Method, system and equipment for predicting service life of projector of full-motion simulator

Abstract

The invention belongs to the field of machine life prediction, and particularly relates to a full-motion simulator projector life prediction method, system and device. The invention aims to solve the problems of neglect of early signals and static acquisition strategy in the prior art. The method comprises the following steps: starting a dark field mode and dividing regions to collect multi-dimensional operation parameters; calculating the brightness, the color change rate and the transmission delay deviation rate; dynamically adjusting an abnormal threshold value according to the equipment working duration, the historical fluctuation and the environmental stability; through multi-condition joint triggering judgment, the collection frequency of the key area is adjusted in a self-adaptive mode; and after extracting regional and global degradation characteristics, inputting the regional and global degradation characteristics into an LSTM neural network model with an attention mechanism to realize high-precision residual life prediction. The method effectively overcomes the defects that early aging signals are neglected and the collection strategy is static and rigid in the prior art, and remarkably improves the early fault recognition capability and prediction precision.

Description

Technical Field

[0001] This invention belongs to the field of machine life prediction, and specifically relates to a method, system and equipment for predicting the life of a full-motion simulator projector. Background Technology

[0002] As a high-end training equipment, the stability and reliability of the projection system in a full-motion simulator directly affect training effectiveness and safety. The projector, as the core display component of the system, experiences gradual performance degradation over time. Accurately predicting its remaining lifespan is crucial for developing proactive maintenance strategies and preventing training interruptions.

[0003] Currently, existing technical solutions in the field of projector lifespan prediction mainly fall into two categories: methods based on traditional statistical data and methods based on stochastic process models. Methods based on traditional statistical data construct a lifespan distribution function by statistically analyzing historical failure time data of the equipment, and then calculate the conditional remaining lifespan of the equipment at a specific moment. This method heavily relies on the accumulation of large amounts of complete failure data and cannot reflect individual differences in equipment and real-time operating status. Methods based on stochastic process models, based on probability and statistics theory, model the evolution of performance degradation variables, and can provide the predicted remaining lifespan in the form of a probability distribution. They not only provide point estimates but also describe the uncertainty of the prediction. However, this type of method still faces significant challenges in practical applications: First, its performance degradation variables are mostly single macroscopic parameters such as brightness and chromaticity, making it difficult to extract deep features directly related to early aging; second, model construction largely relies on single-variable degradation processes, failing to fully explore the coupling correlation information between multiple parameters (such as electrical, optical, and thermal parameters), thus limiting the improvement of prediction accuracy.

[0004] In summary, existing technologies have the following main drawbacks when applied to lifespan prediction of full-motion analog projectors: First, data acquisition lacks specificity, generally neglecting the capture of early aging signals (such as weak brightness anomalies and color drift) in dark-field mode, making it difficult to identify early faults in a timely manner; Second, key performance indicators closely related to optical path loss and circuit aging (such as transmission delay response time) are not effectively utilized, and they are not combined with standardized testing specifications (such as QTG testing), resulting in incomplete input features for the prediction model; Third, the acquisition strategy is static and rigid, with insufficient parameter acquisition frequency in areas of drastic change, failing to capture the dynamic degradation process of key parameters, and the fixed threshold mechanism is difficult to adapt to individual device differences and environmental changes, easily leading to misjudgments or omissions; Fourth, the prediction model is not sensitive to local anomalies, fails to distinguish the importance of features in different areas, and makes it difficult to focus on anomalies in high-impact areas, resulting in large prediction errors.

[0005] Based on this, this application proposes a method, system, and device for predicting the lifespan of a full-motion simulator projector. Summary of the Invention

[0006] To address the aforementioned problems in the prior art, namely the issues of ignoring early signals and static acquisition strategies, this invention provides a method, system, and device for predicting the lifespan of a fully dynamic analog projector.

[0007] In a first aspect, the present invention proposes a method for predicting the lifespan of a full-motion simulator projector, the method comprising: Activate the projector's dark field mode, divide the projected image into multiple independent areas, and collect the operating status parameters, transmission delay response time, and ambient temperature and humidity parameters of each area. Calculate the brightness change rate and color change rate based on the operating status parameters of each area, and compare the current transmission delay response time with the standard reference value to obtain the transmission delay deviation rate. The anomaly detection threshold is dynamically adjusted based on the equipment's cumulative working time, historical parameter fluctuations, and environmental stability. Based on the brightness change rate, color change rate, transmission delay deviation rate, and the adjusted anomaly detection threshold, it is determined whether the cross-parameter joint triggering condition is met; the joint triggering condition includes two-parameter correlation triggering, transmission delay and physical parameter coupling triggering, or multi-parameter trend consistency triggering. For areas that meet the triggering conditions, increase the sampling frequency of their operating status parameters and shorten the delayed sampling interval; for areas that do not meet the conditions, reduce the corresponding sampling frequency and interval. The real-time collected operating status parameters, transmission delay response time, and environmental temperature and humidity parameters are preprocessed, and regional brightness attenuation trend, color drift, delay deviation trend, parameter correlation characteristics, and global fluctuation entropy characteristics are extracted. The feature parameters are input into a long short-term memory neural network model with an attention mechanism, and the remaining life expectancy is predicted.

