Floor temperature and humidity detection method and system

Abstract

This application relates to the field of building environment monitoring and diagnostic technology, and provides a method and system for detecting floor temperature and humidity. The method includes continuously collecting raw data from temperature and humidity sensors pre-installed in the target floor area to obtain multi-dimensional features; obtaining physical structure change signals based on the multi-dimensional features; comparing the physical structure change signals with a pre-installed physical degradation feature pattern library; if the comparison results show a high degree of match, a potential physical problem is identified, and diagnostic information with a clear physical root cause is generated; and based on the diagnostic information, an early warning signal is triggered, and a detailed diagnostic report is generated, including the problem area, the specific physical root cause diagnosed, and recommended preventative maintenance measures. This application enables accurate detection of floor temperature and humidity information.

Description

Technical Field

[0001] This application relates to the field of building environment monitoring and diagnostic technology, and more specifically, to a method and system for detecting floor temperature and humidity. Background Technology

[0002] Inside buildings, slight inaccuracies in floor temperature and humidity information cause the building's temperature and humidity control systems to operate based on these deviations. This results in localized areas of the floor remaining in suboptimal temperature and humidity conditions for extended periods, accelerating the aging of flooring materials. Examples include wood flooring deformation, tile hollowing, or the expansion of microcracks in concrete. When these problems accumulate to a certain extent, traditional detection methods can only report the abnormal state but cannot trace the hidden process of the problem's occurrence or provide accurate, non-invasive diagnostics to determine which specific area or physical mechanism caused the problem. This leads to increased maintenance costs and may even affect the building's long-term lifespan. Summary of the Invention

[0003] This application discloses a method and system for detecting floor temperature and humidity, in order to solve the aforementioned technical problems in the prior art.

[0004] In a first aspect, this application discloses a method for detecting floor temperature and humidity, comprising the following steps:

[0005] The raw data obtained by the temperature and humidity sensors preset in the target floor area are continuously collected, and the raw data is cleaned, denoised and time-synchronized to obtain pre-processed temperature and humidity time series data.

[0006] Multidimensional feature analysis was performed on the preprocessed temperature and humidity time series data. This multidimensional feature analysis included spectrum analysis, amplitude distribution analysis, data coherence analysis, and cross-correlation analysis with related physical quantities, in order to extract the fluctuation patterns and correlation characteristics of the temperature and humidity data in different dimensions and obtain multidimensional features.

[0007] Based on these multi-dimensional characteristics, the source of the temperature and humidity measurement deviation is identified, and temperature and humidity fluctuations that do not conform to the characteristics of environmental changes or sensor drift are identified as potential signals caused by changes in the physical structure of the floor, thus obtaining the physical structure change signal.

[0008] Based on the physical structure change signal, multi-dimensional features of the physical structure change signal are obtained, and these features are compared with a pre-set physical degradation feature pattern library. This library stores multi-dimensional feature patterns of temperature and humidity data corresponding to different types of flooring materials and underlying structures during specific physical degradation processes. If the comparison results show a high degree of match, a potential physical problem is identified, and diagnostic information with a clear physical root cause is generated.

[0009] Based on this diagnostic information, an early warning signal is triggered, and a detailed diagnostic report is generated, which includes the problem area, the specific physical cause diagnosed, and recommended preventive maintenance measures.

[0010] Clearly, this solution ensures data quality and synchronization by continuously collecting raw temperature and humidity data from the floor area and performing refined preprocessing. Based on this, multi-dimensional feature analysis is performed on the preprocessed temperature and humidity time-series data, including spectrum, amplitude distribution, data coherence, and cross-correlation analysis with related physical quantities. This allows for a comprehensive and in-depth extraction of fluctuation patterns and correlation characteristics of temperature and humidity data across different dimensions. Furthermore, based on these multi-dimensional features, the source of temperature and humidity measurement deviations is intelligently identified, accurately identifying temperature and humidity fluctuations that do not conform to normal environmental changes or sensor drift characteristics as potential signals caused by changes in the floor's physical structure. Subsequently, the multi-dimensional features of these physical structure change signals are compared with a pre-set physical degradation feature pattern library containing temperature and humidity data feature patterns corresponding to different types of floor materials and underlying structures during specific physical degradation processes. Once the comparison results show a high degree of match, a potential physical problem can be identified, and diagnostic information with a clear physical root cause can be generated. Finally, based on this diagnostic information, an early warning signal is triggered, and a detailed diagnostic report containing the problem area, specific physical root cause, and recommended preventative maintenance measures is generated.

[0011] It is evident that this application can effectively distinguish between minute temperature and humidity measurement deviations caused by changes in the physical structure of the floor and environmental changes or sensor drift, thereby enabling early, accurate, and physically root-cause-oriented diagnosis of potential physical problems in the floor. This overcomes the shortcomings of existing technologies in tracing the hidden process of problems and providing accurate diagnoses, significantly reducing maintenance costs and extending the service life of buildings.

[0012] In some preferred embodiments, the multi-dimensional features of the physical structure change signal are compared with a preset physical degradation feature pattern library. This library stores multi-dimensional feature patterns of temperature and humidity data corresponding to different types of flooring materials and underlying structures during specific physical degradation processes. If the comparison results show a high degree of match, a potential physical problem is identified, and diagnostic information with a clear physical root cause is generated. This specifically includes the following steps:

[0013] Active acoustic excitation is applied to the floor, and the acoustic response data of the floor is collected;

[0014] The local acoustic impedance spectrum of the floor was constructed based on the acoustic response data;

[0015] The abnormal features of the local acoustic impedance spectrum are correlated with the multi-dimensional features of the physical structure change signal.

[0016] Based on the correlation analysis results, pattern comparison was performed in the physical degradation characteristic pattern library. This library stores acoustic impedance spectral patterns and temperature and humidity response patterns corresponding to different types of floor materials and underlying structures during specific physical degradation processes; and

[0017] If the comparison results are highly consistent, a potential physical problem is identified, and diagnostic information with a clear physical root cause is generated.

[0018] Clearly, by introducing active acoustic excitation and acoustic impedance spectroscopy analysis, this scheme can verify and supplement the structural state of the floor from another physical dimension, making the pattern comparison of physical degradation characteristics more comprehensive and accurate, significantly improving the reliability and accuracy of diagnosis, and reducing the possibility of misjudgment.

[0019] In some preferred embodiments, the anomalous features of the local acoustic impedance spectrum are correlated with the multidimensional features of the physical structure change signal, specifically including the following steps:

[0020] A time-delay correlation analysis was performed on the anomalous features of the local acoustic impedance spectrum and the multidimensional features of the physical structure change signal to identify the time lag relationship between the anomalous features and the multidimensional features.

[0021] Based on this time lag relationship, the dynamic response characteristics between the anomalous features of the local acoustic impedance spectrum and the multidimensional features of the physical structure change signal are calculated.

[0022] A contextual assessment of this dynamic response characteristic is performed, taking into account current environmental parameters and historical degradation trends; and

[0023] Based on the contextual assessment results, the physical directivity of the correlation between the anomalous features of the local acoustic impedance spectrum and the multidimensional features of the physical structure change signal is determined.

[0024] Clearly, this scheme, through time-delay correlation analysis, dynamic response characteristic calculation, and context evaluation, can delve deeper into the intrinsic physical relationship between acoustic response and temperature and humidity signals, thereby more accurately determining the physical orientation of the correlation between the two and providing a more solid physical basis for diagnosis.

[0025] In some preferred embodiments, a time-delay correlation analysis is performed between the anomalous features of the local acoustic impedance spectrum and the multidimensional features of the physical structure change signal to identify the time lag relationship between the anomalous features and the multidimensional features. This specifically includes the following steps:

[0026] Based on the current environmental parameters and the identified degradation stages, the time series of anomalous features of the local acoustic impedance spectrum and the multi-dimensional feature time series of the physical structure change signal are dynamically segmented.

[0027] For the time series of the anomalous feature and the time series of the multidimensional feature within each dynamic segment, time-varying coherence analysis is performed to identify the dynamic phase difference between the anomalous feature and the multidimensional feature at different frequencies.

[0028] Based on this dynamic phase difference, the time lag distribution between the anomaly feature and the multi-dimensional feature is constructed; and

[0029] Based on the shape of the time lag distribution and the context information of the dynamic segmentation, the time lag relationship between the abnormal feature and the multidimensional feature is determined.

[0030] Clearly, this scheme, through dynamic segmentation and time-varying coherence analysis, can more precisely capture the dynamic correlation between acoustic anomalies and temperature and humidity signals at different time periods and frequencies, thereby more accurately identifying time lag relationships and improving the accuracy and robustness of correlation analysis.

