LCD display module moisture-proof and vibration-proof control system based on multi-dimensional environment perception

Abstract

The invention discloses an LCD display module moisture-proof and vibration-proof control system based on multi-dimensional environment perception, and relates to the technical field of module protection, and the system comprises a data collection and preprocessing module which is used for collecting module wet vibration monitoring data and carrying out the preprocessing of the module wet vibration monitoring data; the wet vibration coupling state recognition module is used for evaluating the wet vibration coupling degree, executing fragment recognition and aggregation and generating a wet vibration coupling data set; the resonance risk discriminant analysis module is used for quantifying the resonance risk intensity of the current working condition and executing risk window identification and frequency stability screening; and the wet vibration resonance linkage regulation and control module is used for identifying the regulation and control trigger window, generating regulation and control target parameters, generating regulation and control instructions according to the regulation and control target parameters, and issuing and executing the regulation and control instructions. The problems that in the prior art, under the high-humidity micro-vibration working condition, the vibration transfer ratio is increased due to the fact that foam moisture absorption state changes cannot be considered synchronously, resonance risk judgment is not accurate, and the damp-proof and vibration-proof regulation and control triggering basis is insufficient are solved.

Description

Technical Field

[0001] This invention relates to the field of module protection technology, specifically to a moisture-proof and vibration-proof control system for LCD display modules based on multi-dimensional environmental perception. Background Technology

[0002] With the increasing demands on the reliability of display modules from applications such as in-vehicle cockpit displays, industrial control panels, and outdoor information terminals, technologies for structural protection and operational control of display modules in complex environments are constantly iterating. Related solutions are gradually shifting from single-condition management to comprehensive sensing and closed-loop control of multi-source environmental parameters. Against this backdrop, the use of cavity heating and dehumidification to stabilize the internal humidity of the module, combined with wet vibration resonance linkage control to suppress the accumulation of structural stress and fluctuations in connection status under humid conditions and micro-vibration, has become an important technological development direction for the environmental adaptability design and control strategies of display modules.

[0003] For example, application CN119451045A discloses a heat dissipation module and a display device. The heat dissipation module includes multiple heat sinks, multiple heat pipes, a heat dissipation body, and a first support. A first cavity is formed inside the heat dissipation body, and a second cavity is formed inside each heat pipe. A valve is provided at the connection between the heat dissipation body and the heat pipes, and the first and second cavities are connected or closed via the valve. The first cavity is filled with coolant. A controller is provided inside the heat dissipation body, and a sensor is provided inside each heat pipe. The sensor is electrically connected to the controller, and the controller is electrically connected to each valve. When the sensor detects that a heat pipe has reached a first preset state, the controller controls the valve in the corresponding heat pipe to open; when the sensor detects that a heat pipe has reached a second preset state, the controller controls the valve in the corresponding heat pipe to close. This application uses the above method to achieve targeted cooling of locally high-temperature areas of the heat dissipation module, thereby ensuring the heat dissipation stability of the heat dissipation module.

[0004] However, existing technologies mostly focus on temperature control or heat dissipation path optimization, and generally do not conduct multi-dimensional correlation monitoring of material performance degradation caused by humidity penetration and structural damping drift caused by micro-vibration impact. They also lack systematic identification and control strategies for the wet vibration coupling evolution process, resonance risk triggering mechanism and their interactive effects. In complex environments, traditional heat dissipation or structural control solutions struggle to form a unified understanding of multiple factors such as humidity accumulation, clamping stiffness attenuation, foam softening due to moisture absorption, and enhanced vibration transmission. This can lead to LCD display modules still experiencing insufficient moisture protection, structural instability, and abnormal deformation or display defects induced by resonance during long-term operation, making it difficult to meet the stability requirements of high-reliability display devices throughout their entire life cycle.

[0005] Therefore, in order to address the above issues, there is an urgent need for a moisture-proof and vibration-proof control system for LCD display modules based on multi-dimensional environmental perception. Summary of the Invention

[0006] Technical problems to be solved To address the shortcomings of existing technologies, this invention provides a moisture-proof and vibration-proof control system for LCD display modules based on multi-dimensional environmental perception. This solves the problem that existing technologies cannot simultaneously consider the increase in vibration transmission ratio caused by changes in the moisture absorption state of foam under high humidity and micro-vibration conditions, resulting in inaccurate resonance risk judgment and insufficient triggering basis for moisture-proof and vibration-proof control.

[0007] To achieve the above objectives, the present invention provides the following technical solution: a moisture-proof and vibration-proof control system for LCD display modules based on multi-dimensional environmental perception, comprising: a data acquisition and preprocessing module, used to acquire module damp vibration monitoring data, and perform time synchronization, noise suppression, anomaly removal, missing data completion, and standardization processing on the module damp vibration monitoring data to generate preprocessed module damp vibration monitoring data; and a damp vibration coupling state identification module, used to construct a foam equivalent capacitance change rate sequence, a clamping stiffness change sequence, and a vibration transmissibility change sequence based on the preprocessed module damp vibration monitoring data, evaluate the degree of damp vibration coupling based on the coupling relationship between the sequences, and execute a segment based on the evaluation result. The system identifies and aggregates data to generate a wet vibration coupling dataset. A resonance risk discrimination analysis module performs sliding window frequency domain analysis on the module's triaxial acceleration sequence based on the wet vibration coupling dataset, generating the window's dominant frequency, dominant frequency variation, and dominant frequency amplitude sequence. It also quantifies the resonance risk intensity under the current operating condition, performs risk window identification and frequency stability screening based on the quantification results, and generates a resonance risk dataset. A wet vibration resonance linkage control module constructs a control intensity assessment value based on the wet vibration coupling dataset and the resonance risk dataset. It identifies the control trigger window based on the control intensity assessment value and generates control target parameters. Based on the control target parameters, it generates control commands and issues them for execution, and generates a control execution record set.

[0008] Further, the following steps are taken to collect module damp vibration monitoring data and perform time synchronization, noise suppression, anomaly removal, missing data completion, and standardization on the data to generate preprocessed module damp vibration monitoring data: Real-time acquisition of module damp vibration monitoring data, including module cavity temperature, module cavity relative humidity, module triaxial acceleration, frame triaxial acceleration, clamping point normal pressure, support pad compression, and foam equivalent capacitance; Dynamic time warping algorithm is used to process the acquired module damp vibration monitoring data. Multi-source time series data undergoes time synchronization and rhythm alignment processing, and a linear interpolation resampling algorithm is used to map data with different sampling frequencies to a unified time step. A Kalman filter algorithm is used to perform recursive filtering processing on the module's wet vibration monitoring data. A density-based spatial clustering algorithm is used to cluster, label, and remove abnormal segments in the module's wet vibration monitoring data, and a cubic spline interpolation algorithm is used to interpolate and complete short-time missing intervals. A min-max normalization algorithm is used to standardize the module's wet vibration monitoring data, unify the numerical scale, and eliminate dimensional differences.

[0009] Furthermore, based on the preprocessed module wet vibration monitoring data, a sequence of foam equivalent capacitance change rate, a sequence of clamping stiffness change, and a sequence of vibration transmissibility change are constructed. The specific steps for evaluating the degree of wet vibration coupling based on the coupling relationship between these sequences are as follows: Read the preprocessed module wet vibration monitoring data; calculate the change rate of foam equivalent capacitance values ​​at adjacent sampling points to obtain the foam equivalent capacitance change rate; extract the normal pressure at the clamping point and the compression of the support pad; calculate the clamping stiffness at each sampling point using the ratio of the normal pressure at the clamping point to the compression of the support pad; and calculate the change in clamping stiffness between adjacent sampling points; extract the module triaxial acceleration and the frame triaxial acceleration at each sampling point... The vibration transmissibility of each sampling point is calculated by taking the ratio of the module's vector magnitude to the frame's vector magnitude, and the change in vibration transmissibility between adjacent sampling points is also calculated. The absolute values ​​of the foam's equivalent capacitance change rate, clamping stiffness change, and vibration transmissibility change are multiplied sequentially to obtain the numerator of the wet vibration coupling. The sum of the temperature inside the module cavity and the temperature reference value is multiplied by the sum of the relative humidity inside the module cavity and the constant, and the product is added to the minimum term to obtain the denominator of the wet vibration coupling. The ratio of the wet vibration coupling numerator to the wet vibration coupling denominator is logarithmically calculated, and the square root of the absolute value of the logarithmic function is taken to obtain the wet vibration coupling evaluation value.