[0008] Furthermore, the anomaly detection threshold is dynamically adjusted based on the equipment's cumulative operating time, historical parameter fluctuations, and environmental stability. The method is as follows: Based on the different aging stages to which the cumulative working time of the device belongs, a corresponding first correction coefficient is selected, wherein the aging stages are divided according to the range of working time. The second correction factor is calculated based on the difference between the historical parameter fluctuation amplitude and the average fluctuation standard deviation of the equipment. The third correction coefficient is determined based on whether the environmental temperature and humidity fluctuation data exceed the stability critical value. The initial threshold is multiplied by the first correction coefficient, the second correction coefficient, and the third correction coefficient to obtain the dynamically adjusted final anomaly detection threshold.

[0009] Furthermore, the difference between the historical parameter fluctuation amplitude and the average fluctuation standard deviation of the equipment is compared with the average fluctuation standard deviation of the equipment, and the calculation result is mapped to a preset coefficient range to obtain the second correction coefficient.

[0010] Furthermore, based on the brightness change rate, color change rate, transmission delay deviation rate, and the adjusted anomaly detection threshold, it is determined whether the cross-parameter joint triggering condition is met. The method is as follows: The trigger condition for dual-parameter correlation is: the rate of change or deviation of any two parameters simultaneously reaches the set proportion of their respective abnormal judgment thresholds; The coupling triggering condition between transmission delay and physical parameters is: the transmission delay deviation rate reaches a set proportion of its abnormal judgment threshold, and the current change rate or temperature change rate of the corresponding region exceeds its respective set fluctuation limit. The trigger condition for multi-parameter trend consistency is: within multiple consecutive acquisition cycles, the brightness change rate, color change rate, and transmission delay deviation rate all show a monotonically increasing trend, and the change rate of at least two of these parameters exceeds the set proportion of their abnormal judgment threshold.

[0011] Furthermore, the real-time collected operating status parameters, transmission delay response time, and environmental temperature and humidity parameters are preprocessed, and regional brightness attenuation trends, color drift, delay deviation trends, parameter correlation characteristics, and global fluctuation entropy characteristics are extracted. The method is as follows: The real-time collected operating status parameters, transmission delay response time, and ambient temperature and humidity parameters are preprocessed, including identifying outliers, correcting outliers, and filtering. Based on the preprocessed data, regional feature parameters and global feature parameters are extracted, where: The regional characteristic parameters are obtained by calculating the average attenuation of the brightness value of each region, the average color change rate, and the average transmission delay deviation rate. The parameter correlation characteristics are obtained by calculating the correlation coefficients between the transmission delay deviation rate and the current change rate, and between the transmission delay deviation rate and the temperature change rate. The global fluctuation entropy feature is obtained by calculating the sample entropy of the brightness change rate, color change rate, and delay deviation rate sequence of all regions.

[0012] Furthermore, the feature parameters are input into a long short-term memory neural network model with an attention mechanism to output a remaining lifespan prediction value. The method is as follows: The regional feature parameters and global feature parameters are combined into a model input vector; The input vector is fed into a pre-trained long short-term memory neural network model; The long short-term memory neural network model calculates the weights of the feature parameters of each region through its internal attention mechanism layer, and performs a weighted summation of the feature parameters of the regions to focus on the features of high-influence regions. The processing layer of the long short-term memory neural network model performs calculations on the weighted features and outputs a predicted value representing the normalized remaining lifetime. The normalized remaining lifetime prediction is denormalized to obtain the final remaining lifetime prediction.

[0013] Furthermore, the operating status parameters include at least brightness parameters, color parameters, current parameters, and temperature parameters.

[0014] Furthermore, a maintenance warning is issued when the predicted value is lower than a preset threshold.

[0015] In a second aspect, the present invention provides a lifespan prediction system for a full-motion simulator projector, which is used in a method for predicting the lifespan of a full-motion simulator projector. The system includes: The data acquisition module is configured to activate the projector's dark field mode, divide the projected image into multiple independent areas, and collect the operating status parameters, transmission delay response time, and ambient temperature and humidity parameters of each area. The data calculation module is configured to calculate the brightness change rate and color change rate based on the operating status parameters of each area, and compare the current transmission delay response time with the standard reference value to obtain the transmission delay deviation rate. The threshold update module is configured to dynamically adjust the anomaly detection threshold based on the device's cumulative working time, historical parameter fluctuations, and environmental stability. The trigger condition determination module is configured to determine whether the cross-parameter joint trigger condition is met based on the brightness change rate, color change rate, transmission delay deviation rate, and the adjusted anomaly determination threshold. The joint trigger condition includes two-parameter association triggering, transmission delay and physical parameter coupling triggering, or multi-parameter trend consistency triggering. The acquisition status adjustment module is configured to increase the acquisition frequency of the operating status parameters and shorten the delay sampling interval for areas that meet the trigger conditions, and decrease the corresponding acquisition frequency and interval for areas that do not meet the conditions. The data extraction module is configured to preprocess the real-time collected operating status parameters, transmission delay response time, and environmental temperature and humidity parameters, and extract regional brightness attenuation trend, color drift, delay deviation trend, parameter correlation characteristics, and global fluctuation entropy characteristics. The lifespan prediction module is configured to input feature parameters into a long short-term memory neural network model with an attention mechanism and output a predicted remaining lifespan value.

[0016] In a third aspect, the present invention provides an electronic device comprising: At least one processor; and A memory communicatively connected to at least one of the processors; wherein, The memory stores instructions that can be executed by the processor to implement a method for predicting the lifespan of a full-motion simulator projector.

