis of the target numerical control machine tool sent by the path planning unit, and drive each axis of the machine tool to move according to the new target position coordinates based on the original target position coordinates.

[0083] The servo unit is composed of a plurality of servo devices, and is used to drive the movement of each axis of the target machine tool according to the new target position coordinates, and to perform position control and speed adjustment.

[0084] Optionally, the system further comprises a reinforcement learning module, wherein the reinforcement learning module is connected with the data processing module, the adaptive control module and the working condition judgment module respectively;

[0085] The reinforcement learning module is used to obtain a plurality of running parameters in the preprocessing unit according to a specified period, input the plurality of running parameters into the original machine learning model, and respectively obtain a machine tool temperature and cutting parameter relationship library, a cutting load and cutting parameter relationship library, and a position coordinate and cutting parameter relationship library.

[0086] Meanwhile, the reinforcement learning module is also used to obtain abnormal cutting parameters in the working condition judgment module according to a specified period, and based on the abnormal cutting parameters and the preset original cutting parameters, an adaptive updating algorithm and an adaptive compensation algorithm are constructed, and the adaptive updating algorithm is synchronized to the adaptive updating unit, and the adaptive compensation algorithm is synchronized to the adaptive compensation unit.

[0087] The machine tool temperature and cutting parameter relationship library includes a mapping relationship between the machine tool temperature and the cutting parameter, based on which, in the adaptive updating algorithm, an expected output value of the machine tool temperature under the initial cutting parameter μ0 can be obtained; similarly, the cutting load and cutting parameter relationship library includes a mapping relationship between the cutting load and the cutting parameter, based on which, in the adaptive updating algorithm, an expected output value of the cutting load under the initial cutting parameter μ0 can be obtained. The position coordinate and cutting parameter relationship library includes a mapping relationship between the position of each axis of the target machine tool and the cutting parameter, in the path planning unit, the current position of each axis of the target machine tool can be obtained according to the abnormal cutting parameter μ0, and the adaptive cutting parameter U k The new target position coordinates of each axis of the target machine tool are obtained, and the machine tool is driven by the servo unit to move from the current position to the new position.

[0088] Embodiment two

[0089] Figure 2 A flowchart of a numerical control machine tool adaptive control method provided for embodiment two of the present application, the present embodiment can be applicable to the case of controlling a numerical control machine tool to perform adaptive machining, the method can be executed by a numerical control machine tool adaptive control system, which can be configured in a numerical control machine tool used for part machining. As shown in the figure, the method comprises: Figure 2 S210, acquiring a plurality of running parameters by the data acquisition unit in a timely manner;

[0090] S210, acquiring a plurality of running parameters by the data acquisition unit in a timely manner;

[0091] S220, performing real-time feature extraction on the acquired plurality of running parameters by the data processing unit to obtain a plurality of machine tool features;

[0092] S230, receiving multiple machine tool features from the data processing unit through the working condition judgment module, and determining the working condition state according to the pre-prepared working condition state determination strategy, if the working condition state of the running parameter is determined to be abnormal, obtaining the abnormal cutting parameter corresponding to the abnormal running parameter, and sending the abnormal cutting parameter to the adaptive control module;

[0093] S240, receiving the abnormal cutting parameter transmitted from the working condition judgment module through the adaptive control module, and adaptively adjusting the abnormal cutting parameter according to the pre-prepared adaptive algorithm;

[0094] S250, receiving the cutting parameter adjusted by the adaptive control module through the output control module, and controlling the axial movement of the machine tool according to the cutting parameter.

[0095] Optionally, the method can further include:

[0096] Through the reinforcement learning module, multiple running parameters in the preprocessing unit are obtained according to a specified period; the multiple running parameters are input into the original machine learning model to obtain a machine tool temperature and cutting parameter relationship library, a cutting load and cutting parameter relationship library, and a position coordinate and cutting parameter relationship library, respectively;

[0097] At the same time, the abnormal cutting parameter in the working condition judgment module is obtained according to a specified period, and based on the abnormal cutting parameter and the pre-prepared original cutting parameter, an adaptive update algorithm and an adaptive compensation algorithm are constructed, and the adaptive update algorithm is synchronized to the adaptive update unit, and the adaptive compensation algorithm is synchronized to the adaptive compensation unit.

