Floor adhesion detection method and system

Abstract

The application provides a floor adhesion detection method and system, and relates to the technical field of detection. Through the combination of online, multi-dimensional, time-series monitoring of paint film acoustic response data and dynamic benchmark comparison based on current environmental parameters and production information, and further real-time adaptive adjustment of downstream curing equipment parameters according to the identified curing abnormal information, the problem that the traditional manual preset parameter mode cannot effectively respond to dynamic environmental fluctuations and different substrate paint combinations leading to inconsistent paint film adhesion is solved, and the effect of significantly improving production stability and product quality is achieved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of detection, in particular to a floor adhesion detection method and system. BACKGROUND

[0002] In the continuous production process of floor manufacturing, the adhesion between the paint film and the substrate is a key indicator of the durability of the floor. The size of the adhesion is directly affected by various parameters during the curing process of the paint film, such as the lamp power of the ultraviolet curing equipment, the speed of the conveyor belt, etc. Currently, after the floor substrate passes through the coating process, it is sent into a long-channel ultraviolet curing equipment by a conveyor belt, and the liquid paint film on its surface absorbs ultraviolet energy and undergoes cross-linking reaction to become a solid protective layer.

[0003] In actual production, the production line needs to handle multiple orders involving different types of wood substrates, such as oak and pine wood with different densities, porosities, and surface wettability, and different formulations of coatings, which differ in curing speed and energy threshold. To cope with this diversity, the existing technology usually requires the operator to manually consult the process guide according to the "substrate-coating" combination of each production batch, and to preset the parameters such as the ultraviolet lamp power in the curing equipment and the speed of the conveyor belt. This setting method based on static batch information can ensure product quality under ideal and stable working conditions.

[0004] However, the actual production environment is not constant. The temperature and humidity of the workshop fluctuate, which changes the moisture content of the wood substrate and the initial leveling state of the paint film before curing. For example, an increase in humidity may cause an increase in the moisture content of the substrate, which in turn affects the bonding strength of the paint film and the substrate interface; a decrease in temperature may increase the viscosity of the paint film, affecting its uniform spreading on the substrate surface and thus affecting the curing effect. These unaccounted dynamic environmental disturbances cause inconsistencies in the adhesion of the paint film even for the same batch of products, which in turn leads to some products failing to meet the expected quality standards. The existing technology lacks an effective means to monitor dynamic changes during the curing process of the paint film in real time and to adaptively adjust the curing equipment parameters based on these changes to ensure that the adhesion of the floor paint remains stable and consistent in complex and variable production environments.

[0005] There is currently no effective technical solution to the above problems. SUMMARY

[0006] The purpose of the present application is to provide a floor adhesion detection method and system that can monitor dynamic changes during the curing process of the paint film in real time and adaptively adjust the curing equipment parameters based on these changes, thereby ensuring that the adhesion of the floor paint remains stable and consistent in complex and variable production environments.

[0007] The application provides a floor adhesion detection method, comprising the steps of:

[0008] Acquiring acoustic response data of the paint film at multiple positions along the floor advancing direction inside the ultraviolet light curing channel;

[0009] Signal processing the acoustic response data of the paint film to obtain multi-dimensional acoustic characteristics of the paint film at different positions during the curing process, and constructing an acoustic response time evolution trajectory of the paint film;

[0010] Acquiring a current environmental parameter, and determining a reference range for comparison from a pre-set reference range database according to the current environmental parameter; the reference range database pre-stores standard acoustic response time evolution trajectories of paint films of different substrate paint combinations under different environmental parameters;

[0011] Comparing the acoustic response time evolution trajectory with the reference range to identify curing process abnormal information of the paint film;

[0012] According to the curing process abnormal information, calculating a correction amount of a downstream curing equipment parameter, and adjusting the downstream curing equipment parameter; the downstream is the part of the floor located after the current monitoring point or intervention point in the advancing direction inside the ultraviolet light curing channel.

[0013] Through the above scheme, the curing equipment parameter can be automatically adjusted according to the dynamic changes in the paint film curing process, so as to ensure that the adhesion of the floor paint film remains stable and consistent in the complex and changeable production environment.

[0014] Optionally, the step of acquiring acoustic response data of the paint film at multiple positions along the floor advancing direction inside the ultraviolet light curing channel comprises:

[0015] Through the acoustic sensor array deployed inside the ultraviolet light curing channel, raw acoustic signals of the acoustic response of the paint film are collected at multiple positions in the floor advancing direction, and background noise signals inside the ultraviolet light curing channel are synchronously collected through the environmental noise microphone deployed at a pre-set position inside the ultraviolet light curing channel; the acoustic sensors of the acoustic sensor array include ultrasonic transmission sensors and acoustic surface wave sensors;

[0016] According to the spectral characteristics and time domain features of the background noise signals, signal separation and noise suppression processing are performed on the raw acoustic signals to obtain denoised paint film acoustic response signals;

[0017] The denoised paint film acoustic response signals are quality evaluated, abnormal data points are identified and removed, and the paint film acoustic response data are obtained.

[0018] Through the above scheme, high-quality, high signal-to-noise ratio paint film acoustic response data can be obtained through a multi-sensor array and noise suppression technology, providing accurate and reliable input for subsequent signal processing and abnormality identification.

[0019] Optionally, the step of signal processing the paint film acoustic response data to obtain multi-dimensional acoustic characteristics of the paint film at different positions in the curing process and constructing an acoustic response time evolution trajectory of the paint film comprises:

[0020] Signal processing the paint film acoustic response data to extract acoustic wave propagation speed, acoustic wave attenuation coefficient and frequency domain spectral characteristics of the paint film at different positions in the curing process;

[0021] Combining the acoustic wave propagation speed, acoustic wave attenuation coefficient and frequency domain spectral characteristics as a multi-dimensional acoustic characteristic vector of the paint film at different positions in the curing process;

[0022] Arranging the multi-dimensional acoustic characteristic vectors of the paint film at different positions in time sequence to form the acoustic response time evolution trajectory of the paint film.

[0023] Through the above scheme, multi-dimensional acoustic characteristics of the paint film in the curing process can be comprehensively and accurately extracted, and a time evolution trajectory thereof can be constructed.

[0024] Optionally, the step of obtaining the current environmental parameters, determining the reference range for comparison from the preset reference range database according to the current environmental parameters comprises:

[0025] Real-time acquisition of environmental parameters and production information of the current production batch inside the ultraviolet light curing channel; the environmental parameters include temperature data and humidity data, and the production information includes substrate type information and coating formula information;

[0026] According to the environmental parameters and the production information, performing a matching query in the preset reference range database to obtain the standard acoustic response time evolution trajectory matching the current environmental parameters and production information;

[0027] According to the standard acoustic response time evolution trajectory and a preset deviation threshold, determining the reference range of the acoustic response time evolution trajectory.

[0028] Through the above scheme, the reference range for comparison can be dynamically determined according to real-time environmental parameters and production information, improving the accuracy and adaptability of abnormality identification.

[0029] Optionally, the step of comparing the acoustic response time evolution trajectory with the reference range to identify the curing process abnormality information of the paint film comprises:

[0030] each time point of the acoustic response time evolution trajectory is compared with the reference range point by point to obtain a deviation metric of each time point; the deviation metric includes a quantitative difference between the acoustic wave propagation speed, the acoustic wave attenuation coefficient and the frequency domain spectral feature and the reference range respectively;

[0031] According to the deviation metric, combined with a preset abnormality judgment rule, an abnormal time point in the acoustic response time evolution trajectory that exceeds the reference range is obtained;

[0032] The abnormal time point is analyzed to determine a starting time position and a duration interval of the curing process abnormality;

[0033] According to the starting time position and the deviation metric, curing process abnormality information including an abnormal type, an abnormal amplitude and an abnormal time position is generated.