[0017] The beneficial effects of this invention are: This invention effectively captures early aging signals such as brightness decay and color drift, which are difficult to detect in conventional operating modes, by introducing a regional multi-parameter acquisition strategy in dark field mode, thereby improving the ability to identify early faults. Through an intelligent triggering mechanism based on multi-parameter change rates and dynamic thresholds, the system can adaptively adjust the acquisition frequency of key areas, optimizing system resource allocation while ensuring data validity. By fusing the key performance indicator of transmission delay response time and its deviation from the standard benchmark, and combining parameter correlation features and global stability features, the dimensions of model input features are enriched, enhancing the theoretical basis for lifetime prediction. By introducing a deep learning model with an attention mechanism, focused learning of degradation features in high-impact areas is achieved, improving the model's sensitivity to local aging phenomena. Through a three-level threshold self-correction mechanism, the anomaly judgment criteria can be dynamically adjusted according to the equipment's aging state, historical fluctuation patterns, and environmental conditions, enhancing the system's adaptability and reliability. Attached Figure Description

[0018] Other features, objects, and advantages of this application will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings: Figure 1 This is a flowchart illustrating a method for predicting the lifespan of a fully dynamic simulator projector according to the present invention. Detailed Implementation

[0019] The present application will now be described in further detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the invention. Furthermore, it should be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings.

[0020] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0021] The first embodiment of the present invention provides a method for predicting the lifespan of a full-motion simulator projector, the method comprising: Step S10: Activate the projector's dark field mode, divide the projected image into multiple independent areas, and collect the operating status parameters, transmission delay response time, and ambient temperature and humidity parameters of each area. Step S20: Calculate the brightness change rate and color change rate based on the operating status parameters of each area, and compare the current transmission delay response time with the standard reference value to obtain the transmission delay deviation rate; Step S30: Dynamically adjust the anomaly judgment threshold based on the equipment's cumulative working time, historical parameter fluctuation range, and environmental stability. Step S40: Based on the brightness change rate, color change rate, transmission delay deviation rate, and the adjusted anomaly judgment threshold, determine whether the cross-parameter joint triggering condition is met; the joint triggering condition includes two-parameter association triggering, transmission delay and physical parameter coupling triggering, or multi-parameter trend consistency triggering. Step S50: For areas that meet the triggering conditions, increase the sampling frequency of their operating status parameters and shorten the delayed sampling interval; for areas that do not meet the conditions, decrease the corresponding sampling frequency and interval. Step S60: Preprocess the real-time collected operating status parameters, transmission delay response time and environmental temperature and humidity parameters, and extract regional brightness attenuation trend, color drift, delay deviation trend, parameter correlation characteristics and global fluctuation entropy characteristics. Step S70: Input the feature parameters into the long short-term memory neural network model with attention mechanism, and output the remaining life prediction value.

[0022] To more clearly explain the lifespan prediction method for a fully-motion simulator projector according to the present invention, the following is in conjunction with... Figure 1 The steps in the embodiments of the present invention are described in detail below: Step S10: Activate the projector's dark field mode, divide the projected image into multiple independent areas, and collect the operating status parameters, transmission delay response time, and ambient temperature and humidity parameters of each area. The operating status parameters include at least brightness parameters, color parameters, current parameters, and temperature parameters.

[0023] In the implementation of this invention, firstly, a dark field mode command is sent to the projector through the projector control interface (such as RS232 interface) to turn off the active light source of the projector and retain only the background dim light or start the dedicated dark field calibration light source to ensure that the projected image is in a dark field state and the background brightness is stable at 0.1cd / m². Next, the projected image was divided into 256 independent areas using a 16×16 grid, each area being 1 / 256th of the physical size of the projected image. Then, sensors deployed in each area of ​​the projector collected operational status parameters, transmission delay response time, and ambient temperature and humidity parameters. Specifically, a high-sensitivity photoelectric sensor was placed at the center and four corners of each area to collect brightness parameters, with a measurement range of 0.001-100 cd / m². 2 The system has an accuracy of ±1%. RGB three-color recognition sensors are placed at the edge of each area to collect color parameters, with a sampling frequency of 1kHz. Hall effect current sensors are connected in series in the light source driving circuit corresponding to each area to collect current parameters, with a measurement range of 0-10A and an accuracy of ±0.5%. Two thermocouple temperature sensors are attached near the light source module and optical lens in each area to collect temperature parameters, with a measurement range of -40-150℃ and an accuracy of ±0.3℃. Integrated temperature and humidity sensors are installed at key locations such as the exterior of the projector body to collect ambient temperature and humidity parameters, with a temperature measurement range of -40-85℃ and a humidity measurement range of 0-100%RH, and a temperature accuracy of ±0.2℃ and a humidity accuracy of ±2%RH. At the same time, the transmission delay response time is collected through a QTG test module, which is connected to the projector's signal input and display output terminals. Finally, the brightness value, color parameters (R, G, B), current value, temperature value, transmission delay response time, and ambient temperature and humidity parameters of each area are collected at an initial frequency of 1 time / minute. The data is received in real time through the software layer, and a moving average algorithm is used for filtering. Outliers are identified using the 3σ criterion and corrected by averaging the five adjacent valid values ​​to complete the preliminary data preprocessing.