[0098] The reinforcement learning module is connected with the data processing module to obtain the mapping relationship between the running parameter and the cutting parameter, and is synchronized to the adaptive update unit; at the same time, the reinforcement learning module is connected with the working condition judgment module to obtain two adaptive algorithms, and is synchronized to the adaptive update unit. For the convenience of understanding, Figure 3 A connection relationship diagram of a reinforcement learning module in a system and other functional modules is shown.

[0099] Further, the adaptive control module receives the abnormal cutting parameter transmitted from the working condition judgment module, and adaptively adjusts the abnormal cutting parameter according to the pre-prepared adaptive algorithm, which can include:

[0100] Through the adaptive update unit, the abnormal cutting parameter transmitted from the working condition judgment module is received, and the adaptive cutting parameter is calculated by substituting the abnormal cutting parameter into the pre-prepared adaptive update algorithm;

[0101] The adaptive compensation unit receives the new cutting parameter from the cutting parameter adjustment unit, and calculates the cutting compensation amount by substituting the new cutting parameter into the adaptive compensation algorithm constructed in advance.

[0102] The cutting parameter adjustment unit receives the adaptive cutting parameter from the adaptive update unit and the cutting compensation amount from the adaptive compensation unit, and calculates the sum of the adaptive cutting parameter and the cutting compensation amount to obtain the new cutting parameter.

[0103] For the convenience of understanding, Figure 4 A detailed connection relationship diagram of each functional module in the adaptive control system of the numerical control machine tool is shown, wherein, on the basis of Figure 1 The data flow of each sensor in the data acquisition unit, each abnormality determination unit contained in the working condition determination module, and the data processing sequence of each unit in the adaptive control module are shown.

[0104] Optionally, the output control module receives the adjusted cutting parameter from the adaptive control module, and controls the axial movement of the machine tool according to the cutting parameter, which can include:

[0105] The path planning unit receives the new cutting parameter from the cutting parameter adjustment unit, sends a coordinate acquisition instruction to the position sensor, and receives the original target position coordinates of each axis of the target numerical control machine tool collected by the position sensor, obtains the new target position coordinates of each axis of the target numerical control machine tool according to the preset position coordinate and cutting parameter relationship library.

[0106] The servo unit is used to receive the new target position coordinates of each axis of the target numerical control machine tool from the path planning unit, and drive each axis of the machine tool to move according to the new target position coordinates based on the original target position coordinates.

[0107] For the convenience of understanding, Figure 5 The internal subunit connection relationship diagram of the output control module is shown, which describes the data source of the output control unit and the specific application of the data.

[0108] The embodiment of the present application provides a numerical control machine tool adaptive control method, specifically, a data single machine unit collects operation parameters of a target numerical control machine tool at regular time intervals, sends the operation parameters to a working condition judgment unit after preprocessing, the working condition judgment unit judges whether the operation parameters are abnormal based on a working condition judgment strategy, if the operation parameters are abnormal, abnormal cutting parameters under the current abnormal operation parameters are acquired, and the adaptive control module is used for adaptive adjustment of the abnormal cutting parameters, and the output control module controls the target numerical control machine tool according to the adaptive adjustment result. Wherein, the reinforcement learning module is used for regularly updating a mapping relationship between the cutting parameters and the operation parameters and an adaptive algorithm, and synchronously updating the adaptive control module, the self-learning and optimization capability of the system is enhanced, and efficient operation of the machine tool under different machining conditions can be ensured. Meanwhile, the adjustment of the cutting parameters by the adaptive algorithm can compensate for errors in the machining process, so that the machining precision and stability are improved.

[0109] It should be understood that the various forms of flow shown above can be reordered, added to, or deleted from. For example, each step described in the present application can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions of the present application can be achieved, which is not limited herein.

[0110] The above specific embodiments do not constitute a limitation on the protection scope of the present application. Those skilled in the art should understand that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent replacement and improvement within the spirit and principle of the present application should be included in the protection scope of the present application.