[0034] Through the above scheme, the abnormal type, amplitude and time position in the curing process can be accurately identified through multi-dimensional deviation metrics and abnormality judgment rules, providing detailed basis for subsequent parameter correction.

[0035] Optionally, the abnormality judgment rule includes at least one of the following two rules:

[0036] Rule one: when any dimension of the deviation metric exceeds a preset static threshold, the corresponding time point is identified as an abnormal time point;

[0037] Or, when the deviation metric continuously exceeds a preset dynamic threshold for a plurality of consecutive time points, the time points in the corresponding continuous time interval are identified as abnormal time points;

[0038] Rule two: when the change rate of the deviation metric exceeds a preset rate threshold, the corresponding time point is identified as an abnormal time point.

[0039] Optionally, the step of analyzing the abnormal time point to determine the starting time position and the duration interval of the curing process abnormality includes:

[0040] The abnormal time point is time series scanned to identify a time position at which the abnormality first occurs in the abnormal time point as the starting time position of the curing process abnormality;

[0041] From the starting time position, the continuity of the abnormal time point is tracked in time sequence to determine the duration interval of the abnormality.

[0042] Optionally, the step of calculating a correction amount of a downstream curing equipment parameter according to the curing process abnormality information and adjusting the downstream curing equipment parameter includes:

[0043] According to the curing process abnormal information, a correction amount of the downstream curing equipment parameter is calculated through a preset control strategy, and the correction amount is converted into a control instruction and sent to the downstream curing equipment through a control interface to adjust the downstream curing equipment parameter.

[0044] Optionally, the control strategy comprises:

[0045] According to the abnormal type, an adjustment direction of the correction amount is determined;

[0046] According to the abnormal amplitude, an adjustment magnitude of the correction amount is determined;

[0047] According to the abnormal time position, an action time or an action range of the correction amount is determined.

[0048] In a second aspect, the present application provides a floor adhesion detection system, comprising:

[0049] An acquisition module is configured to acquire acoustic response data of a paint film at multiple positions along a forward direction of a floor inside an ultraviolet light curing channel;

[0050] A construction module is configured to perform signal processing on the acoustic response data of the paint film to obtain multi-dimensional acoustic characteristics of the paint film at different positions in the curing process, and to construct an acoustic response time evolution track of the paint film;

[0051] A determination module is configured to acquire a current environmental parameter, and according to the current environmental parameter, to determine a reference range for comparison from a preset reference range database; the reference range database pre-stores standard acoustic response time evolution tracks of paint films of different substrate paint combinations under different environmental parameters;

[0052] An identification module is configured to compare the acoustic response time evolution track with the reference range, and to identify curing process abnormal information of the paint film;

[0053] An adjustment module is configured to calculate a correction amount of a downstream curing equipment parameter according to the curing process abnormal information, and to adjust the downstream curing equipment parameter; the downstream is a part of the floor located after a current monitoring point or an intervention point in a forward direction inside the ultraviolet light curing channel.

[0054] From the above, the floor adhesion detection method and system provided by the application solves the problem that the traditional manual preset parameter mode cannot effectively cope with dynamic environmental fluctuations and different substrate coating combinations leading to inconsistent paint film adhesion by combining online, multi-dimensional, time-series monitoring of paint film acoustic response data with dynamic benchmark comparison based on current environmental parameters and production information, and further performing real-time adaptive adjustment on downstream curing equipment parameters according to the identified curing abnormal information, thereby achieving the effect of significantly improving production stability and product quality.

[0055] Other features and advantages of the present application will be set forth in the following description, and in part will become apparent from the description, or can be learned by practice of the present application. The objects and other advantages of the present application will be realized and attained by means of the instrumentalities particularly pointed out in the written description and the appended drawings. BRIEF DESCRIPTION OF DRAWINGS

[0056] Fig. 1 A flowchart of the floor adhesion detection method provided by the embodiment of the present application.

[0057] Fig. 2 A structural schematic diagram of the floor adhesion detection system provided by the embodiment of the present application.

[0058] Label explanation: 11, acquisition module; 12, construction module; 13, determination module; 14, identification module; 15, adjustment module. DETAILED DESCRIPTION

[0059] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the accompanying drawings of the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments. The components of the embodiments of the present application described and shown in the accompanying drawings can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the claimed present application, but only represents selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present application.

[0060] It should be noted that: similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. Meanwhile, in the description of the present application, the terms "first", "second", etc. are only used to distinguish the description, and cannot be understood as indicating or implying relative importance.

[0061] For example, assume a batch of oak substrates is coated with a specific UV-curable polyurethane coating and enters a UV-curing tunnel for curing on a continuous production line for floor manufacturing. At the beginning of production, the curing equipment parameters are set according to standard process. However, during production, the workshop ambient temperature drops while the humidity increases. This environmental change causes a slight change in the moisture content of the oak substrates and an increase in the viscosity of the polyurethane coating due to the temperature drop. In this case, the previously preset UV lamp power and conveyor belt speed, although suitable under the initial stable conditions, may result in incomplete or uneven curing of the paint film in the face of changes in the paint film viscosity and substrate moisture content. Specifically, the paint film may not achieve the expected crosslinking density, resulting in adhesion between the paint film and the substrate that is lower than the standard requirement.

[0062] If the above problems are not addressed, the paint film adhesion of the floor product will continue to be inconsistent, directly affecting the durability and service life of the product. This can lead to quality defects such as paint film peeling and cracking in actual application, thereby increasing the output rate of substandard products, causing waste of raw materials and energy. In addition, frequent quality problems will force the production line to stop for inspection or rework, reducing overall production efficiency and capacity utilization. In the long run, it may damage the manufacturer's market reputation and increase the cost of after-sales service and claims.

[0063] In the face of the above problems, the present application first recognizes the limitations of the existing manual preset parameter method, which cannot adapt to dynamically changing environmental parameters and diverse substrate coating combinations during production. In response to this, the present application thinks that relying solely on offline detection or post hoc remedies cannot effectively solve real-time curing quality problems, and therefore proposes the need for a solution that can monitor the paint film curing state in real time, online, and adaptively adjust according to actual conditions.

[0064] Please refer to Figs. 1-2 The present application provides a floor adhesion detection method and system that can monitor dynamic changes during the paint film curing process in real time and adaptively adjust the curing equipment parameters according to these changes, thereby ensuring that the adhesion of the floor paint film remains stable and consistent under complex and variable production environments.

[0065] Please refer to Fig. 1 The present application provides a floor adhesion detection method, comprising the steps of:

[0066] Obtaining paint film acoustic response data at multiple positions along the direction of floor advancement inside the UV-curing tunnel;

[0067] Signal processing the paint film acoustic response data to obtain multi-dimensional acoustic characteristics of the paint film at different positions during the curing process, and constructing an acoustic response time evolution trajectory of the paint film;

[0068] acquire a current environmental parameter, and determine a reference range for comparison from a pre-set reference range database according to the current environmental parameter; the reference range database pre-stores standard acoustic response time evolution trajectories of paint films of different substrate paint combinations under different environmental parameters;

[0069] compare the acoustic response time evolution trajectory with the reference range, and identify curing process abnormal information of the paint film;

[0070] According to the curing process abnormal information, calculate the correction amount of the downstream curing equipment parameter, and adjust the downstream curing equipment parameter; downstream is the part of the floor that is located after the current monitoring point or intervention point in the forward direction inside the ultraviolet light curing channel.

