Laser cutting optimization method and system for batch production of flexible tactile sensors

Abstract

The application provides a laser cutting optimization method and system for batch production of flexible tactile sensors. The method includes: obtaining flexible material characteristic data, configuring an ultrafast laser cutting unit and a thermal annealing laser unit; generating plasma through a plasma generator to improve laser energy absorption efficiency; collecting cutting process parameters and estimating cutting state; dynamically adjusting cutting beam, thermal annealing beam and plasma parameters; evaluating cutting quality and selecting or reconstructing control strategy; realizing simultaneous cutting and post-processing of multiple sensor units. By combining multi-beam laser collaborative cutting with plasma assisted technology, using a distributed unknown input observer and an intelligent control system, the application solves the problems of edge damage, large heat affected zone and material deformation in traditional laser cutting, significantly improving the cutting quality and batch production efficiency of flexible tactile sensors.

Description

Technical Field

[0001] This invention relates to the field of flexible electronics manufacturing technology, and in particular to a laser cutting optimization method and system for mass production of flexible tactile sensors. Background Technology

[0002] Flexible tactile sensors are a new type of intelligent sensor capable of sensing and measuring tactile information, and are widely used in fields such as human-computer interaction, healthcare, and robotics. These sensors are characterized by their thinness, flexibility, and wearability, and can simulate the sensation of external pressure, temperature, and vibration felt by human skin.

[0003] Currently, common manufacturing technologies for flexible tactile sensors mainly include screen printing and photolithography. Screen printing uses a specific template to print conductive materials onto a flexible substrate to form electrodes and sensitive layers; while photolithography uses photosensitive materials to construct micro- and nano-structures on a flexible substrate through processes such as exposure and development. These technologies have made significant progress in realizing the functional structure of sensors.

[0004] In the manufacturing process of flexible tactile sensors, the cutting process is a crucial factor determining the quality and performance of the final product. While traditional laser cutting technology can achieve high-precision cutting, it often faces problems such as edge damage, large heat-affected zones, and material deformation when processing flexible materials. These issues lead to unstable edge structures in the sensor, affecting sensing accuracy and causing a high defect rate in mass production, while also limiting the sensor's use in high-precision applications.

[0005] The main technical drawbacks of traditional laser cutting technology include: a single laser beam cannot simultaneously achieve both cutting efficiency and edge quality; the heat generated during the cutting process is difficult to control effectively, leading to thermal deformation and microcracks in the material; stress concentration and material damage at the cutting edge are difficult to repair in real time during the cutting process; in addition, debris and molten material generated during the cutting process are prone to redeposit at the cutting edge, affecting the cutting quality and subsequent processes. Summary of the Invention

[0006] The purpose of this invention is to provide an optimized laser cutting method and system for the mass production of flexible tactile sensors, which solves the technical problems faced by traditional laser cutting technology when processing flexible materials, such as edge damage, large heat-affected zone, and material deformation, thereby improving the quality and efficiency of mass production of flexible tactile sensors.

[0007] To achieve the above objectives, this invention provides a laser cutting optimization method for the mass production of flexible tactile sensors, comprising: acquiring flexible material characteristic data; configuring an ultrafast laser cutting unit and a thermal annealing laser unit according to the flexible material characteristic data to generate a cutting beam and a thermal annealing beam; generating plasma through a plasma generator and guiding the plasma to the laser cutting area to improve laser energy absorption efficiency; collecting temperature field distribution, plasma density distribution, and cutting front shape data during the cutting process, and estimating cutting process state parameters based on the temperature field distribution, plasma density distribution, and cutting front shape data; dynamically adjusting the energy, frequency, and relative position of the cutting beam and the thermal annealing beam, as well as the density and temperature of the plasma, based on the cutting process state parameters; acquiring a cutting edge image, evaluating the cutting quality, obtaining a cutting quality evaluation result, and selecting or reconstructing a control strategy based on the cutting quality evaluation result; simultaneously cutting multiple sensor units according to the control strategy, and performing post-cutting processing to complete the mass production of flexible tactile sensors.

[0008] Furthermore, the ultrafast laser cutting unit has at least two laser sources. When the ultrafast laser cutting unit is working, one of the low-power laser sources performs a single cut, with a cutting depth of one-third to one-half, forming a relatively flat cut base; the remaining one or more laser sources complete the cutting to the remaining depth.

[0009] Furthermore, the acquisition of flexible material property data, and the configuration of an ultrafast laser cutting unit and a thermal annealing laser unit based on the flexible material property data to generate cutting beams and thermal annealing beams, includes: identifying the type of flexible material through spectral analysis and image recognition technology, acquiring data on the absorption, reflection, and thermal conduction characteristics of the flexible material to lasers of different wavelengths, and generating a flexible material property database; matching the optimal laser parameter combination based on the flexible material property database, configuring a femtosecond laser and a tunable wavelength continuous laser to generate the cutting beam and the thermal annealing beam; and setting the timing, energy, and spatial position of each beam through an optoelectronic control unit, adjusting the optical reflector and the electrically controlled displacement platform to achieve the coordination of the cutting beam and the thermal annealing beam.

[0010] Furthermore, the process of generating plasma through a plasma generator and guiding the plasma to the laser cutting area to improve laser energy absorption efficiency includes: selecting a working gas according to the type of flexible material; generating plasma in the cutting area through radio frequency discharge or microwave discharge technology; guiding the plasma through a plasma transmission channel; adjusting the discharge power and gas flow rate; and controlling the density and temperature parameters of the plasma.

[0011] Furthermore, guiding the plasma to the laser cutting region to improve laser energy absorption efficiency includes: receiving the plasma generated by the plasma generator, guiding the plasma through an electromagnetic field to ensure it coincides with the laser cutting region; monitoring the interaction between the plasma and the laser in the laser cutting region to obtain energy transfer efficiency data; and optimizing the synergistic effect between the plasma and laser cutting based on the energy transfer efficiency data.

[0012] Further, the acquisition of temperature field distribution, plasma density distribution, and cutting front shape data during the cutting process, and the estimation of cutting process state parameters based on the temperature field distribution, plasma density distribution, and cutting front shape data, includes: acquiring temperature field, plasma density, and cutting front shape data during the cutting process to form a multidimensional sensing dataset; receiving the multidimensional sensing dataset, performing data preprocessing and consistency checks to generate an effective monitoring data stream; based on the effective monitoring data stream, establishing a state observation equation using discrete-time linear time-invariant system theory, constructing a distributed unknown input observer model, and estimating initial cutting process state parameters based on the distributed unknown input observer model; decomposing the initial cutting process state parameters into multiple subsystems, processing them in parallel through a distributed computing architecture to estimate unknown input disturbances, and obtaining multi-source state estimation results; weighted fusion of the multi-source state estimation results, evaluating the reliability of the estimation results, and outputting the cutting process state parameters.

[0013] Furthermore, the step of dynamically adjusting the energy, frequency, and relative position of the cutting beam and the thermal annealing beam, as well as the density and temperature of the plasma, based on the cutting process state parameters includes: receiving the cutting process state parameters, comparing them with preset cutting quality standards, and identifying adjustment parameter items; establishing a plasma-laser-material interaction model based on the adjustment parameter items, predicting the optimal parameter combination through machine learning algorithms, and forming parameter adjustment instructions; and controlling the energy, frequency, and relative position of the cutting beam and the thermal annealing beam, as well as the density and temperature of the plasma, according to the parameter adjustment instructions, to achieve real-time optimization of the cutting process.

[0014] Furthermore, the steps of acquiring the cutting edge image, evaluating the cutting quality, obtaining the cutting quality evaluation result, and selecting or reconstructing a control strategy based on the cutting quality evaluation result include: acquiring the cutting edge image, applying an edge detection algorithm to extract edge features, and acquiring edge quality data; receiving the edge quality data, comparing it with a preset standard quality template, and calculating a cutting quality score; receiving the cutting quality score, determining whether it reaches a preset quality score threshold, and forming a control decision request; querying a preset control strategy library based on the control decision request, selecting the most matching control strategy or reconstructing a new control strategy, and generating a cutting control scheme; evaluating the cutting control scheme, obtaining a cutting control scheme that has passed the evaluation, and storing the cutting control scheme that has passed the evaluation in a knowledge base for continuous optimization of the control strategy library.

[0015] Furthermore, the process of simultaneously cutting multiple sensor units according to the control strategy and performing post-cutting processing to complete the mass production of flexible tactile sensors includes: configuring a multi-station parallel cutting system according to the control strategy to achieve simultaneous cutting of multiple sensor units; monitoring the cutting quality in real time, establishing a closed-loop process flow of cutting-detection-adjustment to ensure consistent mass production quality.

[0016] Furthermore, the post-cutting processing to achieve mass production of flexible tactile sensors includes: using plasma cleaning or micro-thermal treatment technology to optimize the physical and chemical properties of the cut edges of the sensor units cut by the multi-station parallel cutting system; and using a full-process digital management system to achieve full-process data acquisition, analysis, and traceability of flexible materials to achieve mass production of high-quality flexible tactile sensors.

[0017] This invention also provides a laser cutting optimization system for the mass production of flexible tactile sensors, comprising:

[0018] A multi-beam laser collaborative cutting unit is used to acquire flexible material property data, and an ultrafast laser cutting unit and a thermal annealing laser unit are configured according to the flexible material property data to generate a cutting beam and a thermal annealing beam.

[0019] A plasma auxiliary unit is used to generate plasma through a plasma generator and guide the plasma to the laser cutting area to improve laser energy absorption efficiency.