[0010] Furthermore, the specific steps for performing segment identification and aggregation based on the evaluation results to generate a wet vibration coupling dataset are as follows: Perform time series traversal on the wet vibration coupling evaluation values, and mark the intervals where the wet vibration coupling evaluation values ​​exceed the wet vibration coupling threshold in consecutive sampling points as wet vibration coupling segments; Perform segment aggregation processing on the set of wet vibration coupling segments, merge segments with adjacent start and end times and whose wet vibration coupling evaluation value changes do not exceed the aggregation threshold, generate a wet vibration coupling segment sequence, and extract the corresponding start and end time index, number of sampling points, and corresponding wet vibration coupling evaluation value to construct a wet vibration coupling dataset.

[0011] Furthermore, based on the wet vibration coupling dataset, a sliding window frequency domain analysis is performed on the module triaxial acceleration sequence to generate the window dominant frequency, dominant frequency change, and dominant frequency amplitude sequence. The specific steps for quantifying the resonance risk intensity under the current working condition are as follows: The wet vibration coupling dataset is read, and the wet vibration coupling segment sequence is segmented into fixed-length sliding time windows. The module triaxial acceleration sequence within each time window is subjected to a fast Fourier transform to obtain the frequency domain amplitude sequence of the corresponding window. The frequency component with the largest frequency domain amplitude within the window is retrieved, and the corresponding frequency component is recorded as the dominant frequency. The corresponding amplitude is extracted and written into the dominant frequency amplitude sequence. The adjacent time window difference processing is performed on the dominant frequency amplitude sequence to obtain the dominant frequency change sequence. The window dominant frequency, dominant frequency change, and dominant frequency amplitude of each time window are extracted, and combined with the corresponding wet vibration coupling evaluation value, a resonance risk evaluation value is calculated, and a resonance risk evaluation value sequence is generated.

[0012] Furthermore, the specific steps for comprehensively calculating the resonance risk assessment value are as follows: Perform an inverse hyperbolic sine function operation on the product of the main frequency amplitude and the main frequency change, and then multiply it by the sum of the wet vibration coupling assessment value and the constant one to obtain the resonance coupling numerator; take the absolute value of the difference between the window main frequency and the frequency reference value and add a minima to obtain the resonance coupling denominator; divide the resonance coupling numerator by the resonance coupling denominator to obtain the resonance risk assessment value.

[0013] Furthermore, based on the quantification results, the specific steps for performing risk window identification and frequency stability screening to generate a resonance risk dataset are as follows: Perform time series traversal on the resonance risk assessment value sequence, and mark the window intervals where the resonance risk assessment value exceeds the resonance risk threshold within N consecutive time windows as initial risk intervals; extract the corresponding window dominant frequency and dominant frequency change for each initial risk interval, construct a frequency stability test sequence, and perform sign consistency detection on the frequency stability test sequence, marking the window intervals with consistent signs and increasing amplitudes as frequency stable sub-intervals; perform interval intersection operation on the initial risk intervals and frequency stable sub-intervals, mark the intersection result as a valid risk interval, and extract the corresponding window dominant frequency, start and end time index, and resonance risk assessment value to construct a resonance risk dataset.

[0014] Furthermore, the specific steps for constructing the control strength assessment value based on the wet vibration coupling dataset and the resonance risk dataset are as follows: Read the wet vibration coupling dataset and the resonance risk dataset, and extract the corresponding window dominant frequency, dominant frequency change, resonance risk assessment value, and wet vibration coupling assessment value for each effective risk interval; divide the difference between the resonance risk assessment value and the wet vibration coupling assessment value by the sum of the two and the sum of the minimum term, and take the absolute value of the obtained ratio to obtain the risk difference term; divide the absolute value of the dominant frequency change by the absolute value of the difference between the window dominant frequency and the frequency reference value and the sum of the minimum term, and take the obtained ratio as the exponent, and take the exponential function value of the natural constant e to obtain the frequency domain sensitive term; multiply the risk difference term and the frequency domain sensitive term to obtain the control strength assessment value.

[0015] Further, the specific steps for identifying the control trigger window and generating control target parameters based on the control intensity assessment value are as follows: Real-time comparison of the control intensity assessment value and the control initiation threshold; marking the effective risk interval where the control intensity assessment value is greater than the control initiation threshold as the control trigger window; reading the corresponding control intensity assessment value, main frequency change, and main frequency offset for each control trigger window, and calculating the difference in wet vibration coupling assessment values ​​between adjacent windows to obtain the wet vibration increment; constructing control target parameters based on different trigger conditions: when the control intensity assessment value exceeds the vibration reduction control threshold, reading the module's triaxial acceleration sequence to calculate the vibration amplitude of the current window, generating vibration reduction control target parameters; when the main frequency offset exceeds the frequency band adjustment threshold, reading the window's main frequency and main frequency change to calculate the main frequency offset rate, generating frequency band adjustment target parameters; when the wet vibration increment exceeds the wet vibration mitigation threshold, reading the relative humidity inside the module cavity and the control trigger window to calculate the humidity accumulation rate, generating humidity mitigation target parameters; and extracting various control target parameters to construct vibration reduction control parameter tables, frequency band adjustment parameter tables, and humidity mitigation parameter tables according to window indices.

[0016] Further, the specific steps for generating and issuing control commands based on the control target parameters, and generating a control execution record set are as follows: Window-level parameter fusion processing is performed on the vibration reduction control parameter table, frequency band adjustment parameter table, and humidity slow-release parameter table. For cases where multiple types of control target parameters exist within the same window, the control intensity evaluation value, main frequency offset, and humidity vibration increment of the corresponding window are read, and a control priority list is constructed based on the control priority rules. All control target parameters within the window are sorted according to the control priority list, and control commands are generated based on the sorted control target parameters and corresponding time indices, constructing a control command sequence. The control command sequence is executed command by command: adjusting the controllable damping parameters of the module clamping mechanism based on the vibration reduction control target parameters; adjusting the frequency band working range of the backlight driver based on the frequency band adjustment target parameters; adjusting the working voltage of the cavity heating element based on the humidity slow-release target parameters; and extracting the execution result of each control command and its corresponding time index to construct a control execution record table.

[0017] The present invention has the following beneficial effects: (1) The moisture-proof and vibration-proof control system of LCD display module based on multi-dimensional environmental perception expresses the changes in material moisture absorption state, structural clamping state and vibration transmission state in a unified coupling scale through the wet vibration coupling evaluation value, so that the hidden risks of vibration amplitude not increasing significantly but local stress continuously accumulating under humidity conditions have searchable segment-level characterization.

[0018] (2) The LCD display module moisture-proof and vibration-proof control system based on multi-dimensional environmental perception performs sliding window frequency domain analysis under the constraint of wet vibration coupling segment and introduces frequency stability test screening, so that the resonant frequency band discrimination does not depend on the transient main frequency result of a single window, but forms a structured identification of the consistency of the main frequency evolution within the risk interval.

[0019] (3) The LCD display module moisture-proof and vibration-proof control system based on multi-dimensional environmental perception uses the control strength assessment value to jointly map the resonance risk assessment value, the wet vibration coupling assessment value and the main frequency deviation sensitivity, so that the control trigger judgment is changed from single threshold trigger to interval-level linkage trigger, and can directly output the trigger window sequence for control.