[0024] Step S20: Calculate the brightness change rate and color change rate based on the operating status parameters of each area, and compare the current transmission delay response time with the standard reference value to obtain the transmission delay deviation rate; In implementation of this invention, at the beginning of each acquisition cycle, for each independent region, the brightness change rate, color change rate, and transmission delay deviation rate are calculated based on the currently acquired operating status parameters; for the calculation of the brightness change rate, the brightness value of region i in the k-th acquisition is taken. Compared with the brightness value collected previously According to the formula Calculations are performed to obtain the percentage value of the brightness change rate of the region in the current period; for the calculation of the color change rate, the RGB color parameter value of region i in the kth acquisition is taken. Corresponding value to the previous collection Calculate the absolute value of the relative change for each channel, i.e.: Then take the maximum value among the three and apply the formula. Perform calculations to obtain the percentage value of the color change rate for the current cycle in this area; For the calculation of the transmission delay deviation rate, first obtain the current transmission delay response time D collected in real time through the QTG test module, and at the same time call the standard reference value preset and stored in the system, that is, the main QTG value D main , this value is obtained by taking the average of multiple QTG tests in the initial brand-new or calibrated state of the projector, and then according to the formula Perform calculations to obtain the percentage value of the transmission delay deviation rate for the current cycle; All calculation processes are automatically completed by the software layer in the system, and the calculation results are stored in the database together with the corresponding area identifier and timestamp for subsequent threshold judgment and feature extraction.

[0025] Step S30, dynamically adjust the abnormal determination threshold according to the cumulative working hours of the device, the fluctuation range of historical parameters, and environmental stability; In this embodiment, step S30 includes: Step S31, select the corresponding first correction coefficient based on the different aging stages to which the cumulative working hours of the device belong, where the aging stages are divided according to the working hour range; Step S32, calculate the second correction coefficient based on the difference between the historical parameter fluctuation range and the average fluctuation standard deviation of the device; Step S33, determine the third correction coefficient based on whether the environmental temperature and humidity fluctuation data exceeds the stability critical value; Step S34, multiply the initial threshold by the first correction coefficient, the second correction coefficient, and the third correction coefficient to obtain the dynamically adjusted final abnormal determination threshold.

[0026] Among them, the difference between the historical parameter fluctuation range and the average fluctuation standard deviation of the device is subjected to a ratio operation with the average fluctuation standard deviation of the device, and the operation result is mapped to a preset coefficient range to obtain the second correction coefficient.

[0027] When the present invention is implemented, the system first reads the cumulative working hours t (unit: hour) of the projector from the device historical database, and makes a judgment according to the preset aging stage threshold. If t≤5000 hours, it is determined that the device is in the low aging stage, and the first correction coefficient k1 takes the value of 1.0; if 5000 hours < t≤10000 hours, it is determined that the device is in the medium aging stage, and k1 takes the value of 0.8; if t>10000 hours, it is determined that the device is in the high aging stage, and k1 takes the value of 0.6; then, the system calculates the standard deviation of the change rate sequences of each parameter (brightness change rate, color change rate, transmission delay deviation rate) within the past 30 days, which are respectively denoted as This serves as the historical parameter fluctuation range, while simultaneously retrieving the average standard deviation of the parameter fluctuation corresponding to this projector model from the system configuration library. 、 、 For the brightness change rate threshold correction, calculate its second correction coefficient. This calculation is achieved by taking the ratio of the difference between the current standard deviation of volatility and the average standard deviation of volatility to the average standard deviation of volatility, and mapping the result to the interval [0.8, 1.2]. Similarly, the calculation of color change rate and transmission delay deviation rate Subsequently, the system reads recent ambient temperature and humidity data and calculates the standard deviation σ of ambient temperature fluctuation. EnvT and humidity fluctuation standard deviation σ H If σ EnvT >2℃ or σ H If the RH level is >5%, the environment is considered unstable, and the third correction factor k3 is set to 1.1; otherwise, k3 is set to 1.0. Finally, the system obtains the initially set anomaly detection threshold baseline value, namely the initial threshold RL0 for the rate of change of brightness. base =3%, Initial threshold for color change rate RC0 base =2%, Initial threshold for transmission delay deviation rate RD0 base =5%, and dynamically adjusted through multiplication to obtain the final dynamic anomaly detection threshold: The final threshold for the rate of change of brightness is RL0 = RL0 base ×k1×k2 RL ×k3, final threshold of color change rate RC0 = RC0 base ×k1×k2 RC ×k3, final threshold for transmission delay deviation rate RD0=RD0 base ×k1×k2 RD ×k3; All calculated final thresholds will be applied to subsequent joint trigger condition judgment logic.

[0028] Step S40: Based on the brightness change rate, color change rate, transmission delay deviation rate, and the adjusted anomaly judgment threshold, determine whether the cross-parameter joint triggering condition is met; the joint triggering condition includes two-parameter association triggering, transmission delay and physical parameter coupling triggering, or multi-parameter trend consistency triggering. In this embodiment, the method for determining whether the cross-parameter joint triggering condition is met is based on the brightness change rate, color change rate, transmission delay deviation rate, and the adjusted anomaly detection threshold. The trigger condition for dual-parameter correlation is: the rate of change or deviation of any two parameters simultaneously reaches the set proportion of their respective abnormal judgment thresholds; The coupling triggering condition between transmission delay and physical parameters is: the transmission delay deviation rate reaches a set proportion of its abnormal judgment threshold, and the current change rate or temperature change rate of the corresponding region exceeds its respective set fluctuation limit. The trigger condition for multi-parameter trend consistency is: within multiple consecutive acquisition cycles, the brightness change rate, color change rate, and transmission delay deviation rate all show a monotonically increasing trend, and the change rate of at least two of these parameters exceeds the set proportion of their abnormal judgment threshold.

