Ice cream machine tool bit monitoring method

Abstract

The invention discloses an ice cream machine tool bit monitoring method which comprises the following steps: according to an initial distribution state, carrying out filtering operation on distance data by adopting a signal processing module, removing noise interference, and determining a stable distance value between a tool bit and a container wall; the stable distance value is compared with a preset threshold range, if it is detected that the distance value exceeds the threshold range, an abnormal signal is triggered, and it is judged that the position of the tool bit deviates; according to the abnormal signal, current tool bit operation parameters are obtained, the adjustment amount is calculated through a pre-established correction model, and a correction instruction of the tool bit position is obtained; according to the adjusted position state, the change trend of the distance between the tool bit and the container wall is continuously collected, and whether the change of the distance tends to be stable or not is judged through a time sequence analysis method; and for the final stable data, recording an association log of the tool bit position and the spacing change, and storing the association log to a system database through a data storage module for subsequent production batch reference.

Description

Technical Field

[0001] The invention relates to the technical field of ice cream machine monitoring, in particular to a method for monitoring a cutter head of an ice cream machine. Background Art

[0002] The research and development and optimization of ice cream machines are of great significance in the field of food processing equipment, which is directly related to the taste, quality and production efficiency of the product. As a popular dessert in daily life, the mixing process in the production process of ice cream plays a decisive role in the uniformity and fineness of the final product. Therefore, how to ensure the stability and accuracy of mixing has become a key issue that cannot be ignored in this field.

[0003] However, the ice cream machines currently on the market still have obvious deficiencies in mixing control. Many devices lack the ability to monitor and dynamically adjust the position of the mixing blade in real time, resulting in deviations in the distance between the blade and the container wall during long-term operation or production of different recipes, affecting the mixing effect and may even cause equipment wear or unstable product quality.

[0004] In-depth analysis of this issue reveals that the core challenge lies in the coordination between the precise perception of the cutter head position and dynamic adjustment. First, due to the lack of high-precision monitoring methods, the slight changes in the spacing between the cutter head and the container wall are often difficult to capture in a timely manner. This lack of perception directly leads to the inability to accurately judge whether the cutter head is in the best working condition. This problem further causes the lag of the adjustment mechanism. Even if the spacing abnormality is found, it is difficult for existing equipment to quickly correct the cutter head position through automated means, resulting in uneven mixing or reduced production efficiency. These two technical factors are interrelated. The lack of perception limits the timeliness of adjustment, and the lag in adjustment exacerbates the uncertainty in the production process, forming a technical problem that needs to be solved urgently. Summary of the invention

[0005] In order to solve the above-mentioned technical problems, the present invention provides a method for monitoring a cutter head of an ice cream machine.

[0006] The technical solution of the present invention is achieved in this way: A method for monitoring a cutter head of an ice cream machine, comprising: The sensor array is arranged on the inner side of the container wall of the ice cream machine to obtain the real-time distance data between the cutter head and the container wall, and each set of data is sampled and processed to obtain the initial distribution state of the cutter head position; According to the initial distribution state, the distance data is filtered to remove noise interference and determine the stable distance value between the cutter head and the container wall; By comparing the stable spacing value with the preset threshold range, if it is detected that the spacing value exceeds the threshold range, an abnormal signal is triggered to determine that there is a deviation in the position of the cutter head; In response to abnormal signals, the current operating parameters of the cutter head are obtained, and the adjustment amount is calculated using the pre-established correction model to obtain the correction instruction of the cutter head position; According to the correction instruction, the axial or radial position of the cutter head is adjusted, the distance data between the cutter head and the container wall is updated in real time, and the position state after adjustment is determined.

[0007] Furthermore, the initial distribution state of the tool head position is obtained including: The real-time distance data between the cutter head and the container wall is continuously collected on the inner side of the container wall by using a sensor array, and the collected raw data is denoised by using a signal preprocessing technology to obtain a filtered distance data group; According to the filtered distance data group, time series segmentation is performed for each group of data to obtain the position change characteristics of the tool head in different time periods and determine the preliminary distribution state of the tool head motion trajectory.

[0008] Furthermore, obtaining the initial distribution state of the tool head position also includes: If there are abnormal points in the preliminary distribution state of the tool head motion trajectory, the preset threshold is used for screening, and the abnormal data exceeding the threshold is eliminated to obtain the corrected motion trajectory data; According to the corrected motion trajectory data, the support vector machine model is used to classify the position distribution of the cutter head, obtain the distribution characteristics of the contact area of the cutter head on the inner side of the container wall, and determine the range of the main contact area; By analyzing the main contact area range and combining the real-time distance data, the frequency and intensity of contact between the cutter head and the container wall are analyzed to obtain the dynamic contact mode of the cutter head during operation; For the dynamic contact mode, combined with the position distribution analysis, the operation stability index of the cutter head in different areas is obtained to determine whether the initial state of the cutter head position distribution meets the expected operating conditions; If the initial state of the tool head position distribution does not meet the expected operating conditions, the acquisition parameters of the sensor array are adjusted through historical data comparison to obtain more accurate real-time distance data and determine the optimized distribution state.

[0009] Further, determining the stable spacing value between the cutter head and the container wall includes: Perform filtering operation on the distance data in the initial distribution state to remove noise interference and obtain a stable distance value between the cutter head and the container wall; According to the stable spacing value, the data analysis tool is used to extract the distribution characteristics of the cutter head position near the container wall, obtain the spacing fluctuation of the cutter head in different areas, and determine the preliminary results of the spacing analysis; For the preliminary results of the spacing analysis, if the fluctuation exceeds the preset threshold, the distance data is processed twice by data smoothing technology to obtain the adjusted stable spacing data.

[0010] Furthermore, the determination of the stable spacing value between the tool head and the container wall further includes: Based on the adjusted stable spacing data and combined with the tool head position information collected in real time, analyze the proximity between the tool head and the container wall surface at different time periods, and judge the dynamic change characteristics of the position monitoring; Through the dynamic change characteristics of the position monitoring, use the support vector machine model to classify the distribution law of the tool head position, obtain the main activity area of the tool head near the container wall surface, and determine the characteristic value of the area distribution; Based on the characteristic value of the area distribution, evaluate the long-term stability of the tool head position to obtain the distance stability index between the tool head and the container wall; For the spacing stability index, if the index value deviates from the preset range, optimize the distance data by adjusting the parameters collected in real time to obtain a more accurate tool head position distribution state.

[0011] Furthermore, the determination that the tool head position is deviated includes: By obtaining the stable spacing data and comparing it with the preset threshold range, if the comparison result shows that the spacing value exceeds the threshold range, an abnormal signal is triggered to obtain a preliminary judgment of the tool head position deviation; According to the triggering situation of the abnormal signal, collect the tool head position data in real time, obtain the specific distribution characteristics of the position deviation, and determine the detailed basis for the deviation judgment.

