Method and system for regulating and controlling rotating speed of cyclone machining main shaft

Abstract

The invention relates to the technical field of spindle rotating speed regulation and control, in particular to a rotational separation machining spindle rotating speed regulation and control method and system.The method comprises the steps that the target rotating speed ratio is calculated based on the tooth number / edge number of a workpiece and the cutter tooth number of a cutter head; based on the tooth number / edge number of the workpiece and the preset rotating speed of a workpiece shaft or the number of cutter teeth of the cutter head and the preset rotating speed of the cutter head, the contact interval between the workpiece and cutter teeth of the cutter head under the target rotating speed ratio is calculated and defined as the theoretical contact interval; in the rotational separation machining process, the contact interval between a workpiece and cutter teeth of a cutter head is collected and defined as the actual contact interval; calculating a spindle rotating speed matching degree based on the theoretical contact interval and the actual contact interval, and judging whether to regulate and control the spindle rotating speed based on the spindle rotating speed matching degree; and calculating the spindle rotating speed regulation quantity, and regulating the spindle rotating speed through the driving end of the spindle. The method can effectively reduce the main shaft rotation speed regulation delay and the matching degree judgment deviation of the main shaft rotation speed and the workpiece rotation speed.

Description

Technical Field

[0001] This invention relates to the field of spindle speed control technology, specifically to a method and system for controlling the spindle speed in rotary machining. Background Technology

[0002] The core of rotary machining is to achieve simultaneous cutting and indexing by using a fixed speed ratio between the cutter head and the workpiece. Its essential characteristic is that the contact interval between the cutter teeth and the workpiece is fixed, and this contact interval is determined by the target speed ratio, the number of cutter teeth, and the number of workpiece teeth.

[0003] In existing technologies, the matching and monitoring of spindle speed and workpiece speed mostly rely on speed sensors. After collecting the speeds of the cutter head and workpiece, the speed ratio is calculated, and the matching degree between the spindle speed and workpiece speed is judged by the speed signal. This method often requires a certain amount of speed deviation to be accumulated before mismatch is detected, which can easily lead to multiple sets of cutter teeth abnormally cutting before triggering speed control, resulting in monitoring and control lag. In addition, existing technologies usually place the speed sensor at the drive end of the spindle. For example, an absolute photoelectric encoder is used as the speed sensor and integrated into the spindle to monitor the rotor speed and position of the spindle to deduce the speed and position of the cutter head. However, the cutter head is at the cutting end of the spindle, and its actual speed signal is easily affected by transmission backlash, sensor error, and mechanical vibration, leading to deviations in the judgment of the matching degree between the spindle speed and workpiece speed.

[0004] Based on the above shortcomings, a spindle speed control technology suitable for rotary machining is proposed. Summary of the Invention

[0005] To address the aforementioned problems, this invention provides a spindle speed control method and system for rotary machining, which reduces spindle speed control delay and deviation in the matching degree judgment between spindle speed and workpiece speed.

[0006] To achieve the above objectives, the technical solution of the present invention is as follows: On the one hand, a method for controlling the spindle speed in rotary machining is provided, including, Calculate the target speed ratio based on the number of teeth / sides of the workpiece and the number of teeth on the cutter head; Based on the number of workpiece teeth / sides and the preset speed of the workpiece shaft or the number of cutter teeth and the preset speed of the cutter head, calculate the contact interval between the workpiece and the cutter head teeth at the target speed ratio, and define it as the theoretical contact interval. During the rotary machining process, the contact interval between the workpiece and the cutting teeth of the cutter head is collected and defined as the actual contact interval; The spindle speed matching degree is calculated based on the theoretical contact interval and the actual contact interval, and the spindle speed matching degree is used to determine whether spindle speed regulation is required. Calculate the spindle speed control amount and adjust the spindle speed through the spindle drive end.

[0007] Furthermore, the formula for calculating the target speed ratio is as follows:

[0008] in, This represents the number of teeth / sides of the workpiece. This refers to the number of teeth on the cutter head.

[0009] Furthermore, the theoretical contact interval calculation formula is as follows:

[0010] in, The theoretical contact interval is used to characterize the fixed contact period between the cutting tooth and the workpiece at the target speed ratio. This represents the number of teeth / sides of the workpiece. The number of teeth on the cutter head. Set the preset spindle speed; Set the preset rotational speed for the workpiece axis.