[0020] A distributed state observation unit is used to collect temperature field distribution, plasma density distribution and cutting front shape data during the cutting process, and to estimate the state parameters of the cutting process based on the temperature field distribution, plasma density distribution and cutting front shape data;

[0021] The parameter co-optimization unit is used to dynamically adjust the energy, frequency, and relative position of the cutting beam and the thermal annealing beam, as well as the density and temperature of the plasma, based on the cutting process state parameters.

[0022] The cutting quality assessment unit is used to acquire cutting edge images, assess cutting quality, obtain cutting quality assessment results, and select or reconstruct control strategies based on the cutting quality assessment results.

[0023] The mass production unit is used to simultaneously cut multiple sensor units according to the control strategy and perform post-cutting processing to complete the mass production of flexible tactile sensors.

[0024] The beneficial effects of this invention include:

[0025] 1. By combining high-energy-density ultrafast lasers with low-energy continuous lasers through multi-beam laser collaborative cutting technology, cutting and thermal annealing can be carried out simultaneously, effectively solving the edge damage problem in traditional single laser cutting;

[0026] 2. Plasma-assisted laser cutting technology is used to change the surface properties of materials by introducing specific plasma, thereby improving laser energy absorption efficiency, reducing the required laser power, and minimizing the heat-affected zone and material deformation;

[0027] 3. A distributed unknown input observer was designed, based on the theory of discrete-time linear time-invariant systems, to realize real-time monitoring and state estimation of key parameters in the cutting process, providing accurate feedback for intelligent control;

[0028] 4. A reconfigurable intelligent surface control system was constructed, which dynamically adjusts the cutting strategy based on observer feedback to achieve adaptive control for different materials and cutting requirements;

[0029] 5. A multi-parameter collaborative optimization algorithm was developed, a plasma-laser-material interaction model was established, and the parameter combination was optimized through machine learning methods to achieve a balance between cutting quality and efficiency;

[0030] 6. A batch parallel cutting process was realized. Through multi-station layout and collaborative control, multiple sensor units were cut simultaneously, which greatly improved production efficiency.

[0031] 7. A full-process digital management technology has been established to realize the collection and analysis of data throughout the entire process from material entry to finished product exit, ensuring the quality consistency and traceability of mass production. Attached Figure Description

[0032] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0033] Figure 1 This is a structural block diagram of the laser cutting optimization system for mass production of the flexible tactile sensor of the present invention;

[0034] Figure 2 This is a schematic diagram of the laser cutting optimization method for mass production of the flexible tactile sensor of the present invention;

[0035] Figure 3 This is a schematic diagram of the structure of the multi-beam laser collaborative cutting unit of the present invention;

[0036] Figure 4 This is a flowchart of the cutting quality assessment unit of the present invention;

[0037] Figure 5 This is a schematic diagram of the layout of the mass production unit of the present invention. Detailed Implementation

[0038] The technical solution of the present invention will now be clearly and completely described in conjunction with the accompanying drawings.

[0039] like Figure 1 As shown, the present invention provides a laser cutting optimization system for mass production of flexible tactile sensors, comprising: a multi-beam laser collaborative cutting unit 10, a plasma-assisted unit 20, a distributed state observation unit 30, a parameter collaborative optimization unit 40, a cutting quality evaluation unit 50, and a mass production unit 60.

[0040] The multi-beam laser collaborative cutting unit 10 is used to acquire flexible material property data, and to configure an ultrafast laser cutting unit and a thermal annealing laser unit according to the flexible material property data to generate a cutting beam and a thermal annealing beam.

[0041] Plasma auxiliary unit 20 is used to generate plasma through a plasma generator and guide the plasma to the laser cutting area to improve laser energy absorption efficiency.

[0042] The distributed state observation unit 30 is used to collect temperature field distribution, plasma density distribution and cutting front shape data during the cutting process, and to estimate the state parameters of the cutting process based on the temperature field distribution, plasma density distribution and cutting front shape data.

[0043] The parameter co-optimization unit 40 is used to dynamically adjust the energy, frequency, and relative position of the cutting beam and the thermal annealing beam, as well as the density and temperature of the plasma, based on the cutting process state parameters.

[0044] The cutting quality assessment unit 50 is used to acquire cutting edge images, assess cutting quality, obtain cutting quality assessment results, and select or reconstruct control strategies based on the cutting quality assessment results.

[0045] The mass production unit 60 is used to simultaneously cut multiple sensor units according to the control strategy and perform post-cutting processing to complete the mass production of flexible tactile sensors.

[0046] In this embodiment, the ultrafast laser cutting unit has at least two laser sources. When the ultrafast laser cutting unit is working, one of the low-power laser sources performs a single cut, reaching a cutting depth of one-third to one-half, forming a relatively flat cut surface. The remaining depth of the cut is completed by the remaining one or more laser sources. By combining the two, the problems of slow cutting speed with a single low-power light source and melting, roughness, and blackening of the cut surface with a single high-power light source are solved.

[0047] like Figure 2 As shown, in one embodiment, the laser cutting optimization method for mass production of flexible tactile sensors provided by the present invention includes the following steps:

[0048] Step S1: Obtain flexible material property data, configure an ultrafast laser cutting unit and a thermal annealing laser unit according to the flexible material property data, and generate a cutting beam and a thermal annealing beam.

[0049] In this step, a spectrometer is first used to scan the flexible material in real time, acquiring its spectral reflectance characteristics. Simultaneously, a high-resolution image sensor is used to obtain the material's surface texture and structural features. The acquired spectral data is compared with a pre-established material property database to quickly identify the type of material being processed. For the identified material, the system automatically retrieves its absorption curves for different wavelengths of laser light, thermal conductivity, and key parameters such as melting point and vaporization point, forming a targeted set of processing parameters. Based on these parameters, the system automatically matches the optimal combination of laser parameters from the laser parameter library, including wavelength, pulse width, pulse energy, and repetition frequency.

[0050] Based on the identified characteristics of the flexible material, the system automatically configures the operating parameters of the ultrafast laser cutting unit. Specifically, the system adjusts the output power, pulse repetition frequency, and pulse width of the femtosecond laser according to the material's thickness and composition, and adjusts the spatial energy distribution of the beam through a beam shaping system to ensure uniform energy density during cutting. Simultaneously, it configures the parameters of the thermal annealing laser unit based on the material's thermophysical properties, including the wavelength selection, output power, and spot size of the continuous laser. The wavelength selection of the thermal annealing laser is optimized based on the material's absorption spectrum characteristics to ensure that energy is effectively absorbed by the material, resulting in an appropriate heat treatment effect.

[0051] Precise control of each laser beam is achieved through a central optoelectronic control unit. This unit sets the timing relationship between the beams—specifically, the delay between the ultrafast laser cutting pulse and the thermal annealing laser—based on optimal parameters calculated by an optimization algorithm; adjusts the energy distribution of each beam to ensure that excessive energy does not cause excessive material damage during cutting; and controls the relative spatial position of each beam to achieve an optimal spatial configuration between the cutting and thermal annealing beams in the working area. This configuration typically involves the thermal annealing beam surrounding the cutting beam, forming a preheating-cutting-annealing spatial sequence. To achieve this precise spatial arrangement, the system uses high-precision optical mirrors and an electrically controlled displacement platform to adjust the position and angle of each beam at the micrometer level, ensuring that the cutting and thermal annealing beams work precisely in tandem.

[0052] Specifically, the process of acquiring flexible material property data and configuring an ultrafast laser cutting unit and a thermal annealing laser unit based on the flexible material property data to generate cutting beams and thermal annealing beams includes: identifying the type of flexible material through spectral analysis and image recognition technology; acquiring data on the absorption, reflection, and thermal conduction characteristics of the flexible material to lasers of different wavelengths; generating a flexible material property database; matching the optimal laser parameter combination based on the flexible material property database; configuring a femtosecond laser and a tunable wavelength continuous laser to generate the cutting beam and the thermal annealing beam; and setting the timing, energy, and spatial position of each beam through an optoelectronic control unit, adjusting the optical reflector and the electrically controlled displacement platform to achieve the coordination of the cutting beam and the thermal annealing beam.

[0053] In the specific implementation of this step, the flexible material to be processed is first scanned in real time using a multifunctional spectroscopic analysis device. This device includes a multi-band reflectance spectrometer, with a working range covering a broad spectrum from ultraviolet to far-infrared (190nm-2500nm), capable of capturing the characteristic reflection peaks of different flexible materials at various wavelengths. Simultaneously, the system is also equipped with a Raman spectrometer to obtain molecular vibrational information of the material, accurately identifying polymer types and modifiers. For composite flexible materials, the system also utilizes attenuated total reflectance (ATR) infrared spectroscopy to analyze the chemical composition of the material surface, ensuring accurate identification of multilayered materials.

[0054] Meanwhile, a high-resolution image acquisition system captures the microscopic morphology of the material surface from multiple angles. Equipped with a macro lens and an adjustable illumination array, this system can capture the texture, color, and reflective properties of the material surface under varying lighting conditions. After preprocessing, the acquired images are fed into a pre-trained deep convolutional neural network for analysis. This network, trained on a large number of flexible material samples, can identify material types from image features with an accuracy of up to 98%. The system cross-validates the results of spectral analysis and image recognition to ensure the accuracy of material type identification, especially for materials that appear similar but have different compositions.