[0012] Furthermore, the determination that the tool head position is deviated further includes: Through the distribution characteristics of the position deviation, continuously monitor the dynamic change of the tool head position to obtain the time series change data of the position deviation; Based on the time series change data, use the support vector machine model to classify the deviation law of the tool head position, obtain the main categories of the deviation distribution, and determine the classification result of the deviation characteristics; Through the classification result of the deviation characteristics, perform a secondary analysis on the frequency and intensity of the abnormal signal to obtain the updated state of the abnormal signal; According to the updated state of the abnormal signal, if the updated state shows that the deviation persists, adjust the data acquisition parameters to obtain more accurate tool head position data and judge the final trend of the position deviation; Through the final trend of the position deviation and combined with the preset threshold range, conduct long-term tracking on the stability of the tool head position to obtain the comprehensive data of the stability evaluation.

[0013] Further, the correction instruction for obtaining the tool head position includes: For the abnormal signal, collect the tool head parameters, and combine with the operating status information to determine the working condition data of the current tool head; According to the working condition data, use the parameter analysis method to extract the features of the tool head parameters and obtain the key change trends in the parameters; Through the key change trends, combine with the pre-constructed correction model, perform adjustment calculations to obtain the preliminary adjustment value of the tool head position; If the preliminary adjustment value exceeds the preset threshold range, perform a secondary verification on the abnormal signal to judge the reliability of the adjustment value; According to the result of the secondary verification, combine with the position deviation information, and use the support vector machine model to optimize the adjustment value to determine the final correction amount; Through the final correction amount, generate the correction instruction for the tool head position and obtain the specific scheme for adjustment execution; According to the specific scheme for adjustment execution, dynamically update the tool head position to obtain the corrected operating status data.

[0014] Further, the determination of the adjusted position state includes: Through the correction instruction, perform axial adjustment or radial adjustment operations on the tool head position to obtain the real-time position data during the adjustment process; According to the real-time position data, use the data acquisition tool to synchronously process the spacing information between the tool head and the container wall to obtain the current spacing change value; For the spacing change value, if the change value exceeds the preset threshold range, check the data through the information processing link to judge whether a position abnormal signal is triggered; According to the verified position abnormal signal, use the support vector machine model to optimize the adjustment parameters to determine the final position adjustment scheme; Through the final position adjustment scheme, dynamically update the tool head position to obtain the updated position state data; For the updated position state data, combine with the synchronously processed spacing information, and verify the stability of the position state through the data comparison tool to obtain the final state confirmation result.

[0015] Further, the method also includes: Continuously collect the spacing change trend between the tool head and the container wall through the adjusted position state, and use the time series analysis method to judge whether the spacing change tends to be stable; For the spacing change that does not tend to be stable, re-obtain the tool head operation parameters, combine with the historical adjustment data, calculate the new correction instruction, and determine the secondary correction result of the tool head position; According to the secondary calibration result, update the automated drive parameters, obtain the final stable data of the cutter head position, and determine whether the operating state of the stirring meets the expectations; For the final stable data, record the correlation log of the cutter head position and the spacing change, and save it to the database for reference in subsequent production batches.

[0016] Compared with the prior art, the present invention has the following beneficial effects: 1. By arranging a sensor array on the inner side of the container wall of the ice cream machine, the present invention can obtain the distance data between the cutter head and the container wall in real time, and use signal preprocessing technology to denoise the data. At the same time, perform time series segmentation on the filtered data, analyze the position change characteristics of the cutter head in different time periods, and determine the preliminary distribution state of the cutter head movement trajectory. In addition, abnormal data is eliminated through threshold screening, and the support vector machine model is used to classify the cutter head position distribution, obtaining the contact area distribution characteristics and dynamic contact modes, so as to more comprehensively understand the operating state of the cutter head and provide an accurate basis for subsequent adjustments, solving the problem that traditional equipment is difficult to capture small spacing changes in a timely manner; 2. By comparing the stable spacing value with the preset threshold range, once it is detected that the spacing value exceeds the threshold range, an abnormal signal is immediately triggered to determine that there is a deviation in the cutter head position. Subsequently, obtain the current cutter head operating parameters, calculate the adjustment amount using the pre-established calibration model, and obtain the correction instruction for the cutter head position. According to the correction instruction, adjust the axial or radial position of the cutter head, and update the spacing data between the cutter head and the container wall in real time to determine the adjusted position state. During the entire monitoring and adjustment process, the cutter head position data is updated in real time, and the stability of the cutter head position is tracked and evaluated in the long term through data analysis tools and models to ensure that the cutter head is always in the best working state, thus solving the problem of lag in adjustment of existing equipment; 3. By accurately monitoring and dynamically adjusting the cutter head position, the present invention ensures the uniformity and fineness of the stirring process, improves the taste and quality of ice cream products, and at the same time reduces problems such as uneven stirring or equipment wear caused by cutter head position deviation, reduces equipment failure rate and maintenance costs, and improves production efficiency and equipment service life. Description of the Drawings

[0017] Figure 1 It is a flowchart of a cutter head monitoring method for an ice cream machine in Embodiment 1; Figure 2 It is a flowchart of a cutter head monitoring method for an ice cream machine in Embodiment 2. Detailed Embodiments

[0018] In order to make the purpose, features and advantages of the present invention more obvious and easy to understand, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described below are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. Example

[0019] like Figure 1 As shown, this embodiment provides an ice cream machine cutter head monitoring method, comprising: The sensor array is arranged on the inner side of the container wall of the ice cream machine to obtain the real-time distance data between the cutter head and the container wall, and each set of data is sampled and processed to obtain the initial distribution state of the cutter head position; According to the initial distribution state, the distance data is filtered to remove noise interference and determine the stable distance value between the cutter head and the container wall; By comparing the stable spacing value with the preset threshold range, if it is detected that the spacing value exceeds the threshold range, an abnormal signal is triggered to determine that there is a deviation in the position of the cutter head; In response to abnormal signals, the current operating parameters of the cutter head are obtained, and the adjustment amount is calculated using the pre-established correction model to obtain the correction instruction of the cutter head position; According to the correction instruction, the axial or radial position of the cutter head is adjusted, the distance data between the cutter head and the container wall is updated in real time, and the position state after adjustment is determined.

[0020] Furthermore, the initial distribution state of the tool head position is obtained including: The real-time distance data between the cutter head and the container wall is continuously collected on the inner side of the container wall by using a sensor array, and the collected raw data is denoised by using a signal preprocessing technology to obtain a filtered distance data group; According to the filtered distance data group, time series segmentation is performed for each group of data to obtain the position change characteristics of the tool head in different time periods and determine the preliminary distribution state of the tool head motion trajectory.

[0021] Furthermore, obtaining the initial distribution state of the tool head position also includes: If there are abnormal points in the preliminary distribution state of the tool head motion trajectory, the preset threshold is used for screening, and the abnormal data exceeding the threshold is eliminated to obtain the corrected motion trajectory data; According to the corrected motion trajectory data, the support vector machine model is used to classify the position distribution of the cutter head, obtain the distribution characteristics of the contact area of the cutter head on the inner side of the container wall, and determine the range of the main contact area; Analyze the contact frequency and intensity between the cutter head and the container wall by combining the range of the main contact area with real-time distance data to obtain the dynamic contact mode during the operation of the cutter head; For the dynamic contact mode, combine the position distribution analysis to obtain the operation stability index of the cutter head in different regions, and determine whether the initial state of the cutter head position distribution meets the expected operation conditions; If the initial state of the cutter head position distribution does not meet the expected operation conditions, then through comparison with historical data, adjust the acquisition parameters of the sensor array to obtain more accurate real-time distance data, and judge the optimized distribution state.