[0011] Furthermore, the actual contact interval is collected using one of the following methods: (1) The current signal of the drive end is collected by a current sensor that is electrically connected to the drive end of the spindle. When the fluctuation of the current signal reaches a preset threshold, it is determined that contact has occurred. (2) The pressure signal is collected by a pressure sensor set between the cutter head and the cutter teeth. When the pressure signal shows a valid fluctuation, it is determined that contact has occurred. Formula for calculating actual contact interval:

[0012] in, is the actual contact interval; k is the sequence number of contact times between the workpiece and the cutter teeth of the cutter head, k=1,2,…,n.

[0013] Furthermore, the formula for calculating the spindle speed matching degree is as follows:

[0014] in, This is the theoretical contact interval; This refers to the actual contact interval; Set matching threshold The matching degree threshold It is directly proportional to the workpiece machining accuracy; when When this occurs, it is determined that the spindle speed is mismatched, triggering spindle speed control.

[0015] Furthermore, the determination of whether to perform spindle speed regulation also includes a deviation prediction step: First, calculate the deviation between adjacent contact intervals:

[0016] in, This is the theoretical contact interval; This refers to the actual contact interval; Reconstruct the time series deviation dataset The dataset is then augmented and normalized.

[0017] in, This represents the maximum value of the historical deviation. This represents the minimum historical deviation. Then, a sliding window is used to divide the input bias sequence into training, validation, and test sets; Finally, a bias prediction model is constructed and trained based on a lightweight LSTM model. By inputting the bias sequence into the trained bias prediction model, the predicted bias is output. ; The deviation prediction model is trained using the mean squared error loss function:

[0018] in, The prediction bias for the kth prediction is... This represents the actual deviation for the kth time.

[0019] Furthermore, the formula for calculating the spindle speed control amount is as follows:

[0020] in: Proportional Term , This is the proportionality coefficient; Integral term , The integral coefficient; Predicted compensation items , To predict the compensation coefficient.

[0021] Furthermore, the aforementioned The proportionality coefficient is derived using the following formula:

[0022] in, Selected based on load and machining accuracy requirements; The The integral coefficients are derived using the following formula:

[0023] in, Based on prediction bias Select.

[0024] Furthermore, the prediction compensation coefficient The value range is 0.8 to 1.2; The value is inversely proportional to the spindle speed matching degree.

[0025] On the other hand, a spindle speed control system for rotary machining is provided, comprising: The data acquisition module is used to acquire the number of workpiece teeth / sides, the number of cutter teeth on the cutter head, the preset spindle speed and the preset workpiece axis speed, as well as the contact signal between the cutter teeth and the workpiece; The data processing module is used to calculate the target speed ratio, theoretical contact interval, and actual contact interval; The data output module is used to calculate the speed matching degree, determine whether to adjust the spindle speed, calculate the spindle speed adjustment amount, and send the spindle speed adjustment amount to the drive end.

[0026] The above approach has the following beneficial effects: 1. Existing technologies rely on speed sensors to collect speed data and indirectly calculate the speed ratio, requiring the accumulation of multiple sets of speed data to detect mismatch. In contrast, this solution directly collects the contact interval between the cutter teeth and the workpiece, and can calculate the actual contact interval and determine the speed matching degree with a single contact. This shortens the time from the occurrence of mismatch to monitoring and identification, reduces the spindle speed control delay, enables rapid triggering of control, avoids abnormal cutting by multiple cutters, and significantly reduces the scrap rate.

[0027] 2. Existing technologies suffer from speed sensors mounted on the drive end of the spindle, creating a transmission gap between the sensor and the cutting end where the cutter head is located. Furthermore, the signal is susceptible to mechanical vibration and electromagnetic interference, leading to potential deviations in the determined speed matching degree. In contrast, this solution uses the contact interval characteristics of rotary machining as the judgment benchmark. The contact signal directly reflects the cutting indexing synchronization and is unaffected by transmission gaps or sensor errors. Through spindle speed matching degree calculation and deviation prediction, accurate speed matching degree judgment can be ensured.