[0055] Once the material type is determined, the system immediately retrieves a complete dataset of its properties from the database. This dataset contains key physical parameters such as the material's absorption coefficient curves for different wavelengths of laser light (from ultraviolet to far-infrared), reflectivity distribution, thermal conductivity, thermal diffusivity, and phase transition temperature. For novel materials not yet included in the database, the system activates a rapid property measurement module to obtain necessary parameters through sample testing and adds the results to the database, continuously expanding the knowledge base. The system also considers the material's thickness, number of layers, and structural characteristics to construct a three-dimensional thermal conductivity model of the material, predicting the heat distribution under laser irradiation.

[0056] Based on the acquired material property data, the optimization algorithm begins calculating the optimal combination of laser parameters. This process employs a multi-objective optimization algorithm, simultaneously considering three objectives: cutting quality, efficiency, and heat-affected zone control. The system simulates the laser-material interaction process under different parameters, calculating energy deposition distribution, thermal diffusion, and material removal efficiency. For the ultrafast laser cutting unit, the system optimizes and selects the most suitable center wavelength (typically between 1030nm and 1064nm), pulse width (typically 200-500 femtoseconds), pulse energy, and repetition frequency. For the thermal annealing laser unit, the system selects the optimal wavelength from the selectable wavelengths of the tunable wavelength continuous laser (typically covering 780nm-1550nm) based on the material's spectral absorption characteristics, and calculates the required power density and irradiation time to achieve the best thermal annealing effect.

[0057] Once the parameters are determined, the actual laser equipment is configured. For femtosecond lasers, the system sets the output power, pulse repetition rate, and compressor parameters to ensure the output pulses achieve the expected time width and energy. The laser output passes through a beam shaping system, which uses a combination of spatial light modulators and phase plates to adjust the original Gaussian distribution beam into a more uniform flat-top distribution or a specific custom energy distribution to optimize the cutting effect. The shaped beam then passes through a high-precision focusing system, which employs a specially designed multi-element lens group that can maintain a small focal point (up to 5 micrometers in diameter) while maintaining a large depth of focus, adapting to the minute undulations that may exist in flexible materials.

[0058] For the thermal annealing laser unit, a suitable wavelength is selected based on calculations, and precise wavelength output is achieved through a tunable diode laser or optical parametric oscillator. The thermal annealing beam is split into multiple paths by a beam splitting system, forming a heat treatment region surrounding the main cutting beam. Each beam is equipped with an independent power regulator and focusing optics system, enabling the system to create different thermal field distributions as needed, such as using a preheating mode in the cutting leading edge region and an annealing mode in the post-cutting region.

[0059] The most complex part is achieving precise coordination of multiple laser beams. The optoelectronic control unit, as the system's central hub, is responsible for the unified scheduling of the timing, energy, and spatial position of each beam. For timing control, the system uses a high-precision delay generator, capable of controlling the time relationship between the ultrafast laser pulse and the thermal annealing laser with picosecond-level accuracy, ensuring that the thermal annealing beam arrives in the working area within the optimal time window after the cutting beam's action. For energy control, the system employs a closed-loop feedback mechanism, monitoring the actual energy of each beam in real time and making rapid adjustments via electro-optic modulators or acousto-optic modulators to maintain the stability and precise proportion of each beam's energy.

[0060] In terms of spatial positioning control, the system employs a combination of high-precision optical mirrors and an electrically controlled displacement platform. These mirrors are driven by piezoelectric ceramics or acousto-optic deflectors, offering fast response speeds and high positioning accuracy, enabling fine-tuning of the beam position within microseconds. The electrically controlled displacement platform, driven by a linear motor, handles a wider range of position adjustments and boasts nanometer-level positioning accuracy. Through the coordinated operation of these precision mechanisms, the system achieves precise positioning and relative position adjustment of the cutting beam and the thermal annealing beam in three-dimensional space, ensuring they maintain optimal spatial configuration relationships at all times, whether in static cutting or high-speed dynamic cutting processes.

[0061] The entire configuration process is automated by the central control system, from material identification and parameter optimization to equipment configuration, requiring no manual intervention. This significantly reduces setup time and improves production efficiency. Simultaneously, the system records the parameters and results of each configuration in the material database, continuously optimizing the parameter prediction model through machine learning algorithms to improve the accuracy and efficiency of future configurations.

[0062] like Figure 3 As shown, the multi-beam laser collaborative cutting unit 10 includes: a femtosecond laser 11 for generating ultrafast laser pulses; a beam shaping system 12 for adjusting the spatial distribution of the laser beam; a high-precision focusing system 13 for focusing the laser beam onto the working area; a tunable wavelength continuous laser 14 for generating a thermally annealed beam; a beam splitting system 15 for splitting the thermally annealed beam into multiple paths; an optical path control system 16 for adjusting the relative position and angle of each beam; a photoelectric control unit 17 for controlling the timing and energy of each beam; an optical reflector 18; and an electrically controlled displacement platform 19 for precisely controlling the spatial position of the beams.

[0063] Step S2: Generate plasma using a plasma generator and guide the plasma to the laser cutting area to improve laser energy absorption efficiency.

[0064] In this step, the most suitable working gas combination is selected from the gas database based on the type of flexible material identified in the previous step. For different flexible materials, the system selects different gas compositions and proportions to generate the most suitable plasma environment for processing that material. For example, for oxygen-containing organic materials, a mixture of argon and a small amount of oxygen might be selected; while for oxygen-sensitive materials, pure argon or an argon-nitrogen mixture might be chosen. The system uses a precision gas flow controller to regulate the flow rate of each component gas, ensuring precise control of the gas mixing ratio.

[0065] After selecting a suitable working gas, the plasma generator is started. Depending on the material properties and processing requirements, the system may choose either radio frequency discharge (RF discharge) or microwave discharge technology to generate plasma. RF discharge typically operates at an industrial frequency of 13.56 MHz, suitable for generating large-area, uniform, low-temperature plasma; while microwave discharge typically operates at a frequency of 2.45 GHz, capable of generating plasma with higher energy density. By adjusting the discharge power and gas flow rate, the density and temperature parameters of the generated plasma are controlled to ensure that it both alters the material surface properties to improve laser absorption rate without causing excessive thermal damage to the material.

[0066] The generated plasma needs to be precisely guided to the laser cutting area. A designed plasma transport channel guides the plasma from the generator to the working area. This transport process is achieved through a carefully designed electrode system and magnetic field confinement, ensuring the concentration and stability of the plasma. Upon reaching the working area, the system uses a precise electromagnetic field adjustment device to fine-tune the plasma distribution, ensuring it precisely coincides with the laser cutting area. Furthermore, the system monitors the interaction between the plasma and the laser in real time, and uses a spectral analysis system to collect the emission spectrum of the working area, analyze the concentration of active particles and energy distribution in the plasma, and evaluate the energy transfer efficiency.

[0067] Based on monitored energy transfer efficiency data, the synergistic effect of plasma and laser cutting is optimized in real time. This optimization includes adjusting the plasma density distribution, changing the spatial position of the plasma relative to the laser cutting area, and adjusting the plasma composition and energy to ensure that the plasma can most effectively change the surface properties of the material, improve laser energy absorption efficiency, reduce the heat-affected zone, and improve cutting quality.

[0068] Specifically, the process of generating plasma through a plasma generator and guiding the plasma to the laser cutting area to improve laser energy absorption efficiency includes: selecting a working gas according to the type of flexible material; generating plasma in the cutting area through radio frequency discharge or microwave discharge technology; guiding the plasma through a plasma transmission channel; adjusting the discharge power and gas flow rate; and controlling the density and temperature parameters of the plasma.

[0069] Furthermore, guiding the plasma to the laser cutting region to improve laser energy absorption efficiency includes: receiving the plasma generated by the plasma generator, guiding the plasma through an electromagnetic field to ensure it coincides with the laser cutting region; monitoring the interaction between the plasma and the laser in the laser cutting region to obtain energy transfer efficiency data; and optimizing the synergistic effect between the plasma and laser cutting based on the energy transfer efficiency data.

[0070] In the actual implementation of the system, the plasma-assisted unit first receives information on the type of flexible material from the preceding unit through a material data interface. Based on a pre-established gas-material matching database, the system selects the optimal working gas combination for different types of flexible materials. For oxygen-containing polymer materials such as PET and PC, the system typically selects an argon-oxygen mixture, with the oxygen proportion controlled between 5% and 15%. This combination maintains a stable plasma state and enhances the oxidative decomposition of the material through reactive oxygen species, thereby improving cutting efficiency. For oxygen-sensitive materials such as PI and PVDF, the system selects pure argon or an argon-nitrogen mixture, with the nitrogen proportion typically between 10% and 30%, to avoid edge degradation caused by oxidation reactions. For fluoropolymer materials such as PTFE, the system uses a specially formulated helium-argon mixture, utilizing the high thermal conductivity and inert properties of helium to reduce the environmental impact of fluoride release. The system achieves precise mixing of up to four gases through a high-precision gas mixing control unit, with a mixing ratio control accuracy of ±0.5%, ensuring the stability and consistency of the gas composition.

[0071] After gas selection, the most suitable plasma generation technology is determined based on material thickness and thermal conductivity. For thin materials (<0.3mm) or heat-sensitive materials, the system preferentially uses radio frequency (RF) discharge technology, typically operating at 13.56MHz. This technology can generate uniform plasma with relatively low temperatures (2000-5000K), avoiding excessive thermal effects. For medium-thick materials (0.3-2mm), the system uses microwave discharge technology, typically operating at 2.45GHz, which can generate plasma with higher energy density (5000-8000K), providing a stronger material activation effect. For particularly thick or difficult-to-cut composite materials, the system employs RF-microwave hybrid discharge technology, combining the advantages of both methods to provide sufficient energy density while maintaining stability. The discharge chamber adopts a specially designed cavity structure, with high-temperature ceramic materials used for the inner wall and equipped with a water cooling system to ensure stability during long-term operation. The geometry of the chamber is carefully optimized to form a directional airflow channel, guiding the plasma to flow towards the cutting area. Inside the cavity, the system is equipped with a multi-point electrode array. By controlling the voltage and phase of each electrode, the spatial distribution of the plasma can be precisely controlled to generate the plasma pattern most suitable for the current cutting task.