Claims

1. An adaptive control system for a CNC machine tool, characterized in that, include: CNC machine tool, data processing module, working condition judgment module, adaptive control module, and output control module; The data processing module includes a data acquisition unit and a preprocessing unit. The data acquisition unit consists of multiple sensors and is used to collect multiple operating parameters at regular intervals. Among them, the CNC machine tool is connected to the data acquisition unit in the data processing module, the data acquisition unit is connected to the preprocessing unit, the preprocessing unit is connected to the working condition judgment module, the working condition judgment module is connected to the adaptive control module, and the adaptive control module is connected to the output control module. The preprocessing unit is used to extract features from multiple collected operating parameters in real time to obtain multiple machine tool features; The working condition judgment module is used to receive multiple machine tool features from the preprocessing unit and perform working condition judgment according to the pre-defined working condition judgment strategy. If the working condition of the operating parameters is determined to be abnormal, the abnormal cutting parameters corresponding to the abnormal operating parameters are obtained and the abnormal cutting parameters are sent to the adaptive control module. The adaptive control module is used to receive abnormal cutting parameters from the working condition judgment module and adaptively adjust the abnormal cutting parameters according to a pre-set adaptive algorithm. The output control module is used to receive the cutting parameters adjusted by the adaptive control module and control the axial movement of the machine tool according to the cutting parameters; The system also includes a reinforcement learning module, which is connected to the data processing module, the adaptive control module, and the working condition judgment module. The reinforcement learning module is used to acquire multiple operating parameters from the preprocessing unit according to a specified period; input the multiple operating parameters into the original machine learning model to obtain the machine tool temperature and cutting parameter relationship library, the cutting load and cutting parameter relationship library, and the position coordinate and cutting parameter relationship library, respectively. Meanwhile, it is also used to obtain abnormal cutting parameters in the working condition judgment module according to a specified cycle, and to construct an adaptive update algorithm and an adaptive compensation algorithm based on the abnormal cutting parameters and the preset original cutting parameters, and to synchronize the adaptive update algorithm to the adaptive update unit and the adaptive compensation algorithm to the adaptive compensation unit. The machine tool temperature and cutting parameter relationship library includes the mapping relationship between machine tool temperature and cutting parameters, which is used by the adaptive update algorithm to obtain the expected output value of machine tool temperature under the initial cutting parameters; the cutting load and cutting parameter relationship library includes the mapping relationship between cutting load and cutting parameters, which is used by the adaptive update algorithm to obtain the expected output value of cutting load under the initial cutting parameters; the position coordinate and cutting parameter relationship library includes the mapping relationship between the position of each axis of the target machine tool and the cutting parameters, which is used by the path planning unit to obtain the current and new position coordinates of each axis of the machine tool based on abnormal cutting parameters.

2. The system according to claim 1, characterized in that, The data acquisition unit includes a temperature sensor, a position sensor, a force sensor, and a speed sensor, wherein the target CNC machine tool is connected to each sensor of the data acquisition unit. A temperature sensor is used to collect the machine tool temperature of the target CNC machine tool based on a time period, and then send it to the working condition judgment module after preprocessing. Force sensors are used to collect the cutting load of the target CNC machine tool based on a time period, and send it to the working condition judgment module after preprocessing. The position sensor is used to receive coordinate acquisition instructions from the output control module, collect the target position coordinates of each axis of the target CNC machine tool, and send them to the output control module after preprocessing. The speed sensor is used to receive data acquisition instructions from the working condition judgment module, collect the target cutting parameters of the target CNC machine tool, and send them to the adaptive control module through the preprocessing unit.

3. The system according to claim 1, characterized in that, The working condition judgment module also includes a temperature abnormality judgment unit and a cutting force abnormality judgment unit; The temperature anomaly determination unit is used to compare the machine tool temperature of the target CNC machine tool with a temperature threshold. When the machine tool temperature data is greater than the temperature threshold, the abnormal cutting parameters at the current abnormal machine tool temperature are obtained through the speed sensor in the data acquisition unit. The abnormal cutting force determination unit is used to compare the cutting load of the target CNC machine tool with the load threshold. When the cutting load is greater than the load threshold, the abnormal cutting parameters under the current abnormal cutting load are obtained by the speed sensor in the data acquisition unit.

4. The system according to claim 1, characterized in that, The adaptive control module includes an adaptive update unit, an adaptive compensation unit, and a cutting parameter adjustment unit. The adaptive update unit is used to receive abnormal cutting parameters from the working condition judgment module, and substitute the abnormal cutting parameters into the pre-built adaptive update algorithm to calculate the control error and new cutting parameters. The adaptive compensation unit is used to receive the control error from the cutting parameter adjustment unit and substitute the control error into the pre-built adaptive compensation algorithm to calculate the cutting compensation amount. The cutting parameter adjustment unit is used to receive the new cutting parameters from the adaptive update unit and the cutting compensation amount from the adaptive compensation unit, and calculate the sum of the new cutting parameters and the cutting compensation amount to obtain the adaptive cutting parameters.