[0020] (4) The LCD display module moisture-proof and vibration-proof control system based on multi-dimensional environmental perception integrates and arranges the vibration reduction control target parameters, frequency band adjustment target parameters and humidity release target parameters under the same window index to form a sequence of control commands that can be issued, so that vibration control, frequency band adjustment and humidity release have a unified scheduling entry point, and support the determination and recording of control commands according to priority rules when multiple triggering conditions coexist. Attached Figure Description

[0021] Figure 1 This is a structural diagram of a moisture-proof and vibration-proof control system for an LCD display module based on multi-dimensional environmental perception. Figure 2 This is a diagram showing the control trigger window determination based on the control intensity assessment value. Figure 3 This is a flowchart of a moisture-proof and vibration-proof control system for LCD display modules based on multi-dimensional environmental perception. Detailed Implementation

[0022] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0023] Please see Figures 1-3This invention provides a technical solution: a moisture-proof and vibration-proof control system for LCD display modules based on multi-dimensional environmental perception, comprising: a data acquisition and preprocessing module for acquiring module wet vibration monitoring data and performing time synchronization, noise suppression, anomaly removal, missing data completion, and standardization on the module wet vibration monitoring data to generate preprocessed module wet vibration monitoring data; and a wet vibration coupling state identification module for constructing a foam equivalent capacitance change rate sequence, a clamping stiffness change sequence, and a vibration transmissibility change sequence based on the preprocessed module wet vibration monitoring data, evaluating the degree of wet vibration coupling based on the coupling relationship between the sequences, and performing segment identification and aggregation based on the evaluation results. The system combines the wet vibration coupling dataset and the resonance risk discrimination analysis module to perform sliding window frequency domain analysis on the module's triaxial acceleration sequence based on the wet vibration coupling dataset. This generates the window dominant frequency, dominant frequency change, and dominant frequency amplitude sequence, and quantifies the resonance risk intensity of the current operating condition. Based on the quantification results, it performs risk window identification and frequency stability screening to generate a resonance risk dataset. The wet vibration resonance linkage control module is used to construct a control intensity assessment value based on the wet vibration coupling dataset and the resonance risk dataset. Based on the control intensity assessment value, it identifies the control trigger window and generates control target parameters. Based on the control target parameters, it generates control commands and issues them for execution, and generates a control execution record set.

[0024] Specifically, the steps for collecting module damp vibration monitoring data and performing time synchronization, noise suppression, anomaly removal, missing data completion, and standardization on the module damp vibration monitoring data to generate preprocessed module damp vibration monitoring data are as follows: Real-time acquisition of module damp vibration monitoring data, including module cavity temperature, module cavity relative humidity, module triaxial acceleration, frame triaxial acceleration, clamping point normal pressure, support pad compression, and foam equivalent capacitance value; wherein, the module cavity temperature is acquired by a digital temperature sensor attached to the inner wall of the module cavity; the module cavity relative humidity is acquired by a sensor placed in the module cavity... The humidity is collected by a capacitive humidity sensor at the flow channel; the module's triaxial acceleration is collected by a triaxial MEMS accelerometer installed at a fixed reference point on the display module; the frame's triaxial acceleration is collected by a triaxial MEMS accelerometer installed at a designated measuring point on the frame's supporting beam; the clamping point's normal pressure is collected by a thin-film pressure sensor arranged within the clamping contact surface; the support pad's compression is collected by a linear displacement sensor installed aligned with the support pad's compression direction; the foam's equivalent capacitance is measured by arranging electrodes on both sides of the foam and connecting them to a capacitance-to-digital converter; during the acquisition process, a sampling timestamp is written to each sampling record and bound to the transmission. Sensor channel identification is used to perform unit consistency checks and value range checks on the module cavity temperature, module cavity relative humidity, module triaxial acceleration, frame triaxial acceleration, clamping point normal pressure, support pad compression, and foam equivalent capacitance value, respectively. Sampling points that fail the checks are added to the anomaly candidate set and their timestamp positions are retained. For the acquired module damp vibration monitoring data, a dynamic time warping algorithm is used to perform time synchronization and rhythm alignment processing on the multi-source time series, and a linear interpolation resampling algorithm is used to map data with different sampling frequencies to a unified time step. Among these steps, the original data sequence is first established using the sampling timestamp. The process begins with an initial time axis index, a unified time step, and the generation of a target time axis. For each data sequence, a cost matrix is ​​constructed with the sampling point number as the node, and a dynamic time warping path is calculated. The alignment index corresponding to the dynamic time warping path is written into an alignment mapping table, and then the data sequences are rearranged to the same time axis position according to the alignment mapping table. Subsequently, the timestamp intervals of adjacent valid sampling points are located on the target time axis, the interpolation coefficients are calculated according to the linear interpolation rule, and the interpolation values ​​of the resampled points are generated. The resampled data sequences are written into a unified step size data matrix. The Kalman filter algorithm is used to perform recursive filtering on the module's wet vibration monitoring data.The process involves establishing one-dimensional state recursion for the module cavity temperature, relative humidity, triaxial acceleration of the module, triaxial acceleration of the frame, normal pressure at the clamping point, compression of the support pad, and equivalent capacitance of the foam. Prediction updates are performed point-by-point using the time index of the data matrix with a unified step size. During the prediction phase, the filtered estimate from the previous moment is read to generate a prior estimate and calculate the prior covariance. During the update phase, the current observation value is read to calculate the Kalman gain and update the posterior estimate. The filtered sequence of each field is written back to the filtered data matrix. A density-based spatial clustering algorithm is used to cluster and label abnormal segments in the module's wet vibration monitoring data, and cubic spline interpolation is used to fill in short-term missing intervals. Specifically, a sample point set is constructed using the multi-field joint vector of the data matrix with a unified step size within a sliding window. The distance between sample points is calculated, and a density-based spatial clustering algorithm is used for clustering. Sample points designated as noise points are backfilled to their original time index positions and merged into anomalous segments based on continuity. Time index intervals corresponding to these anomalous segments are marked for removal, and a list of missing intervals is generated. The list of missing intervals is then processed segment by segment, reading the valid sampling points on both sides of each missing interval and generating a cubic spline interpolation node sequence. The cubic spline interpolation coefficients are calculated based on the node sequence and evaluated point-by-point on the target time axis of the missing interval. The completed values ​​are written to the corresponding positions within the missing intervals. The minimax normalization algorithm is used to standardize the module's wet vibration monitoring data. The minimum and maximum values ​​of each completed field are calculated within the same time window. Each sampling point is mapped to a fixed interval using minimax normalization, and a standardized data matrix is ​​output. Simultaneously, the minimum and maximum values ​​of each field are retained as normalization parameters to achieve a unified numerical scale and eliminate dimensional differences in subsequent wet vibration coupling assessment and resonance risk determination.

[0025] In this implementation scheme, a unified time axis and consistent data expression are established by collecting and recording the temperature inside the module cavity, the relative humidity inside the module cavity, the triaxial acceleration of the module, the triaxial acceleration of the frame, the normal pressure of the clamping point, the compression of the support pad, and the equivalent capacitance value of the foam. This allows the thermal and humidity state, vibration state, and clamping state at the same sampling moment to form a directly correlated continuous sequence, providing a stable data base for the subsequent construction of the foam equivalent capacitance change rate, clamping stiffness change, and vibration transmissibility change, and ensuring that the wet vibration coupling evaluation value has consistent input constraints in segment identification and risk interval determination.