[0022] In one embodiment, the steps to obtain the initial distribution state of the cutter head position can be described as follows: During the process of arranging a sensor array on the inner side of the container wall of the ice cream machine to obtain the real-time distance data between the cutter head and the container wall and performing subsequent processing, first, evenly distribute 10 ultrasonic sensors on the inner side of the container wall. Each sensor covers an angular range of about 36 degrees to ensure full 360-degree coverage. Real-time collect the distance data from the cutter head to the wall surface, set the sampling frequency to 100 times per second, and obtain the initial data stream. For example, in a certain sampling, the distances measured by 10 sensors are 5.2 cm, 5.1 cm, 4.9 cm, 5.3 cm, 5.0 cm, 4.8 cm, 5.4 cm, 5.2 cm, 4.7 cm, 5.1 cm respectively; Next, perform sampling processing on each group of data. Adopt the sliding window average filtering algorithm with a window size of 5 sampling points to calculate the smoothed distance value of each sensor. For example, process the 5 consecutive sampling values of 5.2 cm, 5.3 cm, 5.1 cm, 5.0 cm, 5.2 cm of the first sensor to obtain a smoothed value of (5.2 + 5.3 + 5.1 + 5.0 + 5.2) / 5 = 5.16 cm to reduce noise interference; Subsequently, based on the smoothed data, use the triangulation algorithm combined with the sensor position coordinates (distributed on a circle with a radius of 10 cm centered at the container center) to calculate the three-dimensional position of the cutter head. Assume that the smoothed distance data of 10 sensors at a certain moment is substituted into the algorithm, and the cutter head position is obtained as (x = 2.3 cm, y = 1.8 cm, z = 5.0 cm); Finally, collect multiple groups of position data (such as 1000 groups), analyze the initial distribution state of the cutter head position through Gaussian distribution fitting, calculate the mean and variance of the position distribution. For example, the mean is (x = 2.5 cm, y = 2.0 cm, z = 5.1 cm), and the variance is (0.2, 0.15, 0.1). Then judge whether the cutter head deviates from the center position. If the deviation exceeds the set threshold (such as 0.5 cm), then automatically adjust the cutter head motor parameters to correct the position to ensure the processing accuracy; The above process forms a closed-loop logic, from data collection to processing to distribution analysis and correction, relying on information technology to achieve automation and ensure the stability of ice cream processing.

[0023] Further, determining the stable spacing value between the cutter head and the container wall includes: Perform filtering operation on the distance data in the initial distribution state to remove noise interference and obtain a stable distance value between the cutter head and the container wall; According to the stable spacing value, the data analysis tool is used to extract the distribution characteristics of the cutter head position near the container wall, obtain the spacing fluctuation of the cutter head in different areas, and determine the preliminary results of the spacing analysis; For the preliminary results of the distance analysis, if the fluctuation exceeds the preset threshold, the distance data is processed again through data smoothing technology to obtain the adjusted stable distance data.

[0024] Furthermore, determining the stable spacing value between the cutter head and the container wall also includes: According to the adjusted stable spacing data, combined with the real-time collected cutter head position information, the proximity between the cutter head and the container wall in different time periods is analyzed to determine the dynamic change characteristics of position monitoring; Based on the dynamic change characteristics of position monitoring, the support vector machine model is used to classify the distribution law of the cutter head position, obtain the main activity area of the cutter head near the container wall, and determine the characteristic value of the regional distribution; According to the characteristic values of regional distribution, the long-term stability of the cutter head position is evaluated to obtain the distance stability index between the cutter head and the container wall; For the spacing stability index, if the index value deviates from the preset range, the distance data is optimized by adjusting the parameters collected in real time to obtain a more accurate tool head position distribution state.

[0025] In one embodiment, the step of determining the stable spacing value between the cutter head and the container wall may be as follows: In the process of obtaining the distance data between the cutter head and the wall inside the container wall of the ice cream machine, the initial distribution state is filtered to remove noise interference and determine the stable spacing value. The specific implementation method realizes automatic processing through information technology; First, the distance data is obtained from the eight infrared sensors on the inner side of the container wall. Assume that the distance values collected at a certain time are 6.1 cm, 6.3 cm, 5.9 cm, 6.0 cm, 6.2 cm, 5.8 cm, 6.4 cm, and 5.7 cm, respectively, and the sampling frequency is 50 times per second, forming an initial data stream. Next, for these data, the median filtering algorithm is used for processing. Taking the sampling points with a window size of 3 as an example, for the consecutive three sampling values of 6.1 cm, 6.2 cm, and 6.0 cm of the first sensor, after sorting, the middle value of 6.1 cm is taken as the filtering result, and all sensor data are processed in turn to smooth the fluctuations; Subsequently, weighted average calculation is performed on the filtered data. Assuming that the weights of each sensor are set to 0.12, 0.13, 0.11, 0.12, 0.13, 0.10, 0.14, and 0.11 according to the installation position accuracy, the calculated comprehensive stable spacing value is 6.05 cm; To further analyze the data reliability, standard deviation calculation is introduced. Assuming that the standard deviation of a group of filtered data is 0.25 cm, if it exceeds the preset threshold of 0.3 cm, a data anomaly warning is triggered, and the data acquisition is automatically switched to the backup sensor group to ensure continuity; Finally, the stable spacing value is compared with the historical data. Assuming that the average spacing in the past 10 minutes is 6.08 cm and the deviation of the current value of 6.05 cm is 0.03 cm, which is lower than the tolerance range of 0.1 cm, it is determined to be in a normal state, and the data is stored in the database for subsequent processing parameter optimization, forming a closed-loop logic from data acquisition to filtering and then to stability analysis to ensure the accuracy of the cutter head position data during the ice cream processing.

[0026] Furthermore, the determination of the deviation of the cutter head position includes: By obtaining the stable spacing data and comparing it with the preset threshold range, if the comparison result shows that the spacing value exceeds the threshold range, an abnormal signal is triggered to obtain a preliminary judgment of the cutter head position deviation; According to the triggering situation of the abnormal signal, the cutter head position data is collected in real time to obtain the specific distribution characteristics of the position deviation and determine the detailed basis for the deviation judgment.

[0027] Furthermore, the determination of the deviation of the cutter head position also includes: By the distribution characteristics of the position deviation, the dynamic change of the cutter head position is continuously monitored to obtain the time-series change data of the position deviation; According to the time-series change data, the support vector machine model is used to classify the deviation law of the cutter head position to obtain the main categories of the deviation distribution and determine the classification result of the deviation characteristics; Based on the classification result of the deviation characteristics, the frequency and intensity of the abnormal signal are analyzed again to obtain the updated state of the abnormal signal; According to the updated state of the abnormal signal, if the updated state shows that the deviation persists, the data acquisition parameters are adjusted to obtain more accurate cutter head position data and judge the final trend of the position deviation; Through the final trend of position deviation and the preset threshold range, the stability of the tool head position is tracked over a long period of time to obtain comprehensive data for stability evaluation.