5. The system according to claim 4, characterized in that, The output control module also includes a path planning unit and a servo unit; The path planning unit is used to receive adaptive cutting parameters from the cutting parameter adjustment unit, send coordinate acquisition instructions to the position sensor, receive the original target position coordinates of each axis of the target CNC machine tool collected by the position sensor, and obtain the new target position coordinates of each axis of the target CNC machine tool according to the preset position coordinate and cutting parameter relationship library. The servo unit is used to receive the new target position coordinates of each axis of the target CNC machine tool from the path planning unit, and drive each axis of the machine tool to move according to the new target position coordinates based on the original target position coordinates.

6. An adaptive control method for CNC machine tools, characterized in that, Applied to the adaptive control system of a CNC machine tool as described in any one of claims 1-5, the method comprises: Multiple operating parameters are collected periodically through the data acquisition unit; The preprocessing unit extracts features from multiple collected operating parameters in real time to obtain multiple machine tool features; The working condition judgment module receives multiple machine tool features from the preprocessing unit and performs working condition judgment according to the pre-defined working condition judgment strategy. If the working condition of the operating parameters is determined to be abnormal, the abnormal cutting parameters corresponding to the abnormal operating parameters are obtained and the abnormal cutting parameters are sent to the adaptive control module. The adaptive control module receives abnormal cutting parameters from the working condition judgment module and adjusts the abnormal cutting parameters adaptively according to the preset adaptive algorithm. The output control module receives the cutting parameters adjusted by the adaptive control module and controls the axial movement of the machine tool according to the cutting parameters. The reinforcement learning module acquires multiple operating parameters from the preprocessing unit according to a specified period; these multiple operating parameters are then input into the original machine learning model to obtain the machine tool temperature and cutting parameter relationship database, the cutting load and cutting parameter relationship database, and the position coordinate and cutting parameter relationship database, respectively. Meanwhile, abnormal cutting parameters in the working condition judgment module are obtained according to the specified cycle, and an adaptive update algorithm and an adaptive compensation algorithm are constructed based on the abnormal cutting parameters and the preset original cutting parameters. The adaptive update algorithm is synchronized to the adaptive update unit, and the adaptive compensation algorithm is synchronized to the adaptive compensation unit. The machine tool temperature and cutting parameter relationship library includes the mapping relationship between machine tool temperature and cutting parameters, which is used by the adaptive update algorithm to obtain the expected output value of machine tool temperature under the initial cutting parameters; the cutting load and cutting parameter relationship library includes the mapping relationship between cutting load and cutting parameters, which is used by the adaptive update algorithm to obtain the expected output value of cutting load under the initial cutting parameters; the position coordinate and cutting parameter relationship library includes the mapping relationship between the position of each axis of the target machine tool and the cutting parameters, which is used by the path planning unit to obtain the current and new position coordinates of each axis of the machine tool based on abnormal cutting parameters.

7. The method according to claim 6, characterized in that, The adaptive control module receives abnormal cutting parameters from the working condition judgment module and adaptively adjusts these parameters according to a pre-set adaptive algorithm, including: The adaptive update unit receives abnormal cutting parameters from the working condition judgment module and substitutes these abnormal cutting parameters into a pre-built adaptive update algorithm to calculate the control error and new cutting parameters. The adaptive compensation unit receives the control error from the cutting parameter adjustment unit and substitutes the control error into the pre-built adaptive compensation algorithm to calculate the cutting compensation amount. The cutting parameter adjustment unit receives the new cutting parameters from the adaptive update unit and the cutting compensation amount from the adaptive compensation unit, and calculates the sum of the new cutting parameters and the cutting compensation amount to obtain the adaptive cutting parameters.

8. The method according to claim 6, characterized in that, The output control module receives the cutting parameters adjusted by the adaptive control module and controls the axial movement of the machine tool according to the cutting parameters, including: After receiving the adaptive cutting parameters from the cutting parameter adjustment unit through the path planning unit, it sends a coordinate acquisition command to the position sensor and receives the original target position coordinates of each axis of the target CNC machine tool collected by the position sensor. According to the preset position coordinate and cutting parameter relationship library, it obtains the new target position coordinates of each axis of the target CNC machine tool. The servo unit receives the new target position coordinates of each axis of the target CNC machine tool from the path planning unit, and drives each axis of the machine tool to move according to the new target position coordinates based on the original target position coordinates.

Images