[0029] In this embodiment, the system executes the judgment logic of three joint triggering conditions in parallel. For each independent region, it reads in real time the currently calculated brightness change rate RL(i,k), color change rate RC(i,k), and transmission delay deviation rate RD. bias(i，k) And the dynamically adjusted final anomaly detection thresholds RL0, RC0, and RD0; For the two-parameter correlation trigger condition, the system determines whether either of the following combinations is simultaneously satisfied: the luminance change rate RL(i,k) reaches 80% or more of its threshold RL0 and the color change rate RC(i,k) reaches 80% or more of its threshold RC0, i.e., RL(i,k)≥0.8×RL0 and RC(i,k)≥0.8×RC0; or The rate of change of brightness RL(i,k) reaches 80% or more of its threshold RL0 and the transmission delay deviation rate RD bias(i，k) Reaching 80% or more of its threshold RD0, i.e., RL(i,k)≥0.8×RL0 and RD bias(i，k) ≥0.8×RD0; or The color change rate RC(i,k) reaches 80% or more of its threshold RC0 and the transmission delay deviation rate RD bias(i，k) Reaching 80% or more of its threshold RD0, i.e., RC(i,k)≥0.8×RC0 and RD bias(i，k) ≥0.8×RD0; For the coupling trigger condition between transmission delay and physical parameters, the system first determines the transmission delay deviation rate RD. bias(i，k) Whether it reaches 70% or more of its threshold RD0, i.e., RD bias(i，k) If the value is ≥0.7×RD0, then further determine whether the physical parameters of the region are abnormal, i.e., calculate the rate of change of current in the region. If RI(i,k)≥5%, then an abnormal current fluctuation is determined, or the temperature change rate of the region is calculated. If RT(i,k)≥3%, then abnormal temperature fluctuation is determined. This condition is triggered when the transmission delay deviation condition and any physical parameter abnormal fluctuation condition are met simultaneously. For the multi-parameter trend consistency trigger condition, the system retrieves the brightness change rate sequence RL(i,k-4)...RL(i,k), color change rate sequence RC(i,k-4)...RC(i,k), and transmission delay deviation rate sequence RD for the most recent five consecutive acquisition cycles (k-4,k-3,k-2,k-1,k) in the region. bias(i，k-4) ...RD bias(i，k) First, determine whether each of the three sequences exhibits a monotonically increasing trend, meaning that for any two adjacent time points in the sequence, the value at the later time point is greater than or equal to the value at the previous time point. Then, determine whether, within this continuous period, at least two parameters (brightness and color, brightness and delay, or color and delay) have a rate of change exceeding 60% of their respective final anomaly thresholds (RL0, RC0, RD0) at the current time (time k). Specifically, RL(i, k) > 0.6 × RL0 and RC(i, k) > 0.6 × RC0, or RL(i, k) > 0.6 × RL0 and RD0 > RC0. bias(i，k) >0.6×RD0, or RC(i,k)>0.6×RC0 and RD bias(i，k) >0.6×RD0; If any one of the above three combined triggering conditions is met, the system determines that the region meets the cross-parameter combined triggering condition and generates a corresponding triggering flag signal to drive the acquisition frequency adjustment operation in step S50.

[0030] Step S50: For areas that meet the triggering conditions, increase the sampling frequency of their operating status parameters and shorten the delayed sampling interval; for areas that do not meet the conditions, decrease the corresponding sampling frequency and interval. In this embodiment, the system dynamically adjusts the acquisition strategy for each region based on the cross-parameter joint trigger condition judgment result generated in step S40. For a region that is determined to meet any trigger condition, the system marks it as a "high rate of change region" and increases the acquisition frequency of the region's operating status parameters (including brightness, color, current, and temperature) from the initial 1 time / minute to 5 times / minute by controlling the hardware and software layers of the data acquisition module. At the same time, the sampling interval of the region's transmission delay response time is shortened from the initial synchronization with the operating status parameters (i.e., 1 time / minute) to 1 second. This operation is achieved by sending control commands to the QTG test module to enable it to perform tests and return data at a higher frequency. For areas that are not determined to meet any triggering conditions, the system marks them as "low rate of change areas" and reduces the sampling frequency of the operating status parameters of the area from the initial 1 time / minute to 1 time / 10 minutes. At the same time, the sampling interval of the transmission delay response time of the area is extended to 30 seconds. This frequency adjustment process is executed in real time and automatically. The system maintains an area status mapping table and continuously updates the latest marking status of each area and its currently effective sampling frequency and sampling interval settings. When a region no longer meets any triggering conditions due to changes in subsequent collected data, the system will remove its marker status from "high change rate region" and automatically restore its collection frequency and sampling interval to the low frequency setting. Conversely, when a region that was not previously triggered meets the conditions in a new round of judgment, its collection frequency will be immediately increased and the sampling interval will be shortened. In addition, after each collection frequency adjustment, the system will record the adjustment time, region identifier, frequency and interval values ​​before and after the adjustment, as well as the specific condition type that triggered the adjustment, forming a log for operation and maintenance analysis and auditing.