[0028] In one embodiment, the step of determining whether there is a deviation in the position of the cutter head can be as follows: In ice cream processing equipment, information technology is used to automatically monitor and detect abnormalities in the distance data between the cutter head and the container wall to ensure the stability of the processing process; First, real-time spacing data is obtained from six high-precision laser sensors installed on the inner side of the container wall. Assume that the spacing values collected at a certain time are 5.5 cm, 5.7 cm, 5.4 cm, 5.6 cm, 5.3 cm, and 5.8 cm, respectively, and the sampling frequency is 30 times per second, forming a continuous data stream. Next, these data are compared with the preset threshold range. Assuming that the normal spacing threshold range is set to 5.2cm to 5.9cm, the algorithm calculates the average value of the current data to be 5.55cm, which is found to be within the threshold range. However, one of the sensor data, 5.3cm, is close to the lower limit, and the data point is automatically marked for further analysis. Subsequently, the deviation analysis algorithm was used to calculate the difference between each sensor data and the average value, and the deviation values were 0.05cm, 0.15cm, 0.25cm, 0.05cm, 0.25cm, and 0.25cm, respectively. The deviation threshold was set to 0.3cm, and it was found that the deviations of three data points were close to the threshold, and a potential risk warning was automatically generated and recorded in the log; At the same time, combined with historical trend analysis, assuming that the average spacing in the past 5 minutes is 5.6cm, the current average value of 5.55cm has a deviation of 0.05cm, which is lower than the allowable deviation range of 0.2cm. It is judged to be temporarily stable, but still needs to be continuously monitored; Finally, if the average spacing value exceeds the threshold range at a certain moment, for example, it reaches 6.0 cm, an abnormal signal will be triggered, and the abnormal information will be automatically transmitted to the controller, the tool head operating parameters will be adjusted in conjunction, and the data will be uploaded to the cloud database for subsequent analysis, forming a complete closed loop from data collection to abnormality judgment to information feedback, ensuring the continuity and reliability of the processing process.

[0029] Furthermore, the correction instruction for obtaining the position of the tool head includes: In response to abnormal signals, the cutter head parameters are collected and combined with the operating status information to determine the current working status data of the cutter head; According to the working condition data, the parameter analysis method is used to extract the characteristics of the cutter head parameters and obtain the key change trends in the parameters; Through the key change trend, combined with the pre-built correction model, the adjustment calculation is performed to obtain the preliminary adjustment value of the tool head position; If the preliminary adjustment value exceeds the preset threshold range, the abnormal signal is verified twice to judge the reliability of the adjustment value; According to the result of the second verification and combined with the position deviation information, the support vector machine model is used to optimize the adjustment value to determine the final correction amount; Through the final correction amount, a correction instruction for the tool head position is generated to obtain a specific scheme for adjustment execution; According to the specific scheme of adjustment execution, the tool head position is dynamically updated to obtain the corrected operation state data.

[0030] Among them, the establishment process of the pre-constructed calibration model is as follows: ① Data collection: Historical operation data collection: Collect historical data of the ice cream machine under different operating conditions, including tool head position, operating parameters (such as rotation speed, torque, stirring time, etc.), actual distance data between the tool head and the container wall, and corresponding adjustment records; Labeled data: Label the collected historical data to clarify which data corresponds to the normal operation state and which data corresponds to the abnormal state of the tool head position deviation; ② Data preprocessing: Data cleaning: Remove noise and outliers from the historical data to ensure the accuracy and reliability of the data; Feature extraction: Extract key features from the historical data, such as tool head position change rate, rotation speed fluctuation, torque change, etc. These features will be used as input variables of the model; ③ Model construction: Use the weighted regression analysis method to construct a calibration model. By assigning different weights to each data point, the fitting accuracy of the model to important data points is improved; According to the importance and reliability of the data points, assign weights to each data point. For example, data points with larger distance deviations can be assigned higher weights because these data points can better reflect the abnormal situation of the tool head position; ④ Model training: Use historical operation data to train the weighted regression model, and optimize the model parameters by minimizing the weighted residual sum of squares: , where, is the target value of the i-th data point (such as the tool head position adjustment amount), is the feature vector of the i-th data point, are the model parameters, is the weight of the i-th data point; ⑤ Model verification: Use a part of the data that has not participated in training to verify the model, evaluate the accuracy and generalization ability of the model, and ensure the consistent performance of the model on different data sets through methods such as cross-validation.

[0031] In one embodiment, the steps to obtain the correction instruction for the cutter head position can be described as follows: During the operation of the ice cream processing equipment, when an abnormal signal is detected, the cutter head position correction process will be automatically started, and full automation processing will be achieved through information technology; First, extract the current operating parameters. Assume that the obtained cutter head rotation speed is 800 revolutions per minute, the tilt angle is 3.2 degrees, and the axial offset is 0.4 cm; Subsequently, input these parameters into a pre-established correction model. This model is constructed based on historical operating data and machine learning algorithms, and uses the weighted regression analysis method to calculate that the weight of the rotation speed on the position is 0.6, the weight of the angle is 0.3, and the weight of the axial offset is 0.1. Through formula calculation, the adjustment amount is that the rotation speed needs to be reduced by 50 revolutions per minute, the angle is adjusted to 3.0 degrees, and the axial offset is corrected to 0.2 cm; Next, generate a correction instruction according to the calculation results. The instruction contains specific adjustment parameters and is transmitted to the cutter head drive controller through the internal communication protocol. The drive controller automatically parses the instruction and updates the operating parameters, and at the same time records the parameter comparison data before and after the adjustment to the log. For example, the rotation speed is reduced from 800 revolutions per minute to 750 revolutions per minute, the angle is adjusted from 3.2 degrees to 3.0 degrees, and the offset is reduced from 0.4 cm to 0.2 cm; To ensure the stability after adjustment, the real-time monitoring subroutine will be called to collect cutter head position data at a frequency of 50 times per second within 10 seconds after the adjustment. Assume that the average position offset collected is 0.25 cm, which is lower than the preset allowable offset threshold of 0.3 cm. It is determined that the correction is effective, and the relevant data of this correction process will be uploaded to the cloud analysis platform for subsequent model optimization, forming a complete automated logic chain from abnormal detection to parameter adjustment and then to effect verification; If the offset value is still higher than the threshold after correction, the secondary correction process will be automatically triggered to ensure the accuracy of the processing process.

[0032] Furthermore, the determination of the position state after adjustment includes: Execute axial adjustment or radial adjustment operations on the cutter head position through the correction instruction, and obtain the real-time position data during the adjustment process; According to the real-time position data, use a data acquisition tool to synchronize the distance information between the cutter head and the container wall to obtain the current distance change value; For the distance change value, if the change value exceeds the preset threshold range, the data will be verified through the information processing link to determine whether a position abnormal signal is triggered; According to the verified position abnormal signal, use the support vector machine model to optimize the adjustment parameters to determine the final position adjustment plan; Through the final position adjustment scheme, dynamically update the position of the cutter head and obtain the updated position status data; For the updated position status data, combined with the spacing information processed synchronously, verify the stability of the position status through a data comparison tool to obtain the final status confirmation result.