[0028] 3. In contrast to existing technologies, most methods rely on passive control, adjusting only after the deviation exceeds a threshold. Frequent mismatches can severely impact processing stability. This solution, however, uses a deviation prediction model to predict future contact interval deviations, enabling proactive control and reducing the frequency of speed mismatches, thus improving processing stability. Attached Figure Description

[0029] Figure 1 This is a schematic diagram of the overall process of an embodiment of the spindle speed control method for rotary machining of the present invention; Figure 2 This is a schematic diagram of the deviation prediction model architecture of an embodiment of the spindle speed control method for rotary machining of the present invention; Figure 3This is a schematic diagram of the workflow of an embodiment of the spindle speed control method for rotary machining of the present invention; Figure 4 This is a schematic diagram of an embodiment of the spindle speed control system for rotary machining according to the present invention. Detailed Implementation

[0030] The technical solution of the present invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0031] In the description of this invention, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing the invention and for simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0032] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0033] The following detailed description illustrates the specific implementation method: The hardware improvements of the rotary milling machine include the following: First, hardware for monitoring the contact between the workpiece and the cutter teeth is installed on the electric spindle. In this embodiment, the hardware for monitoring the contact between the workpiece and the cutter teeth is a current sensor, which is electrically connected to the drive end of the spindle. The current sensor is used to collect the current signal from the drive end, and the contact between the workpiece and the cutter teeth is determined based on the fluctuation of the current signal reaching a fluctuation threshold. The fluctuation frequency of the current signal is used as the contact interval between the workpiece and the cutter teeth. In some other embodiments, the hardware for monitoring the contact between the workpiece and the cutter teeth is a pressure sensor, which is located between the cutter and the cutter teeth. The pressure sensor is used to collect the pressure signal between the cutter and the cutter teeth, and the contact between the workpiece and the cutter teeth is determined based on the pressure signal. The fluctuation frequency of the pressure signal is used as the contact interval between the workpiece and the cutter teeth.

[0034] Secondly, an additional data processing unit is added to determine and record the contact interval between the workpiece teeth and the cutter head teeth. In this embodiment, the data processing unit can be a microprocessor, controller, or other control component. For example, it can be a general-purpose central processing unit (CPU), a general-purpose processor, a digital signal processing unit (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. The data processing unit is used to record the timestamp of the contact moment each time the cutter head teeth make cutting contact with the workpiece. In some other embodiments, a data processing module is integrated within the CNC system. This module records a timestamp of the contact moment each time the cutter teeth make cutting contact with the workpiece. .

[0035] Based on the hardware improvements of the aforementioned rotary separator, such as Figure 1 As shown, the spindle speed control method includes the following steps: S101: Obtain the workpiece tooth / side count and cutter head tooth count from the CNC system of the rotary machining center. Calculate the target speed ratio based on these data. Specifically, the workpiece tooth / side count refers to the number of teeth / sides of the workpiece to be processed. The workpiece to be processed can be a workpiece to be toothed, a workpiece to be chamfered, or a workpiece to be edge-cut, etc. When the workpiece to be processed is a workpiece to be toothed or chamfered, the target speed ratio is calculated based on the workpiece tooth count. When the workpiece to be processed is a workpiece to be edge-cut, the target speed ratio is calculated based on the workpiece side count. The specific calculation formula for the target speed ratio is as follows:

[0036] in, This represents the number of teeth / sides of the workpiece. The number of cutting teeth on the cutter head; Main spindle speed (preset by the CNC system); The workpiece axis speed is preset by the CNC system; the spindle speed and workpiece axis speed can also be directly obtained from the CNC system of the rotary machining center.

[0037] S102: Based on the number of workpiece teeth and workpiece rotation speed, or the number of cutter teeth and cutter head rotation speed, calculate the contact interval between the workpiece teeth and the cutter head teeth at the target rotation speed ratio, which is defined as the theoretical contact interval; the specific calculation formula for the theoretical contact interval is as follows:

[0038] S103: During the rotary machining process, the contact interval between the workpiece teeth and the cutter head teeth is collected and defined as the actual contact interval. In this embodiment, the actual contact interval is calculated based on the current fluctuation frequency of the spindle drive end collected by the current sensor. Specifically, the timestamp of the contact moment recorded by the data processing unit is extracted, and the time difference between the contact between adjacent workpieces and the cutter head teeth is calculated, i.e., the actual contact interval.

[0039] Where k is the sequence number of times the workpiece contacts the cutting teeth of the cutter head, k=1,2,…,n.

[0040] S104: Calculate the spindle speed matching degree based on the theoretical and actual contact intervals, and determine whether to adjust the spindle speed based on the spindle speed matching degree. Specifically, first, a matching degree threshold is set based on the workpiece's machining accuracy requirements. Matching threshold The spindle speed matching degree is directly proportional to the workpiece's machining accuracy; when the matching degree is lower than the matching degree threshold... If this occurs, it is determined that the spindle speed is mismatched, meaning spindle speed adjustment is necessary. The spindle speed matching degree is then calculated using the following formula:

[0041] Preferably, a matching degree threshold is set. It is 99.5%, when If this occurs, it is determined that the spindle speed is mismatched, and spindle speed adjustment is required.