[0031] In some preferred embodiments, based on current environmental parameters and identified degradation stages, the time series of anomalous features of the local acoustic impedance spectrum and the multi-dimensional feature time series of the physical structure change signal are dynamically segmented, specifically including the following steps:

[0032] Real-time acquisition of local environmental parameters and characterization of local environmental gradients;

[0033] Based on the local environmental parameters, the thermal and moisture diffusion characteristics of the floor material, and the sensor response time, time alignment and hysteresis compensation are performed on the time series of the local environmental parameters, the time series of the abnormal characteristics of the local acoustic impedance spectrum, and the multi-dimensional characteristic time series of the physical structure change signal.

[0034] The correlation between the time-aligned local environmental gradient and the time series of anomalous features of the local acoustic impedance spectrum and the multidimensional feature time series of the physical structure change signal was analyzed.

[0035] Based on the correlation analysis results and the identified degradation stage, structural change points caused by environmental gradient changes or degradation stage transitions in the time series are identified, and the abnormal characteristic time series of the local acoustic impedance spectrum and the multi-dimensional characteristic time series of the physical structure change signal are dynamically segmented accordingly.

[0036] Clearly, this scheme achieves more intelligent and adaptive dynamic segmentation by considering local environmental parameters, material properties, and sensor response time for time alignment and hysteresis compensation, and by identifying the points of change caused by environmental or deterioration stages. This ensures the contextual accuracy of the analysis and avoids misjudging environmental impacts as structural deterioration.

[0037] In some preferred embodiments, the correlation between the time-aligned local environmental gradient and the time series of anomalous features of the local acoustic impedance spectrum and the multidimensional feature time series of the physical structure change signal is analyzed, specifically including the following steps:

[0038] Multivariate time-frequency analysis is performed on the time-aligned local environmental gradient, the time series of the anomalous features of the local acoustic impedance spectrum, and the multidimensional feature time series of the physical structure change signal to identify the synchronicity or causal relationship between the local environmental gradient and the time series of the anomalous features of the local acoustic impedance spectrum and the multidimensional feature time series of the physical structure change signal at different frequencies and time scales.

[0039] Clearly, this scheme employs multivariate time-frequency analysis, which can reveal the complex synchronicity or causal relationship between local environmental gradients and acoustic, temperature, and humidity signals at different frequencies and time scales. This allows for a more comprehensive understanding of the impact of environmental factors on floor degradation signals, laying the foundation for subsequent causal relationship identification.

[0040] In some preferred embodiments, identifying the synchronicity or causal relationship between the local environmental gradient and the anomalous feature time series of the local acoustic impedance spectrum and the multidimensional feature time series of the physical structure change signal at different frequencies and time scales specifically includes the following steps:

[0041] Multivariate time-frequency analysis was performed on the local environmental gradient, the time series of the abnormal features of the local acoustic impedance spectrum, and the multidimensional feature time series of the physical structure change signal to obtain the multivariate time-frequency analysis results.

[0042] By analyzing the directional information flow in the multivariate time-frequency analysis results, the synchronicity or causal relationship between the local environmental gradient and the anomalous feature time series of the local acoustic impedance spectrum and the multidimensional feature time series of the physical structure change signal at different frequencies and time scales can be identified.

[0043] Clearly, by analyzing the directional information flow in the multivariate time-frequency analysis results, this scheme can more accurately identify the causal relationship between the environmental gradient and the floor response signal, rather than just synchronicity, thereby more effectively stripping away environmental interference and focusing on the real signal caused by the physical degradation of the floor.

[0044] In some preferred embodiments, analyzing the directional information flow in the multivariate time-frequency analysis results specifically includes the following steps:

[0045] Based on current environmental parameters and identified degradation stages, dynamically adjust the time window or frequency range of this information flow analysis;

[0046] Within the dynamically adjusted time window or frequency range, the amount and direction of information transmission between the local environmental gradient, the anomalous feature time series of the local acoustic impedance spectrum, and the multidimensional feature time series of the physical structure change signal are quantified.

[0047] Assess whether the information flow pattern formed by the quantified information transmission volume and direction conforms to the physical coupling characteristics under the current degradation stage and environmental conditions; and

[0048] Based on the assessment results, the physical orientation of the causal relationship between the local environmental gradient and the anomalous feature time series of the local acoustic impedance spectrum and the multidimensional feature time series of the physical structure change signal is determined.

[0049] Clearly, by dynamically adjusting the analysis parameters and evaluating the conformity between the information flow pattern and the physical coupling characteristics, this scheme can make the causal relationship analysis more adaptable to the actual environment and degradation stage, thereby more accurately determining the causal relationship between environmental factors and floor degradation signals, and further improving the accuracy of diagnosis.

[0050] In some preferred embodiments, quantifying the amount and direction of information transfer between the local environmental gradient, the anomalous feature time series of the local acoustic impedance spectrum, and the multidimensional feature time series of the physical structure change signal specifically includes the following steps:

[0051] Based on the current environmental parameters, the identified degradation stage, and the sensor response characteristics, adjust the calculation parameters of the information flow index to adapt to different physical coupling conditions.

[0052] Under the adjusted parameters, the information flow index between the local environmental gradient, the anomalous feature time series of the local acoustic impedance spectrum, and the multidimensional feature time series of the physical structure change signal is calculated to obtain the initial information transmission volume and direction.

[0053] Analyze the known information flow patterns related to the local environmental gradient or the sensor's own characteristics within the initial information transmission volume and direction;

[0054] From the initial information transmission volume and direction, the known information flow pattern related to the local environmental gradient or the sensor's own characteristics is filtered out to obtain the information flow characterizing the degradation of the floor material; and

[0055] The information flow caused by the degradation of the flooring material is quantified to obtain the final information transmission volume and direction.

[0056] Clearly, by adjusting the calculation parameters and filtering out known information flow patterns caused by environmental or sensor characteristics, this scheme can extract the information flow caused by floor material degradation more purely, thereby more accurately quantifying its transmission volume and direction, and greatly improving the specificity and accuracy of the diagnosis.

[0057] Secondly, this application also discloses a floor temperature and humidity detection system, which includes:

[0058] The data acquisition and processing module is used to continuously acquire raw data detected by temperature and humidity sensors preset in the target floor area, and to clean, denoise and synchronize the raw data to obtain pre-processed temperature and humidity time series data.

[0059] The feature analysis module is used to perform multi-dimensional feature analysis on the preprocessed temperature and humidity time series data. The multi-dimensional feature analysis includes spectrum analysis, amplitude distribution analysis, data coherence analysis, and cross-correlation analysis with related physical quantities, so as to extract the fluctuation patterns and correlation characteristics of the temperature and humidity data in different dimensions and obtain multi-dimensional features.

[0060] The deviation identification module is used to identify the source of the temperature and humidity measurement deviation based on the multi-dimensional characteristics, and to identify temperature and humidity fluctuations that do not conform to the characteristics of environmental changes or sensor drift as potential signals caused by changes in the physical structure of the floor, thereby obtaining the physical structure change signal.

[0061] The pattern comparison and diagnosis module is used to obtain multi-dimensional features of physical structure change signals based on these signals, and compare these features with a preset physical degradation feature pattern library. This library stores multi-dimensional feature patterns of temperature and humidity data corresponding to different types of flooring materials and underlying structures during specific physical degradation processes. If the comparison results show a high degree of match, a potential physical problem is identified, and diagnostic information with a clear physical root cause is generated.

[0062] The early warning report module is used to trigger early warning signals based on the diagnostic information and generate a detailed diagnostic report, which includes the problem area, the specific physical root cause diagnosed, and recommended preventive maintenance measures. Attached Figure Description

[0063] Figure 1 This is a flowchart illustrating a floor temperature and humidity detection method provided in this application.

[0064] Figure 2 This is a schematic diagram of the structure of a floor temperature and humidity detection system provided in this application. Detailed Implementation

[0065] The technical solutions in this application will now be clearly and completely described in conjunction with the accompanying drawings.

[0066] This application proposes a method for detecting floor temperature and humidity, such as... Figure 1 As shown, it includes the following steps:

[0067] The raw data obtained by the temperature and humidity sensors preset in the target floor area are continuously collected, and the raw data is cleaned, denoised and time-synchronized to obtain pre-processed temperature and humidity time series data.

[0068] Multidimensional feature analysis was performed on the preprocessed temperature and humidity time series data. The multidimensional feature analysis included spectrum analysis, amplitude distribution analysis, data coherence analysis, and cross-correlation analysis with related physical quantities, in order to extract the fluctuation patterns and correlation characteristics of temperature and humidity data in different dimensions and obtain multidimensional features.

[0069] Based on multi-dimensional characteristics, the sources of temperature and humidity measurement deviations are identified, and temperature and humidity fluctuations that do not conform to the characteristics of environmental changes or sensor drift are identified as potential signals caused by changes in the physical structure of the floor, thus obtaining the physical structure change signal.