[0031] Step S60: Preprocess the real-time collected operating status parameters, transmission delay response time and environmental temperature and humidity parameters, and extract regional brightness attenuation trend, color drift, delay deviation trend, parameter correlation characteristics and global fluctuation entropy characteristics. Specifically, step S60 includes: Step S61: Preprocess the real-time collected operating status parameters, transmission delay response time, and ambient temperature and humidity parameters. The preprocessing includes identifying outliers, correcting outliers, and filtering. Step S62: Based on the preprocessed data, extract regional feature parameters and global feature parameters, where: Step S63, the regional characteristic parameters are obtained by calculating the average attenuation of the brightness value of each region, the average value of the color change rate, and the average value of the transmission delay deviation rate. Step S64, the parameter correlation characteristics are obtained by calculating the correlation coefficient between the transmission delay deviation rate and the current change rate and the temperature change rate; Step S65, the global fluctuation entropy feature is obtained by calculating the sample entropy of the brightness change rate, color change rate and delay deviation rate sequence of all regions.

[0032] In this embodiment, the system first preprocesses the raw data collected in real time. For each parameter sequence (including brightness, color, current, temperature, transmission delay response time and ambient temperature and humidity of each region), the 3σ criterion is used to identify outliers. That is, the mean μ and standard deviation σ of the current data window (the most recent 100 sampling points) of each parameter are calculated. If a data point x satisfies |x-μ|>3σ, it is marked as an outlier. For identified outliers, the average of the five adjacent valid values ​​is used for correction, with the specific formula as follows: ,in The nearest valid data point before and after the outlier position k is used. If there are not enough adjacent valid points, linear interpolation is used for estimation. After outlier correction, a moving average filter with a window size of 5 is applied to smooth each parameter sequence. The filtered output value y k According to the formula Calculation, where to This represents the original data values ​​of the current point k and its preceding and following adjacent points; After preprocessing, the system extracts regional feature parameters based on the filtered data, and calculates the brightness attenuation trend value for each region i. Where L(i, 0) is the initial brightness reference value of the region, L(i, t) is the brightness value of the t-th acquisition, and k is the current total number of acquisitions; calculate the color shift amount. , where RC(i,t) is the color change rate of the t-th acquisition; Calculate the trend of delay deviation ,in Let be the transmission delay deviation rate of the t-th acquisition; simultaneously, calculate the parameter correlation characteristics, i.e., the Pearson correlation coefficient between the transmission delay deviation rate and the current change rate. ,in and Sequences The mean of RI(i,t) and RI(i,t), where RI(i,t) is the rate of change of current; Similarly, calculate the Pearson correlation coefficient Corr between the transmission delay deviation rate and the temperature change rate. {D-T}(i) At the global level, the system calculates the global fluctuation entropy characteristics, first by analyzing the brightness change rate sequence {RL(1,t)...RL(256,t)}, color change rate sequence {RC(1,t)...RC(256,t)}, and delay deviation rate sequence {RD} for all regions. bias(1，t) ...RD bias(256，t) The sequences are concatenated into three long sequences, and then the entropy value of each long sequence is calculated based on the sample entropy algorithm. The embedding dimension m=2, the tolerance r=0.2 multiplied by the standard deviation of the sequence, and finally, three entropy values ​​are obtained. RL Entropy RC Entropy RD The average value is taken as the global fluctuation entropy feature. fluct All extracted feature parameters are eventually organized into feature vectors, timestamped, and stored in the feature database to provide input for subsequent life prediction models.

[0033] Step S70: Input the feature parameters into the long short-term memory neural network model with attention mechanism, and output the remaining life prediction value.

[0034] The system organizes the feature parameters extracted and preprocessed in step S60 into a fixed-format input vector. This vector has a dimension of 1028 and is specifically composed of feature vectors from 256 regions and 4 global feature vectors. Each region's feature vector contains 4 parameters, namely the brightness attenuation trend value A for that region. L(i) Color shift amount A C(i) Delay Deviation Trend A D(i) And the correlation coefficient Corr between transmission delay deviation rate and current change rate {D-I}(i) Therefore, the 256 regions contribute a total of 1024 feature dimensions; the remaining 4 global feature dimensions are: transmission delay response time change rate RD(k), average current I... avg Average temperature T avg and global fluctuation entropy fluct ; Before feeding the input vector into the prediction model, the system calls the pre-trained normalization parameters (including the historical minimum value x for each feature dimension). min and maximum value x max ), using the formula x'=(xx min ) / (x max -x min Each feature value of the input vector is normalized to the [0,1] interval; the normalized input vector is then fed into an improved Long Short-Term Memory (LSTM) neural network model with an attention mechanism. The network structure consists of an input layer (1028 neurons), three hidden layers (each containing 64 LSTM neurons, all using the ReLU activation function), and an output layer (one linearly activated neuron). During forward propagation, the network first applies an attention mechanism to the 1024-dimensional features of 256 regions. Specifically, the system calculates the feature importance score S for each region i using a single-layer neural network. i The formula is S i =W s ·[A L(i) A C(i) A D(i) Corr {D-I}(i) ]+b s W s and b s The weight matrix and bias vector obtained during training; Subsequently, the importance scores of all regions were normalized using the Softmax function to obtain the attention weight for each region. Weighted regional feature vectors From the formula The calculation shows that this 4-dimensional vector is then concatenated with the aforementioned 4-dimensional global feature vector to form an 8-dimensional comprehensive feature vector. This comprehensive feature vector is then sequentially passed through three LSTM hidden layers for sequence modeling and transformation, and finally a normalized remaining lifetime prediction value ŷ is generated by the linear output layer. The system then performs an inverse normalization operation on this output value using the formula... ,in and The maximum and minimum values ​​of the actual remaining lifetime in the training set are used to obtain the final, physically meaningful predicted remaining lifetime (in hours). This predicted value, along with its timestamp and confidence interval (estimated by the model during the training phase), is output to the user interface and stored in the prediction results database.