[0033] In one embodiment, the steps to determine the adjusted position status can be described as follows: During the automatic control process of the ice cream processing equipment, after receiving the correction instruction, drive the automatic controller to precisely adjust the position of the cutter head and update the relevant data in real time to ensure the processing accuracy; First, parse the correction instruction into specific control signals. Assume that the instruction requires the axial position of the cutter head to be adjusted to 2.5 cm from the container wall and the radial position to be adjusted to 0.8 cm off the center line. The controller calculates the number of stepping pulses required for axial movement to be 1200 steps and the number of radial adjustment pulses to be 800 steps through the built-in servo motor drive algorithm. The algorithm uses the proportional-integral-derivative control method to ensure the smoothness during movement, with the error controlled within 0.05 cm. Subsequently, during the adjustment process, collect the spacing data between the cutter head and the container wall through a high-precision laser sensor at a frequency of 100 times per second. Assume that the initial spacing is 3.0 cm, and it stabilizes at 2.5 cm after adjustment, and the radial deviation decreases from 1.0 cm to 0.8 cm. Store these data in the local database in real time, and calculate the smooth curve of the spacing change through the time series analysis algorithm to determine whether there are abnormal fluctuations during the adjustment process. If the fluctuation value is less than the preset threshold of 0.1 cm, the adjustment process is considered stable. Finally, based on the collected final position data, combined with the preset target range (axial 2.4 - 2.6 cm, radial 0.7 - 0.9 cm), automatically analyze the position status of the cutter head, confirm that the adjusted position meets the requirements, and at the same time transmit the status data to the central control through the internal communication interface to form a linkage logic with other processing parameters such as the stirring speed to ensure the coordination of subsequent processing steps. The entire process is driven by information technology and does not require manual intervention. Embodiment

[0034] As Figure 2 shown, this embodiment provides a method for monitoring the cutter head of an ice cream machine, including Arrange a sensor array inside the container wall of the ice cream machine to obtain the real-time distance data between the cutter head and the container wall, and perform sampling processing on each group of data to obtain the initial distribution state of the cutter head position; According to the initial distribution state, perform a filtering operation on the distance data to remove noise interference and determine the stable spacing value between the cutter head and the container wall; By comparing the stable spacing value with the preset threshold range, if it is detected that the spacing value exceeds the threshold range, an abnormal signal is triggered to determine that there is a deviation in the position of the cutter head; In response to abnormal signals, the current operating parameters of the cutter head are obtained, and the adjustment amount is calculated using the pre-established correction model to obtain the correction instruction of the cutter head position; According to the correction instruction, the axial or radial position of the cutter head is adjusted, the distance data between the cutter head and the container wall is updated in real time, and the position state after adjustment is determined.

[0035] Furthermore, the initial distribution state of the tool head position is obtained including: The real-time distance data between the cutter head and the container wall is continuously collected on the inner side of the container wall by using a sensor array, and the collected raw data is denoised by using a signal preprocessing technology to obtain a filtered distance data group; According to the filtered distance data group, time series segmentation is performed for each group of data to obtain the position change characteristics of the tool head in different time periods and determine the preliminary distribution state of the tool head motion trajectory.

[0036] Furthermore, obtaining the initial distribution state of the tool head position also includes: If there are abnormal points in the preliminary distribution state of the tool head motion trajectory, the preset threshold is used for screening, and the abnormal data exceeding the threshold is eliminated to obtain the corrected motion trajectory data; According to the corrected motion trajectory data, the support vector machine model is used to classify the position distribution of the cutter head, obtain the distribution characteristics of the contact area of the cutter head on the inner side of the container wall, and determine the range of the main contact area; By analyzing the main contact area range and combining the real-time distance data, the frequency and intensity of contact between the cutter head and the container wall are analyzed to obtain the dynamic contact mode of the cutter head during operation; For the dynamic contact mode, combined with the position distribution analysis, the operation stability index of the cutter head in different areas is obtained to determine whether the initial state of the cutter head position distribution meets the expected operating conditions; If the initial state of the tool head position distribution does not meet the expected operating conditions, the acquisition parameters of the sensor array are adjusted through historical data comparison to obtain more accurate real-time distance data and determine the optimized distribution state.

[0037] Further, determining the stable spacing value between the cutter head and the container wall includes: Perform filtering operation on the distance data in the initial distribution state to remove noise interference and obtain a stable distance value between the cutter head and the container wall; According to the stable spacing value, the data analysis tool is used to extract the distribution characteristics of the cutter head position near the container wall, obtain the spacing fluctuation of the cutter head in different areas, and determine the preliminary results of the spacing analysis; For the preliminary results of the spacing analysis, if the fluctuation exceeds the preset threshold, the distance data is processed twice by data smoothing technology to obtain the adjusted stable spacing data.

[0038] Furthermore, the determination of the stable spacing value between the tool head and the container wall further includes: According to the adjusted stable spacing data, combined with the tool head position information collected in real time, analyze the proximity between the tool head and the container wall surface at different time periods, and judge the dynamic change characteristics of the position monitoring; Through the dynamic change characteristics of the position monitoring, use the support vector machine model to classify the distribution law of the tool head position, obtain the main activity area of the tool head near the container wall surface, and determine the characteristic value of the area distribution; According to the characteristic value of the area distribution, evaluate the long-term stability of the tool head position to obtain the distance stability index between the tool head and the container wall; For the spacing stability index, if the index value deviates from the preset range, optimize the distance data by adjusting the parameters collected in real time to obtain a more accurate tool head position distribution state.

[0039] Furthermore, the determination that the tool head position is deviated includes: By obtaining the stable spacing data and comparing it with the preset threshold range, if the comparison result shows that the spacing value exceeds the threshold range, an abnormal signal is triggered to obtain a preliminary judgment of the tool head position deviation; According to the triggering situation of the abnormal signal, collect the tool head position data in real time, obtain the specific distribution characteristics of the position deviation, and determine the detailed basis for the deviation judgment.

[0040] Furthermore, the determination that the tool head position is deviated further includes: Through the distribution characteristics of the position deviation, continuously monitor the dynamic change of the tool head position to obtain the time-series change data of the position deviation; According to the time-series change data, use the support vector machine model to classify the deviation law of the tool head position, obtain the main categories of the deviation distribution, and determine the classification result of the deviation characteristics; Through the classification result of the deviation characteristics, perform a secondary analysis on the frequency and intensity of the abnormal signal to obtain the updated state of the abnormal signal; According to the updated state of the abnormal signal, if the updated state shows that the deviation persists, adjust the data acquisition parameters to obtain more accurate tool head position data and judge the final trend of the position deviation; Through the final trend of the position deviation, combined with the preset threshold range, perform long-term tracking on the stability of the tool head position to obtain the comprehensive data of the stability evaluation.