[0070] Based on the physical structure change signal, multi-dimensional features of the physical structure change signal are obtained, and these features are compared with a pre-set physical degradation feature pattern library. This library stores multi-dimensional feature patterns of temperature and humidity data corresponding to different types of flooring materials and underlying structures during specific physical degradation processes. If the comparison results show a high degree of match, a potential physical problem is identified, and diagnostic information with a clear physical root cause is generated.

[0071] Based on the diagnostic information, an early warning signal is triggered, and a detailed diagnostic report is generated, which includes the problem area, the specific physical cause diagnosed, and recommended preventive maintenance measures.

[0072] This application continuously collects and preprocesses temperature and humidity data, then performs multi-dimensional feature analysis on the preprocessed data to comprehensively extract the fluctuation patterns and correlation characteristics of temperature and humidity data across different dimensions. Based on these multi-dimensional features, the source of temperature and humidity measurement deviations can be accurately identified, distinguishing potential signals caused by changes in the floor's physical structure from environmental changes or sensor drift. Furthermore, by comparing the multi-dimensional features of the identified physical structure change signals with a pre-defined physical degradation feature pattern library, this application can determine the existence of potential physical problems and generate diagnostic information with a clear physical root cause. Finally, based on the diagnostic information, an early warning signal is triggered and a detailed diagnostic report is generated, thus achieving early, accurate, and non-invasive diagnosis of changes in the floor's physical structure. This effectively solves the problems of existing technologies that cannot trace hidden degradation processes and cannot provide accurate diagnoses, significantly reducing maintenance costs and extending the building's lifespan.

[0073] Furthermore, by conducting in-depth analysis of temperature and humidity data in the floor area, early identification and diagnosis of potential problems in the floor's physical structure can be achieved. This method is commonly applied to floor structures in various types of buildings, such as residential, commercial, and industrial plants, and is particularly suitable for scenarios with high requirements for floor structural stability, material durability, and indoor environmental comfort.

[0074] Specifically, raw data refers to the unprocessed electrical or digital signals directly output by temperature and humidity sensors. Cleaning, denoising, and time synchronization of this raw data are key steps in data preprocessing. Cleaning aims to remove outliers or erroneous records from the data; denoising aims to eliminate random fluctuations caused by sensor noise, environmental interference, etc.; and time synchronization ensures that data from different sensors or different time points can be accurately aligned to form consistent temperature and humidity time series data, laying the foundation for subsequent analysis.

[0075] Multidimensional feature analysis is a comprehensive data analysis method aimed at uncovering deeper patterns related to changes in the physical structure of the floor from temperature and humidity time-series data. Spectral analysis reveals the energy distribution of temperature and humidity data at different frequencies, such as periodic fluctuations or anomalous oscillations at specific frequencies; amplitude distribution analysis examines the amplitude characteristics of temperature and humidity data fluctuations, such as the presence of anomalous peaks or troughs; data coherence analysis assesses the correlation between different sensors or between data from the same sensor at different time points to identify synchronization or lag phenomena; and cross-correlation analysis with related physical quantities may involve comparing temperature and humidity data with other physical quantities such as external environmental temperature, humidity, air pressure, and floor stress to distinguish between external influences and internal structural changes. Through these analyses, multidimensional features can be obtained, which are comprehensive representations of temperature and humidity data across multiple dimensions, including time, frequency, and space.

[0076] The Physical Deterioration Characteristic Pattern Library is a pre-built database that stores a large number of multi-dimensional characteristic patterns of temperature and humidity data corresponding to different types of flooring materials (such as wood flooring, ceramic tiles, concrete, composite materials, etc.) and their underlying structures (such as leveling layers, moisture-proof layers, insulation layers, structural layers, etc.) when undergoing specific physical deterioration processes (such as hollowing, cracking, dampness, deformation, delamination, corrosion, etc.). These patterns are usually obtained through experiments, simulations, or historical data accumulation and are a key basis for diagnosing physical problems in flooring.

[0077] Diagnostic information is a report or alert generated by the system based on comparison results, pointing to a clear physical root cause. It not only indicates the existence of a problem, but more importantly, specifies the nature of the problem, its possible causes, and the affected area. Ultimately, the generation of early warning signals and detailed diagnostic reports aims to promptly notify users or maintenance personnel and provide specific maintenance recommendations, thereby enabling preventative maintenance and preventing the problem from worsening.

[0078] This application addresses the problem that existing floor temperature and humidity detection systems cannot effectively distinguish minute measurement deviations caused by changes in the physical structure of the floor, and cannot provide accurate, non-invasive diagnostics. The solution is as follows:

[0079] This invention introduces a multi-dimensional feature analysis and physical degradation feature pattern comparison mechanism. Unlike existing technologies that only perform simple data calibration and threshold alarms, this application extracts the fluctuation patterns and correlation characteristics of temperature and humidity data across different dimensions from a deeper and more subtle level by performing spectral analysis, amplitude distribution analysis, data coherence analysis, and cross-correlation analysis with relevant physical quantities on the preprocessed temperature and humidity time series data. This multi-dimensional analysis enables the system to more accurately capture abnormal temperature and humidity signals caused by minute changes in the floor's physical structure and distinguish them from environmental changes or sensor drift.

[0080] Furthermore, this application achieves a clear diagnosis of the physical root cause of floor physical problems by comparing the multi-dimensional features of the identified physical structure change signals with a preset physical degradation feature pattern library. Existing technologies, when detecting anomalies, often only provide a general indication of "abnormal temperature and humidity," without specifying whether it is "hollowing," "cracking," or "dampness."

[0081] In some embodiments described above, by performing multi-dimensional feature analysis on temperature and humidity data and comparing it with a preset pattern library, changes in the physical structure of the floor can be preliminarily identified. However, relying solely on passive monitoring based on temperature and humidity data may not provide sufficiently early or accurate location of physical degradation in the early stages of some conditions or when temperature and humidity changes are not significant, resulting in limitations in the specificity and sensitivity of the diagnosis. Therefore, this application further proposes a diagnostic method incorporating active acoustic excitation to enhance the ability to identify physical structural problems in the floor.

[0082] The above-mentioned method compares the multi-dimensional features of physical structure change signals with a preset physical degradation feature pattern library. This library stores multi-dimensional feature patterns of temperature and humidity data corresponding to different types of flooring materials and underlying structures during specific physical degradation processes. If the comparison results show a high degree of match, a potential physical problem is identified, and diagnostic information with a clear physical root cause is generated. Specifically, this includes the following steps:

[0083] Active acoustic excitation is applied to the floor, and acoustic response data of the floor is collected;

[0084] The local acoustic impedance spectrum of the floor is constructed based on the acoustic response data;

[0085] The abnormal features of the local acoustic impedance spectrum are correlated with the multi-dimensional features of the physical structure change signal;

[0086] Based on the correlation analysis results, pattern comparisons were performed in the physical degradation characteristic pattern library, which stores acoustic impedance spectral patterns and temperature and humidity response patterns corresponding to different types of flooring materials and underlying structures during specific physical degradation processes; and

[0087] If the comparison results are highly consistent, a potential physical problem is identified, and diagnostic information with a clear physical root cause is generated.

[0088] Specifically, applying active acoustic excitation to the floor refers to applying controlled acoustic waves or vibrational energy to a target floor area through an external excitation source (e.g., a piezoelectric exciter, an electromagnetic exciter, or a small impact hammer). This excitation can be broadband or specific in frequency, and its purpose is to stimulate the inherent vibration modes or acoustic responses within the floor structure. Simultaneously, acquiring acoustic response data from the floor involves using highly sensitive sensors (e.g., accelerometers, microphones, or laser vibrometers) to receive the vibrational or acoustic signals generated by the floor after being excited. This response data contains rich information about the floor's current physical state, such as its stiffness, damping, and internal defects.

[0089] The construction of a local acoustic impedance spectrum for a floor based on acoustic response data can be understood as obtaining the acoustic impedance characteristics of the floor at different frequencies by performing signal processing and analysis on the collected acoustic response data, such as Fourier transform and wavelet analysis. Acoustic impedance is a physical quantity that describes a material's ability to impede the propagation of sound waves, and its changes can directly reflect anomalies in the floor's internal structure (such as delamination, hollow areas, cracks, or moisture intrusion). The local acoustic impedance spectrum focuses on the impedance characteristics of a specific area, which helps to accurately locate problem areas.

[0090] Furthermore, based on the correlation analysis results, pattern comparisons were performed in a physical degradation characteristic pattern library. This library not only stores multi-dimensional characteristic patterns of temperature and humidity data corresponding to different types of flooring materials and underlying structures during specific physical degradation processes, but also adds corresponding acoustic impedance spectral patterns. This means the pattern library has been expanded into a multimodal feature library, capable of simultaneously comparing temperature and humidity response patterns and acoustic impedance spectral patterns. Through this multimodal comparison, the degree of matching between the current floor condition and known degradation patterns can be identified more accurately.