[0042] S105: When the spindle speed is mismatched, calculate the spindle speed adjustment amount and adjust the spindle speed through the drive end of the spindle. Specifically, the adjustment principle is to maintain the target speed ratio i, and by adjusting the spindle speed, make the actual contact interval return to the theoretical contact interval, so that the speed ratio between the cutter head and the workpiece at the cutting end of the spindle returns to the target speed ratio.

[0043] In this embodiment, to achieve more efficient and real-time spindle speed control and reduce the probability of abnormal cutting, the need for spindle speed control is predicted, and advance control is triggered based on the prediction results. Specifically, the theoretical contact interval is first obtained, and the actual contact interval is obtained in real time; then, the deviation between adjacent contact intervals is calculated.

[0044] in, Adjacent contact interval deviation, This represents the actual contact interval during the k-th contact. is the theoretical contact interval; k is the sequence number of contact times between the workpiece and the cutter teeth of the cutter head, k=1,2,…,n.

[0045] Then, based on the sliding window, the deviation of the first N contact intervals is selected. (N is a positive integer), the predicted deviation of the future contact interval is output through the deviation prediction model. .

[0046] The deviation prediction model in this embodiment is integrated into the data processing unit and is built based on the LSTM model. It mainly includes the following steps: obtaining the aforementioned adjacent contact interval deviations, based on the timestamp of the moment the cutter head teeth and workpiece make cutting contact. Construct a time-series bias dataset Where m is the total number of contacts between the cutter head teeth and the workpiece. Preferably, a time-series deviation dataset with m ≥ 1000 is constructed for training the deviation prediction model to ensure the training accuracy of the deviation prediction model. The data is augmented by adding common interference scenario data in rotary machining (such as material hard spots, slight tool wear, and load fluctuations) to generate simulated deviation data, avoiding overfitting of the deviation prediction model; for example, adding random deviations of ±0.0001~±0.0005s to simulate small fluctuations in rotational speed. A sliding window is used to divide the input deviation sequence (the time-series sequence of the contact interval deviation between the cutter head teeth and the workpiece in the first few instances), with the window size N preferably being 5~10, meaning each input represents the first 5~10 deviations. The corresponding output is the (k+1)th deviation. That is In addition, the input bias sequence needs to be normalized:

[0047] in, This represents the maximum value of the historical deviation. This represents the minimum historical deviation; normalizing the input deviation sequence can prevent differences in data magnitude from affecting the training of the deviation prediction model.

[0048] To address the need for low-latency spindle speed control during rotary machining, a lightweight LSTM model architecture is adopted to avoid latency caused by complex networks. Preferably, the lightweight LSTM model architecture is as follows: Figure 2 As shown, the input dimension of the input layer is the size of the sliding window; the LSTM hidden layer contains 1-2 layers, with 16-32 hidden units per layer, and the activation function is tanh; the output dimension of the fully connected layer is 1; and the activation function of the output layer is linear. The hyperparameters of the lightweight LSTM model are: batch size = 8-16; learning rate = 0.001-0.005; number of training epochs = 50-100.

[0049] The time-series bias dataset was divided into a training set (70%), a validation set (20%), and a test set (10%) in a 7:2:1 ratio. The training set was used to update the parameters of the bias prediction model, the validation set was used to monitor overfitting, and the test set was used to verify the final prediction accuracy. Mean squared error was adopted to suit the bias regression task, as shown in the following formula:

[0050] in, The prediction bias for the kth prediction is... This represents the actual deviation for the kth time.

[0051] In some other embodiments, the bias prediction model is also optimized, for example, by minimizing the loss function, dynamically adjusting the learning rate, pruning the network weights after training, reducing the computational load during inference, and ensuring low latency.

[0052] Based on the deviation prediction model obtained above, PID feedback regulation is integrated to realize the prediction of spindle speed control demand and the calculation of control amount. Specifically, before step S104, the deviation prediction model is used to predict and output the predicted deviation. In step S104, the prediction bias is obtained. Then, combined with prediction bias Determine the spindle speed mismatch: when and When this occurs, it is determined that the spindle speed is not mismatched, and the current spindle speed is maintained. or When a spindle speed mismatch is detected, step S105 is triggered to calculate the spindle speed control amount and regulate the spindle speed through the spindle drive end; in step S105, a PID control term is constructed: Proportional Term ,in This is the proportionality coefficient; Integral term ,in The integral coefficient; Predicted compensation items ,in To predict the compensation coefficient.