[0071] The acoustic response data of the paint film refers to the response characteristic data of the paint film to the acoustic wave in the curing process. The acoustic response time evolution trajectory refers to the continuous change curve or sequence formed by arranging the multi-dimensional acoustic features of the paint film at different positions (i.e. different curing time points) in the curing process in time sequence, which can be constructed by arranging the multi-dimensional acoustic feature vectors at different positions in time sequence. The curing process abnormal information refers to the specific data indicating that the curing process deviates from the normal state identified by comparing the acoustic response time evolution trajectory with the reference range.

[0072] Specifically, the present method aims to realize the self-adaptive adjustment of curing equipment parameters by monitoring the acoustic response of paint film during the curing process online and combining with environmental parameters, so as to solve the problem of inconsistent paint film adhesion caused by environmental fluctuations and material differences in traditional curing methods. First, the acoustic response data of the paint film is obtained at multiple positions along the forward direction of the floor inside the ultraviolet light curing channel. This process realizes online and non-contact monitoring of the curing state of the paint film. Through continuous data acquisition at multiple positions, the dynamic process of the paint film from liquid to solid state in the entire curing channel is captured, providing a continuous and comprehensive raw data basis for subsequent curing state evaluation. Then, the obtained acoustic response data of the paint film is processed to extract multi-dimensional acoustic features of the paint film at different positions during the curing process, such as sound wave propagation speed, sound wave attenuation coefficient and frequency domain spectral features. These features can more finely and comprehensively represent the changes in the physical and chemical properties of the paint film. Subsequently, the multi-dimensional acoustic features obtained at different positions are arranged in chronological order to construct the acoustic response time evolution trajectory of the paint film, so that the dynamic changes of the paint film curing process are clearly and continuously characterized, providing a quantitative basis for accurately identifying the occurrence, development and persistence of curing abnormalities. At the same time, the current environmental parameters are obtained, including temperature, humidity and other environmental data, as well as substrate types, paint formulations and other production information. According to these real-time parameters, the reference range for comparison is dynamically determined from the pre-set reference range database. This database pre-stores a large number of standard acoustic response time evolution trajectories of paint films under different environmental parameters for different substrate paint combinations, ensuring that the reference range determined is for the "ideal" curing state under the current specific production conditions, thereby effectively addressing the challenges brought by environmental fluctuations and material diversity. Subsequently, the real-time acoustic response time evolution trajectory of the paint film is compared with the dynamically determined reference range point by point or segment by segment, quantitatively identifying the deviation of the paint film curing process from the ideal state, and generating curing process abnormal information including abnormal type, abnormal amplitude and abnormal time position. Identifying these abnormal information is the premise of realizing accurate diagnosis and subsequent intervention of the curing process. Finally, according to the identified curing process abnormal information, the correction amount of the downstream curing equipment parameters is calculated using the pre-set control strategy, and these parameters are adjusted in real time. This dynamic adjustment mechanism based on real-time monitoring and abnormal analysis realizes closed-loop control and self-adaptive optimization of the curing process, which can compensate and correct in the subsequent curing stage after the problem occurs, ensuring that the paint film on the floor in the downstream curing area can achieve the expected adhesion.

[0073] In one embodiment, multiple acoustic sensor arrays are deployed inside the UV curing tunnel, for example, piezoelectric ceramic transducers as ultrasonic transmission sensors, and surface acoustic wave sensors based on interdigital transducer structure, to collect raw acoustic signals of the paint film in real time along the direction of the floor advancement. Meanwhile, ambient noise microphones are set at predetermined positions inside the tunnel to synchronously collect background noise signals. The collected raw acoustic signals are processed by a digital signal processor for signal separation and noise suppression, and the background noise is removed by existing technologies, such as adaptive filtering algorithms, to obtain the denoised acoustic response signals of the paint film. Subsequently, the denoised signals are evaluated for quality, and abnormal data points are identified and removed to obtain high-quality acoustic response data of the paint film. By extracting the acoustic wave propagation speed, acoustic wave attenuation coefficient, and frequency domain spectral features of the paint film at different curing positions, for example, the propagation speed is calculated by time domain analysis, and the attenuation coefficient and frequency spectrum distribution are obtained by frequency domain analysis. These features are combined into a multi-dimensional acoustic feature vector and arranged in chronological order to form the acoustic response time evolution trajectory of the paint film. At the same time, the environmental temperature and humidity data inside the UV curing tunnel are collected in real time by temperature and humidity sensors, and the substrate type and paint formula information of the current production batch are obtained through the production management system. According to these environmental parameters and production information, the matching query is performed in the preset reference range database to obtain the standard acoustic response time evolution trajectory that matches the current working condition, and the reference range of the acoustic response time evolution trajectory for comparison is determined in combination with the preset deviation threshold. Subsequently, the real-time acoustic response time evolution trajectory of the paint film is compared with the determined reference range at each time point. During the comparison process, the quantitative differences between the acoustic wave propagation speed, acoustic wave attenuation coefficient, and frequency domain spectral features and the reference range are calculated to form the deviation metric. According to the preset abnormality judgment rule, for example, when any dimension of the deviation metric exceeds the static threshold, or the dynamic threshold is continuously exceeded for multiple time points, or the change rate exceeds the rate threshold, the abnormal time point is identified. Through time sequence scanning and continuity tracking, the starting time position and duration interval of the curing process anomaly are determined, and the curing process anomaly information including the abnormal type, abnormal amplitude, and abnormal time position is generated. Finally, according to the generated curing process anomaly information, the preset control strategy is called. For example, if the abnormal type is under-curing, the increase amount of UV lamp power is calculated according to the abnormal amplitude; if the abnormal type is over-curing, the adjustment amount of the conveyor belt speed is calculated. The calculated correction amount is converted into a control command and sent to the downstream UV curing equipment controller through industrial Ethernet or Modbus protocol to real-time adjust the power output of the UV lamp or the running speed of the conveyor belt, thereby dynamically compensating and optimizing the curing process.

[0074] Through the above scheme, the application can realize online, dynamic and adaptive control of the floor paint film ultraviolet curing process. The method overcomes the limitations of traditional manual preset parameter method that cannot cope with environmental fluctuations and material diversity, significantly improving the consistency of paint film adhesion and product quality. Through real-time monitoring, multi-dimensional feature extraction, dynamic benchmark comparison and accurate correction of downstream equipment parameters, problems such as insufficient or excessive curing are effectively avoided, reducing the production of substandard products, improving production efficiency and yield.

[0075] In some embodiments, the step of acquiring paint film acoustic response data at multiple positions along the floor advancing direction inside the ultraviolet curing channel includes:

[0076] By deploying an acoustic sensor array inside the ultraviolet curing channel, raw acoustic signals of the paint film acoustic response are collected at multiple positions along the floor advancing direction, and background noise signals inside the ultraviolet curing channel are synchronously collected by deploying an environmental noise microphone at a preset position inside the ultraviolet curing channel, the acoustic sensors of the acoustic sensor array include ultrasonic transmission sensors and surface acoustic wave sensors;

[0077] According to the spectral characteristics and time domain features of the background noise signals, the raw acoustic signals are subjected to signal separation and noise suppression processing to obtain denoised paint film acoustic response signals;

[0078] The denoised paint film acoustic response signals are subjected to quality assessment, abnormal data points are identified and removed (applying existing technology to remove data points in the data set that are obviously deviating from the normal mode), and paint film acoustic response data are obtained.