[0091] Therefore, if the comparison results show a high degree of match, a potential physical problem is identified, and diagnostic information with a clear physical root cause is generated. This high degree of match indicates that the current temperature, humidity, and acoustic response characteristics of the floor are highly consistent with the characteristic patterns of a specific physical degradation (e.g., floor delamination, hollow subfloor, wood swelling or decay caused by moisture intrusion) in the pattern library, thus providing more specific and reliable diagnostic results than relying solely on temperature and humidity data.

[0092] Through the above technical solution, this application can significantly improve the accuracy of floor physical problem diagnosis and early warning capabilities. Compared with methods that rely solely on temperature and humidity data, the introduction of active acoustic excitation and acoustic impedance spectroscopy analysis enables the system to more sensitively capture changes in the internal structure of the floor, effectively identifying even minor, early-stage deterioration. This multimodal data fusion and comparison mechanism not only improves the reliability of diagnostic results and reduces false alarms and false negatives, but also provides diagnostic information with a clear physical root cause, such as whether the structural problem is caused by delamination, hollowness, or moisture. This provides more precise guidance for subsequent preventative maintenance measures, effectively avoiding potential structural damage and safety hazards.

[0093] However, in practical applications, the physical degradation process of flooring is often a dynamic and complex process influenced by multiple factors. Simple correlation analysis may not be able to fully reveal the time dependence, causal relationships, and the influence of environmental factors on these correlations among different physical quantities, which may lead to insufficient accuracy and robustness of the diagnosis.

[0094] In response, this application further proposes steps for correlation analysis between the aforementioned anomalous features of the local acoustic impedance spectrum and the multidimensional features of the physical structure change signal, including:

[0095] Time-delay correlation analysis is performed on the anomalous features of the local acoustic impedance spectrum and the multidimensional features of the physical structure change signal to identify the time lag relationship between the anomalous features and the multidimensional features;

[0096] Based on the time lag relationship, calculate the dynamic response characteristics between the anomalous features of the local acoustic impedance spectrum and the multidimensional features of the physical structure change signal;

[0097] The dynamic response characteristics are evaluated in context, taking into account current environmental parameters and historical degradation trends; and

[0098] Based on the context evaluation results, the physical directivity of the correlation between the anomalous features of the local acoustic impedance spectrum and the multidimensional features of the physical structure change signal is determined.

[0099] Specifically, time-delay correlation analysis refers to identifying whether a leading or lagging relationship exists between two time series by calculating their correlation at different time offsets. For example, methods such as cross-correlation functions, Granger causality tests, or dynamic time warping can be used for analysis. Its purpose is to accurately capture the temporal evolution of the acoustic response caused by changes in the floor's physical structure and the relationship between temperature and humidity changes, which is crucial for understanding degradation mechanisms.

[0100] Dynamic response characteristics can be understood as the features of how one physical quantity responds over time when another physical quantity changes. For example, when hollow areas or delamination occur inside a floor, the abnormal characteristics of its acoustic impedance spectrum may appear immediately, while due to thermal inertia or the hysteresis of moisture diffusion, anomalies in temperature and humidity signals may only manifest after a period of time. By calculating these dynamic response characteristics, the coupling strength and response speed between different physical phenomena can be quantified.

[0101] In practical applications, contextual assessment specifically involves combining current environmental parameters (such as ambient temperature, humidity, and air pressure) with historical degradation trends (such as past degradation records, maintenance history, and material aging models for the floor area) to comprehensively judge dynamic response characteristics. For example, in high-temperature and high-humidity environments, certain degradation processes may accelerate, leading to a shorter lag time or an increased response amplitude in acoustic and temperature / humidity responses. This assessment can eliminate the interference of environmental factors on measurement results and more accurately determine the degradation state.

[0102] Therefore, determining the physical orientation of the correlation means, after considering time lag, dynamic response, and contextual information, clarifying what physical mechanism is at play between acoustic anomalies and temperature / humidity anomalies. For example, does acoustic change lead to temperature / humidity change, or does temperature / humidity change lead to acoustic change, or are both caused by a common physical deterioration source? This helps to fundamentally understand the deterioration process of the floor.

[0103] This application addresses the limitations of existing correlation analysis by introducing time-delay correlation analysis, dynamic response characteristic calculation, and contextual assessment. Specifically, time-delay correlation analysis reveals the temporal sequence and lag relationship between anomalous acoustic impedance spectrum features and multi-dimensional temperature and humidity characteristics, which is crucial for understanding the dynamic evolution of physical degradation processes. For example, certain structural defects (such as cracking and delamination) may initially cause rapid changes in acoustic properties, while their impact on the temperature and humidity field may be delayed due to the material's thermal and moisture diffusion characteristics. By identifying this time lag relationship, it is possible to more accurately determine which signal is the "leading indicator," thereby enabling earlier warning of degradation.

[0104] Furthermore, by calculating the dynamic response characteristics based on the identified time lag relationships, the intensity and speed of the interaction between different physical quantities can be quantified. This allows the system not only to identify correlations but also to gain a deeper understanding of the "dynamic" manifestations of these correlations. For example, the dynamic characteristics of the acoustic and temperature / humidity responses may differ significantly for different types of degradation (such as expansion caused by moisture versus contraction caused by dryness).

[0105] Furthermore, contextual assessment combining current environmental parameters and historical degradation trends can effectively eliminate interference from environmental factors (such as fluctuations in ambient temperature and humidity) on measurement results and calibrate dynamic response characteristics. For example, when ambient temperature changes drastically, temperature and humidity sensor data may fluctuate, but contextual assessment can distinguish whether these fluctuations are normal phenomena caused by the environment or abnormal responses caused by changes in the floor's physical structure. Simultaneously, the introduction of historical degradation trends allows the system to learn and adapt to the typical behavioral patterns of specific flooring materials at different stages of degradation, thereby improving the accuracy and robustness of diagnosis.

[0106] Therefore, through the above multi-level analysis, the physical directionality of the correlation between the anomalous features of the local acoustic impedance spectrum and the multi-dimensional features of the physical structure change signal can be determined. This means that the system not only knows that the two are related, but also knows how they are related and the specific physical mechanism behind this correlation, thus providing a more solid physical basis for the subsequent generation of diagnostic information.

[0107] Through the above technical solutions, this application can significantly improve the accuracy and reliability of diagnosing physical problems in flooring. By deeply analyzing the time lag relationship and dynamic response characteristics between acoustic response and temperature and humidity changes, the system can more accurately capture early signals of changes in the internal physical structure of the flooring and effectively distinguish interference caused by environmental factors or sensor drift. Furthermore, contextual assessment combining environmental parameters and historical degradation trends further enhances the robustness of the diagnosis and reduces the risk of false alarms and missed alarms. Finally, the clear physical orientation of the correlation makes the generated diagnostic information more interpretable and instructive, providing users with diagnostic results that clearly point to the physical root cause, thereby enabling more precise preventative maintenance and intervention, effectively extending the service life of the flooring and reducing maintenance costs.

[0108] Specifically, the aforementioned time-delay correlation analysis of the anomalous features of the local acoustic impedance spectrum and the multi-dimensional features of the physical structure change signal to identify the time lag relationship between the anomalous features and the multi-dimensional features may include the following steps:

[0109] Based on the current environmental parameters and the identified degradation stages, the time series of abnormal features of the local acoustic impedance spectrum and the multi-dimensional feature time series of the physical structure change signal are dynamically segmented.

[0110] Time-varying coherence analysis is performed on the time series of the anomalous features and the time series of the multidimensional features within each dynamic segment to identify the dynamic phase difference between the anomalous features and the multidimensional features at different frequencies.

[0111] Based on the dynamic phase difference, a time lag distribution between the abnormal features and the multi-dimensional features is constructed; and

[0112] Based on the shape of the time lag distribution and the context information of the dynamic segmentation, the time lag relationship between the abnormal features and the multi-dimensional features is determined.

[0113] Specifically, dynamic segmentation refers to the intelligent division of continuously acquired time series data on anomalous features of local acoustic impedance spectra and multi-dimensional feature time series data on physical structure changes, based on real-time acquired environmental parameters (such as temperature, humidity, and air pressure) and the current deterioration stage of the flooring material (such as initial cracking, delamination, and hollowing). The purpose of this segmentation is to ensure that the impact of environmental changes on data characteristics, as well as the response changes that may be caused by the deterioration process itself, are fully considered when analyzing data from different time periods. For example, when the ambient temperature changes drastically, the physical response of the flooring may differ from that when the temperature is stable; dynamic segmentation can differentiate and process data under these different environmental conditions.