[0035] In this embodiment, step S80 is further included after step S70: A maintenance warning is issued when the predicted value is lower than a preset threshold.

[0036] In this embodiment, the system monitors the remaining life prediction value output in step S70 in real time and compares it with a preset maintenance threshold. This maintenance threshold is a fixed value pre-set and stored in the system configuration library based on the equipment model, historical maintenance records, and criticality; for example, it can be set to 500 hours. When the system detects that the remaining life prediction value is less than or equal to this maintenance threshold, it immediately triggers a maintenance warning process. First, the system generates a structured warning message containing the following fields: a unique warning identifier (generated from a timestamp and equipment ID hash), trigger time, equipment number, predicted remaining life value, preset maintenance threshold, and specific trigger conditions. Subsequently, the system sends the warning information in parallel through multiple integrated communication interfaces, including real-time display and prompts in the system's graphical user interface (GUI) in the form of a red pop-up window and sound alarm, while simultaneously calling the enterprise's internal email... The system's API interface sends warning information to the email addresses of equipment administrators and maintenance engineers according to a preset email template format. It also pushes core information about the warning (such as equipment number and remaining lifespan) to the mobile terminals of relevant personnel via SMS gateway (SMSGateway). Furthermore, the warning message is automatically recorded in the maintenance work order database, generating an emergency maintenance work order with a status of "Pending," which is automatically assigned to the corresponding maintenance team. The system continuously monitors the warning status. If the work order status is not updated to "Processed" or "Confirming" within a preset time (e.g., 24 hours), the system automatically triggers the warning escalation process, repeating the above notification process and additionally copying it to higher-level management personnel. All warning triggering, notification sending, work order generation, and status update operations are recorded in detail in the system audit log to ensure process traceability.

[0037] Although the steps in the above embodiments are described in the above order, those skilled in the art will understand that in order to achieve the effect of this embodiment, different steps do not need to be executed in such an order. They can be executed simultaneously (in parallel) or in a reverse order. These simple variations are all within the protection scope of this invention.

[0038] A second embodiment of the present invention proposes a lifespan prediction system for a full-motion simulator projector, used to implement a method for predicting the lifespan of a full-motion simulator projector. The system includes: The data acquisition module is configured to activate the projector's dark field mode, divide the projected image into multiple independent areas, and collect the operating status parameters, transmission delay response time, and ambient temperature and humidity parameters of each area. The data calculation module is configured to calculate the brightness change rate and color change rate based on the operating status parameters of each area, and compare the current transmission delay response time with the standard reference value to obtain the transmission delay deviation rate. The threshold update module is configured to dynamically adjust the anomaly detection threshold based on the device's cumulative working time, historical parameter fluctuations, and environmental stability. The trigger condition determination module is configured to determine whether the cross-parameter joint trigger condition is met based on the brightness change rate, color change rate, transmission delay deviation rate, and the adjusted anomaly determination threshold. The joint trigger condition includes two-parameter association triggering, transmission delay and physical parameter coupling triggering, or multi-parameter trend consistency triggering. The acquisition status adjustment module is configured to increase the acquisition frequency of the operating status parameters and shorten the delay sampling interval for areas that meet the trigger conditions, and decrease the corresponding acquisition frequency and interval for areas that do not meet the conditions. The data extraction module is configured to preprocess the real-time collected operating status parameters, transmission delay response time, and environmental temperature and humidity parameters, and extract regional brightness attenuation trend, color drift, delay deviation trend, parameter correlation characteristics, and global fluctuation entropy characteristics. The lifespan prediction module is configured to input feature parameters into a long short-term memory neural network model with an attention mechanism and output a predicted remaining lifespan value.

[0039] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working process and related descriptions of the system described above can be found in the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0040] It should be noted that the above-described embodiment of the full-motion simulator projector life prediction system is merely an example of the division of the functional modules. In practical applications, the functions can be assigned to different functional modules as needed, that is, the modules or steps in the embodiments of the present invention can be further decomposed or combined. For example, the modules in the above embodiments can be merged into one module, or further divided into multiple sub-modules to complete all or part of the functions described above. The names of the modules and steps involved in the embodiments of the present invention are merely for distinguishing the various modules or steps and are not considered as an improper limitation of the present invention.

[0041] An electronic device according to a third embodiment of the present invention includes: At least one processor; and A memory communicatively connected to at least one of the processors; wherein, The memory stores instructions that can be executed by the processor to implement the above-described method for predicting the lifespan of a full-motion simulator projector.

[0042] A fourth embodiment of the present invention provides a computer-readable storage medium storing computer instructions, which are executed by the computer to implement the above-described method for predicting the lifespan of a full-motion simulator projector.