[0079] Wherein, the acoustic sensor array refers to a collection of multiple acoustic sensors arranged in a specific configuration, which can be used to synchronously collect acoustic signals at different positions or from different directions to provide spatial or multi-point acoustic data. The ultrasonic transmission sensor refers to a sensor that uses ultrasonic waves to penetrate materials to measure their internal acoustic characteristics, which can be used to obtain the speed and attenuation information inside the material. The surface acoustic wave sensor refers to a sensor that uses surface acoustic waves to propagate on the surface of a material to sense its surface characteristics, which can be used to obtain the curing state and adhesion-related characteristics of the material surface. The environmental noise microphone refers to a microphone specifically used to collect environmental background noise, which can be used to obtain acoustic information of non-target signals.

[0080] Wherein, the signal separation and noise suppression processing refers to a technique that separates the target acoustic signal from the mixed noise and reduces the noise impact, which can be implemented using adaptive filtering, Wiener filtering or spectral subtraction algorithms, etc., which are not specifically limited here.

[0081] The quality evaluation refers to a process of checking the reliability and effectiveness of the data, for example, by calculating the signal-to-noise ratio (SNR) of the denoised paint film acoustic response signal. If the SNR is lower than a preset threshold, it is considered that the data point is of poor quality.

[0082] Specifically, in order to cope with the inevitable noise interference in the actual production environment, the scheme further synchronously collects the background noise signal inside the ultraviolet curing channel through the environmental noise microphone deployed at a preset position inside the ultraviolet curing channel. Synchronous collection of the background noise signal is the key, which enables the system to understand the noise condition of the current environment in real time, providing necessary information for subsequent noise suppression. Subsequently, according to the spectral characteristics and time domain features of the background noise signal, the original acoustic signal is subjected to signal separation and noise suppression processing to obtain a denoised paint film acoustic response signal. This step is the core of solving the noise problem. By analyzing the frequency spectrum and time domain features of the background noise, the noise component can be accurately identified and separated from the original acoustic signal, thereby effectively suppressing the noise and ensuring that the obtained paint film acoustic response signal is pure and true, avoiding the interference of noise on subsequent feature extraction and curing state judgment. Finally, the denoised paint film acoustic response signal is subjected to quality evaluation to identify and eliminate abnormal data points, obtaining the final paint film acoustic response data. Even after noise suppression, there may still be abnormal data points in the data caused by sensor failure, transient interference or other unknown factors. Quality evaluation and elimination of these abnormal points can further improve the reliability and accuracy of the data, ensuring that the data input to the subsequent signal processing link is of high quality, thereby avoiding misjudgment or false correction caused by abnormal data points, and providing a solid data foundation for the accuracy and stability of the entire floor adhesion detection method.

[0083] Through the above technical solutions, the present application can effectively cope with the complex environmental noise and interference inside the ultraviolet curing channel, significantly improving the quality and accuracy of the collected paint film acoustic response data.

[0084] In some embodiments, the step of performing signal processing on the paint film acoustic response data to obtain multi-dimensional acoustic features of the paint film at different positions during the curing process and constructing an acoustic response time evolution trajectory of the paint film includes:

[0085] The signal processing of the acoustic response data of the paint film (which can be completed by a dedicated digital signal processor (DSP) or a high-performance microcontroller unit (MCU)) extracts the sound wave propagation speed (which can be measured by the time of flight (TOF) measurement technology) and the sound wave attenuation coefficient (which can be obtained by comparing the difference between the incident energy and the outgoing energy of the ultrasonic wave signal) of the paint film at different positions in the curing process, as well as the frequency domain spectrum characteristics (such as the main frequency, bandwidth and spectrum peak value of the acoustic surface wave signal in the acoustic response data, which are obtained by performing fast Fourier transform on the acoustic surface wave signal).

[0086] The sound wave propagation speed, the sound wave attenuation coefficient and the frequency domain spectrum characteristics are combined as a multi-dimensional acoustic feature vector of the paint film at different positions in the curing process.

[0087] The multi-dimensional acoustic feature vectors of the paint film at different positions are arranged in the order of their collection time to form an acoustic response time sequence evolution trajectory of the paint film.

[0088] Specifically, first, the acoustic response data of the paint film is signal-processed to extract the sound wave propagation speed, sound wave attenuation coefficient, and frequency domain spectral features of the paint film at different positions in the curing process. This step is the core, which converts the original acoustic response signal into a quantitative feature with physical meaning. The sound wave propagation speed reflects the elastic modulus and density of the material, which will change significantly during the transition of the paint film from liquid to solid; the sound wave attenuation coefficient characterizes the energy loss of the sound wave during its propagation in the medium, which is closely related to the viscoelasticity, internal structure, and curing degree of the paint film; the frequency domain spectral features can reveal the molecular structure or micro-defects of the paint film at different curing stages. By extracting these complementary and key acoustic parameters, the curing state of the paint film can be fully described from multiple dimensions, overcoming the information deficiency or one-sidedness problem caused by a single feature, and providing rich data support for accurate judgment of the curing degree. Secondly, the sound wave propagation speed, sound wave attenuation coefficient, and frequency domain spectral features are combined as a multi-dimensional acoustic feature vector of the paint film at different positions in the curing process. This combination operation integrates the above-mentioned independent features into a unified vector representation. The construction of this multi-dimensional vector enables the state of the paint film at each time point or position to be represented by a comprehensive data point, so that the complex changes in the curing process can be captured more comprehensively and robustly. It avoids the judgment bias caused by analyzing each feature separately, and improves the completeness of the feature representation. Finally, the multi-dimensional acoustic feature vectors of the paint film at different positions are arranged in the order of their collection time to form the acoustic response time evolution trajectory of the paint film. This step organizes the discrete feature vectors according to their collection sequence inside the ultraviolet curing channel, and constructs a continuous trajectory. This trajectory dynamically shows the evolution process of the acoustic characteristics of the paint film from entering the curing channel to complete curing. Through this time-sequential representation, the dynamic change trend of the paint film curing process can be clearly observed, rather than just a static point, which is crucial for identifying the starting point, duration, and abnormal pattern of the curing process, and provides accurate time and state basis for subsequent abnormal diagnosis and equipment parameter adjustment.

[0089] By extracting the sound wave propagation speed, sound wave attenuation coefficient, and frequency domain spectral features, the state of the paint film in the curing process can be fully characterized. Combining these features into a multi-dimensional acoustic feature vector provides a more complete and robust representation of the curing process, effectively overcoming the limitations of single parameter analysis. In addition, arranging these vectors in time sequence to form the acoustic response time evolution trajectory makes dynamic monitoring of the curing process possible. This helps to accurately identify the subtle changes and deviations in the paint film curing process, ensuring that the subsequent comparison and abnormal identification steps can accurately find potential problems.

[0090] In some embodiments, the step of acquiring the current environmental parameters, and determining the reference range for comparison from the pre-set reference range database according to the current environmental parameters comprises:

[0091] Real-time collection of environmental parameters inside the ultraviolet light curing channel and production information of the current production batch; the environmental parameters include temperature data and humidity data, and the production information includes substrate type information and paint formula information;

[0092] According to the environmental parameters and the production information, a matching query is performed in the pre-set reference range database to obtain a standard acoustic response time evolution trajectory matching the current environmental parameters and the production information;

[0093] According to the standard acoustic response time evolution trajectory and the pre-set deviation threshold, the reference range of the acoustic response time evolution trajectory is determined.