[0041] Further, the correction instruction for obtaining the tool head position includes: For the abnormal signal, collect the tool head parameters, and combine with the operation status information to determine the working condition data of the current tool head; According to the working condition data, use the parameter analysis method to extract the characteristics of the tool head parameters, and obtain the key change trend in the parameters; Through the key change trend, combine with the pre-constructed calibration model, perform adjustment calculations to obtain the preliminary adjustment value of the tool head position; If the preliminary adjustment value exceeds the preset threshold range, perform a secondary verification on the abnormal signal to judge the reliability of the adjustment value; According to the result of the secondary verification, combine with the position deviation information, and use the support vector machine model to optimize the adjustment value to determine the final correction amount; Through the final correction amount, generate the correction instruction for the tool head position, and obtain the specific scheme for adjustment execution; According to the specific scheme for adjustment execution, dynamically update the tool head position to obtain the corrected operation status data.

[0042] Further, the determination of the adjusted position status includes: Through the correction instruction, perform axial adjustment or radial adjustment operations on the tool head position, and obtain the real-time position data during the adjustment process; According to the real-time position data, use the data acquisition tool to synchronously process the spacing information between the tool head and the container wall to obtain the current spacing change value; For the spacing change value, if the change value exceeds the preset threshold range, check the data through the information processing link to judge whether a position abnormal signal is triggered; According to the verified position abnormal signal, use the support vector machine model to optimize the adjustment parameters to determine the final position adjustment scheme; Through the final position adjustment scheme, dynamically update the tool head position to obtain the updated position status data; For the updated position status data, combine with the synchronously processed spacing information, and verify the stability of the position status through the data comparison tool to obtain the final status confirmation result.

[0043] Further, this method further includes: Through the adjusted position status, continuously collect the spacing change trend between the tool head and the container wall, and use the time series analysis method to judge whether the spacing change tends to be stable; For the spacing change that does not tend to be stable, re-obtain the tool head operation parameters, combine with the historical adjustment data, calculate the new correction instruction, and determine the secondary correction result of the tool head position; Update the automated drive parameters according to the secondary calibration results, obtain the final stable data of the cutter head position, and determine whether the operating state of the stirring meets the expectations; For the final stable data, record the correlation log of the cutter head position and the spacing change, and save it to the database for reference in subsequent production batches.

[0044] Further, the determination of whether the spacing change tends to be stable includes: Continuously obtain the spacing change data between the cutter head and the container wall through the adjusted position state, and use a data acquisition tool to record the change data in real time to obtain a preliminary spacing change data set; For the preliminary spacing change data set, use the time series analysis method to process the change trend, extract the trend characteristic information, and determine the fluctuation law of the spacing change; According to the fluctuation law of the spacing change, obtain the comparison result between the fluctuation characteristic and the preset threshold. If the fluctuation characteristic exceeds the preset threshold range, the data is verified through the information processing link to determine whether the fluctuation is in an abnormal state; For the judgment result of whether the fluctuation is in an abnormal state, obtain the classification information of the abnormal state, and screen the classification information through a data comparison tool to obtain the key time points of the abnormal fluctuation; According to the key time points of the abnormal fluctuation, obtain the corresponding spacing data between the cutter head and the container wall surface, use the support vector machine model to optimize and adjust the position state, and determine the adjusted position parameters; Drive the controller to dynamically update the cutter head position through the adjusted position parameters, obtain the updated position state data, and determine whether the position state meets the stable standard; According to the judgment result of whether the position state meets the stable standard, if the preset standard is not reached, a new adjustment instruction is generated through the information processing link and the data acquisition process is restarted.

[0045] In one embodiment, the steps of determining whether the spacing change tends to be stable can be described as follows: Continuously monitor the spacing change trend between the cutter head and the container wall through the adjusted cutter head position state to ensure the stability during the processing; First, use a high-precision ultrasonic sensor to collect the spacing data at a frequency of 50 times per second. Assume that the initial adjusted spacing is 2.2 cm, and the target stable range is 2.1 - 2.3 cm; Next, the time series analysis method is adopted. Specifically, the moving average algorithm is used to smooth 250 data points within the past 5 seconds, and the trend curve of the spacing change is calculated. Assuming that the spacing fluctuation value is detected as 0.08 cm at the 3rd second, and then the fluctuation value drops to 0.03 cm at the 5th second. By comparing the fluctuation value with the preset threshold of 0.05 cm, it is judged whether the spacing change tends to be stable; At the same time, the autoregressive model is combined to predict the spacing change in the next 2 seconds. The prediction result shows that the spacing will be stable at 2.15 cm, which meets the target range; To further ensure stability, the analysis results are correlated with the vibration frequency data of the processing equipment. If the vibration frequency is lower than the predetermined value of 0.2 Hz, it is considered that the environmental conditions have no significant interference on the spacing; All data and analysis processes are stored in the cloud database. If the spacing is stable and the temperature exceeds the preset range of 35 - 40 degrees Celsius, the cooling mechanism is automatically triggered to ensure the comprehensive stability of the processing environment, and the entire process is completed automatically.

[0046] Furthermore, the secondary correction result for determining the tool head position includes: Through the data processing link, relevant information on the current spacing change is extracted from the tool head operation parameters, and the extracted data is preliminarily sorted using an information comparison tool to obtain the operation parameter set in the unstable state; According to the operation parameter set in the unstable state, combined with the historical adjustment records, the data analysis tool is used to conduct a correlation comparison between the two to determine the matching characteristics between the operation parameters and the historical adjustments; If the matching characteristics meet the preset threshold range, a preliminary correction instruction is generated through the information processing link, and the adjustment basis data for the tool head position is obtained; If the matching characteristics exceed the preset threshold range, the operation parameter set is secondarily verified through the information processing link to determine whether there are abnormal fluctuations, and the verified parameter characteristics are obtained; According to the verified parameter characteristics, the support vector machine model is used to optimize the calculation of the tool head position to determine the correction instruction parameters required for secondary correction; Through the correction instruction parameters, the controller is driven to dynamically adjust the tool head position to obtain the adjusted position correction data; According to the adjusted position correction data, it is compared with the preset standard through the information processing link to determine whether it reaches the stable state and determine the final correction result.

[0047] In one embodiment, the steps for determining the secondary correction result of the tool head position can be described as follows: In the intelligent control of ice cream processing equipment, when it is detected that the change in the distance between the cutter head and the container wall has not reached a stable state, a series of processing procedures will be automatically started to achieve the optimal adjustment of the cutter head position; First, re-obtain the real-time operation data of the cutter head. For example, the current rotation speed is 800 revolutions per minute, and the cutter head deflection angle is 0.5 degrees; Subsequently, call the historical adjustment records stored in the local database, extract the average offset of the past 10 adjustments as 0.3 cm, and combine with the current parameters. Use the weighted linear regression algorithm to calculate a new correction instruction, and obtain an instruction value that the cutter head needs to be adjusted inward by 0.2 cm; Next, send this instruction to the cutter head drive controller through the internal control protocol. The drive controller automatically completes the position correction according to the instruction, and the corrected spacing data is fed back in real time. Assuming that the adjusted spacing is 2.4 cm, which is within the target range of 2.0 - 2.5 cm; To ensure the reliability of the correction result, further analyze the parameter change trends before and after the correction, calculate that the deflection angle fluctuation after adjustment drops from 0.5 degrees to 0.1 degrees, and confirm that the correction is effective; At the same time, conduct a correlation analysis on the correction data and the operation load data of the equipment. If the load value is lower than the preset threshold of 500 watts, it is determined that the correction process has not imposed an additional burden on the overall operation of the equipment. All analysis results are automatically uploaded to the cloud for backup, forming a complete data chain to ensure that subsequent adjustments are based on evidence, and the entire process is completed independently.