[0072] The generated plasma needs to be guided to the cutting area through a specially designed transmission channel. This transmission channel is a multi-segment guiding structure with an internal temperature gradient design, where the temperature gradually decreases along the channel's length, reducing energy loss and compositional changes during transmission. Multiple adjustment nodes are located inside the channel, each equipped with an electromagnetic coil and a pneumatic control valve. By adjusting the electromagnetic field strength and gas flow pattern, the plasma's flow trajectory and diffusion range are precisely controlled. The channel's exit end is designed as a deformable nozzle, dynamically adjusting its shape according to changes in the cutting profile to ensure the plasma always precisely covers the cutting front area. Specifically, for high-precision cutting tasks, a focusing device is installed at the channel exit to compress the plasma into a highly directional stream with a diameter as small as 0.5 mm, suitable for the precise cutting of microstructures.

[0073] Precise control of plasma density and temperature parameters is achieved through precise discharge power control and gas flow rate regulation. The discharge power control employs fully digital power modulation technology, with an output power range of 50–2000W, adjustment accuracy better than ±5W, and a response time of less than 10ms, enabling rapid adjustment of discharge intensity based on real-time feedback. The gas flow control system utilizes a thermal mass flow controller array, with independent control of each gas, a flow rate range of 0.1–20L / min, and control accuracy better than ±1%, achieving precise regulation of the total gas flow rate and mixing ratio. Through the coordinated control of these two key parameters, the system precisely regulates the plasma density distribution (typically ranging from 10^15 to 10^17 cm^-3) and temperature gradient (core temperature 2000–10000K). Specifically, increasing the discharge power while decreasing the gas flow rate produces high-temperature, high-density plasma, suitable for thick or difficult-to-cut materials; while decreasing the power and increasing the flow rate produces lower-temperature plasma with a larger coverage area, suitable for processing heat-sensitive materials. The system dynamically adjusts these parameters based on real-time material temperature feedback and cutting progress, ensuring cutting efficiency while avoiding overheating damage.

[0074] After the plasma flows out of the transmission channel, the system's electromagnetic field guidance device takes over precise control. This device includes multiple sets of orthogonally arranged electromagnetic coils and a high-frequency electric field generator. By generating a precisely controlled electromagnetic field distribution, it applies a directional force to the charged plasma particles, adjusting their trajectory. The system employs a real-time closed-loop control strategy. Based on the plasma position and morphology information collected by a high-speed camera and spectrometer, it calculates the deviation between the current plasma distribution and the ideal state. Then, by adjusting the current magnitude and direction of each electromagnetic coil, it corrects the spatial distribution of the plasma in real time, ensuring precise alignment with the laser cutting area. In practice, the system uses multi-level electromagnetic field control, including far-field guidance, mid-field focusing, and near-field fine adjustment, achieving full-process control of the plasma from coarse to fine adjustment. Even during high-speed cutting (cutting speeds up to 500 mm / s), the system maintains dynamic synchronization between the plasma and the cutting front, with a tracking accuracy better than 0.1 mm, ensuring that the plasma always acts on the most needed area.

[0075] To ensure optimal synergy between plasma and laser, a dedicated interaction monitoring module was designed. This module includes a high-temporal-resolution spectral analysis system, a plasma diagnostic probe array, and a material temperature monitoring system. The spectral analysis system employs a combination of fiber optic array acquisition and a grating spectrometer, enabling the acquisition of emission spectra from the cutting region at microsecond-level temporal resolution, from which key parameters such as plasma temperature, electron density, and excited-state distribution are extracted. Specifically, the system monitors specific spectral line intensity ratios, such as the ratio of the 4p-4s transition line of argon atoms to the background continuous spectrum; this ratio directly reflects the efficiency of laser energy absorption and conversion by the plasma. The plasma diagnostic probe array is deployed around the cutting region to collect data such as plasma current, potential distribution, and ion flux; these data reflect the plasma activity and the strength of its interaction with the material. The material temperature monitoring system uses high-speed infrared thermography to capture the temperature field distribution and its temporal evolution in the cutting region, directly reflecting the energy deposition and conduction within the material.

[0076] These monitoring data are processed and fused in real time to form a comprehensive energy transfer efficiency dataset. The system calculates several key indicators, including the conversion efficiency of laser energy to plasma, the transfer efficiency of plasma energy to materials, the material cutting efficiency (material removal rate per unit energy input), and the spatial distribution efficiency of energy utilization. These indicators together constitute a complete description of the plasma-laser-material energy transfer chain, revealing the efficiency bottlenecks of energy flow and conversion under the current configuration. Based on these efficiency data, combined with preset optimization objectives (such as maximizing cutting speed, minimizing the heat-affected zone, or a balance between the two), the system determines the optimization direction and generates specific adjustment strategies.

[0077] Based on energy transfer efficiency data, the system enters the synergistic effect optimization stage. This process employs an adaptive optimization algorithm, comprehensively considering the complex interactions between multiple control parameters. First, the system adjusts the synergistic relationship between plasma and laser in the time domain, including plasma pretreatment time (before laser action), plasma-laser coexistence time, and plasma post-treatment time (after laser action), to find the optimal timing configuration, enabling the plasma to provide the most effective assistance at the critical moments of laser cutting. Second, the system optimizes the synergistic relationship in the spatial domain, adjusting the direction, size, and shape of the plasma flow to maximize the laser cutting effect while avoiding excessive plasma diffusion into non-cutting areas that could cause unnecessary thermal effects. Third, the system optimizes the synergistic relationship in the energy domain, adjusting the distribution ratio between laser energy and plasma energy while maintaining a constant total energy input, to find the combination with the highest energy utilization efficiency.

[0078] Through this comprehensive optimization, the optimal synergy between plasma and laser cutting can be achieved. With this optimized configuration, plasma not only significantly improves laser energy absorption efficiency (by 30%–50%), but also alters the surface chemical state of the material, reducing decomposition energy consumption. Simultaneously, the airflow effect removes debris and molten material generated during cutting, preventing edge contamination caused by redeposition. This synergistic effect allows the system to maintain or improve cutting efficiency while reducing laser power, significantly reducing the heat-affected zone (by 40%–60%) and material deformation, thereby significantly improving the cutting quality and production stability of flexible tactile sensors. The system continuously monitors and optimizes this synergistic effect to ensure optimal operating conditions regardless of changes in material properties or fluctuations in process conditions.

[0079] The plasma auxiliary unit 20 includes: a plasma generator for generating cryogenic plasma; a gas supply system for providing the required working gas; a plasma transmission channel for guiding the plasma to the cutting area; an electromagnetic field adjustment device for controlling the spatial distribution of the plasma; a density and temperature control unit for adjusting the plasma physical parameters; and a spectral analysis system for monitoring the composition and state of the plasma.

[0080] Step S3: Collect temperature field distribution, plasma density distribution and cutting front shape data during the cutting process, and estimate the cutting process state parameters based on the temperature field distribution, plasma density distribution and cutting front shape data.

[0081] In this step, multiple sensors are deployed to comprehensively monitor key parameters of the cutting process. First, a high-speed infrared thermal imager scans the cutting area in real time to acquire temperature field distribution data, achieving a temperature resolution of 0.1℃ and a spatial resolution of 50 micrometers, accurately capturing instantaneous temperature changes and spatial distribution during cutting. Simultaneously, an optical emission spectrometer monitors the intensity and distribution of the plasma emission spectrum, thereby calculating the plasma density distribution. Furthermore, the system uses a high-speed camera and structured light scanning technology to capture the shape and evolution of the cutting front in real time, analyzing cutting quality and speed. The data collected by these sensors is synchronously acquired through a high-speed data acquisition system, forming a multi-dimensional sensor dataset of the cutting process.

[0082] The acquired multidimensional sensor data first undergoes processing by a data preprocessing module. This module employs digital filtering technology to remove signal noise, performs data calibration and verification, and ensures the temporal synchronization and spatial correspondence of data from different sensors. Then, these data undergo consistency checks, identifying and removing outlier data points to ensure data validity and reliability. The processed data forms an effective monitoring data stream for subsequent state estimation.

[0083] Based on effective monitoring of the data stream, state observation equations for the cutting process are established using discrete-time linear time-invariant system theory. These equations describe the relationship between key state parameters of the cutting process (such as cutting depth, cutting speed, and heat-affected zone width) and observable signals (temperature field, plasma density, and cutting front shape). Based on these equations, a distributed unknown input observer model is constructed, which can accurately estimate the system state even in the presence of unknown disturbances and measurement noise. Using this model, the system estimates the initial state parameters of the cutting process, including the actual cutting depth, material removal rate, and heat-affected zone range.

[0084] To improve computational efficiency and robustness, the initial state parameters are decomposed into multiple subsystems, such as the cutting dynamics subsystem, the heat conduction subsystem, and the plasma influence subsystem. These subsystems are processed in parallel using a distributed computing architecture, with each subsystem responsible for estimating a specific set of state parameters. Through parallel processing, the system can complete state estimation within milliseconds, meeting the requirements of real-time control. This distributed processing approach also improves the system's fault tolerance; even if some sensor data is missing or a single observer fails, the system can still provide reliable state estimates.