[0114] Furthermore, time-varying coherence analysis is an advanced signal processing technique applied to data within each dynamic segment. This analysis aims to identify the dynamic phase difference at different frequencies between the anomalous characteristic time series of the local acoustic impedance spectrum and the multidimensional characteristic time series of the physical structure change signal. While coherence analysis reveals the correlation between two signals in the frequency domain, time-varying coherence allows this correlation to dynamically adjust over time, thus more accurately capturing transient or nonlinear responses caused by floor structure changes. By analyzing the dynamic phase difference, the time-leading or lagging relationship between the acoustic response and the temperature and humidity response can be inferred, which is crucial for understanding energy transfer and information coupling during physical degradation processes.

[0115] Therefore, based on the identified dynamic phase difference, a time lag distribution between anomalous features and multidimensional features can be constructed. This distribution can be a probability distribution, histogram, or trend graph, used to quantify the time delay between acoustic anomalies and temperature / humidity anomalies at different frequencies and time points. For example, if a tiny crack appears inside the floor, the acoustic signal anomaly may occur before or after the temperature / humidity signal anomaly, and this time lag may vary as the crack expands. Constructing a time lag distribution helps to comprehensively understand this dynamic relationship.

[0116] Ultimately, based on the shape of the constructed time lag distribution (e.g., whether it is concentrated at a specific point in time or exhibits a broad distribution) and the contextual information of the dynamic segments (e.g., the environmental conditions and degradation stages corresponding to each segment), the time lag relationship between anomalous features and multidimensional features can be determined. This determination is not merely a simple time difference, but a deeper correlation judgment combining physical background and degradation mechanisms. For example, determining whether acoustic anomalies cause temperature and humidity anomalies, or vice versa, or whether both are jointly triggered by a potential physical event.

[0117] This application's solution overcomes the limitations of traditional time-delay analysis methods when processing non-stationary and nonlinear data by introducing dynamic segmentation, time-varying coherence analysis, and time-lag distribution construction. Specifically, dynamic segmentation allows the analysis to adapt to constantly changing environmental conditions and floor degradation stages, ensuring the validity and comparability of data under different operating conditions. Time-varying coherence analysis can capture the dynamic phase relationship between acoustic and temperature / humidity responses at different frequencies, which is crucial for revealing the energy transfer and information coupling mechanisms in complex physical degradation processes. By constructing a time-lag distribution, the dynamic temporal correlation between acoustic anomalies and temperature / humidity anomalies can be quantified and understood more comprehensively and precisely, providing a more accurate and reliable basis for subsequent physical source identification. This multi-level, dynamic analysis method enables the system to more accurately identify potential signals caused by changes in the floor's physical structure and distinguish them from fluctuations caused by environmental changes or sensor drift.

[0118] Through the above technical solutions, this application can significantly improve the accuracy and robustness of time-delay correlation analysis. Traditional time-delay analysis often assumes that the signal is stationary and the environmental conditions are constant, which is difficult to meet in actual floor degradation monitoring. This application, through dynamic segmentation, enables the analysis to adapt to non-stationary data and dynamic environments, thereby avoiding misjudgments caused by environmental changes or degradation stage transitions. Time-varying coherence analysis can reveal the dynamic phase relationship between signals at different frequencies, which is crucial for understanding complex physical coupling mechanisms, especially when the microstructure of the floor material undergoes changes, enabling more sensitive detection of early degradation signs. Therefore, the determined time-delay relationship is more physically directional and can more accurately reflect the true dynamic response of changes in the floor's physical structure, thus providing more reliable input for subsequent comparison of physical degradation characteristic patterns, ultimately improving the accuracy of floor physical problem diagnosis and early warning capabilities.

[0119] However, in practical applications, fluctuations in environmental parameters, such as temperature, humidity, and air pressure, as well as the evolution of the deterioration stage of flooring materials, can significantly affect temperature and humidity data and acoustic response data. If these external factors are not fully considered and dynamic segmentation is performed solely based on the fluctuations in the data itself, the segmentation boundaries may be inaccurate, thereby affecting the accuracy of subsequent time-delay correlation analysis, or even misjudging environmental fluctuations as structural change signals.

[0120] In response, this application further proposes a more accurate and robust dynamic segmentation method, which introduces environmental parameters and degradation stage information to more accurately identify structural change points in the time series.

[0121] In response, this application further proposes the following steps for dynamically segmenting the time series of anomalous features of the local acoustic impedance spectrum and the multi-dimensional feature time series of physical structure change signals based on current environmental parameters and identified degradation stages:

[0122] Real-time acquisition of local environmental parameters and characterization of local environmental gradients;

[0123] Based on local environmental parameters, the thermal and moisture diffusion characteristics of the floor material, and the sensor response time, time alignment and hysteresis compensation are performed on the time series of local environmental parameters, the time series of anomalous features of local acoustic impedance spectra, and the multi-dimensional feature time series of physical structure change signals.

[0124] The correlation between time-aligned local environmental gradients and the time series of anomalous features in local acoustic impedance spectra, as well as the multi-dimensional feature time series of signals indicating physical structure changes, was analyzed.

[0125] Based on the correlation analysis results and the identified degradation stages, structural change points caused by environmental gradient changes or degradation stage transitions in the time series are identified, and the time series of anomalous features of local acoustic impedance spectra and multidimensional feature signals of physical structure change signals are dynamically segmented accordingly.

[0126] Specifically, real-time acquisition of local environmental parameters refers to the continuous monitoring and recording of various physical parameters of the current environment through auxiliary sensors deployed in or near the target floor area, such as temperature sensors, humidity sensors, and barometric pressure sensors. These parameters are used to characterize the local environmental gradient, that is, the rate of change of environmental parameters in space or time, such as temperature gradient or humidity gradient, with the aim of capturing dynamic environmental changes that may affect the response of the floor material.

[0127] Specifically, based on local environmental parameters, the thermal and moisture diffusion characteristics of the floor material, and the sensor response time, time alignment and hysteresis compensation are performed on the time series of local environmental parameters, the time series of anomalous features of the local acoustic impedance spectrum, and the multi-dimensional feature time series of physical structure change signals. This can be understood as performing precise time synchronization processing on time series data from different sources. Since changes in environmental parameters, the response of the floor material to environmental changes (thermal and moisture diffusion characteristics), and the response speed of the sensor itself all have certain time lags, it is necessary to use algorithms (such as cross-correlation analysis, dynamic time warping, etc.) to perform precise time calibration on these time series to eliminate errors caused by time lags and ensure the accuracy of subsequent correlation analysis.

[0128] In practical applications, the correlation between time-aligned local environmental gradients and the time series of anomalous features in the local acoustic impedance spectrum, as well as the multi-dimensional feature time series of signals indicating changes in physical structure, is analyzed. Specifically, statistical methods or machine learning algorithms, such as Granger causality tests, mutual information, or deep learning-based temporal correlation models, are used to quantify and identify the mutual influence between environmental gradient changes and anomalous features in floor temperature, humidity, and acoustic response. The aim is to distinguish between signal fluctuations caused by environmental changes and the true signals caused by changes in the floor's physical structure.

[0129] Furthermore, based on the correlation analysis results and the identified degradation stages, structural change points in the time series caused by environmental gradient changes or degradation stage transitions are identified. Accordingly, the time series of anomalous features in the local acoustic impedance spectrum and the multi-dimensional feature time series of physical structure change signals are dynamically segmented. This means that when segmenting the time series, not only the statistical characteristics of the data itself are considered, but also the influence of environmental factors and the current degradation state of the floor are taken into account. For example, when the ambient temperature changes drastically, the temperature and humidity data may fluctuate accordingly. In this case, this fluctuation should be attributed to environmental factors, not changes in the floor structure. Simultaneously, when the floor transitions from one degradation stage (e.g., initial cracking) to another (e.g., intensified delamination), its temperature, humidity, and acoustic response patterns may change significantly. These points of change should also be identified as important segmentation boundaries. In this way, dynamic segmentation can more accurately reflect the true time points of changes in the floor's physical structure, avoiding misjudging environmental noise or stage changes during normal degradation as anomalous signals.

[0130] This application's solution introduces real-time acquisition of local environmental parameters and characterization of environmental gradients, enabling the system to perceive and quantify the impact of the external environment on floor temperature, humidity, and acoustic response. By precisely aligning and compensating for time lags between the environmental parameter time series and the temperature, humidity, and acoustic characteristic time series, time deviations caused by differences in physical processes and sensor response speeds are eliminated, ensuring data synchronization and comparability. Therefore, when analyzing the correlation between the time-aligned local environmental gradient and floor characteristic data, it can effectively distinguish between fluctuations caused by environmental changes and true signals caused by changes in the floor's physical structure. Finally, combining this correlation analysis results with identified degradation stages, the system can intelligently identify key time points in the time series truly caused by structural changes or degradation stage transitions, thereby achieving precise dynamic segmentation of the time series of anomalous characteristics in the local acoustic impedance spectrum and multi-dimensional characteristic time series of physical structure change signals. This method avoids the shortcomings of traditional methods that may misjudge environmental noise or normal environmental responses as structural anomalies, significantly improving the accuracy and reliability of dynamic segmentation and providing a purer and more accurate data foundation for subsequent time-delay correlation analysis.