[0094] Specifically, first, by real-time collection of temperature data and humidity data inside the ultraviolet light curing channel, and substrate type information (e.g. oak, pine) and paint formula information (e.g. UV-cured acrylate, polyurethane) of the current production batch, these environmental parameters and production information are the core factors affecting the curing characteristics of the paint film. Temperature and humidity directly affect the water content of the substrate and the initial leveling of the paint film, while the substrate type and the paint formula determine the inherent characteristics of the paint film curing. Real-time acquisition of such multi-dimensional information ensures the pertinence of subsequent reference selection, timely reflection, and avoids reference deviation caused by environmental fluctuations or product type differences.

[0095] Secondly, based on these real-time collected environmental parameters and production information, a matching query is performed in the pre-set reference range database. By comprehensively considering temperature, humidity, substrate type and paint formula, the ideal curing trajectory that meets the current production state can be located from the data. This multi-dimensional matching query method ensures that the standard trajectory obtained is determined according to specific conditions and can be used as a reference for the current paint film curing process.

[0096] Finally, according to the standard acoustic response time evolution trajectory obtained and the pre-set deviation threshold (the deviation threshold can be a percentage value or a fixed numerical value), the reference range of the acoustic response time evolution trajectory is determined (the reference range can be defined as the upper and lower envelope lines around the standard trajectory, which are generated by adding and subtracting the deviation threshold from the value of each time point of the standard trajectory, thus forming a dynamic reference interval allowing certain fluctuations). This step takes the matched standard trajectory as the center and combines the allowed deviation range to construct a reference interval that can change with conditions and adapt. This means that only when the actual acoustic response of the paint film deviates from the standard trajectory under this specific condition beyond the pre-set threshold, it will be identified as an anomaly.

[0097] Through the combination of the above steps, the determined reference range can reflect the paint film curing characteristics under the current production conditions. This reference provides a good basis for subsequent comparison of the actual acoustic response time evolution trajectory with the reference range, thereby significantly improving the correctness and stability of the paint film curing process anomaly identification, avoiding false positives due to normal process fluctuations or minor environmental changes, enabling anomaly identification and equipment parameter adjustment to achieve the intended purpose, thereby ensuring consistent floor adhesion quality.

[0098] In some embodiments, the step of comparing the acoustic response time evolution trajectory with the reference range to identify the curing process anomaly information of the paint film includes:

[0099] Comparing each time point of the acoustic response time evolution trajectory with the reference range point by point in time to obtain a deviation metric at each time point; the deviation metric includes the quantitative difference (e.g., represented by Euclidean distance) between the sound wave propagation speed, the sound wave attenuation coefficient, and the frequency domain spectral characteristics, respectively, and the reference range;

[0100] According to the deviation metric, in combination with a pre-set abnormal judgment rule, an abnormal time point in the acoustic response time evolution trajectory that exceeds the reference range is obtained;

[0101] Analyzing the abnormal time point to determine the starting time position and the duration interval of the curing process anomaly;

[0102] According to the starting time position and the deviation metric, generating curing process anomaly information containing anomaly type, anomaly amplitude, and anomaly time position.

[0103] Wherein, the point-by-point comparison refers to comparing the data of each sampling point or time window in the acoustic response time evolution trajectory with the data of the corresponding time point or time window in the reference range one by one (e.g., using difference calculation).

[0104] Wherein, the abnormal time point refers to a specific time marker in the acoustic response time evolution trajectory that is judged to exceed the reference range.

[0105] Specifically, to overcome the limitations of traditional general contrast, the method compares each time point in the acoustic response time evolution trajectory with the preset reference range point by point. In this comparison process, the system calculates and obtains the deviation measure of each time point, which not only covers the paint film sound wave propagation speed and sound wave attenuation coefficient, but also includes the quantitative difference between the frequency domain spectrum characteristics and the reference range. This multi-dimensional, point-by-point quantification enables a comprehensive and detailed reflection of the deviation degree of the paint film curing state, providing an objective quantitative basis for subsequent abnormality judgment. On this basis, the system uses these deviation measures and combines the preset abnormality judgment rules to automatically select the abnormal time points in the acoustic response time evolution trajectory that exceed the reference range. This solves the problem of only having quantitative differences but being unable to automatically identify abnormalities. Through intelligent judgment rules, the system can objectively identify key time points indicating curing abnormalities. Further, to more comprehensively understand the evolution process of curing abnormalities, the method analyzes the identified abnormal time points in depth to determine the starting time position of the curing process abnormality and its duration interval. By determining the start and duration of the abnormality, it can be determined whether the abnormality is a transient fluctuation or a persistent problem, providing key time dimension information for subsequent intervention. Finally, the method uses the determined starting time position and the deviation measure of each time point to generate structured curing process abnormality information. This information not only includes the type of abnormality (e.g., sound speed abnormality or attenuation coefficient abnormality), but also includes the magnitude of the abnormality (the degree of deviation from the reference) and the precise time position of the abnormality. By providing the type, magnitude, and precise time position of the abnormality, subsequent calculations of downstream curing equipment parameter correction amounts based on this information can be targeted, such as adjusting specific parameters based on the type of abnormality, determining the adjustment level based on the magnitude of the abnormality, and determining the adjustment timing based on the time position of the abnormality. This fine and multi-dimensional abnormality information significantly improves the accuracy and effectiveness of curing process control, thereby solving the problem of ambiguous abnormality information in traditional methods that makes it difficult to effectively guide correction, and providing a solid technical support for ensuring the adhesion of floor paint film.

[0106] In one specific embodiment, the method is applied to a floor UV curing production line. When the paint film is traveling in the curing tunnel, its acoustic response data is continuously acquired, and an acoustic response time evolution trajectory is constructed, which contains the sound wave propagation speed, sound wave attenuation coefficient and frequency domain spectral features of the paint film at different curing stages. At the same time, according to the current environmental parameters and production batch information, the reference range matching the current working condition is determined from the preset database. When identifying the curing process abnormality, each time point in the acoustic response time evolution trajectory of the paint film, such as the data points collected every 0.1 seconds, is compared one by one with the acoustic features of the corresponding time points in the reference range. For example, for a certain time point, if the measured sound wave propagation speed is 1200 meters / second, and the reference range is 1000±50 meters / second, then the deviation measure of the sound wave propagation speed is calculated as +200 meters / second. Similarly, the deviation measures of the sound wave attenuation coefficient and the frequency domain spectral features are also calculated, which together constitute the multi-dimensional deviation measure of the time point. Subsequently, according to these deviation measures, and in combination with the preset abnormality judgment rules, abnormal time points are identified. For example, one judgment rule can be set as: if the deviation measure of the sound wave propagation speed exceeds the preset dynamic threshold for three consecutive time points, or the deviation measure of the sound wave attenuation coefficient exceeds the preset static threshold at a single time point, then these time points are marked as abnormal. When the abnormal time points are identified, further analysis is performed on these points to determine the starting time position and duration interval of the abnormality. For example, if the continuous abnormal time points are first detected at the third meter position of the curing tunnel (corresponding to a curing time of 15 seconds), then 15 seconds is marked as the starting time position of the abnormality. If the abnormality lasts to the fourth meter position of the curing tunnel (corresponding to a curing time of 20 seconds), then the duration interval of the abnormality is determined to be 5 seconds. Finally, according to this starting time position and the deviation measures during the abnormality, structured curing process abnormality information is generated. This information can be specifically represented as: "Abnormality type: sound wave propagation speed abnormality, abnormality amplitude: maximum deviation from the upper limit of the reference range by 20%, abnormality time position: curing tunnel from the third meter to the fourth meter (curing time from 15 seconds to 20 seconds)". This detailed abnormality information can then be used to guide the parameter adjustment of the downstream curing equipment, for example, according to the type of sound wave propagation speed abnormality, it can be recommended to increase the power of the ultraviolet light, according to the amplitude of 20%, the magnitude of power increase is determined, and according to the time position of 15 seconds to 20 seconds, the corresponding region of the curing tunnel is intervened. Thus, the adhesion consistency of the final production floor paint film is ensured.