[0026] Specifically, based on the preprocessed module wet vibration monitoring data, a sequence of foam equivalent capacitance change rate, a sequence of clamping stiffness change, and a sequence of vibration transmissibility change are constructed. The specific steps for evaluating the degree of wet vibration coupling based on the coupling relationship between these sequences are as follows: The preprocessed module wet vibration monitoring data is read, and the change rate of the foam equivalent capacitance value at adjacent sampling points is calculated to obtain the foam equivalent capacitance change rate. The foam equivalent capacitance change rate is used to characterize the transient drift intensity of the foam equivalent capacitance value between adjacent sampling points and serves as the input quantity for the wet vibration coupling numerator to characterize the contribution of the material's moisture absorption state to the change over time. The normal pressure at the clamping point and the compression of the support pad are extracted. The clamping stiffness at each sampling point is calculated using the ratio of the normal pressure at the clamping point to the compression of the support pad, and the change in clamping stiffness between adjacent sampling points is also calculated. The clamping stiffness characterizes the force constraint strength of the normal pressure at the clamping point relative to the compression of the support pad, and the change in clamping stiffness characterizes the drift amplitude of the clamping state between adjacent sampling points, serving as an input to the wet vibration coupling numerator to characterize the structural contribution of the clamping constraint to time-varying drift. The vector magnitudes of the module's triaxial acceleration and the frame's triaxial acceleration at each sampling point are extracted, and the vector magnitudes of the module and frame are used as the basis for calculation. The vibration transmissibility ratio at each sampling point is calculated using the ratio of the vibration transmissibility ratios, and the change in vibration transmissibility ratio between adjacent sampling points is also calculated. The vector magnitude is used to map the triaxial acceleration at each sampling point into a single amplitude sequence to maintain comparability between sampling points. The vibration transmissibility ratio characterizes the proportional relationship of vibration input transmission from the frame side to the module side. The change in vibration transmissibility ratio characterizes the abrupt change amplitude of the transmission path between adjacent sampling points and serves as the input to the wet vibration coupling numerator to characterize the transmission contribution of vibration transmission characteristics drifting over time. The absolute values ​​of the foam equivalent capacitance change rate, the absolute values ​​of the clamping stiffness change, and the change in vibration transmissibility ratio are used as the basis for the calculation. The absolute values ​​are multiplied sequentially to obtain the numerator of the wet vibration coupling. The absolute values ​​are used to eliminate differences in the direction of change and unify the sequence input into an amplitude quantity. The sequential multiplication is used to perform coupling convergence of the three types of change intensities under the same dimensional structure, ensuring that the numerator maintains a monotonic response to any increase in change intensity. The sum of the temperature inside the module cavity and the temperature reference value is multiplied by the sum of the relative humidity inside the module cavity and the constant 1. The product is then added to the minima to obtain the denominator of the wet vibration coupling. The minima are small but non-zero positive real numbers used to avoid numerical instability caused by division by zero during calculation. Their range is [insert range here]. arrive Unless otherwise specified, all subsequent minima will adopt this definition and value range. The sum of the temperature inside the module cavity and the temperature reference value is used to map the temperature state to an offset relative to the reference. The sum of the relative humidity inside the module cavity and a constant is used to map the humidity state to a positive constraint. The product of the two is used to form a joint normalized reference for the thermal and humid states. The ratio of the numerator and denominator of the wet vibration coupling is logarithmically calculated, and the absolute value of the logarithmic function is squared to obtain the wet vibration coupling evaluation value. The logarithmic function is used to map the multiplicative scale of the ratio to a compressible nonlinear scale to suppress the dominance of extreme ratios on the sequence amplitude. The absolute value is used to unify the sign expression after logarithmic mapping, and the square root is used to further perform nonlinear compression on the amplitude after logarithmic mapping and maintain the monotonic representation of amplitude changes, so that the wet vibration coupling evaluation value can be used for continuous sequence input for subsequent segment recognition.

[0027] The specific formula for calculating the damp vibration coupling evaluation value is as follows: ; In the formula, This represents the wet vibration coupling evaluation value. This represents the rate of change of the equivalent capacitance of the foam. This indicates the change in clamping stiffness. This represents the change in the vibration transmissibility. This indicates the temperature inside the module cavity. Indicates the temperature reference value. This indicates the relative humidity inside the module cavity. Indicates a minus term.

[0028] In this implementation scheme, the changes in the equivalent capacitance of foam, the normal pressure at the clamping point, the compression of the support pad, the triaxial acceleration of the module, and the triaxial acceleration of the frame at adjacent sampling points are uniformly mapped to the change rate of the equivalent capacitance of foam, the change in clamping stiffness, and the change in vibration transmission ratio. Combined with the temperature and relative humidity inside the module cavity, comparable wet vibration coupling evaluation values ​​are formed. This allows the clamping constraint drift and vibration transmission path drift caused by humidity softening to be stably characterized by the same quantitative scale, thereby providing a continuous and consistent judgment input for the subsequent identification of wet vibration coupling segments.

[0029] Specifically, the steps for generating a wet vibration coupling dataset by performing segment identification and aggregation based on the evaluation results are as follows: A time-series traversal is performed on the wet vibration coupling evaluation values. The wet vibration coupling evaluation values ​​are arranged in order of sampling timestamps and scanned point by point. During the scanning process, each sampling point is recorded to determine whether it meets the wet vibration coupling threshold condition. When a sampling point where the wet vibration coupling evaluation value first exceeds the wet vibration coupling threshold is encountered, the timestamp of that sampling point is recorded as the segment start position. When a sampling point where the wet vibration coupling evaluation value falls back below the wet vibration coupling threshold is encountered, the timestamp of the previous sampling point is recorded as the segment end position. The interval where the wet vibration coupling evaluation value exceeds the wet vibration coupling threshold in consecutive sampling points is marked as a wet vibration coupling segment. For each wet vibration coupling segment, a segment number is synchronously written, and the segment start timestamp, segment end timestamp, and segment start and end time index are saved. Based on the segment start and end time index, a subsequence of wet vibration coupling evaluation values ​​within the segment is extracted as the segment amplitude record. Segment aggregation processing is performed on the wet vibration coupling segment set. In the aggregation processing, the segments are sorted by their start timestamps and traversed segment by segment. The end timestamps of two adjacent wet vibration coupling segments are read. The start and end timestamps are used to determine the adjacency of start and end times. The wet vibration coupling evaluation value subsequences of two adjacent wet vibration coupling segments are read, and the difference in wet vibration coupling evaluation values ​​at the segment boundaries is calculated to obtain the change amplitude of the wet vibration coupling evaluation value. Segments with adjacent start and end times and whose wet vibration coupling evaluation value change amplitude does not exceed the aggregation threshold are merged. During merging, the start timestamp of the first segment is used as the start timestamp of the merged segment, and the end timestamp of the second segment is used as the end timestamp of the merged segment. The two wet vibration coupling evaluation value subsequences are concatenated according to time index to form the wet vibration coupling evaluation value subsequence of the merged segment, generating a wet vibration coupling segment sequence. The corresponding start and end time indices, the number of sampling points, and the corresponding wet vibration coupling evaluation values ​​are extracted to construct a wet vibration coupling dataset. The start and end time indices are determined by the index positions of the segment start timestamp and end timestamp in the wet vibration coupling evaluation value sequence. The number of sampling points is obtained by subtracting the segment start timestamp from the segment end timestamp and adding a constant. The wet vibration coupling evaluation values ​​are written into the wet vibration coupling evaluation value subsequence extracted according to the start and end timestamp.

[0030] In this implementation scheme, by organizing the wet vibration coupling evaluation values ​​into intervals along the sampling timestamp dimension and maintaining a consistent expression of the segment boundaries using start and end time indices, the wet vibration coupling segment sequence can carry the wet vibration coupling threshold determination results and aggregated threshold constraint results with unified time constraints. This transforms the scattered over-threshold intervals into a structured wet vibration coupling dataset that can be directly used for subsequent frequency domain analysis and linkage control.