[0131] In some of the embodiments described above in this application, when analyzing the correlation between the time-aligned local environmental gradient and the anomalous feature time series of the local acoustic impedance spectrum and the multidimensional feature time series of the physical structure change signal, a multivariate time-frequency analysis method can be used.

[0132] Specifically, the above analysis of the correlation between the time-aligned local environmental gradient and the anomalous feature time series of the local acoustic impedance spectrum and the multidimensional feature time series of the physical structure change signal includes the following steps: performing multivariate time-frequency analysis on the time-aligned local environmental gradient, the anomalous feature time series of the local acoustic impedance spectrum, and the multidimensional feature time series of the physical structure change signal to identify the synchronicity or causal relationship between the local environmental gradient and the anomalous feature time series of the local acoustic impedance spectrum and the multidimensional feature time series of the physical structure change signal at different frequencies and time scales.

[0133] Multivariate time-frequency analysis (MTA) is a technique that can simultaneously analyze the relationships between multiple time series in the time and frequency domains. This analytical method can reveal synchronous or lag relationships between different variables at specific frequency components, and how these relationships evolve over time. For example, it can be achieved using wavelet coherence analysis, cross-spectral density analysis, or Granger causality analysis. Through such analysis, it is possible to identify how local environmental gradients (such as changes in temperature and humidity) affect the acoustic response of the floor and the signals of changes in the physical structure of temperature and humidity, and at which these effects occur in the frequency ranges and time scales. Synchronicity refers to the simultaneous change of multiple signals at a specific frequency or time point, while causality further reveals whether a change in one signal leads to a change in another signal.

[0134] This application's approach, by introducing multivariate time-frequency analysis, enables a more refined analysis of the complex interactions between the time series of anomalous features in local environmental gradients, local acoustic impedance spectra, and multidimensional feature time series of physical structural change signals. Traditional time-domain or frequency-domain analyses may fail to fully capture the dynamic correlations between these variables at different frequencies and time scales. Time-frequency analysis can identify how environmental changes cause anomalies in the floor structure's response within a specific frequency range, or how structural degradation leads to specific fluctuation patterns in temperature and humidity signals. For example, acoustic impedance anomalies at certain frequencies may be synchronized with ambient temperature fluctuations at specific frequencies, potentially indicating structural stress caused by material expansion or contraction due to temperature changes. Furthermore, by analyzing information flow or Granger causality, it is possible to further determine whether environmental changes cause the structural response or, in turn, affect local environmental perception, thus providing more accurate physical indications for subsequent identification and diagnosis of degradation stages.

[0135] Specifically, the above-mentioned identification of the synchronicity or causal relationship between the anomalous feature time series of local environmental gradients and local acoustic impedance spectra and the multidimensional feature time series of physical structure change signals at different frequencies and time scales can be further achieved through the following steps.

[0136] Multivariate time-frequency analysis was performed on the time series of the abnormal features of the local environmental gradient, the local acoustic impedance spectrum, and the multidimensional feature time series of the physical structure change signal to obtain the multivariate time-frequency analysis results.

[0137] By analyzing the directional information flow in the multivariate time-frequency analysis results, the synchronicity or causal relationship between the local environmental gradient and the anomalous feature time series of the local acoustic impedance spectrum and the multidimensional feature time series of the physical structure change signal at different frequencies and time scales can be identified.

[0138] Multivariate time-frequency analysis results refer to the output obtained by jointly analyzing multiple time series data, such as local environmental gradients, anomalous feature time series of local acoustic impedance spectra, and multidimensional feature time series of physical structure change signals, in the time and frequency domains. This analysis aims to reveal the interrelationships of these variables at different frequency components and time points, such as their energy distribution, phase relationships, and correlations. Specifically, methods such as wavelet coherence analysis, cross-spectral density analysis, or Granger causality analysis can be used to generate such results.

[0139] Furthermore, directional information flow refers to the direction and intensity of the influence of one variable on another in a multivariate system. In the context of time-frequency analysis, analyzing directional information flow can reveal how information is transmitted from one signal to another at a specific frequency and time scale. For example, this directional information flow can be quantified and identified by calculating indicators such as transmission entropy, conditional Granger causality, or partial coherence. The aim is to distinguish whether changes in floor temperature, humidity, and acoustic response are caused by environmental changes or by the physical degradation of the floor itself, thus more accurately attributing the signal source.

[0140] This application's solution, through analysis of directional information flow in multivariate time-frequency analysis results, can deeply reveal the intrinsic connections between the time series of anomalous features of local environmental gradients, local acoustic impedance spectra, and multidimensional feature time series of signals indicating physical structural changes. Traditional methods may only identify correlations or synchronicities between variables, but struggle to clarify causal relationships or the direction of information transmission. By introducing the concept of directional information flow, the path and intensity of information flowing from one variable to another can be quantified and identified. For example, it can determine whether changes in ambient temperature cause the floor's temperature and humidity response, or whether structural degradation within the floor causes the anomalies in temperature, humidity, and acoustic response. This analysis helps eliminate interference from environmental factors, more accurately pinpointing signals caused by changes in the floor's physical structure, thereby improving diagnostic accuracy.

[0141] However, in practical applications, the dynamic changes in environmental parameters and the evolution of floor degradation stages may lead to the complexity of information flow patterns, making it insufficient to simply identify synchronicity or causality to accurately determine its physical orientation, which may affect the accuracy and reliability of diagnosis.

[0142] In this regard, this application further proposes steps for analyzing the directional information flow in multivariate time-frequency analysis results, specifically including the following steps:

[0143] The time window or frequency range of the information flow analysis is dynamically adjusted based on the current environmental parameters and the identified degradation stages.

[0144] Within the dynamically adjusted time window or frequency range, the amount and direction of information transmission between the local environmental gradient, the anomalous feature time series of the local acoustic impedance spectrum, and the multidimensional feature time series of the physical structure change signal are quantified.

[0145] Assess whether the information flow pattern formed by the quantified information transmission volume and direction conforms to the physical coupling characteristics under the degradation stage and environmental conditions; and

[0146] Based on the evaluation results, the physical orientation of the causal relationship between the local environmental gradient and the anomalous feature time series of the local acoustic impedance spectrum and the multidimensional feature time series of the physical structure change signal is determined.

[0147] Specifically, dynamically adjusting the time window or frequency range of information flow analysis means that, considering floor degradation is a dynamic process, and its response to environmental changes may vary depending on the stage of degradation and environmental conditions, the parameters of information flow analysis should not be fixed. For example, in the early stages of degradation, a wider frequency range may be needed to capture weak structural change signals; while in the later stages of degradation, a narrower frequency range may be needed to focus on specific resonant frequency shifts. Dynamically adjusting the time window can adapt to rapid changes or slow evolution of environmental parameters, ensuring that the most relevant temporal information is captured during analysis.

[0148] Quantifying the amount and direction of information transfer between multidimensional characteristic time series of local environmental gradients, local acoustic impedance spectra, and physical structure change signals can employ various information theory or statistical methods. For example, indices such as Granger causality, transfer entropy, or mutual information can be used to quantify the information flow between different time series. These indices can reveal the degree and direction of the influence of changes in one series on the future changes of another series, thereby determining whether a causal relationship exists between them and the strength of that causal relationship.

[0149] Assessing whether the information flow pattern formed by the quantified amount and direction of information transmission conforms to the physical coupling characteristics under the degradation stage and environmental conditions is a crucial step in ensuring the physical meaning of diagnostic results. This means that the identified information flow pattern must correspond to the known or expected physical response mechanism of the flooring material during a specific degradation process. For example, if a change in humidity is diagnosed as causing floor expansion, then the direction of the information flow should be from humidity to the structural response, and its intensity should match the material's hygroscopic expansion coefficient. This assessment can be based on pre-established physical models, experimental data, or expert knowledge bases.

[0150] Therefore, based on the assessment results, the physical directionality of the causal relationship between the local environmental gradient and the anomalous characteristic time series of the local acoustic impedance spectrum and the multidimensional characteristic time series of the physical structure change signal can be determined. This means that it is not only possible to identify correlations or synchronicities, but also to clearly point out which environmental factor or structural change caused the occurrence of another phenomenon, thus providing a clear physical root cause for subsequent diagnosis and maintenance.