[0107] In some embodiments, the abnormality judgment rules include at least one of the following two rules:

[0108] Rule one: when any dimension in the deviation metric exceeds a pre-set static threshold (the static threshold refers to a fixed value pre-set for judging whether the deviation metric instantaneously exceeds the normal range in a certain dimension), the corresponding time point is identified as an abnormal time point;

[0109] Or, when the deviation metric continuously exceeds a pre-set dynamic threshold (the dynamic threshold refers to a value pre-set for judging whether the deviation metric continuously exceeds the normal range at consecutive time points, which can be a fixed value, but its application is based on the continuity of time series) for a plurality of consecutive time points, the time points in the corresponding continuous time period are identified as abnormal time points;

[0110] Rule two: when the change rate of the deviation metric exceeds a pre-set rate threshold, the corresponding time point is identified as an abnormal time point.

[0111] Specifically, rule one: when any dimension in the deviation metric, such as the deviation of sound wave propagation speed, instantaneously exceeds a pre-set static threshold, the corresponding time point is immediately identified as an abnormal time point. This mechanism can quickly capture the severe, instantaneous or large amplitude abnormal situation occurring in the curing process, ensuring timely response to serious deviations. Or, when the deviation metric continuously exceeds a pre-set dynamic threshold at consecutive time points, all time points in this continuous time period are identified as abnormal. This judgment method effectively avoids misjudging temporary random fluctuations as abnormal, while discovering chronic problems such as insufficient curing energy or continuous slight deviation of environmental parameters, improving the accuracy and robustness of abnormality identification.

[0112] The present application also considers the change rate of the deviation metric. When the change rate of the deviation metric (such as the deviation speed of the sound wave attenuation coefficient) exceeds a pre-set rate threshold, it can prospectively discover the rapid deterioration trend of the curing process, thereby achieving earlier intervention and avoiding further expansion of the problem.

[0113] The abnormality judgment rules of the present application can comprehensively cover different types and different development stages of curing process abnormalities, greatly improving the accuracy, sensitivity and robustness of abnormal information identification. This multi-dimensional and multi-level abnormality judgment mechanism, combined with the step of comparing the acoustic response time series evolution trajectory with the reference range to obtain the deviation metric, provides a reliable basis for subsequent accurate calculation of correction amount and adjustment of downstream curing equipment parameters, thereby effectively solving the false negative or false positive problems that may be caused by a single judgment rule in complex production environments.

[0114] In some embodiments, the step of analyzing the abnormal time points to determine the starting time position and the duration interval of the curing process abnormality comprises:

[0115] performing a time sequence scan on the abnormal time points, identifying a time position at which the abnormality first occurs in the abnormal time points as a starting time position of the curing process abnormality;

[0116] starting from the starting time position, tracing the continuity of the abnormal time points in time sequence to determine a duration interval of the abnormality duration.

[0117] In some embodiments, the step of calculating the correction amount of the downstream curing equipment parameters and adjusting the downstream curing equipment parameters according to the curing process abnormality information comprises:

[0118] The scheme is implemented by the following steps: first, performing a time sequence scan on the abnormal time points, identifying a time position at which the abnormality first occurs in the abnormal time points as a starting time position of the curing process abnormality. This technical means systematically checks the arrangement of all identified abnormal data points in time sequence, accurately capturing the precise time at which the curing process abnormality first occurs. This is crucial for timely discovering problems and avoiding further deterioration, as it provides a clear signal of the start of the problem, enabling a rapid response. By identifying the "time position at which the abnormality first occurs", the onset of a truly persistent problem can be effectively distinguished from occasional transient fluctuations, thereby improving the accuracy of abnormality judgment and the timeliness of intervention.

[0119] Second, starting from the starting time position, tracing the continuity of the abnormal time points in time sequence to determine a duration interval of the abnormality duration. After determining the starting point of the abnormality, this step further traces the continuous occurrence of abnormal points along the time axis. This not only enables us to know when the problem started, but also accurately understands how long the abnormal phenomenon lasted. Determining the "duration interval" is crucial for a comprehensive assessment of the severity and potential impact of the abnormality. For example, a short-term abnormality may only require minor adjustments, while a long-term continuous abnormality may indicate a deeper problem that requires more substantial or complex intervention measures. In this way, more comprehensive and guiding abnormal information can be provided, providing sufficient and accurate basis for subsequent correction amount calculation and control strategy formulation, ensuring that the adjustment of the downstream curing equipment is accurate and effective, thereby improving the overall performance of floor adhesion detection and control.

[0120] In some embodiments, the step of calculating the correction amount of the downstream curing equipment parameters and adjusting the downstream curing equipment parameters according to the curing process abnormality information comprises:

[0121] According to the curing process abnormality information, the correction amount of the downstream curing equipment parameters is calculated through a pre-set control strategy, and the correction amount is converted into a control instruction and sent to the downstream curing equipment through a control interface to adjust the downstream curing equipment parameters.

[0122] Specifically, the present solution first receives the curing process anomaly information generated by the preceding step. These anomaly information details the deviations occurred in the paint film curing process, including the type, magnitude, and time position of the anomaly. It is due to these detailed and quantitative anomaly information that the present solution can proceed with the subsequent precise adjustment. Based on these anomaly information, through the preset control strategy, the required correction amount of the downstream curing equipment parameters is calculated. This process is not simply the application of fixed rules, but according to the specific nature of the anomaly, the adjustment direction and magnitude are determined. This calculation based on specific anomaly information and control strategy ensures the accuracy and pertinence of the correction amount, avoids blind or empirical adjustment, and thus improves the effectiveness of the adjustment. Subsequently, the calculated correction amount is converted into control instructions that can be directly recognized and executed by the downstream curing equipment. This conversion ensures the compatibility between the control logic and the physical equipment, so that the calculation result can be actually applied. Finally, through the preset control interface, the converted control instructions are transmitted to the downstream curing equipment in real time. After receiving the instructions, the downstream curing equipment will immediately adjust its operating parameters, such as increasing or decreasing the ultraviolet light intensity, or changing the conveyor belt speed. This real-time parameter adjustment enables a rapid response to the detected curing anomaly, timely corrects the deviations in the production process, and thus ensures the curing quality of the subsequent floor paint film and improves the consistency and stability of product adhesion. The present solution is closely combined with the preceding step (for example, by comparing the acoustic response time evolution trajectory of the paint film with the reference range to identify the curing process anomaly information of the paint film) to form a complete closed-loop control. The preceding step provides accurate anomaly diagnosis, while the present solution converts the diagnosis results into actual intervention measures. This combination enables not only to find problems, but also to automatically solve problems, thereby effectively dealing with the challenges brought by environmental fluctuations and substrate coating diversity in the production process, and improving the consistency of paint film adhesion and product quality stability.

