A method and system for cutting acoustic cotton board

Abstract

The embodiment of the application provides a sound-absorbing cotton board cutting control method and system, relates to the sound-absorbing cotton board cutting control technical field, and the method comprises the following steps: acquiring the cutting force between a cutter and the sound-absorbing cotton board; judging the local material characteristics at a cutting point of the sound-absorbing cotton board according to the cutting force; adjusting the vibration frequency and the pressing depth of the cutter under the premise that the advancing speed of the cutter is kept unchanged according to the local material characteristics at the cutting point; and cutting the sound-absorbing cotton board according to the adjusted vibration frequency and the pressing depth of the cutter. The application can improve the cutting precision and product quality, and prolong the service life of the cutter.

Description

Technical Field

[0001] This application relates to the field of sound-absorbing cotton board cutting control technology, and in particular to a sound-absorbing cotton board cutting control method and system. Background Technology

[0002] In related technologies, sound-absorbing cotton panels are widely used as key noise reduction components in modern industrial production lines such as automobile manufacturing and home appliance production. These sound-absorbing cotton panels are usually made of materials such as polyester fibers and are supplied in large-size sheet form, requiring precise cutting into preset shapes by automated cutting equipment. A typical automated cutting process involves fixing the sound-absorbing cotton panel on a cutting platform, the control system loading the digital drawing of the part, and generating motion trajectory instructions for the cutting tool. A high-frequency vibrating knife, driven by a servo motor, moves at high speed and vibrates at high frequency along the planned path to achieve the cutting and separation of the sound-absorbing cotton panel, aiming to ensure cutting dimensional accuracy and improve production efficiency. However, existing control methods are based on the ideal assumption that the physical properties of the sound-absorbing cotton panel are completely uniform. In reality, due to the influence of the manufacturing process, the fiber distribution and density inside the sound-absorbing cotton panel are not absolutely uniform, and there may be "hard spots" with higher density or "soft spots" with lower density. This material inhomogeneity has a significant negative impact on the high-speed cutting process. The problem becomes apparent when the control system executes the cutting task with fixed parameters (such as constant forward speed, fixed vibration frequency, and pressure depth). When the cutting tool encounters a high-density "hard spot" area, the material resistance increases instantaneously, causing slight deformation and deflection of the tool, resulting in dimensional deviations. Simultaneously, the intense compression and friction between the tool and the fibers causes excessive compaction of the fibers at the cut edge, forming hardened burrs that affect appearance and subsequent assembly. Conversely, when the tool enters a low-density "soft spot" area, the material support is insufficient, and the fiber bonding is loose. Fixed cutting parameters lead to excessive cutting force, causing the blade to tear the fibers rather than cleanly cut them, resulting in numerous fiber filaments of varying lengths at the cut edge, forming rough, flocculent edges that affect product quality and NVH performance. Summary of the Invention

[0003] This application aims to address at least one of the technical problems existing in the prior art. To this end, this application proposes a method and system for controlling the cutting of sound-absorbing cotton boards, aiming to improve cutting accuracy and product quality while extending the service life of the cutting tools.

[0004] In a first aspect, embodiments of this application provide a method for controlling the cutting of sound-absorbing cotton boards, including: Obtain the cutting force between the blade and the sound-absorbing cotton board; Based on the cutting force, determine the local material properties at the cutting point of the sound-absorbing cotton board; Based on the local material properties at the cutting point, the vibration frequency and depth of the cutting tool are adjusted while keeping the tool's forward speed constant. Cut the sound-absorbing cotton board according to the adjusted vibration frequency and pressing depth of the cutter.

[0005] According to some embodiments of this application, the step of adjusting the vibration frequency and depth of the cutting tool based on the local material properties at the cutting point, while keeping the tool feed speed constant, further includes: Monitor the temperature of the tool tip micro-region; Based on the comparison between the temperature of the cutting tip micro-region and the preset crosslinking agent activation temperature threshold, the cooling intensity of the cutting tool cooling system is adjusted to control the temperature of the cutting tip micro-region below the crosslinking agent activation temperature threshold.

[0006] According to some embodiments of this application, the step of determining the local material properties at the cutting point of the sound-absorbing cotton board based on the cutting force includes: To obtain the instantaneous forces acting on the cutting tool in multiple directions during the cutting process; Obtain changes in the vibration mode of the tool body; Based on the instantaneous forces in the multiple directions and the changes in the vibration mode, the local material properties at the cutting point of the sound-absorbing cotton board are identified.

[0007] According to some embodiments of this application, the step of adjusting the vibration frequency and depth of the cutting tool based on the local material properties at the cutting point, while keeping the tool feed speed constant, includes: Obtain information on the distribution of material properties in front of the cutting point of the tool; Based on the material property distribution information in front of the cutting point and the current forward speed of the tool, predict the material property change points and trends in the area that the tool is about to enter; Based on the material property change points and trends, as well as the tool response delay, calculate the pre-adjustment amount and timing for the tool vibration frequency and depth of cut. Before the tool actually reaches the point where the material properties change, the vibration frequency and depth of the tool are adjusted based on the local material properties at the cutting point, the pre-adjustment amount, and the pre-adjustment timing, while keeping the tool's forward speed constant.

[0008] According to some embodiments of this application, the step of obtaining the material property distribution information in front of the cutting point of the tool includes: During the cutting process, control the ultrasonic or laser sensor to emit signals in front of the cutting point; The echo signal from the ultrasonic or laser sensor is received, and the attenuation, phase, or time of flight of the echo signal is analyzed to obtain the density gradient and internal structure information of the material in front. The system receives real-time data from environmental signal sensors and tool vibration sensors, and performs noise filtering and compensation on the echo signals. Based on the echo signal after noise filtering and compensation, the material property distribution information in front of the cutting point is identified.

[0009] According to some embodiments of this application, the step of identifying the material property distribution information in front of the cutting point based on the echo signal after noise filtering and compensation includes: Monitor the operating status parameters of the ultrasonic or laser sensor, the environmental signal sensor, and the tool vibration sensor; Based on the operating status parameters, determine whether the ultrasonic or laser sensor, the environmental signal sensor, and the tool vibration sensor are abnormal; When the ultrasonic or laser sensor, the environmental signal sensor, or the tool vibration sensor malfunctions, the material property distribution information in front of the cutting point is corrected, or backup sensor data is used for evaluation.