[0151] This application's solution dynamically adjusts the parameters of information flow analysis, enabling the analysis process to better adapt to complex and changing environmental conditions and the deterioration stages of the floor. By quantifying the amount and direction of information transmission, it can more accurately reveal the causal relationships between different physical quantities, rather than merely correlations. Furthermore, by comparing and evaluating the quantified information flow pattern with known physical coupling characteristics, it ensures that the identified causal relationships have a solid physical basis, avoiding misdiagnosis or missed diagnosis. This method makes the diagnosis of changes in the physical structure of the floor more in-depth and accurate, enabling the extraction of signals truly caused by structural deterioration from complex temperature and humidity data, and clarifying its physical root cause.

[0152] In some embodiments described above in this application, causal relationships between local environmental gradients, anomalous time series of local acoustic impedance spectra, and multidimensional characteristic time series of physical structure change signals are quantified to identify these relationships. However, in practical applications, the amount and direction of information transmitted through direct quantization may be affected by various factors, such as rapid fluctuations in environmental parameters or the sensor's own response characteristics. These factors may introduce noise or spurious correlations unrelated to the deterioration of the floor's physical structure, thereby affecting the accuracy and reliability of the diagnosis.

[0153] In response, this application further proposes steps for quantifying the amount and direction of information transfer between the aforementioned local environmental gradient, the aforementioned anomalous feature time series of the local acoustic impedance spectrum, and the aforementioned multidimensional feature time series of the physical structure change signal, including:

[0154] Based on the current environmental parameters, the identified degradation stage, and the sensor response characteristics, adjust the calculation parameters of the information flow index to adapt to different physical coupling conditions.

[0155] Under the adjusted parameters, the information flow index between the local environmental gradient, the anomalous feature time series of the local acoustic impedance spectrum, and the multidimensional feature time series of the physical structure change signal is calculated to obtain the initial information transmission volume and direction.

[0156] Analyze the known information flow patterns related to the local environmental gradient or the sensor's own characteristics in the initial information transmission volume and direction;

[0157] From the initial information transmission volume and direction, the known information flow patterns related to local environmental gradients or sensor characteristics are filtered out to obtain the information flow characterizing the degradation of the floor material; and

[0158] The information flow caused by the degradation of the flooring material is quantified to obtain the final information transmission quantity and direction.

[0159] Specifically, when quantifying the amount and direction of information transfer between the time series of anomalous features of local environmental gradients, local acoustic impedance spectra, and multidimensional feature time series of physical structure change signals, the calculation parameters of the information flow index are first adjusted based on the current environmental parameters, the identified degradation stages, and the sensor response characteristics. The current environmental parameters can include temperature, humidity, and air pressure; the identified degradation stages can refer to different degradation states of the floor, such as initial cracking, delamination, or moisture expansion; and the sensor response characteristics refer to the sensor's response speed and accuracy to environmental changes. These parameter adjustments aim to ensure that the information flow calculation can adapt to different physical coupling conditions. For example, in a humid environment, the thermal-humid coupling characteristics of materials will change, requiring adjustments to the corresponding calculation weights or model parameters.

[0160] Secondly, under the adjusted parameters mentioned above, information flow indices are calculated among the time series of anomalous features of the local environmental gradient, the local acoustic impedance spectrum, and the multi-dimensional feature time series of physical structure change signals to obtain the initial information transfer quantity and direction. Information flow indices can be quantified using various mature methods, such as transfer entropy, Granger causality, or mutual information. These indices quantify the predictive power of one time series for the future state of another, thus revealing the information transfer relationship between them. The initial information transfer quantity and direction refer to the information flow results calculated directly from the raw data before any filtering or correction.

[0161] Furthermore, the known information flow patterns related to the local environmental gradient or the sensor's own characteristics are analyzed within the initial information transmission volume and direction mentioned above. For example, when the ambient humidity increases sharply, the temperature and humidity sensor may respond immediately and generate corresponding signal fluctuations. These fluctuations are directly caused by environmental changes, rather than by floor structure deterioration. Similarly, the sensor may have inherent drift or noise patterns, which should also be identified as known information flow patterns.

[0162] Subsequently, from the initial information transmission volume and direction, known information flow patterns related to local environmental gradients or sensor characteristics are filtered out to obtain the information flow characterizing the degradation of the floor material. This filtering process can be implemented through various signal processing techniques, such as adaptive filtering, pattern recognition, or machine learning classification, aiming to strip away information flow components caused by non-structural degradation, thereby highlighting the information flow truly caused by floor material degradation.

[0163] Finally, the information flow characterized by the degradation of the flooring material was quantified to obtain the final information transmission quantity and direction. This final quantification result is purer and more accurate, and can more directly reflect the information transmission pattern caused by the degradation of the flooring's physical structure, providing a reliable basis for subsequent diagnosis.

[0164] This application's solution effectively addresses the problems of environmental factors and sensor characteristic interference in traditional information flow analysis by introducing dynamic adjustment of information flow index calculation parameters, initial information flow calculation, identification and filtering of known interference patterns, and final information flow requantization. Specifically, by adjusting the calculation parameters according to current environmental parameters, identified degradation stages, and sensor response characteristics, the information flow model is ensured to adapt to actual physical coupling conditions, improving calculation accuracy. The calculation of initial information transmission volume and direction provides the foundation for subsequent refinement. Crucially, by analyzing and filtering out known information flow patterns related to local environmental gradients or sensor characteristics, information flow components caused by non-structural degradation can be effectively isolated, thus avoiding misjudging environmental fluctuations or sensor drift as structural degradation signals. Consequently, the final quantified information flow can more accurately and purely characterize the information transmission caused by floor material degradation, greatly improving the physical directivity and reliability of the diagnostic results.

[0165] This application also discloses a floor temperature and humidity detection system, such as... Figure 2 As shown, the system includes:

[0166] The data acquisition and processing module 1 is used to continuously acquire raw data detected by temperature and humidity sensors in the target floor area, and to clean, denoise and synchronize the raw data to obtain pre-processed temperature and humidity time series data.

[0167] Feature analysis module 2 is used to perform multi-dimensional feature analysis on the preprocessed temperature and humidity time series data. The multi-dimensional feature analysis includes spectrum analysis, amplitude distribution analysis, data coherence analysis, and cross-correlation analysis with related physical quantities, so as to extract the fluctuation patterns and correlation characteristics of the temperature and humidity data in different dimensions and obtain multi-dimensional features.

[0168] Deviation identification module 3 is used to identify the source of the temperature and humidity measurement deviation based on the multi-dimensional features, and to identify temperature and humidity fluctuations that do not conform to the characteristics of environmental changes or sensor drift as potential signals caused by changes in the physical structure of the floor, thereby obtaining a physical structure change signal.

[0169] The pattern comparison and diagnosis module 4 is used to obtain multi-dimensional features of the physical structure change signal based on the physical structure change signal, and compare these multi-dimensional features with a preset physical degradation feature pattern library. The physical degradation feature pattern library stores multi-dimensional feature patterns of temperature and humidity data corresponding to different types of flooring materials and underlying structures during specific physical degradation processes. If the comparison results show a high degree of match, a potential physical problem is determined, and diagnostic information with a clear physical root cause is generated.

[0170] The early warning report module 5 is used to trigger an early warning signal based on the diagnostic information and generate a detailed diagnostic report, which includes the problem area, the specific physical root cause diagnosed, and recommended preventive maintenance measures.

[0171] The above description is merely an embodiment of this application and is not intended to limit the scope of protection of this application.

Claims

1. A method for detecting floor temperature and humidity, characterized in that, Includes the following steps: The raw data detected by the temperature and humidity sensors preset in the target floor area are continuously collected, and the raw data is cleaned, denoised and time-synchronized to obtain pre-processed temperature and humidity time series data. Multi-dimensional feature analysis is performed on the preprocessed temperature and humidity time series data. The multi-dimensional feature analysis includes spectrum analysis, amplitude distribution analysis, data coherence analysis, and cross-correlation analysis with related physical quantities, in order to extract the fluctuation patterns and correlation characteristics of temperature and humidity data in different dimensions and obtain multi-dimensional features. Based on the multi-dimensional characteristics, the source of temperature and humidity measurement deviation is identified, and temperature and humidity fluctuations that do not conform to the characteristics of environmental change or sensor drift are identified as potential signals caused by changes in the physical structure of the floor, thus obtaining the physical structure change signal. Based on the physical structure change signal, multi-dimensional features of the physical structure change signal are obtained, and these features are compared with a preset physical degradation feature pattern library. This library stores multi-dimensional feature patterns of temperature and humidity data corresponding to different types of flooring materials and underlying structures during specific physical degradation processes. If the comparison results show a high degree of match, a potential physical problem is identified, and diagnostic information with a clear physical root cause is generated. Based on the diagnostic information, an early warning signal is triggered, and a detailed diagnostic report is generated, which includes the problem area, the specific physical cause diagnosed, and recommended preventive maintenance measures.