[0048] Furthermore, the judgment of whether the operation state of stirring meets the expectation includes: According to the secondary correction result, update the drive parameters in the controller, extract the preliminary data after parameter adjustment through the information processing link, and obtain the updated record of the cutter head position; For the updated record of the cutter head position, use an information comparison tool to perform a matching analysis with the preset standard, obtain the deviation characteristics between the position data and the standard, and determine whether the deviation is within the acceptable range; If the deviation characteristics exceed the preset standard range, deeply analyze the position data through the information processing link, extract the potential abnormal fluctuation information, and obtain the distribution characteristics of the abnormal fluctuation; According to the distribution characteristics of the abnormal fluctuation, use the support vector machine model to optimize the adjustment of the cutter head position, generate a correction instruction for the drive parameters, and obtain the adjusted parameter set; Through the adjusted parameter set, the drive controller dynamically adjusts the operation state of stirring, extracts the adjusted state information from it, and judges whether it meets the preset standard; If the adjusted status information still fails to meet the preset standard, the operation status is continuously monitored through the information processing link to obtain the trend data of status changes and determine the direction of further adjustment; According to the trend data of status changes and combined with the historical operation records, an optimization plan for stirring is generated through an information comparison tool to obtain the final stable operation parameters.

[0049] In one embodiment, the steps of determining whether the operation status of stirring meets the expectation can be described as follows: In the automatic control of ice cream processing equipment, the processing flow based on the secondary correction result realizes full-automatic operation through information technology to ensure the final stability of the cutter head position and the normal operation of stirring; First, the cutter head position data after secondary correction, for example, the spacing value is 2.6 cm, is compared with the preset target value of 2.5 cm through the built-in dynamic parameter adjustment algorithm, and the offset to be fine-tuned is calculated as 0.1 cm. The position control coefficient in the drive parameters is automatically updated from the original 1.2 to 1.25 to optimize the subsequent operation accuracy, and the updated parameters are immediately stored in the local cache; Subsequently, the final stable data of the cutter head position is collected through a high-precision sensor network. Assuming that the actual spacing collected is 2.51 cm, and the cutter head vibration frequency is recorded as 3.5 times per second at the same time. The time series analysis algorithm is used to evaluate the position fluctuations in the past 5 minutes, and the fluctuation standard deviation is obtained as 0.02 cm, which is less than the preset threshold of 0.05 cm, indicating that the position has reached a stable state; To further determine whether the operation status of stirring meets the expectation, the collected cutter head rotation speed data, for example, 750 revolutions per minute, is matched with the standard range of 700 - 780 revolutions, and the stirring resistance value is analyzed. Assuming that the current resistance is 320 Newtons, which is lower than the upper limit value of 400 Newtons, the operation stability index is calculated as 92% through the comprehensive evaluation algorithm, which is higher than the expected threshold of 85%, confirming that the stirring operation is normal; It is detected that the current motor temperature is 45.3 degrees Celsius, which does not exceed the safety value of 50 degrees Celsius. An operation status report is automatically generated and uploaded to the cloud log to ensure that there is data support for subsequent maintenance, and the entire process is completed independently.

[0050] Furthermore, the associated log recording the changes in the cutter head position and spacing includes: The recorded content of the cutter head position and spacing changes is sorted to obtain the preliminarily sorted position information set; According to the preliminarily sorted position information set, an information comparison tool is used to extract the characteristic features of the associated information of the cutter head position and spacing changes to determine the change rule features between the two; Regarding the variation law characteristics, through the information processing link, in-depth analysis is carried out. If the characteristic value after analysis deviates from the preset threshold, the position information set is corrected twice to obtain the corrected position data group; According to the corrected position data group, the support vector machine model is used to classify the correlation information between the tool head position and the spacing change, and the classified data category distribution is obtained; Through the classified data category distribution, the information processing link is used to perform stability verification on each category of data. If the verification result shows that the fluctuation of a certain category of data exceeds the preset range, the data of this category is marked to obtain the marked abnormal data subset; Regarding the marked abnormal data subset, the difference characteristics between the abnormal data subset and the historical records are obtained; According to the difference characteristics, through the information processing link, an adjustment strategy for the abnormal data subset is generated, the adjusted data storage scheme is determined, and it is saved to the database for reference by the production batch;

[0051] Specifically, in the automatic control of ice cream processing equipment, for the processing of the final stable data, the correlation log of the tool head position and the spacing change is realized through information technology and saved to the database for reference by subsequent production batches; First, the tool head position data is collected in real time by using a high-precision sensor array. Assuming that the current stable position is 3.2 cm, compared with 3.25 cm in the previous cycle, the spacing change value is 0.05 cm. The spacing change trend in the past 10 minutes is analyzed through the built-in linear regression algorithm, and the average value of the change rate is calculated to be 0.03 cm / minute, which is lower than the preset warning value of 0.1 cm / minute, indicating that the position adjustment is within the controllable range; Next, the position data is associated with the spacing change value to form a log record with a timestamp of 2023-10-15 14:30:00, including specific values and the analysis results of the change rate. The distributed storage technology is used to ensure data redundancy backup to prevent loss; At the same time, the batch association algorithm is automatically called to bind the current log with the production batch number (such as Batch_20231015_001) to generate a unique identification code for subsequent traceability; To form a complete logical chain, the current raw material viscosity data is collected as 280 Pa·s, and its potential impact on the tool head position change is analyzed, and the correlation coefficient is obtained as 0.15, which is lower than the impact threshold of 0.3, confirming that the raw material factor does not interfere with the position stability; Finally, the database automatically updates the index to ensure that the log data can be queried within 1 second, and all processes are completed independently, providing data support for subsequent production optimization.

[0052] The specific embodiments of the invention have been described in detail above. However, these are only examples, and the invention is not limited to the specific embodiments described above. Those skilled in the art should understand that the above embodiments and the descriptions in the specification only illustrate the principles of the invention. Without departing from the spirit and scope of the invention, the invention will have various changes and improvements, and these changes and improvements all fall within the scope of the claimed invention. The scope of protection of the invention is defined by the appended claims and their equivalents.

Claims

1. A method for monitoring the cutter head of an ice cream machine, characterized in that, include: The sensor array is arranged on the inner side of the container wall of the ice cream machine to obtain the real-time distance data between the cutter head and the container wall, and each set of data is sampled and processed to obtain the initial distribution state of the cutter head position; According to the initial distribution state, the distance data is filtered to remove noise interference and determine the stable distance value between the cutter head and the container wall; By comparing the stable spacing value with the preset threshold range, if it is detected that the spacing value exceeds the threshold range, an abnormal signal is triggered to determine that there is a deviation in the position of the cutter head; In response to abnormal signals, the current operating parameters of the cutter head are obtained, and the adjustment amount is calculated using the pre-established correction model to obtain the correction instruction of the cutter head position; According to the correction instruction, the axial or radial position of the cutter head is adjusted, the distance data between the cutter head and the container wall is updated in real time, and the position state after adjustment is determined.