[0010] According to some embodiments of this application, the step of identifying the material property distribution information in front of the cutting point based on the echo signal after noise filtering and compensation includes: Assess the accuracy and stability of the material property distribution information in front of the cutting point; When the accuracy or stability is lower than a preset threshold, monitor the transmission power, frequency, or pulse width of the ultrasonic or laser sensor, the environmental signal sensor, and the tool vibration sensor; When the emission power, frequency, or pulse width of the ultrasonic or laser sensor, the environmental signal sensor, or the tool vibration sensor are frequently adjusted, the operating range of the parameters of the ultrasonic or laser sensor, the environmental signal sensor, and the tool vibration sensor is predicted based on the material characteristic distribution information in front of the cutting point, the environmental interference mode, and the historical adjustment data of the ultrasonic or laser sensor, the environmental signal sensor, and the tool vibration sensor. Based on the predicted parameter operating range, a smooth curve-based parameter adjustment strategy is adopted to adjust the emission power, frequency, or pulse width of the ultrasonic or laser sensor, as well as the gain or sampling rate of the environmental signal sensor and the tool vibration sensor.

[0011] According to some embodiments of this application, the step of adjusting the emission power, frequency, or pulse width of the ultrasonic or laser sensor, and the gain or sampling rate of the environmental signal sensor and the tool vibration sensor using a smooth curve-based parameter adjustment strategy based on the predicted parameter operating range includes: Acquire the operating status parameters of the ultrasonic or laser sensor, the environmental signal sensor, and the tool vibration sensor; A multidimensional parameter space is constructed based on the material property distribution information in front of the cutting point, the working state parameters, and the predicted parameter working range; Based on the material property distribution information in front of the cutting point and the preset mapping relationship between material properties and sensor parameters, the optimal parameter combination is calculated in the multi-dimensional parameter space; Based on the optimal parameter combination and the sensor's response delay, a smooth parameter transition path is generated; Based on the smooth parameter transition path, the emission power, frequency, or pulse width of the ultrasonic or laser sensor, as well as the gain or sampling rate of the environmental signal sensor and the tool vibration sensor, are adjusted.

[0012] According to some embodiments of this application, the step of calculating the optimal parameter combination in the multidimensional parameter space based on the material property distribution information in front of the cutting point and the preset mapping relationship between material properties and sensor parameters includes: Analyze the degree of matching between the material property distribution information in front of the cutting point and the preset mapping relationship between material properties and sensor parameters; When the matching degree is lower than a preset threshold, an adaptive calibration mechanism is activated, the adaptive calibration mechanism including: Acquire the operating status parameters and historical cutting data of the passive environmental signal receiving sensor; Based on the material property distribution information in front of the cutting point, the working status parameters of the ultrasonic or laser sensor and the passive environmental signal receiving sensor, and historical cutting data, the preset mapping relationship between material properties and sensor parameters is dynamically adjusted. Based on the adjusted mapping relationship, the optimal parameter combination is recalculated in the multidimensional parameter space.

[0013] Secondly, embodiments of this application provide a sound-absorbing cotton board cutting control system, including: The cutting force acquisition module is used to acquire the cutting force between the blade and the sound-absorbing cotton board; The material property discrimination module is used to determine the local material properties at the cutting point of the sound-absorbing cotton board based on the cutting force. The cutting parameter adjustment module is used to adjust the vibration frequency and depth of the cutting tool based on the local material characteristics at the cutting point, while keeping the tool's forward speed constant. The execution module is used to cut the sound-absorbing cotton board according to the adjusted vibration frequency and pressing depth of the cutter.

[0014] The technical solution according to the embodiments of this application has at least the following beneficial effects: The sound-absorbing cotton board cutting control method disclosed in this application obtains the cutting force between the cutter and the sound-absorbing cotton board in real time, and determines the local material characteristics at the cutting point of the sound-absorbing cotton board accordingly. It then dynamically adjusts the vibration frequency and pressing depth of the cutter, thereby achieving precise cutting of the sound-absorbing cotton board while maintaining a constant cutter forward speed. This method effectively solves the problems in the prior art caused by the non-uniformity of the sound-absorbing cotton board material, such as decreased cutting quality, rough or hardened cut edges, dimensional deviations, and accelerated cutter wear. Through real-time perception and adaptive adjustment of local material characteristics, this application can ensure that the cutter always cuts with optimal parameters, avoiding the limitations of traditional fixed-parameter open-loop control, significantly improving cutting accuracy and product quality, while extending the tool life and reducing production costs.

[0015] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0016] The accompanying drawings are used to provide a further understanding of the technical solutions of this application and constitute a part of the specification. They are used together with the embodiments of this application to explain the technical solutions of this application and do not constitute a limitation on the technical solutions of this application.

[0017] Figure 1 A schematic flowchart illustrating a sound-absorbing cotton board cutting control method provided in one embodiment of this application; Figure 2 This is a schematic diagram of a sound-absorbing cotton board cutting control system provided in one embodiment of this application. Detailed Implementation

[0018] To make the objectives, technical methods, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0019] It should be noted that the meaning of "multiple" (or "more than") in the description of the embodiments of this application refers to two or more, and "greater than," "less than," "exceeding," etc. are understood to exclude the number itself, while "above," "below," "within," etc. are understood to include the number itself. If "first," "second," etc. are used in the description, they are only for the purpose of distinguishing technical features and should not be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated or the order of the technical features indicated.

[0020] In this application embodiment, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent the existence of A alone, the simultaneous existence of A and B, or the existence of B alone. A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one of the following" and similar expressions refer to any combination of these items, including any combination of singular or plural items. For example, at least one of a, b, and c can represent: the existence of a alone, the existence of b alone, the existence of c alone, the simultaneous existence of a and b, the simultaneous existence of a and c, the simultaneous existence of b and c, or the simultaneous existence of a, b, and c, where a, b, and c can be single or multiple.

[0021] In the description of this application, unless otherwise expressly defined, terms such as "setup," "installation," and "connection" should be interpreted broadly, and those skilled in the art can reasonably determine the specific meaning of the above terms in this application in conjunction with the specific content of the technical solution.

[0022] Based on the above, this application proposes a method and system for controlling the cutting of sound-absorbing cotton boards, aiming to improve cutting accuracy and product quality, while extending the service life of the cutting tools.