[0053] Combining the proportional term, integral term, and predictive compensation term above, calculate the spindle speed control amount: The data is then output from the data processing unit to the drive end of the spindle, and the control amount of the spindle drive end is... + This allows the actual contact interval to return to the theoretical contact interval. .

[0054] In this embodiment, the scaling factor and integral coefficient The value selection and deviation prediction model work together, with the core principle being the proportionality coefficient. The integral factor increases with increasing cutting load. The proportionality coefficient decreases as the cutting load increases; when the prediction result of the deviation prediction model is too large, the proportionality coefficient... Take the upper limit to achieve rapid control of the spindle speed, and the corresponding integral coefficient. Use the lower limit to avoid integral saturation; when the prediction result of the bias prediction model is too small, adjust the proportional coefficient. Take the lower limit.

[0055] Specifically, the proportionality coefficient The value selection strategy can be based on the adjacent contact interval deviation. The convergence is automatically selected: if the deviation converges slowly (failure to return to the allowable range after more than 5 contacts), the proportional coefficient is gradually increased. Increase the speed by 20 r / min each time; if the spindle speed fluctuates (the contact gap deviation varies greatly), gradually decrease the proportional coefficient. The speed is reduced by 20 r / min each time. In some other embodiments, the proportional coefficient can also be calculated directly using the following formula. :

[0056] in, Selection is based on load and machining accuracy requirements.

[0057] Specifically, the integral coefficient The value selection strategy can be automatically selected based on the average of several contact interval deviations: if the average of several contact interval deviations Then gradually increase the integral coefficient. Each increment is 0.05 r / (min·s); if integral saturation occurs, i.e., the speed is continuously adjusted in one direction, the integral coefficient is gradually reduced. The rate decreases by 0.05 r / (min·s) each time. In some other embodiments, the integral coefficient can also be calculated using the following formula. :

[0058] in, Based on prediction bias Select.

[0059] In this embodiment, the aforementioned prediction compensation coefficient The value ranges from 0.8 to 1.2, and is dynamically corrected based on the speed matching degree M: using the matching degree threshold. Taking 99.5% as an example, when hour, ;when hour, ;when hour, .

[0060] like Figure 3 As shown, the workflow of the above method is as follows: Initialization: Collect the number of workpiece teeth, the number of cutter teeth on the cutter head, and the target speed ratio, and automatically calculate the theoretical contact interval and matching degree threshold; Signal acquisition: Record the timestamp of each cutting contact between the cutter teeth and the workpiece. It also collects the spindle speed and workpiece shaft speed; Matching degree and prediction calculation: Real-time calculation of actual contact interval Spindle speed matching and prediction bias ;like or This triggers the spindle speed control. Dynamic control: Calculates the spindle speed control amount. The spindle drive end performs control; repeated signal acquisition - matching degree and prediction calculation - dynamic control, until... and .

[0061] Based on the above spindle speed control method, a spindle speed control system adapted to it is constructed, such as... Figure 4 As shown, the system mainly consists of a data acquisition module, a data processing module, and a data output module, which are connected and interact with each other sequentially. The data acquisition module is connected to the CNC system and the current sensor, while the data output module is connected to the spindle drive. Specifically, the data acquisition module obtains the workpiece tooth / side count and the cutter head tooth count from the CNC system, and simultaneously acquires the current signal from the current sensor. The data processing module calculates the target speed ratio based on the workpiece tooth / side count and the cutter head tooth count; simultaneously, it calculates the contact interval between the workpiece and the cutter head teeth at the target speed ratio, defined as the theoretical contact interval, based on the workpiece tooth / side count and workpiece speed or the cutter head tooth count and cutter head speed, and calculates the actual contact interval based on the current signal acquired by the current sensor. The data output module calculates the spindle speed matching degree based on the theoretical and actual contact intervals, determines whether spindle speed adjustment is needed based on the spindle speed matching degree, and calculates the spindle speed adjustment amount when spindle speed adjustment is required, sending it to the spindle drive.

[0062] Obviously, the above embodiments are merely illustrative examples for clear explanation and are not intended to limit the implementation. Those skilled in the art will recognize that other variations or modifications can be made based on the above description. It is neither necessary nor possible to exhaustively list all possible implementations here. However, obvious variations or modifications derived therefrom are still within the scope of protection of this invention.