[0031] Specifically, the following steps are taken to perform sliding window frequency domain analysis on the module triaxial acceleration sequence based on the wet vibration coupling dataset, generating the window dominant frequency, dominant frequency change, and dominant frequency amplitude sequence, and quantifying the resonance risk intensity of the current working condition: The wet vibration coupling dataset is read, and the module triaxial acceleration sampling interval corresponding to each wet vibration coupling segment is located according to the start and end time index of the wet vibration coupling segment sequence. The module triaxial acceleration within each wet vibration coupling segment is written into the segment acceleration sequence set in the order of sampling timestamps. A fixed-length sliding time window segmentation process is then performed on the wet vibration coupling segment sequence, with a unified time step used in the segmentation process. The window length and window sliding step size are determined. A time window index list is generated for each sampling interval within the wet vibration coupling segment that meets the window length condition, using an incrementing window starting index. A Fast Fourier Transform (FFT) is performed on the module triaxial acceleration sequence within each time window to obtain the corresponding window's frequency domain amplitude sequence. Before the FFT, the module triaxial acceleration sequence within the time window is mean-reduced and written to the window sequence buffer. A frequency index sequence is generated based on the number of sampling points within the window and established with the frequency domain amplitude sequence. The frequency component with the largest frequency domain amplitude within the window is retrieved, and this frequency component is recorded as the dominant frequency. The corresponding amplitude is written into the main frequency amplitude sequence. During the retrieval process, the frequency position in the corresponding frequency index sequence is located by the maximum value index of the frequency domain amplitude sequence. The frequency value corresponding to this frequency position is written into the window main frequency sequence, and the amplitude corresponding to this frequency position is written into the main frequency amplitude sequence. A window number and a window start and end timestamp are written for this window. Adjacent time window difference processing is performed on the main frequency amplitude sequence to obtain the main frequency change sequence. In the difference processing, the window main frequencies of adjacent windows are differentially processed according to the window number order, and the absolute value of the difference result is taken as the main frequency change. The main frequency change and the corresponding window number are written into the main frequency change sequence. The process involves extracting the dominant frequency, frequency change, and amplitude of each time window, and combining them with the corresponding damp vibration coupling evaluation value to calculate the resonance risk assessment value and generate a resonance risk assessment value sequence. Specifically, for each time window, the process involves retrieving the time coverage relationship in the damp vibration coupling dataset based on the start and end timestamps of the window, reading the corresponding damp vibration coupling evaluation value for that time window, establishing a window mapping table, writing the dominant frequency, frequency change, amplitude, and damp vibration coupling evaluation value of the window into the resonance evaluation calculation table according to the window number, and then performing the resonance risk assessment value calculation window by window according to the window number order in the resonance evaluation calculation table and outputting the resonance risk assessment value sequence.

[0032] In this implementation scheme, a unified mapping is established between the start and end time indices of the wet vibration coupling segment sequence and the sliding time window frequency domain analysis of the module's triaxial acceleration. This enables the window's dominant frequency, dominant frequency change, and dominant frequency amplitude to form a consistent aligned input with the wet vibration coupling evaluation value under the same window number. This limits the resonance risk evaluation value sequence to the effective time range corresponding to the wet vibration coupling dataset, providing a directly referable quantitative basis for the resonance risk intensity for the subsequent identification of the effective risk interval.

[0033] Specifically, the steps for comprehensively calculating the resonance risk assessment value are as follows: Perform an inverse hyperbolic sine function operation on the product of the main frequency amplitude and the main frequency change. During this process, the inverse hyperbolic sine function is used to nonlinearly stretch the joint change of the main frequency amplitude and the main frequency change, making the frequency domain abrupt change more easily reflect the intensity difference in subsequent calculations. Then multiply by the sum of the wet vibration coupling assessment value and a constant. By explicitly superimposing the wet vibration coupling assessment value into the frequency domain change structure, the influence of the wet vibration background on the frequency domain response is enhanced, resulting in the resonance coupling numerator. Take the absolute value of the difference between the window main frequency and the frequency reference value and add a minimum term. By introducing this minimum term, numerical instability caused when the difference is close to zero is avoided, and the resolution of the frequency offset in the overall ratio structure is enhanced, resulting in the resonance coupling denominator. The frequency reference value represents the reference main frequency corresponding to the same wet vibration coupling segment and is used as the reference quantity for the window main frequency offset. The frequency reference value is obtained by: after obtaining the window main frequency sequence and the main frequency change sequence, extracting the segment starting position from the beginning position in chronological order for each wet vibration coupling segment. Using a time window as the reference window interval, median aggregation is performed on the dominant frequencies within the reference window interval to obtain the frequency reference value. The reference window number ranges from 3 to 15. The numerator of the resonance coupling is divided by the denominator of the resonance coupling. This ratio structure forms a comprehensive quantification of frequency domain amplitude changes, frequency abrupt changes, and wet vibration coupling strength, thus obtaining the resonance risk assessment value.

[0034] The specific formula for calculating the resonance risk assessment value is as follows: ; In the formula, This indicates the resonance risk assessment value. Indicates the main frequency amplitude. This represents the change in the main frequency. Indicates the window's main frequency. Indicates the frequency reference value. This represents the wet vibration coupling evaluation value. Indicates a minus term.

[0035] In this implementation scheme, the main frequency amplitude, main frequency change, window main frequency, frequency reference value, and wet vibration coupling evaluation value are uniformly quantified under the same nonlinear ratio framework. This enables the resonance risk evaluation value to simultaneously characterize the frequency domain amplitude surge characteristics, frequency shift characteristics, and wet vibration background intensity characteristics. Under the constraint of the minimum term, it maintains stable comparability for scenarios close to the reference frequency, thereby providing a continuous and consistent risk input for subsequent effective risk interval determination.

[0036] Specifically, the steps for generating a resonance risk dataset by performing risk window identification and frequency stability screening based on the quantification results are as follows: A time series traversal is performed on the resonance risk assessment value sequence. Before the traversal, the number of continuous time windows N is limited to three to fifteen, and the resonance risk assessment values ​​are judged window by window according to the window number order. For each window number, a judgment mark is recorded indicating whether the resonance risk assessment value exceeds the resonance risk threshold. During the traversal, a continuous window interval of length N is used as the judgment unit. When the resonance risk assessment value of each window in a continuous window interval exceeds the resonance risk threshold, the starting window number of the continuous window interval is recorded as the initial risk interval starting index, and the ending window number of the continuous window interval is recorded as the initial risk interval ending index. The corresponding window interval is then marked as the initial risk interval. For each initial risk interval, the corresponding window main frequency and the main frequency change are extracted, and the window main frequency is written into the main frequency according to the window number order of the initial risk interval. The process involves verifying the frequency stability test sequence by writing the dominant frequency change into the change test sequence, constructing a frequency stability test sequence based on the change test sequence, and performing a sign consistency check on the frequency stability test sequence. During the check, the frequency stability test sequence is mapped to a sign sequence window by window, with the sign of the first window as the reference sign. The signs of each subsequent window are compared one by one to see if they are consistent. At the same time, the amplitude of the frequency stability test sequence is judged to be increasing, and the amplitude comparison results of each adjacent window are recorded. The window intervals with consistent signs and increasing amplitudes are marked as frequency stable sub-intervals. An interval intersection operation is performed on the initial risk interval and the frequency stable sub-intervals. In the intersection operation, the window number is used as the interval coordinate. The start index and end index of the initial risk interval and the start index and end index of the frequency stable sub-interval are read. The start index and end index of the overlap are calculated. The intersection result is marked as a valid risk interval, and the corresponding window dominant frequency, start and end time index, and resonance risk assessment value are extracted to construct a resonance risk dataset.

[0037] In this implementation scheme, by introducing an interval constraint of the number of continuous time windows N on the resonance risk assessment value sequence and unifying the initial risk interval, frequency stability sub-interval, and effective risk interval under the window number coordinate for consistent judgment, the resonance risk dataset can simultaneously meet the resonance risk threshold condition and the frequency stability test condition. This allows isolated high values ​​caused by transient fluctuations to be separated from the effective risk interval, forming a stable risk input that can be directly used for subsequent control trigger window determination.