[0023] The sound-absorbing cotton board cutting control method provided in this application embodiment can be applied to a terminal, a server, or software running on either a terminal or a server. In some embodiments, the terminal can be a smartphone, tablet, laptop, desktop computer, etc.; the server can be configured as an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms; the software can be an application that implements the sound-absorbing cotton board cutting control method, etc., but is not limited to the above forms.

[0024] This application can be applied to numerous general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics devices, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices. This application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via communication networks. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices. It should be noted that in various specific embodiments of this invention, when processing is required based on data related to the characteristics of an object (e.g., user attributes or sets of attribute information), permission or consent from the corresponding object is obtained first, and the collection, use, and processing of this data comply with relevant laws and standards. Furthermore, when the embodiments of the present invention need to obtain the attribute information of an object, they will obtain the separate permission or separate consent of the corresponding object through pop-up windows or redirection to a confirmation page. After obtaining the separate permission or separate consent of the corresponding object, they will then obtain the relevant data of the object necessary for the embodiments of the present invention to operate normally.

[0025] See Figure 1 , Figure 1 This is a flowchart illustrating a method for controlling the cutting of sound-absorbing cotton boards according to an embodiment of this application. The method for controlling the cutting of sound-absorbing cotton boards provided in this embodiment includes, but is not limited to, steps S110 to S140, which will be described in detail below.

[0026] Step S110: Obtain the cutting force between the blade and the sound-absorbing cotton board; Step S120: Determine the local material properties at the cutting point of the sound-absorbing cotton board based on the cutting force; Step S130: Based on the local material properties at the cutting point, adjust the vibration frequency and depth of the cutting tool while keeping the tool's forward speed constant. Step S140: Cut the sound-absorbing cotton board according to the adjusted vibration frequency and pressing depth of the cutter.

[0027] It should be noted that "cutting force" refers to the force generated by the interaction between the cutting tool and the sound-absorbing cotton board during the cutting process; its magnitude and direction reflect the material's resistance characteristics. "Local material properties at the cutting point" refers to the physical properties of the sound-absorbing cotton board at the current cutting position, such as density, hardness, and fiber distribution; these characteristics directly affect the cutting effect. "Tool vibration frequency" refers to the number of vibrations per second during the cutting process; high-frequency vibration helps reduce cutting resistance and improve cutting efficiency. "Tool penetration depth" refers to the vertical distance between the tool tip and the surface of the sound-absorbing cotton board, determining the depth to which the tool penetrates the material. This method is typically implemented on automated cutting equipment, which includes, but is not limited to, a high-frequency vibrating blade, a servo motor, a force sensor, a control unit, and a cooling system.

[0028] In one embodiment, the cutting force between the cutting tool and the sound-absorbing cotton board needs to be acquired first. This cutting force can be acquired in various ways. For example, a high-precision triaxial force sensor can be integrated into the tool holder or tool mounting base to measure the instantaneous forces exerted by the tool in the X, Y, and Z directions during the cutting process in real time. These force sensors can be piezoelectric sensors or strain gauge sensors, which can convert mechanical force into electrical signals for analysis by the control system. As a preferred embodiment, the cutting force is indirectly calculated by monitoring the changes in current and voltage of the servo motor driving the cutting tool. When the cutting tool encounters materials of different densities, the servo motor needs to output different torques to maintain the preset motion state, and these torque changes correspond to the cutting force. After acquiring the cutting force, the local material properties at the cutting point of the sound-absorbing cotton board need to be determined based on the cutting force. One implementation is to compare the acquired cutting force data with a pre-established material property database. This database can be constructed by performing standard cutting experiments on sound-absorbing cotton boards of different densities and hardnesses and recording their corresponding cutting force characteristic curves. When the cutting force suddenly increases and persists for a period of time, it may indicate that the tool has entered a high-density "hard spot" region; when the cutting force suddenly decreases and is accompanied by slight tool vibration, it may indicate that the tool has entered a low-density "soft spot" region. As a preferred implementation, this is determined by combining changes in the vibration mode of the tool body. During cutting, the tool's vibration mode is affected by material properties. For example, when cutting hard spots, the tool's natural frequency may shift slightly, or the amplitude may be suppressed. By installing a miniature accelerometer or laser vibrometer on the tool body, the tool's vibration mode can be monitored in real time and fused with cutting force data for analysis, thereby more accurately identifying local material characteristics. Based on the identified local material characteristics at the cutting point, the tool's vibration frequency and depth of penetration are adjusted while maintaining a constant tool forward speed. For example, when the cutting point is identified as a high-density "hard spot" region, to effectively cut and reduce burrs, the tool's vibration frequency can be appropriately increased to increase the contact frequency between the tool and the material, thus cutting the fibers more effectively; simultaneously, the depth of penetration can be appropriately increased to ensure that the tool can completely penetrate the high-density region. Conversely, when the cutting point is identified as a low-density "soft spot" area, to avoid excessive tearing and rough edges, the vibration frequency of the cutting tool can be appropriately reduced to minimize disturbance to the loose fibers. Simultaneously, the depth of cutter penetration can be appropriately decreased to avoid unnecessary damage to the material. These adjustments and strategies can be dynamically calculated based on real-time identification results using algorithms such as fuzzy control and PID control. Finally, the sound-absorbing cotton board is cut according to the adjusted cutting tool vibration frequency and penetration depth. The control system sends the adjusted parameter commands to the cutting tool drive module, such as a servo motor and vibration generator.The servo motor adjusts the vertical position of the cutter according to the new pressing depth command, while the vibration generator adjusts the vibration state of the cutter according to the new vibration frequency command. The cutter continues to cut under these new parameters, thereby achieving precise cutting of the sound-absorbing cotton board.

[0029] It should be noted that the blade tip micro-area temperature refers to the local temperature of the area where the blade contacts the sound-absorbing cotton board. This temperature directly affects the physicochemical state of the material and the cutting performance of the blade. It can be monitored in real time using thermocouples, infrared sensors, or fiber optic temperature sensors integrated near the blade tip. The preset crosslinking agent activation temperature threshold refers to the lowest temperature at which the crosslinking agent that may be present in the sound-absorbing cotton board begins to undergo a chemical reaction. This threshold is predetermined based on the material formulation and process requirements of the sound-absorbing cotton board, aiming to avoid unexpected changes in material properties due to high temperatures during the cutting process. The blade cooling system can be understood as a device used to reduce the blade tip temperature, such as a gas jet cooling system, a liquid circulation cooling system, or a semiconductor refrigeration module. Cooling intensity refers to the cooling system's ability to control the blade tip temperature, which can be achieved by adjusting the flow rate, temperature, or cooling power of the cooling medium.