2. The method for detecting floor temperature and humidity according to claim 1, characterized in that, The step involves comparing the multi-dimensional features of the physical structure change signal with a preset physical degradation feature pattern library. This library stores multi-dimensional feature patterns of temperature and humidity data corresponding to different types of flooring materials and underlying structures during specific physical degradation processes. If the comparison results show a high degree of match, a potential physical problem is identified, and diagnostic information with a clear physical root cause is generated. This process specifically includes the following steps: Active acoustic excitation is applied to the floor, and acoustic response data of the floor is collected; The local acoustic impedance spectrum of the floor is constructed based on the acoustic response data; The abnormal features of the local acoustic impedance spectrum are correlated with the multi-dimensional features of the physical structure change signal; Based on the correlation analysis results, pattern comparison is performed in the physical degradation feature pattern library, which stores acoustic impedance spectrum patterns and temperature and humidity response patterns corresponding to different types of floor materials and substructures during specific physical degradation processes. as well as If the comparison results are highly consistent, a potential physical problem is identified, and diagnostic information with a clear physical root cause is generated.

3. The method for detecting floor temperature and humidity according to claim 2, characterized in that, The correlation analysis between the anomalous features of the local acoustic impedance spectrum and the multi-dimensional features of the physical structure change signal specifically includes the following steps: Time-delay correlation analysis is performed on the anomalous features of the local acoustic impedance spectrum and the multidimensional features of the physical structure change signal to identify the time lag relationship between the anomalous features and the multidimensional features; Based on the time lag relationship, calculate the dynamic response characteristics between the anomalous features of the local acoustic impedance spectrum and the multidimensional features of the physical structure change signal; The dynamic response characteristics are evaluated in context, taking into account current environmental parameters and historical degradation trends. as well as Based on the context evaluation results, the physical directivity of the correlation between the anomalous features of the local acoustic impedance spectrum and the multidimensional features of the physical structure change signal is determined.

4. The method for detecting floor temperature and humidity according to claim 3, characterized in that, The step of performing time-delay correlation analysis on the anomalous features of the local acoustic impedance spectrum and the multi-dimensional features of the physical structure change signal to identify the time lag relationship between the anomalous features and the multi-dimensional features specifically includes the following steps: Based on the current environmental parameters and the identified degradation stages, the time series of abnormal features of the local acoustic impedance spectrum and the multi-dimensional feature time series of the physical structure change signal are dynamically segmented. Time-varying coherence analysis is performed on the time series of the anomalous features and the time series of the multidimensional features within each dynamic segment to identify the dynamic phase difference between the anomalous features and the multidimensional features at different frequencies. Based on the dynamic phase difference, a time lag distribution between the abnormal features and the multi-dimensional features is constructed; as well as Based on the shape of the time lag distribution and the context information of the dynamic segmentation, the time lag relationship between the abnormal features and the multi-dimensional features is determined.

5. The method for detecting floor temperature and humidity according to claim 4, characterized in that, The step of dynamically segmenting the time series of abnormal features of the local acoustic impedance spectrum and the multi-dimensional feature time series of the physical structure change signal based on current environmental parameters and identified degradation stages specifically includes the following steps: Real-time acquisition of local environmental parameters and characterization of local environmental gradients; Based on the local environmental parameters, the thermal and moisture diffusion characteristics of the floor material, and the sensor response time, time alignment and hysteresis compensation are performed on the time series of the local environmental parameters, the time series of the abnormal characteristics of the local acoustic impedance spectrum, and the multi-dimensional characteristic time series of the physical structure change signal. The correlation between the time-aligned local environmental gradient and the anomalous feature time series of the local acoustic impedance spectrum and the multidimensional feature time series of the physical structure change signal is analyzed. Based on the correlation analysis results and the identified degradation stages, structural change points caused by environmental gradient changes or degradation stage transitions in the time series are identified, and the abnormal feature time series of the local acoustic impedance spectrum and the multi-dimensional feature time series of the physical structure change signal are dynamically segmented accordingly.

6. The method for detecting floor temperature and humidity according to claim 5, characterized in that, The analysis of the correlation between the time-aligned local environmental gradient and the anomalous feature time series of the local acoustic impedance spectrum and the multi-dimensional feature time series of the physical structure change signal specifically includes the following steps: Multivariate time-frequency analysis is performed on the time-aligned local environmental gradient, the anomalous feature time series of the local acoustic impedance spectrum, and the multidimensional feature time series of the physical structure change signal to identify the synchronicity or causal relationship between the local environmental gradient and the anomalous feature time series of the local acoustic impedance spectrum and the multidimensional feature time series of the physical structure change signal at different frequencies and time scales.

7. The method for detecting floor temperature and humidity according to claim 6, characterized in that, The identification of the synchronicity or causal relationship at different frequencies and time scales between the time series of anomalous features of the local environmental gradient and the local acoustic impedance spectrum and the multi-dimensional feature time series of the physical structure change signal specifically includes the following steps: Multivariate time-frequency analysis was performed on the time series of the abnormal features of the local environmental gradient, the local acoustic impedance spectrum, and the multidimensional feature time series of the physical structure change signal to obtain the multivariate time-frequency analysis results. By analyzing the directional information flow in the multivariate time-frequency analysis results, the synchronicity or causal relationship between the local environmental gradient and the anomalous feature time series of the local acoustic impedance spectrum and the multidimensional feature time series of the physical structure change signal at different frequencies and time scales can be identified.

8. The method for detecting floor temperature and humidity according to claim 7, characterized in that, The analysis of the directional information flow in the multivariate time-frequency analysis results specifically includes the following steps: The time window or frequency range of the information flow analysis is dynamically adjusted based on the current environmental parameters and the identified degradation stages. Within the dynamically adjusted time window or frequency range, the amount and direction of information transmission between the local environmental gradient, the anomalous feature time series of the local acoustic impedance spectrum, and the multidimensional feature time series of the physical structure change signal are quantified. The assessment evaluates whether the information flow pattern formed by the quantified information transmission volume and direction conforms to the physical coupling characteristics under the aforementioned degradation stage and environmental conditions; and Based on the evaluation results, the physical orientation of the causal relationship between the local environmental gradient and the anomalous feature time series of the local acoustic impedance spectrum and the multidimensional feature time series of the physical structure change signal is determined.

9. A method for detecting floor temperature and humidity according to claim 8, characterized in that, The process of quantifying the information transfer quantity and direction between the local environmental gradient, the anomalous feature time series of the local acoustic impedance spectrum, and the multidimensional feature time series of the physical structure change signal specifically includes the following steps: Based on the current environmental parameters, the identified degradation stage, and the sensor response characteristics, adjust the calculation parameters of the information flow index to adapt to different physical coupling conditions. Under the adjusted parameters, the information flow index between the local environmental gradient, the anomalous feature time series of the local acoustic impedance spectrum, and the multidimensional feature time series of the physical structure change signal is calculated to obtain the initial information transmission volume and direction. Analyze the known information flow patterns related to the local environmental gradient or the sensor's own characteristics in the initial information transmission volume and direction; From the initial information transmission volume and direction, known information flow patterns related to local environmental gradients or sensor characteristics are filtered out to obtain the information flow characterizing the deterioration of the floor material. as well as The information flow caused by the degradation of the flooring material is quantified to obtain the final information transmission quantity and direction.

10. A floor temperature and humidity detection system, characterized in that, The system includes: The data acquisition and processing module is used to continuously acquire raw data detected by temperature and humidity sensors preset in the target floor area, and to clean, denoise and time synchronize the raw data to obtain pre-processed temperature and humidity time series data. The feature analysis module is used to perform multi-dimensional feature analysis on the preprocessed temperature and humidity time series data. The multi-dimensional feature analysis includes spectrum analysis, amplitude distribution analysis, data coherence analysis, and cross-correlation analysis with related physical quantities, so as to extract the fluctuation patterns and correlation characteristics of temperature and humidity data in different dimensions and obtain multi-dimensional features. The deviation identification module is used to identify the source of temperature and humidity measurement deviation based on the multi-dimensional features, and to identify temperature and humidity fluctuations that do not conform to the characteristics of environmental changes or sensor drift as potential signals caused by changes in the physical structure of the floor, thereby obtaining the physical structure change signal. The pattern comparison and diagnosis module is used to obtain multi-dimensional features of physical structure change signals based on the physical structure change signals, and compare these multi-dimensional features with a preset physical degradation feature pattern library. This library stores multi-dimensional feature patterns of temperature and humidity data corresponding to different types of flooring materials and underlying structures during specific physical degradation processes. If the comparison results show a high degree of match, a potential physical problem is identified, and diagnostic information with a clear physical root cause is generated. The early warning report module is used to trigger an early warning signal based on the diagnostic information and generate a detailed diagnostic report, which includes the problem area, the specific physical cause diagnosed, and recommended preventive maintenance measures.

Images