[0038] Specifically, the steps for constructing control strength assessment values ​​based on the damp vibration coupling dataset and resonance risk dataset are as follows: Read the damp vibration coupling dataset and resonance risk dataset. During the reading process, locate the corresponding window number range according to the start and end time index of the effective risk interval. For each effective risk interval, extract the corresponding window dominant frequency, dominant frequency change, resonance risk assessment value, and damp vibration coupling assessment value, so that subsequent calculations use the same window number as the alignment basis. Divide the difference between the resonance risk assessment value and the damp vibration coupling assessment value by the sum of the two and the sum of the minimum terms. This normalized difference structure characterizes the degree of deviation of the resonance risk assessment value from the damp vibration coupling assessment value and weakens the influence of the magnitude difference comparison value. Take the absolute value of the obtained ratio. To eliminate the interference of the difference sign on the deviation magnitude determination, a risk difference term is obtained. The absolute value of the main frequency change is divided by the sum of the absolute value of the difference between the window main frequency and the frequency reference value and the minimum term. This ratio structure characterizes the sensitivity of the main frequency change to the main frequency offset. The minimum term is used to constrain the numerical divergence when the denominator is close to zero. The obtained ratio is used as the exponent, and the natural constant e is taken as the exponential function value. The nonlinear amplification characteristic of the exponential function is used to enhance the discrimination of the sensitivity difference in the subsequent product structure, resulting in a frequency domain sensitivity term. The risk difference term and the frequency domain sensitivity term are multiplied together. Through product coupling, the deviation magnitude information and the frequency domain sensitivity information are synthesized into a single quantized output on the same scale, resulting in the control strength assessment value.

[0039] The specific formula for calculating the control intensity assessment value is as follows: ; In the formula, This indicates the control intensity assessment value. This indicates the resonance risk assessment value. This represents the wet vibration coupling evaluation value. This represents the change in the main frequency. Indicates the window's main frequency. Indicates the frequency reference value. Indicates a minus term.

[0040] In this embodiment, Table 1 shows the control strength assessment results and their corresponding input data for the five effective risk intervals. Specifically: the resonance risk assessment value for effective risk interval S1 is 3.80, the wet vibration coupling assessment value is 2.10, the dominant frequency change is 4.20, the window dominant frequency is 172.00, the frequency reference value is 188, and the minima are... The calculated control strength assessment value is 0.49. The resonance risk assessment value for the effective risk interval S2 is 5.60, the wet vibration coupling assessment value is 1.40, the dominant frequency change is 7.80, the window dominant frequency is 195.00, the frequency reference value is 180, and the minima are... The calculated control strength assessment value is 1.01. The resonance risk assessment value for the effective risk interval S3 is 2.20, the wet vibration coupling assessment value is 3.10, the dominant frequency change is 2.60, the window dominant frequency is 183.50, the frequency reference value is 180, and the minima are... The calculated control strength assessment value is 0.36. The resonance risk assessment value for the effective risk interval S4 is 6.30, the wet vibration coupling assessment value is 5.80, the dominant frequency change is 1.20, the window dominant frequency is 181.00, the frequency reference value is 180, and the minima are... The calculated control strength assessment value is 0.14. The resonance risk assessment value for the effective risk interval S5 is 4.10, the wet vibration coupling assessment value is 0.90, the dominant frequency change is 5.50, the window dominant frequency is 160.00, the frequency reference value is 180, and the minima are... The calculated control strength assessment value is 0.84. Table 1 lists the resonance risk assessment value, wet vibration coupling assessment value, main frequency change, window main frequency, frequency reference value, and minima, which can correlate the input and output of the control strength assessment value on an interval scale. This is used for subsequent determination of the control trigger window and construction of control target parameters.

[0041] Table 1. Data on Control Intensity Assessment Values

[0042] like Figure 2 As shown in the figure, the control intensity assessment values ​​for five effective risk intervals and their comparison with the control activation threshold are displayed. The bar chart uses two colors to distinguish whether control has been triggered: blue bars indicate that the control intensity assessment value for the corresponding effective risk interval does not exceed the control activation threshold, and orange bars indicate that the control intensity assessment value for the corresponding effective risk interval exceeds the control activation threshold. A blue horizontal solid line marks the control activation threshold line in the figure, used to determine the triggering of the control intensity assessment value; the top of each bar is labeled with the corresponding control intensity assessment value, facilitating a direct comparison of the control intensity amplitudes of different effective risk intervals. As can be seen from the figure, the control intensity assessment values ​​for S2 and S5 are both higher than the control activation threshold line, corresponding to orange bars, and are determined to be control trigger windows; the control intensity assessment values ​​for S1, S3, and S4 are all lower than the control activation threshold line, corresponding to blue bars, and do not belong to control trigger windows. Figure 2 By visualizing the results of triggering effective risk intervals using column colors, threshold lines, and control intensity assessment values, the system provides a structured representation of these results, offering a direct reference for generating control target parameters and issuing control commands based on the control trigger window.

[0043] In this implementation scheme, by aligning and compressing the window main frequency, main frequency change, resonance risk assessment value, and damp vibration coupling assessment value within the effective risk range under the same window number into a single control strength assessment value, the deviation of the risk difference term from the resonance risk assessment value relative to the damp vibration coupling assessment value has a unified dimension expression. At the same time, the nonlinear mapping of the frequency domain sensitive term is used to enhance the distinguishability under different frequency offset conditions, thereby providing a directly comparable continuous quantitative input for determining the control start threshold.

[0044] Specifically, the steps for identifying the control trigger window and generating control target parameters based on the control strength assessment value are as follows: Real-time comparison of the control strength assessment value and the control initiation threshold; during the comparison process, performing window-by-window judgment on the control strength assessment value according to the window numbering order of the effective risk interval, and writing the judgment result corresponding to each window into the trigger judgment sequence; marking the effective risk interval where the control strength assessment value is greater than the control initiation threshold as the control trigger window; reading the corresponding control strength assessment value, main frequency change, and main frequency offset for each control trigger window; during the reading process, locating the corresponding window based on the start and end time index of the control trigger window. The system calculates the wet vibration coupling evaluation value and completes window alignment. It then calculates the difference between the wet vibration coupling evaluation values ​​of adjacent windows. During the difference calculation, the wet vibration coupling evaluation value of the previous window is selected based on temporal proximity and subtracted from the current window's wet vibration coupling evaluation value to obtain the difference result. The algebraic value of the difference result is taken to maintain the increasing direction information, thus obtaining the wet vibration increment. Based on different triggering conditions, control target parameters are constructed: when the control strength evaluation value exceeds the vibration reduction control threshold, the module triaxial acceleration sequence corresponding to the control trigger window is read. The module triaxial acceleration sampling segment within the window is extracted according to the window's start and end timestamps while maintaining the sampling timestamp order. The module triaxial acceleration within the window is then calculated. The velocity vector magnitude sequence is processed, and its maximum and minimum values ​​are extracted. The difference between the maximum and minimum values ​​is calculated to obtain the vibration amplitude of the current window, generating vibration reduction control target parameters. When the main frequency offset exceeds the frequency band adjustment threshold, the main frequency and main frequency change of the window are read. During the reading process, the difference between the frequency reference value and the main frequency of the window is used as the main frequency offset, which is kept consistent with the window number. The ratio of the main frequency offset to the main frequency change is calculated as the main frequency offset rate, and this ratio and the window number are written into the target parameter record to generate the frequency band adjustment target parameters. When the wet vibration increment exceeds the wet vibration mitigation threshold, the relative humidity inside the module cavity is read. The sampling interval within the control trigger window is located, and the differential sequence of relative humidity between adjacent sampling points in the module cavity within this sampling interval is calculated. The cumulative amount of humidity is obtained by summing the differential sequence. Then, the ratio of the cumulative amount of humidity to the time length is calculated using the time length of the control trigger window as the normalized time reference to obtain the humidity accumulation rate, and humidity release target parameters are generated. Various control target parameters are extracted and constructed into vibration reduction control parameter table, frequency band adjustment parameter table and humidity release parameter table according to window index. During the construction process, the window index is used as the primary key field and the corresponding target parameters are written into the same row of records to maintain the alignment consistency within the table.