[0030] In one embodiment, it is assumed that the sound-absorbing cotton board contains a crosslinking agent that begins to activate at 80°C. During the cutting process, when the vibration frequency and depth of the blade are adjusted according to the local material properties, the temperature of the blade tip micro-area may begin to rise. When the blade tip micro-area temperature reaches 75°C in real time, monitored by an infrared sensor installed near the blade tip, the control system immediately activates the gas jet cooling system, increasing the nitrogen flow rate to cool the blade tip. The cooling intensity is dynamically adjusted to ensure that the blade tip micro-area temperature is always kept below 78°C, thereby effectively preventing the crosslinking agent from being prematurely activated during the cutting process, ensuring the smoothness of the cut edges and the final performance of the material.

[0031] It should be noted that acquiring the instantaneous forces acting on the cutting tool in multiple directions during the cutting process refers to real-time monitoring of the instantaneous forces, such as pressure and shear force, acting on the tool in the X, Y, and Z axes when cutting the sound-absorbing cotton board by installing multi-axial force sensors on the tool or its supporting structure. This force data reflects the immediate resistance and interaction between the tool and the material. For example, when the tool encounters a hard region or density change within the material, the instantaneous forces it experiences will change significantly. Furthermore, acquiring changes in the vibration mode of the tool body refers to real-time acquisition of vibration signals from the tool during the cutting process by installing vibration sensors (such as accelerometers) on or near the tool body. The local material properties of the sound-absorbing cotton board, such as density, hardness, and fiber orientation, will affect the vibration response of the tool during cutting. For example, when the tool cuts into areas of different densities, the tool's natural frequency, amplitude, or harmonic components may change, forming specific vibration modes. Therefore, based on the instantaneous forces acting on the tool in multiple directions and the changes in vibration modes, the local material properties at the cutting point of the sound-absorbing cotton board can be identified. Specifically, the collected instantaneous force data and vibration mode change data can be input into a pre-trained machine learning model (such as a support vector machine or neural network). This model, by learning from a large number of mechanical and vibration data corresponding to different material properties, can establish a mapping relationship between mechanical / vibration characteristics and material properties. For example, when the instantaneous force suddenly increases and is accompanied by specific high-frequency vibrations, it may indicate the presence of a high-density region or hard impurities at the cutting point; while when the force is stable and the vibration frequency is low, it may indicate that the material is uniform and soft. In this way, the local material properties at the cutting point of the sound-absorbing cotton board can be identified in real time and accurately, such as its density, hardness, toughness, or internal structural uniformity.

[0032] It should be noted that "obtaining material property distribution information in front of the cutting point" refers to scanning the sound-absorbing cotton board area in front of the current cutting point of the tool using non-contact sensors (such as ultrasonic sensors or laser sensors) to obtain material property data such as density, hardness, and fiber structure of this area. The purpose is to provide forward-looking data support for subsequent prediction and pre-adjustment. Specifically, "predicting the material property change points and trends in the area the tool is about to enter based on the material property distribution information in front of the cutting point and the current forward speed of the tool" can be understood as the system combining the material property data in front and the real-time forward speed of the tool, using an algorithmic model (such as a machine learning model or physical model trained on historical data) to analyze the specific locations (change points) where significant changes in material properties may occur, and whether these changes are gradually increasing, decreasing, or abrupt (trends). The purpose is to anticipate the material challenges the tool will face in advance. In practical applications, "calculating the pre-adjustment amount and pre-adjustment timing of tool vibration frequency and depth of cut based on material property change points and trends, and tool response delay" means that, considering the time required for the tool to complete adjustment from receiving the command (i.e., response delay), the system accurately calculates when (pre-adjustment timing) and by what magnitude (pre-adjustment amount) to begin adjusting the tool's vibration frequency and depth of cut based on predicted material change information. This ensures that the adjustment is in place or smoothly transitioning when the tool actually reaches the change point. The aim is to achieve seamless and smooth parameter transitions. Furthermore, "adjusting the tool's vibration frequency and depth of cut based on local material properties at the cutting point, pre-adjustment amount, and pre-adjustment timing, while maintaining a constant tool feed speed" means that the system begins executing the pre-calculated adjustment strategy before the tool even contacts the predicted material change area. This adjustment not only considers forward-looking prediction data but also incorporates the local material properties at the current cutting point to ensure the accuracy and stability of the adjustment. By maintaining a constant tool feed speed, the control logic can be simplified, and stable production efficiency can be maintained. Its purpose is to improve the adaptability and quality of cutting without sacrificing production efficiency.

[0033] In one embodiment, it is assumed that the sound-absorbing cotton board transitions from a low-density homogeneous structure to a high-density sandwich structure in a certain region. Before the cutting tool reaches this transition region, the system acquires the density gradient information of the material ahead using an ultrasonic sensor. Combined with the current cutting tool speed of 100 mm / s, it predicts that a significant density change point will appear 50 mm ahead, and the density will gradually increase. Considering the cutting tool's response delay of 20 milliseconds, the system calculates that a change in density needs to occur when the cutting tool is 60 mm away from the change point (i.e., 50 mm + 100 mm / s). The adjustment begins in 0.02 seconds. Specifically, the system calculates that the vibration frequency of the cutter needs to be gradually increased from 20kHz to 25kHz, while the compression depth needs to be gradually increased from 5mm to 6mm. These parameter adjustments are completed smoothly by the time the cutter actually reaches the high-density sandwich area. As a result, the cutter can cut with optimal parameters adapted to the characteristics of the new material, ensuring the continuity of the cutting process and the stability of the cutting quality.