[0085] Finally, the multi-source state estimation results generated by each subsystem are weighted and fused. The fusion process considers the reliability and uncertainty of each estimation result, employing an adaptive weighting method to assign higher weights to more reliable estimates. The overall reliability of the fusion result is also evaluated by calculating the estimation error covariance matrix to quantify the level of uncertainty in the state estimation. Ultimately, the system outputs high-confidence cutting process state parameters, providing accurate feedback information for subsequent parameter optimization and control.

[0086] Specifically, the acquisition of temperature field distribution, plasma density distribution, and cutting front shape data during the cutting process, and the estimation of cutting process state parameters based on the temperature field distribution, plasma density distribution, and cutting front shape data, includes: acquiring temperature field, plasma density, and cutting front shape data during the cutting process to form a multidimensional sensing dataset; receiving the multidimensional sensing dataset, performing data preprocessing and consistency checks to generate an effective monitoring data stream; establishing a state observation equation based on the effective monitoring data stream using discrete-time linear time-invariant system theory, constructing a distributed unknown input observer model, and estimating initial cutting process state parameters based on the distributed unknown input observer model; decomposing the initial cutting process state parameters into multiple subsystems, processing them in parallel through a distributed computing architecture to estimate unknown input disturbances, and obtaining multi-source state estimation results; weighted fusion of the multi-source state estimation results, evaluating the reliability of the estimation results, and outputting the cutting process state parameters.

[0087] The distributed state observation unit 30 includes: a multi-sensor acquisition module for acquiring temperature field, plasma density, and cutting front shape data during the cutting process; a data preprocessing module for data filtering and calibration; a state parameter model construction module for establishing state observation equations; a distributed computing module for decomposing state parameters into multiple subsystems for processing; a state estimation module for performing unknown input disturbance estimation; and a result evaluation and fusion module for weighted fusion of multi-source state estimation results.

[0088] Step S4: Based on the cutting process state parameters, dynamically adjust the energy, frequency, and relative position of the cutting beam and the thermal annealing beam, as well as the density and temperature of the plasma.

[0089] In this step, the system first receives cutting process status parameters from the distributed state observation unit. These parameters include key indicators such as cutting depth, cutting speed, heat-affected zone width, and material removal rate. The system then compares and analyzes these real-time status parameters with preset cutting quality standards. These quality standards are predefined based on the functional requirements and performance indicators of different flexible tactile sensors, including cutting edge roughness, maximum allowable width of the heat-affected zone, and cutting accuracy deviation range. Through comparative analysis, the system identifies parameters that need adjustment. For example, when the heat-affected zone exceeds the preset range, the system will identify the need to adjust the laser energy or thermal annealing beam parameters; when the cutting speed is insufficient, it may be necessary to adjust the plasma density or laser pulse frequency.

[0090] Based on the identified adjustment parameters, the system activates the parameter optimization module. This module first establishes a plasma-laser-material interaction model to describe the complex energy transfer and matter transformation relationships among the three. This model comprehensively considers physical phenomena such as laser energy absorption and conduction, plasma ionization and energy transfer effects, and material phase transitions and vaporization processes. The system utilizes machine learning algorithms, particularly deep reinforcement learning-based methods, to predict the cutting effect under different parameter combinations based on this model. Through training with a large amount of historical cutting data, it can quickly predict which parameter combination will produce the best cutting effect under the current material and conditions. Based on these predictions, the system generates specific parameter adjustment instructions.

[0091] Based on the generated parameter adjustment instructions, the control unit begins to execute the actual parameter adjustments. For a cutting beam, the system may adjust the laser's output power, pulse repetition frequency, and pulse width; for a thermal annealing beam, the system may adjust its energy density, spot size, and relative position; for plasma, the system may adjust the discharge power, gas flow rate, and component ratio, thereby changing the plasma's density and temperature. These adjustments are achieved through a sophisticated electronic control system with a response time in the millisecond range, ensuring adaptability to rapidly changing cutting conditions.

[0092] Specifically, the system optimizes the synergistic effects between various parameters. For example, when increasing the cutting beam energy to improve cutting efficiency, the system simultaneously adjusts the energy and position of the thermal annealing beam to compensate for any potential increase in the heat-affected zone; when changing the plasma density, the laser parameters are adjusted accordingly to maintain optimal energy absorption efficiency. This multi-parameter synergistic optimization ensures that the system improves cutting efficiency without sacrificing cutting quality.

[0093] It also records the effects of each parameter adjustment, including changes in state before and after the adjustment and improvements in cutting quality. These records are stored in a parameter optimization knowledge base to continuously improve the parameter optimization model and enhance the accuracy of future predictions. Through this closed-loop learning mechanism, the system's parameter optimization capabilities will continuously improve with usage time, enabling it to cope with increasingly complex cutting scenarios and material variations.

[0094] Specifically, the step of dynamically adjusting the energy, frequency, and relative position of the cutting beam and the thermal annealing beam, as well as the density and temperature of the plasma, based on the cutting process state parameters includes: receiving the cutting process state parameters, comparing them with preset cutting quality standards, and identifying adjustment parameter items; establishing a plasma-laser-material interaction model based on the adjustment parameter items, predicting the optimal parameter combination through machine learning algorithms, and forming parameter adjustment instructions; and controlling the energy, frequency, and relative position of the cutting beam and the thermal annealing beam, as well as the density and temperature of the plasma, according to the parameter adjustment instructions, to achieve real-time optimization of the cutting process.

[0095] In establishing the plasma-laser-material interaction model, a multiphysics coupling equation system is used to represent the relationship among the three. This model includes the laser energy transfer equation, the plasma physical parameter evolution equation, and the material thermodynamic response equation, mathematically expressed as follows:

[0096] The laser energy transfer process is described by the following formula:

[0097] E(r,t)=E0·exp(-αd)·f(r)·g(t)

[0098] Where E(r,t) represents the energy distribution at spatial location r and time t, E0 is the initial laser energy, α is the material absorption coefficient, d is the propagation distance, and f(r) and g(t) are the spatial and temporal distribution functions, respectively.

[0099] The plasma density evolution equation is adopted as follows:

[0100]

[0101] Where n is the plasma density, S is the source term (related to laser energy), αr is the recombination coefficient, and v is the plasma velocity.

[0102] The temperature field distribution of the material is determined using the heat conduction equation:

[0103]

[0104] Where ρ is the material density, c is the specific heat capacity, T is the temperature, κ is the thermal conductivity, and Q is the heat source term (related to laser energy and plasma interaction).

[0105] Based on the above model, a deep reinforcement learning algorithm is used for parameter optimization. Specifically, a Double Deep Q-Network (DDQN) structure is used, which contains two identical neural networks: a main network and a target network. Each network consists of four layers: an input layer (32 nodes), two hidden layers (64 and 32 nodes respectively), and an output layer, with ReLU as the activation function.

[0106] The state space is defined as a 17-dimensional vector, which includes the temperature values ​​of key points in the temperature field (5 points), the plasma density distribution characteristic values ​​(5 points), the cutting front shape parameters (5 characteristic points), the current cutting speed, and the current heat-affected zone width.

[0107] The action space is defined as a set of discretized parameter adjustments, including cutting beam energy (5 levels), thermal annealing beam energy (5 levels), relative position of the two beams (3 configurations), and plasma density (3 levels), for a total of 225 combinations.

[0108] The reward function is designed as follows:

[0109] Among them, Q cut For the cutting quality rating (0-10), W HAZ T represents the width of the heat-affected zone. process For processing time, S edge For edge smoothness, w1 to w4 are weighting coefficients.

[0110] Training data was acquired through two channels: first, high-quality samples, approximately 1000 parameter-effect pairs, were selected from historical cutting records; second, the state-action-reward sequence was recorded during each actual cutting process through online learning. An experience replay mechanism was adopted, maintaining a replay buffer with a capacity of 10000, and 256 batches were randomly sampled for parameter updates during each training session.

[0111] The Adam optimizer was used during training, with an initial learning rate of 0.001 and a learning rate decay strategy. To balance exploration and exploitation, an ε-greedy strategy was employed, with ε initially set at 0.9 and linearly decaying to 0.05 during training. The model was trained for at least 50,000 steps, and convergence was considered achieved when the average reward increase was less than 1% over 5,000 consecutive steps.

[0112] The parameter co-optimization unit 40 includes: a parameter comparison module 41, used to compare state parameters with quality standards; an interaction model construction module 42, used to establish a plasma-laser-material interaction model; a machine learning optimization module 43, used to predict the optimal parameter combination; a parameter control execution module 44, used to execute parameter adjustment instructions; and a parameter history record module 45, used to store parameter optimization records to support system learning.

[0113] Step S5: Acquire the cutting edge image, evaluate the cutting quality, obtain the cutting quality evaluation result, and select or reconstruct the control strategy based on the cutting quality evaluation result.

[0114] In this step, edge images of the cut area are acquired using high-resolution industrial cameras. These cameras are equipped with specialized optical systems capable of capturing detailed features of the cut edges from multiple angles and under varying lighting conditions. The acquired raw images undergo preliminary processing by an image processing system, including image enhancement, noise removal, and contrast adjustment to highlight the features of the cut edges. Advanced edge detection algorithms, such as the Canny algorithm or deep learning-based edge detection networks, are applied to extract precise edge contours from the processed images. These algorithms can identify sub-pixel-level edge locations, ensuring detection accuracy down to the micrometer level. After edge detection, the geometric properties of the edges, such as straightness, smoothness, and microstructure, are further analyzed to comprehensively evaluate the quality of the cut edges.