Claims

1. A method for controlling the spindle speed in rotary machining, characterized in that, include: Calculate the target speed ratio based on the number of teeth / sides of the workpiece and the number of teeth on the cutter head; Based on the number of workpiece teeth / sides and the preset speed of the workpiece shaft or the number of cutter teeth and the preset speed of the cutter head, calculate the contact interval between the workpiece and the cutter head teeth at the target speed ratio, and define it as the theoretical contact interval. During the rotary machining process, the contact interval between the workpiece and the cutting teeth of the cutter head is collected and defined as the actual contact interval; The spindle speed matching degree is calculated based on the theoretical contact interval and the actual contact interval, and the spindle speed matching degree is used to determine whether spindle speed regulation is required. Calculate the spindle speed control amount and adjust the spindle speed through the spindle drive end.

2. The spindle speed control method for rotary machining according to claim 1, characterized in that, The formula for calculating the target speed ratio is as follows: ； in, This represents the number of teeth / sides of the workpiece. This refers to the number of teeth on the cutter head.

3. The spindle speed control method for rotary machining according to claim 1, characterized in that, The theoretical contact interval calculation formula is as follows: ； in, The theoretical contact interval is used to characterize the fixed contact period between the cutting tooth and the workpiece at the target speed ratio. This represents the number of teeth / sides of the workpiece. The number of teeth on the cutter head. Set the preset spindle speed; Set the preset rotational speed for the workpiece axis.

4. The spindle speed control method for rotary machining according to claim 1, characterized in that, The actual contact interval is collected using one of the following methods: (1) The current signal of the drive end is collected by a current sensor that is electrically connected to the drive end of the spindle. When the fluctuation of the current signal reaches a preset threshold, it is determined that contact has occurred. (2) The pressure signal is collected by a pressure sensor set between the cutter head and the cutter teeth. When the pressure signal shows a valid fluctuation, it is determined that contact has occurred. The formula for calculating the actual contact interval is as follows: ； in, is the actual contact interval; k is the sequence number of contact times between the workpiece and the cutter teeth of the cutter head, k=1,2,…,n.

5. The spindle speed control method for rotary machining according to claim 1, characterized in that, The formula for calculating spindle speed matching is as follows: ； in, This is the theoretical contact interval; This refers to the actual contact interval; Set matching threshold The matching degree threshold It is directly proportional to the workpiece machining accuracy; when When this occurs, it is determined that the spindle speed is mismatched, triggering spindle speed control.

6. The spindle speed control method for rotary machining according to claim 1, characterized in that, The determination of whether to perform spindle speed control also includes a deviation prediction step: First, calculate the deviation between adjacent contact intervals: ； in, This is the theoretical contact interval; This refers to the actual contact interval; Reconstruct the time series deviation dataset The dataset is then augmented and normalized. ； in, This represents the maximum value of the historical deviation. This represents the minimum historical deviation. Then, a sliding window is used to divide the input bias sequence into training, validation, and test sets; Finally, a bias prediction model is constructed and trained based on a lightweight LSTM model. By inputting the bias sequence into the trained bias prediction model, the predicted bias is output. ; The deviation prediction model is trained using the mean squared error loss function: ； in, The prediction bias for the kth prediction is... This represents the actual deviation for the kth time.

7. The spindle speed control method for rotary machining according to claim 6, characterized in that, The formula for calculating the spindle speed control amount is as follows: ； in: Proportional Term , This is the proportionality coefficient; Integral term , The integral coefficient; Predicted compensation items , To predict the compensation coefficient.

8. The spindle speed control method for rotary machining according to claim 7, characterized in that, The The proportionality coefficient is derived using the following formula: ； in, Selected based on load and machining accuracy requirements; The The integral coefficients are derived using the following formula: ； in, Based on prediction bias Select.

9. The spindle speed control method for rotary machining according to claim 7, characterized in that, The prediction compensation coefficient The value range is 0.8 to 1.2; The value is inversely proportional to the spindle speed matching degree.

10. A spindle speed control system for rotary machining, applicable to the spindle speed control method for rotary machining according to any one of claims 1-9, characterized in that, include: The data acquisition module is used to acquire the number of workpiece teeth / sides, the number of cutter teeth on the cutter head, the preset spindle speed and the preset workpiece axis speed, as well as the contact signal between the cutter teeth and the workpiece; The data processing module is used to calculate the target speed ratio, theoretical contact interval, and actual contact interval; The data output module is used to calculate the speed matching degree, determine whether to adjust the spindle speed, calculate the spindle speed adjustment amount, and send the spindle speed adjustment amount to the drive end.

Images