[0034] It should be noted that, to achieve accurate sensing of the material properties in front of the sound-absorbing cotton board, ultrasonic sensors or laser sensors can be used. As a preferred embodiment, the ultrasonic sensor can be configured to emit high-frequency sound pulses towards the area in front of the cutting point of the sound-absorbing cotton board, while the laser sensor can emit a laser beam. These sensors are precisely controlled to ensure that the signal can effectively penetrate the sound-absorbing cotton board and return echoes from different depths and positions. The received echo signals carry rich information about the material in front. By deeply analyzing the attenuation, phase change, and time of flight of these echo signals, the density gradient and structural information inside the sound-absorbing cotton board can be inferred. For example, the degree of signal attenuation may be related to the material's density and porosity, the phase change may reflect the presence of internal interfaces, and the time of flight can be used to determine the distance the signal propagates and the sound speed or light speed characteristics of the material. Thus, a preliminary characteristic profile of the material in front can be constructed. Furthermore, to improve the accuracy and reliability of the echo signals, real-time data from environmental signal sensors and tool vibration sensors are required. Environmental signal sensors monitor environmental factors such as temperature, humidity, and airflow in the cutting area, which can interfere with the propagation of ultrasonic or laser signals. Tool vibration sensors monitor the vibration of the tool itself in real time, as tool vibration can also interfere with the signals transmitted and received by the sensors. Based on this real-time data, the received echo signals can be finely processed for noise filtering and compensation. For example, environmental noise can be removed using digital signal processing algorithms, or artifacts caused by tool vibration can be eliminated using vibration compensation algorithms. Finally, based on the noise-filtered and compensated echo signals, the material property distribution information in front of the cutting point can be accurately identified.

[0035] It should be noted that operating status parameters can be understood as various indicators reflecting the current operating status of the sensor, such as the sensor's power supply voltage, current, internal temperature, signal output strength, signal-to-noise ratio, self-test status code, data transmission rate, and calibration deviation. These parameters can reflect in real time whether the sensor is within its normal operating range. Sensor anomalies can be determined by comparing the real-time monitored operating status parameters with preset normal operating thresholds. For example, when the signal output strength is below a certain threshold, the signal-to-noise ratio is too low, or the self-test status code indicates a fault, the corresponding sensor can be determined to be abnormal. Furthermore, when a sensor anomaly is detected, two strategies can be adopted to ensure the accuracy of the material property distribution information in front of the cutting point. The first strategy is to correct the acquired material property distribution information. Correction methods may include, but are not limited to: cross-validation and compensation using data from other normally operating sensors; prediction and filling of abnormal data based on historical data and machine learning models; or using data smoothing, filtering, and other algorithms to eliminate the influence of abnormal data. The second strategy is to use backup sensor data for evaluation. This means that redundant sensors can be pre-configured in the system. When the main sensor malfunctions, the system can automatically switch to the backup sensor and use the data provided by the backup sensor to continue identifying the material property distribution information, thereby ensuring the continuity and reliability of the data stream.

[0036] It should be noted that, assuming that during the cutting process of the sound-absorbing cotton board, after the ultrasonic sensor emits a signal, the signal-to-noise ratio of the received echo signal suddenly drops significantly and remains below the preset normal operating threshold, the system determines that the ultrasonic sensor is malfunctioning by monitoring its operating status parameters (e.g., signal-to-noise ratio). To ensure the accuracy of the material property distribution information in front of the cutting point, the system can activate a correction mechanism. Specifically, the system can combine normal data provided by environmental signal sensors and tool vibration sensors, as well as material property data of this area from historical cutting processes, to correct the abnormal data provided by the ultrasonic sensor through a data fusion algorithm. For example, Kalman filtering or neural network models can be used to predict and compensate for potential deviations of the ultrasonic sensor based on the inputs of other sensors and historical trends. As another specific implementation, if the system is equipped with a backup ultrasonic sensor, when the main ultrasonic sensor is determined to be malfunctioning, the system can immediately switch to the backup ultrasonic sensor and use the data provided by the backup sensor to continue acquiring material property distribution information in front of the cutting point. Through these two methods, even in the event of sensor malfunction, the system can continuously provide accurate material property information, thereby ensuring that the adjustment of the tool vibration frequency and pressing depth is always based on reliable data, thus ensuring the cutting quality of the sound-absorbing cotton board.

[0037] It should be noted that evaluating the accuracy and stability of material property distribution information in front of the cutting point can be understood as performing a quality check on the material property data acquired by ultrasonic or laser sensors, environmental signal sensors, and tool vibration sensors after noise filtering and compensation. This can be achieved in various ways, such as comparing the real-time acquired material property data with a preset material model or historical data to calculate its deviation, variance, or consistency index; or using multi-sensor redundancy verification, cross-validating data acquired by sensors of different types or locations. Preset thresholds can be set according to the actual application scenario and the requirements for cutting accuracy. For example, when the fluctuation of the material density gradient exceeds a certain percentage, or the confidence level of the internal structural information identification is lower than a certain level, the accuracy or stability is considered insufficient. When the accuracy or stability is lower than the preset threshold, the system will activate a monitoring mechanism to track the working status parameters of the ultrasonic or laser sensors, environmental signal sensors, and tool vibration sensors in real time. These parameters include, but are not limited to, the emission power, frequency, or pulse width of the ultrasonic or laser sensors, and the gain or sampling rate of the environmental signal sensors and tool vibration sensors. The purpose of monitoring is to identify potential causes of data quality degradation, such as insufficient sensor transmission energy, decreased receiver sensitivity, or excessive environmental noise. Furthermore, when frequent adjustments to the transmission power, frequency, or pulse width of ultrasonic or laser sensors, environmental signal sensors, or tool vibration sensors are detected, it indicates that the sensors may be in an unstable operating state or facing complex and changing environmental challenges. In this case, the system will combine information on the current material properties distribution in front of the cutting point, identified environmental interference patterns (e.g., periodic noise, sudden vibrations, etc.), and historical sensor adjustment data to predict the future operating range of the sensor parameters. Historical adjustment data can include records of the sensor's optimal operating parameters under different materials and environmental conditions, as well as feedback on the effects of parameter adjustments. Through machine learning algorithms or statistical models, this data can be analyzed to predict the optimal configuration range of sensor parameters in the current and future periods. Based on the predicted parameter operating range, this application adopts a smooth curve-based parameter adjustment strategy. This means that the adjustment of sensor parameters is not instantaneous but rather gradually transitions to the new target value over a certain period through a preset smoothing function (e.g., an S-curve, an exponential curve, etc.). This smooth adjustment strategy effectively avoids system oscillations, data acquisition interruptions, or the introduction of new interference caused by sudden parameter changes, thereby ensuring the continuity and stability of sensor data acquisition. Specifically, the emission power, frequency, or pulse width of ultrasonic or laser sensors can be adjusted to optimize signal penetration and echo quality; simultaneously, the gain or sampling rate of environmental signal sensors and tool vibration sensors can be adjusted to improve noise suppression and signal acquisition accuracy.