[0115] The extracted edge quality data is compared with preset standard quality templates. These standard templates are the optimal set of edge features obtained under ideal cutting conditions, representing the highest quality level achievable under specific materials and cutting parameters. The comparison process employs a multi-index comprehensive scoring mechanism, quantifying the gap between the current cutting quality and the standard from multiple dimensions such as edge smoothness, perpendicularity, heat-affected zone width, and microcrack density. The system weights and synthesizes the scores from these dimensions to calculate a comprehensive cutting quality score, reflecting the overall level of the current cutting quality.

[0116] The system receives a cutting quality score and compares it to a preset quality score threshold. This threshold represents the minimum quality standard required to meet product functional requirements. If the score is below the threshold, the system marks the current cutting quality as unacceptable and requires adjustment of the control strategy. If the score exceeds the threshold but is still far from the optimal score, the system marks the current cutting as acceptable but with room for optimization. If the score is close to the optimal score, the system confirms the effectiveness of the current control strategy. Based on this judgment, a specific control decision request is generated, clarifying whether a minor adjustment to the current strategy is needed, or whether a new control strategy needs to be selected or reconstructed.

[0117] Based on the control decision request, a pre-defined control strategy library is queried. This library contains a set of control strategies for different materials, cutting conditions, and quality requirements. Each strategy consists of a series of specific operating parameters and control rules. A similar case retrieval algorithm is used to find the control strategy in the library that best matches the current situation. If no perfectly matching strategy is found, or if the current quality score is particularly low, a strategy reconstruction module is activated. This module creates a new control strategy by combining effective elements from existing strategies or introducing new control concepts. This reconstruction process is based on machine learning algorithms, enabling the extraction of successful experiences from historical data and avoiding the repetition of previous errors.

[0118] The generated cutting control scheme undergoes internal evaluation by the system. Simulations predict the scheme's potential effects under current conditions, calculating the risks and expected benefits of its implementation. If the evaluation results indicate that the scheme effectively improves cutting quality and the risks are manageable, the system marks it as a passed cutting control scheme, ready for implementation in the next cutting cycle. Simultaneously, this scheme and its evaluation results are stored in the control knowledge base as a reference for future decisions. This continuous learning and updating mechanism ensures that the control strategy library can be continuously optimized to adapt to new material properties and cutting requirements.

[0119] Specifically, the steps of acquiring the cutting edge image, evaluating the cutting quality, obtaining the cutting quality evaluation result, and selecting or reconstructing a control strategy based on the cutting quality evaluation result include: acquiring the cutting edge image, applying an edge detection algorithm to extract edge features, and acquiring edge quality data; receiving the edge quality data, comparing it with a preset standard quality template, and calculating a cutting quality score; receiving the cutting quality score, determining whether it reaches a preset quality score threshold, and forming a control decision request; querying a preset control strategy library based on the control decision request, selecting the most matching control strategy or reconstructing a new control strategy, and generating a cutting control scheme; evaluating the cutting control scheme, obtaining a cutting control scheme that has passed the evaluation, and storing the cutting control scheme that has passed the evaluation in a knowledge base for continuous optimization of the control strategy library.

[0120] In the specific implementation of the cutting quality assessment process, a high-precision image acquisition device is first used to acquire microscopic images of the cutting edge. This device consists of multiple collaborative imaging systems, including a high-resolution industrial camera, a microscope objective lens group, and a professional lighting system. The camera uses a global shutter CMOS sensor with a pixel size of less than 2μm and a resolution of over 20 million pixels, ensuring the capture of micron-level edge details. The microscope objective lens group provides variable magnification of 5-50x to adapt to different precision requirements in various inspection scenarios. The lighting system employs a multi-angle, multi-wavelength combined lighting scheme, including a ring LED light source, a structured light projector, and a laser confocal light source, which can highlight various defect features of the cutting edge under different angles and conditions, such as microcracks, melt residue, and heat-affected coloration areas. In addition, the system is equipped with a 3D contour scanner, which uses white light interferometry or laser triangulation principles to acquire 3D morphological data of the cutting edge with a resolution of up to 50nm, providing accurate data for edge perpendicularity and roughness analysis.

[0121] The acquired raw image data first undergoes a series of preprocessing steps. An adaptive histogram equalization algorithm is applied to improve image contrast, making edge features more prominent. Then, nonlocal mean filtering or wavelet transform denoising methods are used to effectively suppress image noise while preserving edge details. Next, geometric correction is performed to eliminate distortion caused by lens distortion and viewing angle differences. Finally, multiple images are registered and fused, integrating image information acquired under different lighting conditions and angles into an enhanced synthetic image, providing comprehensive visual information for subsequent analysis. For 3D contour data, the system applies point cloud filtering and surface reconstruction algorithms to generate a high-precision 3D edge model.

[0122] The preprocessed image data is fed into the edge feature extraction module. This module first applies an improved Canny edge detection algorithm, adaptively selecting the optimal threshold parameter to accurately identify the contour line of the cut edge. Then, the system extracts various quantitative feature parameters along the identified edge contour: calculating the edge roughness index and spectral characteristics through Fourier analysis and wavelet transform; measuring the edge linearity deviation and local undulations through morphological analysis; identifying the density and distribution of microcracks and stress traces through texture analysis; assessing the extent and degree of the heat-affected zone through color analysis; and calculating the edge perpendicularity, tilt angle, and surface roughness Ra value through three-dimensional data analysis. In addition, the system detects specific edge defects, such as molten beads, spatter, and incomplete cut areas, and records their location, size, and density. These extracted feature parameters collectively constitute a multi-dimensional data description of the edge quality, comprehensively reflecting all aspects of the cutting quality.

[0123] After receiving this edge quality data, a scientific comparison is performed with preset standard quality templates. These standard templates are pre-established quality reference standards for different types of flexible materials, thicknesses, and application scenarios, representing the optimal cutting quality achievable under ideal conditions. The comparison process employs a multi-level weighted scoring mechanism: First, the system normalizes the deviation of each feature parameter from its corresponding standard value into a score within the range of 0-1; then, based on the varying sensitivity of different application scenarios to quality features, the system assigns different weight coefficients to each feature parameter. For example, for tactile sensor electrodes requiring high conductivity, edge smoothness and heat-affected zone control receive higher weights; while for structural components requiring high flexibility, microcrack control and stress distribution receive higher weights. The system calculates a comprehensive cutting quality score using a weighted summation method and generates a quality analysis report in radar chart format, visually displaying the scores of each indicator and helping operators understand the current strengths and weaknesses of the cutting quality.

[0124] After the quality score is calculated, the system immediately compares it with preset quality score thresholds. These thresholds are divided into multiple levels, corresponding to different product quality requirements, ranging from the most basic functional availability level to the most stringent high-precision application level. The judgment process not only considers the overall score but also checks whether key characteristic parameters meet minimum requirements. For example, even if the overall score is high, if there are penetrating microcracks, it will still be judged as unqualified. Based on the comparison results, the system will generate specific control decision requests: if the overall score is below the minimum threshold, the system will generate an "emergency adjustment" request, requiring the current cutting to be stopped immediately and significant parameter adjustments to be made; if the score is between the minimum threshold and the ideal threshold, the system will generate an "optimization adjustment" request, suggesting fine-tuning of parameters while maintaining production continuity; if the score reaches or exceeds the ideal threshold, the system will generate a "maintain current" request, confirming the validity of the current cutting parameters. In addition, the system will also analyze the current quality trend based on historical data. If a gradual decline in quality is detected, even if it has not yet fallen below the threshold, an early warning signal will be issued, suggesting preventative adjustments.

[0125] Upon receiving a control decision request, the system queries a pre-defined control strategy library, one of the core knowledge bases of the system. This library contains a set of strategies for dealing with various materials, cutting problems, and quality deviations. These strategies are empirical rules summarized by the system through extensive experimental and production data analysis. Each strategy includes clearly defined applicable conditions, parameter adjustment schemes, and expected effects. The query process employs a hybrid approach of case-based reasoning (CBR) and fuzzy matching: First, the system selects a set of candidate strategies from the strategy library based on the current material type, cutting conditions, and quality problem characteristics. Then, it calculates the matching degree between each candidate strategy and the current situation, considering multiple factors such as material similarity, quality problem similarity, and process condition similarity. Finally, it selects the strategy with the highest matching degree as the basic solution. If the highest matching degree is lower than a preset threshold, indicating that there are not enough readily available matching strategies in the strategy library, the system will activate the strategy reconstruction module. Based on genetic algorithms or reinforcement learning methods, it extracts effective elements from multiple related strategies and combines them to form a new control strategy. This strategy reconstruction capability enables the system to cope with unprecedented material combinations or cutting problems, demonstrating strong adaptability.

[0126] The selected or reconfigured control strategy is further refined and specified to form an executable cutting control scheme. This scheme includes several aspects: laser parameter adjustment schemes, such as specific adjustment values ​​for parameters like energy, frequency, and focus position of the cutting laser and thermal annealing laser; plasma parameter adjustment schemes, such as adjustment values ​​for discharge power, gas composition, and flow rate; cutting path and speed adjustment schemes, optimizing the cutting sequence and speed curve; and special processing schemes, such as the application of techniques like pre-cutting and multiple scanning in specific areas. The system generates detailed execution steps and timing arrangements for the scheme to ensure a smooth transition during the adjustment process and avoid instability that may be caused by large parameter changes.