2. The ice cream machine cutter head monitoring method according to claim 1, characterized in that The initial distribution state of the tool head position is obtained including: The real-time distance data between the cutter head and the container wall is continuously collected on the inner side of the container wall by using a sensor array, and the collected raw data is denoised by using a signal preprocessing technology to obtain a filtered distance data group; According to the filtered distance data group, time series segmentation is performed for each group of data to obtain the position change characteristics of the tool head in different time periods and determine the preliminary distribution state of the tool head motion trajectory.

3. The method for monitoring the cutter head of an ice cream machine according to claim 2, characterized in that, The initial distribution state of the tool head position is obtained further comprising: If there are abnormal points in the preliminary distribution state of the tool head motion trajectory, the preset threshold is used for screening, and the abnormal data exceeding the threshold is eliminated to obtain the corrected motion trajectory data; According to the corrected motion trajectory data, the support vector machine model is used to classify the position distribution of the cutter head, obtain the distribution characteristics of the contact area of the cutter head on the inner side of the container wall, and determine the range of the main contact area; By analyzing the main contact area range and combining the real-time distance data, the frequency and intensity of contact between the cutter head and the container wall are analyzed to obtain the dynamic contact mode of the cutter head during operation; For the dynamic contact mode, combined with the position distribution analysis, the operation stability index of the cutter head in different areas is obtained to determine whether the initial state of the cutter head position distribution meets the expected operating conditions; If the initial state of the tool head position distribution does not meet the expected operating conditions, the acquisition parameters of the sensor array are adjusted through historical data comparison to obtain more accurate real-time distance data and determine the optimized distribution state.

4. The method for monitoring the cutter head of an ice cream machine according to claim 1, characterized in that Determining the stable spacing value between the cutter head and the container wall comprises: Perform filtering operation on the distance data in the initial distribution state to remove noise interference and obtain a stable distance value between the cutter head and the container wall; According to the stable spacing value, the data analysis tool is used to extract the distribution characteristics of the cutter head position near the container wall, obtain the spacing fluctuation of the cutter head in different areas, and determine the preliminary results of the spacing analysis; For the preliminary results of the distance analysis, if the fluctuation exceeds the preset threshold, the distance data is processed again through data smoothing technology to obtain the adjusted stable distance data.

5. A method for monitoring the cutter head of an ice cream machine according to claim 4, characterized in that, Determining the stable spacing value between the cutter head and the container wall also includes: Based on the adjusted stable spacing data and combined with the real-time collected tool head position information, analyze the proximity of the tool head to the container wall surface at different time periods to judge the dynamic change characteristics of position monitoring; Through the dynamic change characteristics of position monitoring, use the support vector machine model to classify the distribution law of the tool head position, obtain the main activity area of the tool head near the container wall surface, and determine the characteristic values of the area distribution; According to the characteristic values of the area distribution, evaluate the long-term stability of the tool head position to obtain the distance stability index between the tool head and the container wall; For the spacing stability index, if the index value deviates from the preset range, optimize the distance data by adjusting the real-time collected parameters to obtain a more accurate tool head position distribution state.

6. The method for monitoring the cutter head of an ice cream machine according to claim 1, characterized in that, The determination of the deviation of the tool head position includes: By obtaining the stable spacing data and comparing it with the preset threshold range, if the comparison result shows that the spacing value exceeds the threshold range, an abnormal signal is triggered to obtain a preliminary judgment of the tool head position deviation; According to the triggering situation of the abnormal signal, collect the tool head position data in real time, obtain the specific distribution characteristics of the position deviation, and determine the detailed basis for the deviation judgment.

7. A method for monitoring the cutter head of an ice cream machine according to claim 6, characterized in that, The determination of the deviation of the tool head position also includes: Through the distribution characteristics of the position deviation, continuously monitor the dynamic change of the tool head position to obtain the time series change data of the position deviation; According to the time series change data, use the support vector machine model to classify the deviation law of the tool head position, obtain the main categories of the deviation distribution, and determine the classification result of the deviation characteristics; Through the classification result of the deviation characteristics, perform a secondary analysis on the frequency and intensity of the abnormal signal to obtain the updated state of the abnormal signal; According to the updated state of the abnormal signal, if the updated state shows that the deviation persists, adjust the data acquisition parameters to obtain more accurate tool head position data and judge the final trend of the position deviation; Through the final trend of the position deviation and combined with the preset threshold range, conduct long-term tracking on the stability of the tool head position to obtain the comprehensive data of the stability evaluation.

8. The method for monitoring the cutter head of an ice cream machine according to claim 1, characterized in that, The obtaining of the correction instruction for the tool head position includes: For the abnormal signal, collect the tool head parameters and combine with the operating state information to determine the working condition data of the current tool head; According to the working condition data, use the parameter analysis method to extract the characteristics of the tool head parameters to obtain the key change trend in the parameters; Through the key change trend and combined with the pre-constructed correction model, perform adjustment calculations to obtain the preliminary adjustment value of the tool head position; If the preliminary adjustment value exceeds the preset threshold range, conduct a secondary verification of the abnormal signal to judge the reliability of the adjustment value; According to the result of the secondary verification and combined with the position deviation information, use the support vector machine model to optimize the adjustment value to determine the final correction amount; Through the final correction amount, generate a correction instruction for the tool head position to obtain the specific scheme for adjustment execution; According to the specific scheme for adjustment execution, dynamically update the tool head position to obtain the corrected operating state data.

9. The method for monitoring the cutter head of an ice cream machine according to claim 1, wherein, The determination of the adjusted position state includes: Through the correction instruction, perform axial adjustment or radial adjustment operations on the tool head position to obtain the real-time position data during the adjustment process; According to the real-time position data, a data acquisition tool is used to synchronously process the spacing information between the tool head and the container wall to obtain the current spacing change value; For the spacing change value, if the change value exceeds the preset threshold range, the data is verified through the information processing link to determine whether a position anomaly signal is triggered; According to the verified position anomaly signal, a support vector machine model is used to optimize the adjustment parameters to determine the final position adjustment plan; Through the final position adjustment plan, the position of the tool head is dynamically updated to obtain the updated position status data; For the updated position status data, combined with the synchronously processed spacing information, the stability of the position status is verified through a data comparison tool to obtain the final status confirmation result.

10. A method for monitoring the cutter head of an ice cream machine according to claim 1, characterized in that, It also includes: Continuously collect the spacing change trend between the tool head and the container wall through the adjusted position status, and use the time series analysis method to determine whether the spacing change tends to be stable; For the spacing change that does not tend to be stable, re-obtain the tool head operation parameters, combine the historical adjustment data, calculate a new correction instruction, and determine the secondary correction result of the tool head position; According to the secondary correction result, update the automation drive parameters, obtain the final stable data of the tool head position, and determine whether the operation status of the stirring meets the expectations; For the final stable data, record the correlation log of the tool head position and the spacing change, and save it to the database for reference in subsequent production batches.

Images