[0038] In one embodiment, it is assumed that during the cutting process, an ultrasonic sensor is used to detect the material properties in front of the sound-absorbing cotton board. After identifying the material property distribution information in front of the cutting point, the system analyzes the characteristics of continuous echo signals (such as attenuation rate and phase change) and finds that its accuracy or stability is below a preset threshold, for example, the standard deviation of the density gradient reading exceeds 10% within 5 consecutive seconds. At this point, the system begins to monitor the transmission power and frequency of the ultrasonic sensor. If it is found that the transmission power of the ultrasonic sensor frequently switches between low and medium power in the past minute, it indicates that it may be struggling to adapt to material changes or environmental noise. The system combines the current average density of the material, the background noise level of the workshop environment, and the historical best operating parameters of the ultrasonic sensor under similar material and noise conditions to predict that the optimal transmission power of the ultrasonic sensor should be within a certain range (e.g., 15% higher than the current average power) and the frequency should remain stable within the next 10 seconds. Based on this prediction, the system will use a smooth exponential growth curve to gradually increase the transmission power of the ultrasonic sensor from the current value to the predicted optimal range within 2 seconds, while fine-tuning the frequency to ensure that the quality of the echo signal is optimized, thereby obtaining more accurate and stable information on the distribution of material properties in front, providing a solid data foundation for subsequent tool parameter adjustments.

[0039] It should be noted that acquiring the operating status parameters of ultrasonic or laser sensors, environmental signal sensors, and tool vibration sensors refers to real-time monitoring and collection of various performance indicators of these sensors under current operating conditions, such as internal temperature, supply voltage, current, signal-to-noise ratio, calibration status, and the presence of abnormal conditions such as overload or underload. Specifically, constructing a multi-dimensional parameter space based on the material property distribution information in front of the cutting point, operating status parameters, and predicted parameter operating ranges can be understood as creating a data model containing multiple dimensions. These dimensions may include, but are not limited to: the emission power, frequency, and pulse width of the ultrasonic or laser sensor; the gain and sampling rate of the environmental signal sensor; the gain and sampling rate of the tool vibration sensor; and the density, hardness, and internal structure characteristics of the material in front. Calculating the optimal parameter combination in the multi-dimensional parameter space based on the material property distribution information in front of the cutting point and the preset mapping relationship between material properties and sensor parameters refers to using a pre-established mathematical model or lookup table describing the correspondence between material properties and the optimal operating parameters of the sensors. This mapping relationship can be obtained through experimental data, simulation, or machine learning. Furthermore, generating a smooth parameter transition path based on the optimal parameter combination and the sensor's response delay means that after determining the target optimal parameter combination, a gradual parameter change trajectory is designed, taking into account the time required for the sensor to adjust from its current operating state to the target state (i.e., the response delay). This path can be a linear, exponential, or a smooth curve generated using spline interpolation, etc. Its purpose is to avoid drastic parameter jumps in a short period, thereby reducing the impact on the sensor hardware and ensuring the continuity and stability of data acquisition. Therefore, adjusting the transmission power, frequency, or pulse width of the ultrasonic or laser sensor, as well as the gain or sampling rate of the environmental signal sensor and the tool vibration sensor, according to the smooth parameter transition path means that the system gradually and dynamically changes the various operating parameters of the sensors according to the pre-generated smooth transition path, allowing them to smoothly transition from the current state to the state defined by the optimal parameter combination.

[0040] In one embodiment, assuming that when cutting a sound-absorbing cotton board composed of layers with different densities and internal structures, the system detects that the cutter is about to enter a region with a significantly increased density using an ultrasonic sensor. First, the system acquires real-time operating status parameters from the ultrasonic sensor, environmental signal sensor, and cutter vibration sensor. These parameters include the internal temperature, transmission power stability, and signal-to-noise ratio of the ultrasonic sensor; the ambient temperature and humidity of the environmental signal sensor; and the vibration amplitude and frequency of the cutter vibration sensor. Next, the system combines these real-time operating status parameters with information on the material distribution characteristics ahead (e.g., the density of the region to be entered is 0.5 g / cm³, containing a large amount of fiber) and a predicted parameter operating range (e.g., the ultrasonic sensor's transmission power range is 10W-50W, and the frequency range is 1MHz-5MHz) to construct a multi-dimensional parameter space. This space may include multiple dimensions such as transmission power, frequency, pulse width, gain, sampling rate, and material density. Then, based on a preset mapping relationship between material properties and sensor parameters (for example, this mapping relationship might indicate that for a fiber material with a density of 0.5 g / cm³, the ultrasonic sensor achieves optimal penetration and echo signal quality at a frequency of 3 MHz and a transmission power of 40 W), the system calculates the optimal parameter combination in this multi-dimensional parameter space. For example, the calculation result might indicate that the ultrasonic sensor should be adjusted to a frequency of 3.2 MHz and a transmission power of 42 W, with corresponding adjustments to the gain and pulse width. Considering the approximately 50-millisecond response delay of the ultrasonic sensor from its current operating state to the new parameter combination, the system generates a smooth parameter transition path. For example, the system might begin using a cubic spline interpolation algorithm 100 milliseconds before the tool actually reaches the high-density region, smoothly transitioning the ultrasonic sensor's transmission power and frequency from their current values ​​to the calculated optimal parameter combination within 50 milliseconds. Finally, based on this smooth parameter transition path, the system precisely adjusts the ultrasonic sensor's transmission power, frequency, and pulse width, as well as the gain or sampling rate of the environmental signal sensor and the tool vibration sensor. In this way, when the cutter actually enters the high-density area, the sensor is already in its optimal working state, thus continuously providing accurate and stable information on the distribution of material properties in front, ensuring the precision and efficiency of the cutting process.