[0045] In this implementation scheme, by aligning the trigger determination of the control intensity assessment value with the window number of the control trigger window, and transforming the main frequency change, main frequency offset, and wet vibration increment into vibration reduction control target parameters, frequency band adjustment target parameters, and humidity slow release target parameters under the same time window coordinate, various control target parameters can form a structured parameter table with the window index as a unified entry point. This provides a directly referable window-level target input for the generation of subsequent control commands in the wet vibration resonance linkage control link, and provides a consistent data entry point for the window-level quantization and trigger determination of cavity heating and dehumidification related target parameters.

[0046] Specifically, the steps for generating and issuing control commands based on the control target parameters, and generating a control execution record set are as follows: Window-level parameter fusion processing is performed on the vibration reduction control parameter table, frequency band adjustment parameter table, and humidity release parameter table. Before fusion processing, the record rows of the corresponding windows in the three parameter tables are read window by window using the window index as the alignment key. The target parameters corresponding to missing record rows are marked as null values ​​to maintain the continuity of the window index. For cases where multiple control target parameters exist within the same window, the control intensity evaluation value, main frequency offset, and humidity vibration increment of the corresponding window are read, and the control intensity evaluation value, main frequency offset, and humidity vibration increment are written to... The priority determination field of this window constructs a control priority list based on the control priority rules. During the construction process, the control intensity assessment value, the main frequency offset, and the wet vibration increment are mapped to priority determination values ​​and priority numbers are generated. All control target parameters within the window are sorted according to the control priority list. In the sorting process, the priority number is used as the first sorting key, and the time index is used as the second sorting key to determine the execution order within the same window. Control instructions are generated based on the sorted control target parameters and corresponding time indices, constructing a control instruction sequence. During the construction process, each control instruction is written with an instruction number, window index, and time index. The system includes: target parameter type identifier and target parameter value; execution of instruction-by-instruction in the control command sequence: adjusting the controllable damping parameter of the module clamping mechanism based on the vibration reduction control target parameter, writing the vibration reduction control target parameter into the controllable damping parameter set value field and simultaneously writing the instruction number and time index during the instruction issuance process; adjusting the backlight drive frequency band operating range based on the frequency band adjustment target parameter, mapping the frequency band adjustment target parameter to the upper and lower limit set values ​​of the frequency band operating range and writing the instruction number and time index during the instruction issuance process; adjusting the working voltage of the cavity heating element based on the humidity slow-release target parameter, mapping the humidity slow-release target parameter to the working voltage during the instruction issuance process. The set value is pressed and written with the instruction number and time index; the execution result of each control instruction and the corresponding time index are extracted to construct a control execution record table. During the extraction process, the instruction number, window index, time index, execution parameter set value, parameter value before execution, parameter value after execution, and execution status mark are recorded; in particular, before issuing the set value for the controllable damping parameter, the frequency band working range of the backlight drive, and the working voltage of the cavity heating element, the lower safety limit value and the upper safety limit value of the corresponding parameter are read respectively, the range constraint verification is performed on the set value to be issued, and the set value exceeding the lower safety limit value and the upper safety limit value is corrected to the corresponding safety boundary before being issued.

[0047] In this implementation scheme, by using a window index to integrate and sort the vibration reduction control parameter table, frequency band adjustment parameter table, and humidity slow release parameter table, and by incorporating the control intensity assessment value, main frequency offset, and wet vibration increment into the same priority determination entry, the control command sequence can form a traceable execution link at the time index scale. At the same time, the set value changes and execution status corresponding to each control command are recorded as a control execution record table, thereby forming a unified execution closed loop oriented towards multiple triggering conditions under the wet vibration resonance linkage control path, and providing a structured basis for the trigger boundary tuning and control priority rule verification of cavity heating and dehumidification related commands.

[0048] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0049] The preferred embodiments of the present invention disclosed above are merely illustrative of the invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the invention to the specific implementations described. Clearly, many modifications and variations can be made based on the content of this specification. This specification selects and specifically describes these embodiments to better explain the principles and practical applications of the invention, thereby enabling those skilled in the art to better understand and utilize the invention. The invention is limited only by the claims and their full scope and equivalents.

Claims

1. A moisture-proof and anti-vibration control system for an LCD display module based on multi-dimensional environment perception, characterized in that, include: The data acquisition and preprocessing module is used to acquire module damp vibration monitoring data and perform time synchronization, noise suppression, anomaly removal, missing data completion and standardization on the module damp vibration monitoring data to generate preprocessed module damp vibration monitoring data; The wet vibration coupling state identification module is used to construct a sequence of foam equivalent capacitance change rate, clamping stiffness change amount and vibration transmissibility change amount based on the preprocessed module wet vibration monitoring data. It evaluates the degree of wet vibration coupling based on the coupling relationship between the sequences, and performs segment identification and aggregation based on the evaluation results to generate a wet vibration coupling dataset. The resonance risk discrimination analysis module is used to perform sliding window frequency domain analysis on the module's triaxial acceleration sequence based on the wet vibration coupling dataset, generate the window main frequency, main frequency change and main frequency amplitude sequence, quantify the resonance risk intensity of the current working condition, perform risk window identification and frequency stability screening based on the quantification results, and generate a resonance risk dataset. The wet vibration and resonance linkage control module is used to construct control strength assessment values ​​based on the wet vibration coupling dataset and the resonance risk dataset, identify the control trigger window based on the control strength assessment values ​​and generate control target parameters, generate control instructions based on the control target parameters and issue them for execution, and generate a control execution record set. 2.The LCD display module moisture-proof and vibration-proof control system based on multi-dimensional environment perception of claim 1, wherein: The specific steps for collecting module damp vibration monitoring data and performing time synchronization, noise suppression, anomaly removal, missing data completion, and standardization on the module damp vibration monitoring data to generate preprocessed module damp vibration monitoring data are as follows: Real-time acquisition of module damp vibration monitoring data, including module cavity temperature, module cavity relative humidity, module triaxial acceleration, frame triaxial acceleration, clamping point normal pressure, support pad compression, and foam equivalent capacitance value; For the collected module wet vibration monitoring data, a dynamic time warping algorithm is used to perform time synchronization and rhythm alignment processing on the multi-source time series, and a linear interpolation resampling algorithm is used to map data with different sampling frequencies to a unified time step. A Kalman filter algorithm is used to perform recursive filtering processing on the module wet vibration monitoring data. A density-based spatial clustering algorithm is used to cluster, label, and remove abnormal segments in the module wet vibration monitoring data, and a cubic spline interpolation algorithm is used to interpolate and complete short-time missing intervals. A min-max normalization algorithm is used to standardize the module wet vibration monitoring data, unify the numerical scale, and eliminate dimensional differences.