[0127] The generated cutting control scheme is not immediately put into use, but first enters the evaluation phase. The system first predicts the possible effects of the scheme after implementation using an internal simulation model. This simulation model, based on a combination of physical principles and machine learning, can simulate the laser-material interaction process and cutting results under different parameters. Through simulation, the system can estimate the expected quality improvement of the scheme and potential risks, such as the risk of thermal damage due to excessive energy input. The system also evaluates the operational feasibility, resource requirements, and impact on production efficiency of the scheme. If the evaluation results show that the scheme can effectively improve the current quality problems, the risks are controllable, and it will not significantly affect production efficiency, the system will mark it as a "passed evaluation" cutting control scheme, ready for implementation in the next production cycle.

[0128] Finally, the evaluated cutting control schemes and their underlying decision-making logic are stored in a knowledge base. This storage process not only records the specific parameters of the scheme, but also includes the characteristics of quality problems that trigger the scheme, the theoretical basis of the scheme, the expected effects, and the feedback after actual implementation. The system regularly analyzes these historical records to evaluate the success rate and effectiveness stability of different strategies under different conditions, providing a basis for strategy rating and optimization. Through this continuous learning and knowledge accumulation mechanism, the control strategy library will be continuously expanded and optimized, and the applicability and effectiveness of the strategies will continuously improve as the system is used for a longer period of time. This self-evolutionary capability enables the system to cope with constantly changing material types and production needs, maintaining long-term technological leadership.

[0129] In the edge feature extraction process, a multi-scale Canny edge detection algorithm combined with the deep learning edge segmentation network UNet++ is adopted. The Canny algorithm parameters are set as follows: high threshold 0.3, low threshold 0.1, and Gaussian smoothing kernel size of 5×5. The UNet++ network uses ResNet-34 as the backbone network, and the input is a 224×224 pixel edge image. Through four downsampling and upsampling operations, the final output is a fine-grained edge segmentation map of the same size.

[0130] The UNet++ network architecture specifically includes:

[0131] (1) Encoder part: 4 coding blocks, each block contains 3×3 convolution, batch normalization and ReLU activation, with the number of channels being 64, 128, 256 and 512 respectively;

[0132] (2) Decoder section: 4 decoding blocks, each block contains 3×3 convolution, batch normalization, ReLU activation and 2×2 upsampling, with the number of channels being 512, 256, 128 and 64 respectively;

[0133] (3) Skip connections: Add dense connections between corresponding levels to enhance feature fusion;

[0134] (4) Output layer: 1×1 convolution maps the feature map to a binary edge map.

[0135] The network was pre-trained on a medical image segmentation dataset and then fine-tuned on 2000 labeled cutting edge images using transfer learning. Training employed a combined loss function.

[0136] Loss=0.7·Dice_loss+0.3·Binary_cross_entropy

[0137] The Adam optimizer was used with an initial learning rate of 0.0001, a batch size of 8, and 100 training epochs.

[0138] The case retrieval algorithm employs a hybrid retrieval method based on K-Nearest Neighbors (KNN) and cosine similarity. First, a 10-dimensional feature vector is extracted from the current edge quality data, including parameters such as average roughness, maximum roughness, edge perpendicularity, and microcrack density. Then, the cosine similarity between this vector and the feature vectors of each case in the strategy library is calculated.

[0139] similarity(A,B)=(A·B) / (||A||·||B||)

[0140] Where A is the current feature vector and B is the feature vector of the cases in the library.

[0141] The K most similar cases (K initially set to 5) are selected, and the final control strategy is determined by weighted voting, with the weights proportional to the similarity values. When the highest similarity among all candidate cases falls below 0.75, a control strategy reconstruction mechanism is triggered.

[0142] The control policy reconstruction process employs a combination of deep reinforcement learning and genetic algorithms. First, high-performance policies from the existing policy library are considered as the initial population, with each policy consisting of a set of control rules and parameters. Then, new candidate policies are generated through crossover and mutation operations. The evaluation function is designed as follows:

[0143] F=w1·predicted_quality+w2·robustness-w3·complexity

[0144] Where predicted_quality is the prediction quality score, robustness is the policy robustness score, and complexity is the policy complexity.

[0145] The knowledge base is organized using a graph database structure, where each node represents a control strategy, and edges between nodes represent the evolution or combination relationships between strategies. The indexing mechanism employs a multi-level structure: the first level is indexed by material type, the second by cutting shape features, and the third by quality requirement level. Retrieval utilizes multi-path parallel search to improve matching efficiency. The knowledge base achieves high availability through distributed storage and incorporates periodic compression and optimization mechanisms to ensure performance stability during long-term use.

[0146] like Figure 4As shown, the cutting quality assessment unit 50 includes: an image acquisition module 51 for acquiring cutting edge images; a feature extraction module 52 for extracting features using an edge detection algorithm; a quality scoring module 53 for calculating cutting quality scores; a decision request module 54 for generating control decision requests; a strategy selection module 55 for selecting or reconstructing strategies from a control strategy library; a scheme evaluation module 56 for evaluating cutting control schemes; and a knowledge base management module 57 for storing and optimizing control strategies.

[0147] Step S6: According to the control strategy, multiple sensor units are cut simultaneously, and post-cutting processing is performed to complete the mass production of flexible tactile sensors.

[0148] In this step, a multi-station parallel cutting system is first configured based on the approved control strategy. This system employs a modular design, comprising multiple independent laser cutting workstations, each equipped with a complete multi-beam laser collaborative cutting unit and a plasma-assisted unit. Specific cutting tasks and parameter settings are assigned to each workstation according to the control strategy, optimizing task allocation between workstations while considering differences in material properties, cutting shape complexity, and quality requirements. The system also coordinates the work rhythm of each workstation to achieve continuous, assembly-line production, maximizing overall capacity.

[0149] During parallel cutting, a quality monitoring subsystem distributed across each workstation monitors the status and quality of each cutting process in real time. These subsystems collect data on the temperature field, plasma state, and cutting front shape during the cutting process and feed this data directly to the central control system. Based on this real-time feedback, the central control system dynamically adjusts the cutting parameters of each workstation to maintain the stability and consistency of the cutting process. When an abnormality in the cutting quality of a workstation is detected, the relevant parameters are immediately adjusted, or in severe cases, the cutting task of that workstation is suspended pending manual intervention to prevent the production of a large number of defective products.

[0150] This real-time monitoring and adjustment mechanism establishes a complete closed-loop process flow for cutting, inspection, and adjustment. In this process, the output quality of each cutting unit is evaluated in real time, and the evaluation results directly influence the next parameter adjustment decision, forming closed-loop control. This closed-loop process flow ensures that even with fluctuations in material properties or changes in environmental conditions, the system can maintain stable cutting quality, achieving consistent quality in mass production.

[0151] For the sensor units that have been cut, post-cutting processing is performed. Depending on the specific material properties and product requirements, the system may choose plasma cleaning or micro-heat treatment technology to optimize the physical and chemical properties of the cut edges. Plasma cleaning technology uses low-temperature plasma to remove particulate residues and organic contaminants from the cut edges, improving edge cleanliness; micro-heat treatment technology uses precisely controlled localized heating to release residual stress introduced during the cutting process, preventing edge cracking during subsequent use. These post-processing processes are completed through specially designed workstations, forming a continuous production line with the cutting workstation.

[0152] The entire mass production process is coordinated and monitored by a fully digital management system. This system enables data collection, analysis, and traceability throughout the entire process, from raw material input to finished product output. Each sensor unit is assigned a unique digital identifier, and all parameter settings, quality monitoring data, and post-processing records during the production process are associated with this identifier, forming a complete digital twin record. This end-to-end data management not only supports quality control during production but also provides powerful tools for product quality traceability and problem analysis, meeting the needs of high-end medical, aerospace, and other application fields with stringent requirements for product traceability.

[0153] Specifically, the process of simultaneously cutting multiple sensor units according to the control strategy and performing post-cutting processing to complete the mass production of flexible tactile sensors includes: configuring a multi-station parallel cutting system according to the control strategy to achieve simultaneous cutting of multiple sensor units; monitoring the cutting quality in real time, establishing a closed-loop process flow of cutting-detection-adjustment to ensure consistent mass production quality.

[0154] Furthermore, the post-cutting processing to achieve mass production of flexible tactile sensors includes: using plasma cleaning or micro-thermal treatment technology to optimize the physical and chemical properties of the cut edges of the sensor units cut by the multi-station parallel cutting system; and using a full-process digital management system to achieve full-process data acquisition, analysis, and traceability of flexible materials to achieve mass production of high-quality flexible tactile sensors.

[0155] like Figure 5 As shown, the mass production unit 60 includes: a multi-station parallel cutting system 61 for simultaneously cutting multiple sensor units; a quality monitoring system 62 for real-time monitoring of cutting quality; a closed-loop process control system 63 for establishing a cutting-inspection-adjustment closed-loop process; a post-processing system 64 for plasma cleaning or micro-thermal treatment of the cut sensor units; and a digital management system 65 for realizing full-process data acquisition and analysis.