[0041] It should be noted that analyzing the matching degree between the material property distribution information in front of the cutting point and the preset mapping relationship between material properties and sensor parameters refers to quantifying the accuracy of the mapping relationship by comparing the difference between the actual detected material property distribution information in front and the material properties predicted based on the current sensor parameters and the preset mapping relationship, or by evaluating the correlation between the sensor output data and the actual cutting effect. For example, statistical methods (such as correlation coefficient, mean squared error) or machine learning models (such as classifiers, regressors) can be used to calculate the matching degree. This matching degree reflects the effectiveness of the current preset mapping relationship in describing the relationship between actual material properties and sensor parameters. When the matching degree is lower than a preset threshold, it means that the current mapping relationship is insufficient to support accurate parameter optimization, and the system will automatically activate the adaptive calibration mechanism. This preset threshold can be set according to empirical values, experimental data, or the system's requirements for cutting accuracy. The adaptive calibration mechanism aims to dynamically optimize and update the mapping relationship to adapt to constantly changing actual working conditions. Specifically, this mechanism will make comprehensive adjustments using multi-source information: First, based on the material property distribution information in front of the cutting point, real-time material state data, such as density gradient and internal structure, is obtained. Secondly, the operating parameters of ultrasonic or laser sensors and passively received environmental signal sensors, such as transmission power, frequency, gain, and sampling rate, are combined. These parameters reflect the sensor's own operating status and environmental interference. Thirdly, historical cutting data, including past material properties, sensor parameters, actual cutting results, and corresponding matching degrees, are used as training or reference datasets. Through comprehensive analysis and learning of the above multi-source data, such as using machine learning algorithms (reinforcement learning, neural networks, adaptive filtering, etc.), the preset mapping relationship between material properties and sensor parameters is dynamically adjusted. This adjustment can be a fine-tuning of parameters or an update of the model structure, aiming to make the mapping relationship more accurately reflect the current situation. Finally, based on the adjusted mapping relationship, the optimal parameter combination is recalculated in a multi-dimensional parameter space. This means that after the mapping relationship is updated, the system will re-execute the calculation process of the optimal parameter combination based on the new and more accurate mapping relationship, thereby obtaining sensor parameter settings that better match the current actual working conditions.

[0042] In one embodiment, it is assumed that during the cutting process of the sound-absorbing cotton board, due to the replacement of different batches of sound-absorbing cotton boards, there are slight differences in the internal fiber density and adhesive content compared to previous batches. During the cutting process, ultrasonic or laser sensors continuously acquire information on the material property distribution in front of the cutting point. Initially, the system calculates the optimal parameter combination based on a preset mapping relationship between material properties and sensor parameters, and adjusts the sensor parameters accordingly. However, as the cutting progresses, the system analyzes the differences between the actual received echo signal attenuation, phase, and other information and the material properties predicted based on the preset mapping relationship. It finds that the degree of matching between the two gradually decreases and falls below a preset threshold (e.g., the correlation coefficient is below 0.8). At this point, an adaptive calibration mechanism is automatically activated. The system collects the current material property distribution information in front of the cutting point, the operating status parameters (such as transmit power, receive gain, etc.) of the ultrasonic or laser sensors and the passively received environmental signal sensors, and combines them with stored historical cutting data. A built-in machine learning model uses these real-time and historical data as training samples to learn and update the original mapping relationship between material properties and sensor parameters online. The model identifies new correlation patterns between the properties of new batches of materials and sensor parameters, and adjusts the weights or parameters in the mapping relationship. For example, the model might find that for a new batch of materials, a slight increase in the transmission power of the ultrasonic sensor is needed to obtain a clear echo signal. After the mapping relationship is dynamically adjusted, the system immediately recalculates a new optimal combination of parameters in the multidimensional parameter space based on this updated mapping relationship. For example, the new optimal combination of parameters might indicate that the transmission power of the ultrasonic sensor needs to be increased by 5%, while the gain of the environmental signal sensor needs to be fine-tuned by 2%. The system then generates a smooth parameter transition path based on this new optimal combination of parameters and the sensor response delay, and adjusts the transmission power, frequency, or pulse width of the ultrasonic or laser sensor, as well as the gain or sampling rate of the environmental signal sensor and the tool vibration sensor. Through this adaptive calibration and adjustment, even with changes in material batches, the system ensures that the sensor parameters are always in optimal working condition, thereby maintaining high-precision cutting quality of the sound-absorbing cotton board.

[0043] See Figure 2 , Figure 2 This is a schematic diagram of a sound-absorbing cotton board cutting control system provided in one embodiment of this application. The sound-absorbing cotton board cutting control system 200 includes: The cutting force acquisition module 210 is used to acquire the cutting force between the blade and the sound-absorbing cotton board; The material property discrimination module 220 is used to determine the local material properties at the cutting point of the sound-absorbing cotton board based on the cutting force. The cutting parameter adjustment module 230 is used to adjust the vibration frequency and depth of the cutting tool according to the local material characteristics at the cutting point, while keeping the cutting tool forward speed constant. The execution module 240 is used to cut the sound-absorbing cotton board according to the adjusted vibration frequency and pressing depth of the cutter.

[0044] It should be noted that the information interaction and execution process between the above modules are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, which will not be repeated here.

[0045] It will be understood by those skilled in the art that all or some of the steps and systems in the methods disclosed above can be implemented as software, firmware, hardware, and suitable combinations thereof. Some or all of the physical components can be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit. Such software can be distributed on a computer-readable medium, which can include computer storage media (or non-transitory media) and communication media (or transient media). As is known to those skilled in the art, the term computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and is accessible to a computer. Furthermore, as is known to those skilled in the art, communication media typically include computer-readable instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

[0046] The foregoing has provided a detailed description of the preferred embodiments of this application. However, this application is not limited to the above-described embodiments. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of this application. All such equivalent modifications or substitutions are included within the scope defined in this application.