3. The moisture-proof and vibration-proof control system for LCD display modules based on multi-dimensional environmental perception as described in claim 1, characterized in that: The specific steps for constructing the foam equivalent capacitance change rate sequence, clamping stiffness change sequence, and vibration transmissibility change sequence based on the preprocessed module wet vibration monitoring data, and evaluating the degree of wet vibration coupling based on the coupling relationship between the sequences are as follows: Read the pre-processed module wet vibration monitoring data, calculate the rate of change of the equivalent capacitance value of foam at adjacent sampling points, and obtain the rate of change of the equivalent capacitance of foam; extract the normal pressure of the clamping point and the compression of the support pad, calculate the clamping stiffness of each sampling point by the ratio of the normal pressure of the clamping point to the compression of the support pad, and calculate the change in clamping stiffness between adjacent sampling points. Extract the vector magnitudes of the module's triaxial acceleration and the frame's triaxial acceleration at each sampling point. Calculate the vibration transmission ratio at each sampling point using the ratio of the module's vector magnitude to the frame's vector magnitude, and calculate the change in vibration transmission ratio between adjacent sampling points. The absolute values ​​of the change rate of the equivalent capacitance of the foam, the change in clamping stiffness, and the change in vibration transmissibility are multiplied sequentially to obtain the numerator of the wet vibration coupling. The sum of the temperature inside the module cavity and the temperature reference value is multiplied by the sum of the relative humidity inside the module cavity and the constant, and the product is added to the minima to obtain the denominator of the wet vibration coupling. The ratio of the wet vibration coupling numerator to the wet vibration coupling denominator is logarithmically calculated, and the square root of the absolute value of the logarithmic function is taken to obtain the wet vibration coupling evaluation value. 4.The LCD display module moisture-proof and vibration-proof control system based on multi-dimensional environment perception of claim 3, wherein: The specific steps for performing fragment identification and aggregation based on the evaluation results to generate a wet vibration coupling dataset are as follows: A time series traversal is performed on the wet vibration coupling evaluation values, and intervals where the wet vibration coupling evaluation values ​​exceed the wet vibration coupling threshold at consecutive sampling points are marked as wet vibration coupling segments. Segment aggregation processing is performed on the set of wet vibration coupling segments, and segments with adjacent start and end times and whose wet vibration coupling evaluation value changes do not exceed the aggregation threshold are merged to generate a wet vibration coupling segment sequence. The corresponding start and end time indices, number of sampling points, and corresponding wet vibration coupling evaluation values ​​are extracted to construct a wet vibration coupling dataset. 5.The LCD display module moisture-proof and vibration-proof control system based on multi-dimensional environment perception of claim 1, wherein: The specific steps for performing sliding window frequency domain analysis on the module's triaxial acceleration sequence based on the wet vibration coupling dataset, generating the window dominant frequency, dominant frequency change, and dominant frequency amplitude sequence, and quantifying the resonance risk intensity under the current operating condition are as follows: The damp vibration coupling dataset is read, and the damp vibration coupling segment sequence is segmented into fixed-length sliding time windows. A Fast Fourier Transform (FFT) is performed on the module triaxial acceleration sequence within each time window to obtain the frequency domain amplitude sequence for that window. The frequency component with the largest amplitude within the window is retrieved, and this frequency component is designated as the dominant frequency. The corresponding amplitude is extracted and written into the dominant frequency amplitude sequence. The dominant frequency amplitude sequence is then subjected to adjacent time window difference processing to obtain the dominant frequency change sequence. The dominant frequency, dominant frequency change, and dominant frequency amplitude of each time window are extracted, and combined with the corresponding damp vibration coupling evaluation value, a resonance risk assessment value is calculated, and a resonance risk assessment value sequence is generated. 6.The LCD display module moisture-proof and vibration-proof control system based on multi-dimensional environment perception of claim 5, wherein: The specific steps for obtaining the resonance risk assessment value through comprehensive calculation are as follows: Perform an inverse hyperbolic sine function operation on the product of the main frequency amplitude and the main frequency change, and then multiply it by the sum of the wet vibration coupling evaluation value and the constant one to obtain the numerator of the resonance coupling; take the absolute value of the difference between the window main frequency and the frequency reference value and add the minima to obtain the denominator of the resonance coupling. Dividing the numerator of resonance coupling by the denominator of resonance coupling yields the resonance risk assessment value. 7.The LCD display module moisture-proof and vibration-proof control system based on multi-dimensional environment perception of claim 1, wherein: The specific steps for performing risk window identification and frequency stability screening based on quantization results to generate a resonance risk dataset are as follows: Perform time series traversal on the resonance risk assessment value sequence, and mark the window interval where the resonance risk assessment value exceeds the resonance risk threshold within N consecutive time windows as the initial risk interval; For each initial risk interval, the corresponding window dominant frequency and the change in dominant frequency are extracted to construct a frequency stability test sequence. The sign consistency test is performed on the frequency stability test sequence, and the window intervals with consistent signs and increasing amplitudes are marked as frequency stable sub-intervals. The interval intersection operation is performed on the initial risk interval and the frequency stable sub-intervals, and the intersection result is marked as a valid risk interval. The corresponding window dominant frequency, start and end time index, and resonance risk assessment value are extracted to construct a resonance risk dataset. 8.The LCD display module moisture-proof and vibration-proof control system based on multi-dimensional environment perception of claim 1, wherein: The specific steps for constructing the control strength assessment value based on the damp vibration coupling dataset and the resonance risk dataset are as follows: Read the damp vibration coupling dataset and the resonance risk dataset, and extract the corresponding window main frequency, main frequency change, resonance risk assessment value and damp vibration coupling assessment value for each effective risk interval; The risk difference term is obtained by dividing the difference between the resonance risk assessment value and the damp vibration coupling assessment value by the sum of the two and the sum of the minimum term, and taking the absolute value of the ratio. The frequency domain sensitivity term is obtained by dividing the absolute value of the change in the dominant frequency by the sum of the absolute value of the difference between the window dominant frequency and the frequency reference value and the minimum term, and taking the exponent of the ratio with respect to the natural constant e. The control strength assessment value is obtained by multiplying the risk difference term and the frequency domain sensitivity term.

9. The moisture-proof and vibration-proof control system for LCD display modules based on multi-dimensional environmental perception according to claim 1, characterized in that: The specific steps for identifying the control trigger window and generating control target parameters based on the control intensity assessment value are as follows: Real-time comparison of control intensity assessment value and control initiation threshold; marking the effective risk interval where the control intensity assessment value is greater than the control initiation threshold as the control trigger window. For each control trigger window, the corresponding control strength evaluation value, main frequency change, and main frequency offset are read, and the difference between the wet vibration coupling evaluation values ​​of adjacent windows is calculated to obtain the wet vibration increment; control target parameters are constructed based on different trigger conditions: When the control strength assessment value exceeds the vibration reduction control threshold, the module's triaxial acceleration sequence is read to calculate the vibration amplitude of the current window and generate vibration reduction control target parameters; When the main frequency offset exceeds the frequency band adjustment threshold, the main frequency in the window and the main frequency change are read to calculate the main frequency offset rate and generate the frequency band adjustment target parameters. When the wet vibration increment exceeds the wet vibration slow-release threshold, the relative humidity inside the module cavity is read and the humidity accumulation rate is calculated using the control trigger window to generate the humidity slow-release target parameter. Various control target parameters were extracted and constructed according to window indexes to create vibration reduction control parameter tables, frequency band adjustment parameter tables, and humidity slow release parameter tables. 10.The multi-dimensional environment perception based LCD display module moisture-proof and vibration-proof control system according to claim 9, wherein: The specific steps for generating and issuing control commands based on the control target parameters, and generating a control execution record set are as follows: Window-level parameter fusion processing is performed on the vibration reduction control parameter table, frequency band adjustment parameter table and humidity slow release parameter table. When multiple control target parameters exist in the same window, the control intensity evaluation value, main frequency offset and wet vibration increment of the corresponding window are read, and a control priority list is constructed based on the control priority rule. All control target parameters within the window are sorted according to the control priority list, and control instructions are generated based on the sorted control target parameters and corresponding time indices to construct a control instruction sequence. The controllability control parameters of the module clamping mechanism are adjusted based on the target parameters of vibration reduction control. Adjust the frequency band working interval of the backlight drive based on the frequency band adjustment target parameter; Adjust the working voltage of the cavity heating sheet based on the humidity release target parameter; And extract the execution result of each control instruction and the corresponding time index to construct a control execution record table.

Images