[0123] In one specific embodiment, when an abnormality is identified in the paint film curing process, for example, an abnormality is detected in which the sound wave propagation speed of the paint film in the middle section of the curing channel is lower than the reference range, and the deviation amplitude reaches 15%, which indicates that there may be a situation of insufficient curing. At this time, the correction amount of the downstream curing equipment parameters can be calculated according to the preset control strategy. The preset control strategy contains the rule of "if the curing is insufficient and the amplitude is greater than 10%, then increase the ultraviolet light power and appropriately reduce the conveyor belt speed". According to this strategy, for example, the correction amount of the ultraviolet light lamp power needs to be increased by 10%, and the conveyor belt speed needs to be reduced by 5%. Subsequently, these correction amounts can be converted into control instructions that can be recognized by the downstream curing equipment. For example, "increasing the ultraviolet light lamp power by 10%" is converted into a specific digital signal or Modbus register write instruction, and "reducing the conveyor belt speed by 5%" is converted into another corresponding instruction. These control instructions can be sent to the downstream curing equipment through the control interface. The control interface can be an industrial Ethernet interface that sends instructions to the programmable logic controller connected on the network through the TCP / IP protocol. After receiving the instructions, the programmable logic controller can immediately drive the power module of the ultraviolet light lamp to increase the output power, and adjust the frequency converter of the conveyor belt to reduce its running speed. In this way, real-time and automatic intervention in the curing process can be achieved, and the stability and consistency of the paint film curing quality can be ensured.

[0124] In some embodiments, the control strategy includes:

[0125] determining the adjustment direction of the correction amount according to the type of abnormality;

[0126] determining the adjustment level of the correction amount according to the abnormality amplitude;

[0127] determining the action time or action range of the correction amount according to the abnormality time position.

[0128] Specifically, based on the above refined control strategy, when the curing process abnormal information is identified, the information contains key data such as abnormal type, abnormal amplitude and abnormal time position. First, the adjustment direction of the correction amount is determined according to the abnormal type. For example, if the abnormal type indicates insufficient curing, the adjustment direction may point to increasing the ultraviolet light intensity or reducing the conveyor belt speed; on the contrary, if it indicates over-curing, the adjustment direction may point to reducing the ultraviolet light intensity or increasing the conveyor belt speed. This directional adjustment based on the nature of the abnormality ensures the pertinence of the correction measures. Secondly, the adjustment magnitude of the correction amount is determined according to the abnormal amplitude. This means that for a slight abnormality, a small amplitude correction amount is calculated, while for a serious abnormality, a larger amplitude correction amount is calculated. This quantitative adjustment avoids over-intervention or insufficient correction, so that the curing process can be stably restored. Finally, the action time or action range of the correction amount is determined according to the abnormal time position. For example, if the abnormality occurs in a specific area of the curing channel, the correction instruction can be accurately sent to the ultraviolet light group or conveyor belt segment corresponding to the area, or adjusted when the floor is about to enter the area. This precise action time and range enables the correction measures to be timely and targeted applied to the affected floor, avoiding unnecessary adjustment to unaffected areas, improving response efficiency and resource utilization. By comprehensively considering the three-dimensional information of abnormal type, abnormal amplitude and abnormal time position, the control strategy of the present application can generate highly customized correction amounts, so that the adjustment of downstream curing equipment parameters is no longer a simple and extensive response, but a fine and intelligent intervention. Compared with the previous scheme which only relies on preset strategy, it can more effectively correct the deviation in the curing process, ensure the consistency of paint film adhesion, and thus improve product quality.

[0129] Please refer to Fig. 2 , in a second aspect, the present application provides a floor adhesion detection system, comprising:

[0130] The acquisition module 11 is configured to acquire the acoustic response data of the paint film at a plurality of positions along the advancing direction of the floor inside the ultraviolet light curing channel.

[0131] The construction module 12 is configured to process the acoustic response data of the paint film to obtain the multi-dimensional acoustic characteristics of the paint film at different positions in the curing process, and construct the acoustic response time evolution trajectory of the paint film.

[0132] The determination module 13 is configured to acquire the current environmental parameters, and determine the reference range for comparison from the pre-set reference range database according to the current environmental parameters; the reference range database pre-stores the standard acoustic response time evolution trajectory of the paint film of different substrate paint combinations under different environmental parameters.

[0133] The recognition module 14 is configured to compare the acoustic response time evolution trajectory with the reference range to identify the curing process abnormal information of the paint film.

[0134] The adjustment module 15 is configured to calculate the correction amount of the downstream curing equipment parameter according to the curing process abnormal information, and adjust the downstream curing equipment parameter; downstream refers to the part of the floor after the current monitoring point or intervention point in the forward direction inside the ultraviolet light curing channel.

[0135] Specifically, the acquisition module 11 continuously collects the paint film acoustic response data to capture the change information of the physical state of the paint film in real time. These data are then sent to the construction module 12 for signal processing to extract multi-dimensional acoustic features and construct the acoustic response time evolution trajectory of the paint film, so as to convert the original signal into a high-dimensional feature representation with physical meaning and time continuity. At the same time, the determination module 13 acquires the current environmental parameters and production batch information in real time, and dynamically determines the reference range most matched with the current actual production conditions from the pre-set reference range database. Then, the recognition module 14 accurately compares the real-time acoustic response time evolution trajectory with the dynamically determined reference range to accurately identify the abnormal information in the curing process, including the type, amplitude and occurrence time and position of the abnormality. Finally, the adjustment module 15 receives these abnormal information, and intelligently calculates the accurate correction amount of the downstream curing equipment parameter based on the pre-set control strategy, and converts it into a control instruction to send to the downstream curing equipment to realize the real-time and automatic adjustment of the equipment parameter. This closed-loop control mechanism from real-time data acquisition, feature construction, dynamic reference matching, abnormality recognition to parameter adaptive adjustment enables the system to effectively cope with the dynamic fluctuations of the environmental parameters in the production process, ensures the consistency of the paint film adhesion, and significantly improves the intelligent level of the production line and the product qualification rate.

[0136] The floor adhesion detection system provided in this embodiment is used to perform the steps in the floor adhesion detection method provided in the first aspect, and the principle of the floor adhesion detection system provided in this embodiment is the same as that of the floor adhesion detection method provided in the first aspect, which will not be discussed in detail here.

[0137] In this document, the terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between the entities or operations.

[0138] The above only describes the embodiments of the present application and does not limit the protection scope of the present application. For those skilled in the art, the present application can have various modifications and changes. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A floor adhesion detection method characterized by, The method comprises the steps of: acquiring acoustic response data of the paint film at multiple positions along the floor advancing direction inside the ultraviolet light curing channel; processing the acoustic response data of the paint film to obtain multi-dimensional acoustic characteristics of the paint film at different positions during the curing process, and constructing an acoustic response time evolution track of the paint film; acquiring current environmental parameters, and determining a reference range for comparison from a pre-set reference range database according to the current environmental parameters; the reference range database pre-stores standard acoustic response time evolution tracks of paint films of different substrate paint combinations under different environmental parameters; comparing the acoustic response time evolution track with the reference range to identify curing process abnormal information of the paint film; calculating a correction amount of downstream curing equipment parameters according to the curing process abnormal information, and adjusting the downstream curing equipment parameters; the downstream is the part of the floor located after the current monitoring point or intervention point in the advancing direction inside the ultraviolet light curing channel; the step of acquiring acoustic response data of the paint film at multiple positions along the floor advancing direction inside the ultraviolet light curing channel comprises: acquiring original acoustic signals of the acoustic response of the paint film at multiple positions in the advancing direction of the floor through an acoustic sensor array deployed inside the ultraviolet light curing channel, and synchronously acquiring background noise signals inside the ultraviolet light curing channel through an environmental noise microphone deployed at a pre-set position inside the ultraviolet light curing channel; the acoustic sensors of the acoustic sensor array include ultrasonic transmission sensors and acoustic surface wave sensors; performing signal separation and noise suppression processing on the original acoustic signals according to the spectral characteristics and time domain features of the background noise signals to obtain denoised paint film acoustic response signals; performing quality assessment on the denoised paint film acoustic response signals, identifying and removing abnormal data points to obtain the paint film acoustic response data; the step of acquiring current environmental parameters, and determining a reference range for comparison from a pre-set reference range database according to the current environmental parameters comprises: real-time acquisition of environmental parameters inside the ultraviolet light curing channel and production information of the current production batch; the environmental parameters include temperature data and humidity data, and the production information includes substrate type information and paint formula information; performing matching query in the pre-set reference range database according to the environmental parameters and the production information to acquire the standard acoustic response time evolution track matching the current environmental parameters and production information; determining the reference range of the acoustic response time evolution track according to the standard acoustic response time evolution track and a pre-set deviation threshold.