Claims

1. A method for controlling the cutting of sound-absorbing cotton boards, characterized in that, include: Obtain the cutting force between the blade and the sound-absorbing cotton board; Based on the cutting force, determine the local material properties at the cutting point of the sound-absorbing cotton board; Based on the local material properties at the cutting point, the vibration frequency and depth of the cutting tool are adjusted while keeping the tool's forward speed constant. Cut the sound-absorbing cotton board according to the adjusted vibration frequency and pressing depth of the cutter; The step of adjusting the vibration frequency and depth of the cutting tool based on the local material properties at the cutting point, while keeping the tool's feed speed constant, includes: Obtain information on the distribution of material properties in front of the cutting point of the tool; Based on the material property distribution information in front of the cutting point and the current forward speed of the tool, predict the material property change points and trends in the area that the tool is about to enter; Based on the material property change points and trends, as well as the tool response delay, calculate the pre-adjustment amount and timing for the tool vibration frequency and depth of cut. Before the tool actually reaches the point where the material properties change, the vibration frequency and depth of the tool are adjusted based on the local material properties at the cutting point, the pre-adjustment amount, and the pre-adjustment timing, while keeping the tool's forward speed constant.

2. The method according to claim 1, characterized in that, The step of adjusting the vibration frequency and depth of the cutting tool based on the local material properties at the cutting point, while keeping the tool feed speed constant, further includes: Monitor the temperature of the tool tip micro-region; Based on the comparison between the temperature of the cutting tip micro-region and the preset crosslinking agent activation temperature threshold, the cooling intensity of the cutting tool cooling system is adjusted to control the temperature of the cutting tip micro-region below the crosslinking agent activation temperature threshold.

3. The method according to claim 1, characterized in that, The step of determining the local material properties at the cutting point of the sound-absorbing cotton board based on the cutting force includes: To obtain the instantaneous forces acting on the cutting tool in multiple directions during the cutting process; Obtain changes in the vibration mode of the tool body; Based on the instantaneous forces in the multiple directions and the changes in the vibration mode, the local material properties at the cutting point of the sound-absorbing cotton board are identified.

4. The method according to claim 3, characterized in that, The step of obtaining the material property distribution information in front of the cutting point of the tool includes: During the cutting process, control the ultrasonic or laser sensor to emit signals in front of the cutting point; The echo signal from the ultrasonic or laser sensor is received, and the attenuation, phase, or time of flight of the echo signal is analyzed to obtain the density gradient and internal structure information of the material in front. The system receives real-time data from environmental signal sensors and tool vibration sensors, and performs noise filtering and compensation on the echo signals. Based on the echo signal after noise filtering and compensation, the material property distribution information in front of the cutting point is identified.

5. The method according to claim 4, characterized in that, The step following the identification of material property distribution information in front of the cutting point based on the echo signal after noise filtering and compensation includes: Monitor the operating status parameters of the ultrasonic or laser sensor, the environmental signal sensor, and the tool vibration sensor; Based on the operating status parameters, determine whether the ultrasonic or laser sensor, the environmental signal sensor, and the tool vibration sensor are abnormal; When the ultrasonic or laser sensor, the environmental signal sensor, or the tool vibration sensor malfunctions, the material property distribution information in front of the cutting point is corrected, or backup sensor data is used for evaluation.

6. The method according to claim 5, characterized in that, The step following the identification of material property distribution information in front of the cutting point based on the echo signal after noise filtering and compensation includes: Assess the accuracy and stability of the material property distribution information in front of the cutting point; When the accuracy or stability is lower than a preset threshold, monitor the transmission power, frequency, or pulse width of the ultrasonic or laser sensor, the environmental signal sensor, and the tool vibration sensor; When the emission power, frequency, or pulse width of the ultrasonic or laser sensor, the environmental signal sensor, or the tool vibration sensor are frequently adjusted, the operating range of the parameters of the ultrasonic or laser sensor, the environmental signal sensor, and the tool vibration sensor is predicted based on the material characteristic distribution information in front of the cutting point, the environmental interference mode, and the historical adjustment data of the ultrasonic or laser sensor, the environmental signal sensor, and the tool vibration sensor. Based on the predicted parameter operating range, a smooth curve-based parameter adjustment strategy is adopted to adjust the emission power, frequency, or pulse width of the ultrasonic or laser sensor, as well as the gain or sampling rate of the environmental signal sensor and the tool vibration sensor.

7. The method according to claim 6, characterized in that, The step of adjusting the emission power, frequency, or pulse width of the ultrasonic or laser sensor, as well as the gain or sampling rate of the environmental signal sensor and the tool vibration sensor, using a smooth curve-based parameter adjustment strategy based on the predicted parameter operating range, includes: Acquire the operating status parameters of the ultrasonic or laser sensor, the environmental signal sensor, and the tool vibration sensor; A multidimensional parameter space is constructed based on the material property distribution information in front of the cutting point, the working state parameters, and the predicted parameter working range; Based on the material property distribution information in front of the cutting point and the preset mapping relationship between material properties and sensor parameters, the optimal parameter combination is calculated in the multi-dimensional parameter space; Based on the optimal parameter combination and the sensor's response delay, a smooth parameter transition path is generated; Based on the smooth parameter transition path, the emission power, frequency, or pulse width of the ultrasonic or laser sensor, as well as the gain or sampling rate of the environmental signal sensor and the tool vibration sensor, are adjusted.

8. The method according to claim 7, characterized in that, The step of calculating the optimal parameter combination in the multidimensional parameter space based on the material property distribution information in front of the cutting point and the preset mapping relationship between material properties and sensor parameters includes: Analyze the degree of matching between the material property distribution information in front of the cutting point and the preset mapping relationship between material properties and sensor parameters; When the matching degree is lower than a preset threshold, an adaptive calibration mechanism is activated, the adaptive calibration mechanism including: Acquire the operating status parameters and historical cutting data of the passive environmental signal receiving sensor; Based on the material property distribution information in front of the cutting point, the working status parameters of the ultrasonic or laser sensor and the passive environmental signal receiving sensor, and historical cutting data, the preset mapping relationship between material properties and sensor parameters is dynamically adjusted. Based on the adjusted mapping relationship, the optimal parameter combination is recalculated in the multidimensional parameter space.

9. A sound-absorbing cotton board cutting control system, used to execute the method as described in claim 8, characterized in that, include: The cutting force acquisition module is used to acquire the cutting force between the blade and the sound-absorbing cotton board; The material property discrimination module is used to determine the local material properties at the cutting point of the sound-absorbing cotton board based on the cutting force. The cutting parameter adjustment module is used to adjust the vibration frequency and depth of the cutting tool based on the local material characteristics at the cutting point, while keeping the tool's forward speed constant. The execution module is used to cut the sound-absorbing cotton board according to the adjusted vibration frequency and pressing depth of the cutter.

Images