[0156] In another embodiment of the present invention, the laser cutting optimization system for mass production of the flexible tactile sensor includes: a multi-beam laser collaborative cutting unit for acquiring flexible material characteristic data, configuring an ultrafast laser cutting unit and a thermal annealing laser unit according to the flexible material characteristic data, and generating a cutting beam and a thermal annealing beam; a plasma auxiliary unit for generating plasma through a plasma generator and guiding the plasma to the laser cutting area to improve laser energy absorption efficiency; a distributed state observation unit for collecting temperature field distribution, plasma density distribution, and cutting front shape data during the cutting process, and estimating cutting process state parameters based on the temperature field distribution, plasma density distribution, and cutting front shape data; a parameter collaborative optimization unit for dynamically adjusting the energy, frequency, and relative position of the cutting beam and the thermal annealing beam, as well as the density and temperature of the plasma, based on the cutting process state parameters; a cutting quality evaluation unit for acquiring cutting edge images, evaluating cutting quality, obtaining cutting quality evaluation results, and selecting or reconstructing control strategies based on the cutting quality evaluation results; and a mass production unit for simultaneously cutting multiple sensor units according to the control strategy and performing post-cutting processing to complete the mass production of the flexible tactile sensor.

[0157] Although specific embodiments of the present invention have been described above, these descriptions are not intended to limit the scope of protection of the present invention. Those skilled in the art can make modifications or equivalent substitutions to the above embodiments without departing from the design concept of the present invention, and all such modifications or equivalent substitutions are within the scope of protection of the present invention.

Claims

1. A laser cutting optimization method for mass production of flexible tactile sensors, characterized in that, include: Acquire flexible material property data, configure an ultrafast laser cutting unit and a thermal annealing laser unit based on the flexible material property data, and generate a cutting beam and a thermal annealing beam; Plasma is generated by a plasma generator and guided to the laser cutting area to improve laser energy absorption efficiency. The temperature field distribution, plasma density distribution, and cutting front shape data of the cutting process are collected, and the cutting process state parameters are estimated based on the temperature field distribution, plasma density distribution, and cutting front shape data. Based on the cutting process state parameters, the energy, frequency, and relative position of the cutting beam and the thermal annealing beam, as well as the density and temperature of the plasma, are dynamically adjusted. Acquire cutting edge images, evaluate cutting quality, obtain cutting quality evaluation results, and select or reconstruct control strategies based on the cutting quality evaluation results; According to the control strategy, multiple sensor units are cut simultaneously, and post-cutting processing is performed to complete the mass production of flexible tactile sensors. The acquisition of temperature field distribution, plasma density distribution, and cutting front shape data during the cutting process, and the estimation of cutting process state parameters based on the temperature field distribution, plasma density distribution, and cutting front shape data, including: Collect temperature field, plasma density, and cutting front shape data during the cutting process to form a multidimensional sensing dataset; Receive the multidimensional sensor dataset, perform data preprocessing and consistency verification, and generate an effective monitoring data stream; Based on the effective monitoring data stream, a state observation equation is established using the discrete-time linear time-invariant system theory, a distributed unknown input observer model is constructed, and the initial cutting process state parameters are estimated based on the distributed unknown input observer model. The initial cutting process state parameters are decomposed into multiple subsystems and processed in parallel through a distributed computing architecture to estimate unknown input disturbances and obtain multi-source state estimation results. The multi-source state estimation results are weighted and fused to evaluate the reliability of the estimation results and output the state parameters of the cutting process.

2. The laser cutting optimization method for mass production of flexible tactile sensors according to claim 1, characterized in that, The process of acquiring flexible material property data, configuring an ultrafast laser cutting unit and a thermal annealing laser unit based on the flexible material property data, and generating a cutting beam and a thermal annealing beam includes: By using spectral analysis and image recognition technology to identify the types of flexible materials, data on the absorption, reflection, and thermal conductivity characteristics of flexible materials to different wavelengths of laser light are obtained, and a database of flexible material properties is generated. Based on the flexible material property database, the optimal combination of laser parameters is matched, and a femtosecond laser and a tunable wavelength continuous laser are configured to generate the cutting beam and the thermal annealing beam. The timing, energy, and spatial position of each beam are set by the photoelectric control unit, and the optical reflector and the electrically controlled displacement platform are adjusted to achieve the coordination of the cutting beam and the thermal annealing beam.

3. The laser cutting optimization method for mass production of flexible tactile sensors according to claim 2, characterized in that, The process of generating plasma via a plasma generator and guiding the plasma to the laser cutting area to improve laser energy absorption efficiency includes: The working gas is selected according to the type of flexible material, and plasma is generated in the cutting area through radio frequency discharge or microwave discharge technology. The plasma is guided through a plasma transmission channel, and the discharge power and gas flow rate are adjusted to control the density and temperature parameters of the plasma.

4. The laser cutting optimization method for mass production of flexible tactile sensors according to claim 3, characterized in that, The step of guiding the plasma to the laser cutting region to improve laser energy absorption efficiency includes: The plasma generated by the plasma generator is received, and the plasma is guided by an electromagnetic field to ensure that it coincides with the laser cutting area; The interaction between the plasma and the laser in the laser cutting area is monitored to obtain energy transfer efficiency data; and based on the energy transfer efficiency data, the synergistic effect between the plasma and laser cutting is optimized.

5. The laser cutting optimization method for mass production of flexible tactile sensors according to claim 1, characterized in that, The dynamic adjustment of the energy, frequency, and relative position of the cutting beam and the thermal annealing beam, as well as the density and temperature of the plasma, based on the cutting process state parameters, includes: The system receives the cutting process status parameters, compares them with preset cutting quality standards, and identifies and adjusts the parameters accordingly. Based on the aforementioned adjustment parameters, a plasma-laser-material interaction model is established, and the optimal parameter combination is predicted using a machine learning algorithm to generate parameter adjustment instructions. According to the parameter adjustment instructions, the energy, frequency, and relative position of the cutting beam and the thermal annealing beam, as well as the density and temperature of the plasma, are controlled to achieve real-time optimization of the cutting process.

6. The laser cutting optimization method for mass production of flexible tactile sensors according to claim 1, characterized in that, The process of acquiring the cutting edge image, evaluating the cutting quality, obtaining the cutting quality evaluation result, and selecting or reconstructing a control strategy based on the cutting quality evaluation result includes: The cut edge image is acquired, and edge features are extracted using an edge detection algorithm to obtain edge quality data; Receive the edge quality data, compare it with a preset standard quality template, and calculate the cutting quality score; Receive the cutting quality score, determine whether it reaches the preset quality score threshold, and form a control decision request; Based on the control decision request, query the preset control strategy library, select the most matching control strategy or reconstruct a new control strategy, and generate a cutting control scheme. The cutting control scheme is evaluated to obtain the approved cutting control scheme, which is then stored in the knowledge base for continuous optimization of the control strategy library.

7. The laser cutting optimization method for mass production of flexible tactile sensors according to claim 1, characterized in that, The process of simultaneously cutting multiple sensor units according to the control strategy and performing post-cutting processing to achieve mass production of the flexible tactile sensor includes: According to the control strategy, a multi-station parallel cutting system is configured to enable simultaneous cutting by multiple sensor units. Real-time monitoring of cutting quality, establishing a closed-loop process of cutting-inspection-adjustment, and ensuring consistent quality in mass production.

8. The laser cutting optimization method for mass production of flexible tactile sensors according to claim 7, characterized in that, The post-cutting processing to achieve mass production of the flexible tactile sensor includes: For the sensor unit that is cut by the multi-station parallel cutting system, plasma cleaning or micro-thermal treatment technology is used to optimize the physical and chemical properties of the cut edge. Through a full-process digital management system, the entire process of flexible material data collection, analysis, and traceability can be achieved, enabling the mass production of high-quality flexible tactile sensors.

9. A laser cutting optimization system for mass production of flexible tactile sensors, characterized in that, include: A multi-beam laser collaborative cutting unit is used to acquire flexible material property data, and an ultrafast laser cutting unit and a thermal annealing laser unit are configured according to the flexible material property data to generate a cutting beam and a thermal annealing beam. A plasma auxiliary unit is used to generate plasma through a plasma generator and guide the plasma to the laser cutting area to improve laser energy absorption efficiency. A distributed state observation unit is used to collect temperature field distribution, plasma density distribution and cutting front shape data during the cutting process, and to estimate the state parameters of the cutting process based on the temperature field distribution, plasma density distribution and cutting front shape data. The parameter co-optimization unit is used to dynamically adjust the energy, frequency, and relative position of the cutting beam and the thermal annealing beam, as well as the density and temperature of the plasma, based on the cutting process state parameters. The cutting quality assessment unit is used to acquire cutting edge images, assess cutting quality, obtain cutting quality assessment results, and select or reconstruct control strategies based on the cutting quality assessment results. A mass production unit is used to simultaneously cut multiple sensor units according to the control strategy and perform post-cutting processing to complete the mass production of flexible tactile sensors. The acquisition of temperature field distribution, plasma density distribution, and cutting front shape data during the cutting process, and the estimation of cutting process state parameters based on the temperature field distribution, plasma density distribution, and cutting front shape data, including: Collect temperature field, plasma density, and cutting front shape data during the cutting process to form a multidimensional sensing dataset; Receive the multidimensional sensor dataset, perform data preprocessing and consistency verification, and generate an effective monitoring data stream; Based on the effective monitoring data stream, a state observation equation is established using the discrete-time linear time-invariant system theory, a distributed unknown input observer model is constructed, and the initial cutting process state parameters are estimated based on the distributed unknown input observer model. The initial cutting process state parameters are decomposed into multiple subsystems and processed in parallel through a distributed computing architecture to estimate unknown input disturbances and obtain multi-source state estimation results. The multi-source state estimation results are weighted and fused to evaluate the reliability of the estimation results and output the state parameters of the cutting process.

Images