2. The floor adhesion detection method according to claim 1, wherein the step of processing the acoustic response data of the paint film to obtain multi-dimensional acoustic characteristics of the paint film at different positions during the curing process, and constructing an acoustic response time evolution track of the paint film comprises: processing the acoustic response data of the paint film to extract the sound wave propagation speed, sound wave attenuation coefficient and frequency domain spectral characteristics of the paint film at different positions during the curing process; The sound wave propagation speed, the sound wave attenuation coefficient, and the frequency domain spectrum feature are combined as a multi-dimensional acoustic feature vector of the paint film at different positions in the curing process; The multi-dimensional acoustic feature vectors of the paint film at different positions are arranged in time sequence to form an acoustic response time evolution trajectory of the paint film.

3. The floor adhesion detection method according to claim 2, wherein The step of comparing the acoustic response time evolution trajectory with the reference range to identify the curing process abnormal information of the paint film includes: Each time point of the acoustic response time evolution trajectory is compared with the reference range point by point to obtain a deviation metric at each time point; the deviation metric includes the quantitative difference between the sound wave propagation speed, the sound wave attenuation coefficient, and the frequency domain spectrum feature and the reference range; According to the deviation metric, combined with a preset abnormal judgment rule, an abnormal time point in the acoustic response time evolution trajectory that exceeds the reference range is obtained; Analyzing the abnormal time point to determine the starting time position and the duration interval of the curing process abnormality; According to the starting time position and the deviation metric, curing process abnormal information including abnormal type, abnormal amplitude, and abnormal time position is generated.

4. The floor adhesion detection method according to claim 3, wherein The abnormal judgment rule includes at least one of the following two rules: Rule one: when any dimension of the deviation metric exceeds a preset static threshold, the corresponding time point is identified as an abnormal time point; Or, when the deviation metric continuously exceeds a preset dynamic threshold at consecutive time points, the time points in the corresponding continuous time period are identified as abnormal time points; Rule two: when the change rate of the deviation metric exceeds a preset rate threshold, the corresponding time point is identified as an abnormal time point.

5. The floor adhesion detection method according to claim 3, wherein The step of analyzing the abnormal time point to determine the starting time position and the duration interval of the curing process abnormality includes: Time sequence scanning is performed on the abnormal time point to identify the time position where the abnormality first appears in the abnormal time point as the starting time position of the curing process abnormality; From the starting time position, the continuity of the abnormal time point is tracked in time sequence to determine the duration interval of the abnormality.

6. The floor adhesion detection method according to claim 3, wherein The step of calculating the correction amount of the downstream curing equipment parameter according to the curing process abnormal information, and adjusting the downstream curing equipment parameter includes: According to the curing process abnormal information, the correction amount of the downstream curing equipment parameter is calculated through a preset control strategy; and the correction amount is converted into a control instruction and sent to the downstream curing equipment through a control interface to adjust the downstream curing equipment parameter.

7. The floor adhesion detection method according to claim 6, wherein The control strategy includes: According to the abnormal type, the adjustment direction of the correction amount is determined; According to the abnormal amplitude, the adjustment order of the correction amount is determined; According to the abnormal time position, the action time or action range of the correction amount is determined.

8. A floor adhesion detection system characterized by, It includes: An acquisition module is configured to acquire paint film acoustic response data at multiple positions along the floor advancement direction inside the ultraviolet light curing channel; An analysis module is configured to analyze the paint film acoustic response data to obtain a multi-dimensional acoustic feature vector of the paint film at different positions in the curing process; the multi-dimensional acoustic feature vector includes at least one of the following features: The sound wave propagation speed; The sound wave attenuation coefficient; The frequency domain spectrum feature. An identification module is configured to compare the acoustic response time evolution trajectory with the reference range to identify the curing process abnormal information of the paint film. An adjustment module is configured to calculate the correction amount of the downstream curing equipment parameter according to the curing process abnormal information, and adjust the downstream curing equipment parameter. The control strategy includes: According to the abnormal type, the adjustment direction of the correction amount is determined; According to the abnormal amplitude, the adjustment order of the correction amount is determined; According to the abnormal time position, the action time or action range of the correction amount is determined. The construction module is configured to perform signal processing on the paint film acoustic response data to obtain multi-dimensional acoustic characteristics of the paint film at different positions in the curing process, and to construct an acoustic response time evolution track of the paint film. The determination module is configured to obtain a current environmental parameter, and determine a reference range for comparison from a preset reference range database according to the current environmental parameter. The reference range database pre-stores standard acoustic response time evolution tracks of paint films of different substrate paint combinations under different environmental parameters. The identification module is configured to compare the acoustic response time evolution track with the reference range, and identify curing process abnormal information of the paint film. The adjustment module is configured to calculate a correction amount of a downstream curing equipment parameter according to the curing process abnormal information, and adjust the downstream curing equipment parameter. The downstream is a part of the floor located after the current monitoring point or intervention point in the advancing direction inside the ultraviolet light curing channel. The acquisition module, when acquiring the paint film acoustic response data at multiple positions in the advancing direction of the floor inside the ultraviolet light curing channel, specifically performs: The acoustic sensor array deployed inside the ultraviolet light curing channel collects original acoustic signals of the paint film acoustic response at multiple positions in the advancing direction of the floor, and the environmental noise microphone deployed at a preset position inside the ultraviolet light curing channel synchronously collects background noise signals inside the ultraviolet light curing channel. The acoustic sensors of the acoustic sensor array include ultrasonic transmission sensors and surface acoustic wave sensors. The original acoustic signals are subjected to signal separation and noise suppression processing according to the spectral characteristics and time domain features of the background noise signals, to obtain denoised paint film acoustic response signals. The denoised paint film acoustic response signals are subjected to quality assessment, and abnormal data points are identified and removed, to obtain the paint film acoustic response data. The determination module, when obtaining a current environmental parameter and determining a reference range for comparison from a preset reference range database according to the current environmental parameter, specifically performs: The environmental parameters inside the ultraviolet light curing channel and the production information of the current production batch are collected in real time. The environmental parameters include temperature data and humidity data, and the production information includes substrate type information and paint formula information. The standard acoustic response time evolution track matching the current environmental parameter and production information is obtained by matching query in the preset reference range database according to the environmental parameters and the production information. The reference range of the acoustic response time evolution track is determined according to the standard acoustic response time evolution track and a preset deviation threshold.

Images