[0043] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working process and related descriptions of the storage device and processing device described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0044] Those skilled in the art will recognize that the modules and method steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. The programs corresponding to the software modules and method steps can be placed in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disks, removable disks, CD-ROMs, or any other form of storage medium known in the art. To clearly illustrate the interchangeability of electronic hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in electronic hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the invention.

[0045] The terms “first”, “second”, etc., are used to distinguish similar objects, not to describe or indicate a specific order or sequence.

[0046] The term "comprising" or any other similar term is intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus / device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent in such process, method, article, or apparatus / device.

[0047] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of the present invention.

Claims

1. A method for predicting the lifespan of a fully-motion simulator projector, characterized in that, The method includes: Activate the projector's dark field mode, divide the projected image into multiple independent areas, and collect the operating status parameters, transmission delay response time, and ambient temperature and humidity parameters of each area. Calculate the brightness change rate and color change rate based on the operating status parameters of each area, and compare the current transmission delay response time with the standard reference value to obtain the transmission delay deviation rate. The anomaly detection threshold is dynamically adjusted based on the equipment's cumulative working time, historical parameter fluctuations, and environmental stability. Based on the brightness change rate, color change rate, transmission delay deviation rate, and the adjusted anomaly detection threshold, it is determined whether the cross-parameter joint triggering condition is met; the joint triggering condition includes two-parameter correlation triggering, transmission delay and physical parameter coupling triggering, or multi-parameter trend consistency triggering. For areas that meet the triggering conditions, increase the sampling frequency of their operating status parameters and shorten the delayed sampling interval; for areas that do not meet the conditions, reduce the corresponding sampling frequency and interval. The real-time collected operating status parameters, transmission delay response time, and environmental temperature and humidity parameters are preprocessed, and regional brightness attenuation trend, color drift, delay deviation trend, parameter correlation characteristics, and global fluctuation entropy characteristics are extracted. The feature parameters are input into a long short-term memory neural network model with an attention mechanism, and the remaining life expectancy is predicted.

2. The method for predicting the lifespan of a fully-motion simulator projector according to claim 1, characterized in that, The anomaly detection threshold is dynamically adjusted based on the equipment's cumulative operating time, historical parameter fluctuations, and environmental stability. The method is as follows: Based on the different aging stages to which the cumulative working time of the device belongs, a corresponding first correction coefficient is selected, wherein the aging stages are divided according to the range of working time. The second correction factor is calculated based on the difference between the historical parameter fluctuation amplitude and the average fluctuation standard deviation of the equipment. The third correction coefficient is determined based on whether the environmental temperature and humidity fluctuation data exceed the stability critical value. The initial threshold is multiplied by the first correction coefficient, the second correction coefficient, and the third correction coefficient to obtain the dynamically adjusted final anomaly detection threshold.

3. The method for predicting the lifespan of a fully-motion simulator projector according to claim 2, characterized in that, The difference between the historical parameter fluctuation amplitude and the average fluctuation standard deviation of the equipment is compared with the average fluctuation standard deviation of the equipment, and the calculation result is mapped to a preset coefficient range to obtain the second correction coefficient.

4. The method for predicting the lifespan of a fully-motion simulator projector according to claim 1, characterized in that, Based on the brightness change rate, color change rate, transmission delay deviation rate, and the adjusted anomaly detection threshold, the method for determining whether the cross-parameter joint triggering condition is met is as follows: The trigger condition for dual-parameter correlation is: the rate of change or deviation of any two parameters simultaneously reaches the set proportion of their respective abnormal judgment thresholds; The coupling triggering condition between transmission delay and physical parameters is: the transmission delay deviation rate reaches a set proportion of its abnormal judgment threshold, and the current change rate or temperature change rate of the corresponding region exceeds its respective set fluctuation limit. The trigger condition for multi-parameter trend consistency is: within multiple consecutive acquisition cycles, the brightness change rate, color change rate, and transmission delay deviation rate all show a monotonically increasing trend, and the change rate of at least two of these parameters exceeds the set proportion of their abnormal judgment threshold.

5. The method for predicting the lifespan of a fully-motion simulator projector according to claim 1, characterized in that, The real-time collected operating status parameters, transmission delay response time, and environmental temperature and humidity parameters are preprocessed, and regional brightness attenuation trends, color shift, delay deviation trends, parameter correlation characteristics, and global fluctuation entropy characteristics are extracted. The method is as follows: The real-time collected operating status parameters, transmission delay response time, and ambient temperature and humidity parameters are preprocessed, including identifying outliers, correcting outliers, and filtering. Based on the preprocessed data, regional feature parameters and global feature parameters are extracted, where: The regional characteristic parameters are obtained by calculating the average attenuation of the brightness value of each region, the average color change rate, and the average transmission delay deviation rate. The parameter correlation characteristics are obtained by calculating the correlation coefficients between the transmission delay deviation rate and the current change rate, and between the transmission delay deviation rate and the temperature change rate. The global fluctuation entropy feature is obtained by calculating the sample entropy of the brightness change rate, color change rate, and delay deviation rate sequence of all regions.

6. The method for predicting the lifespan of a fully-motion simulator projector according to claim 5, characterized in that, The feature parameters are input into a long short-term memory neural network model with an attention mechanism, and the remaining life expectancy is predicted. The method is as follows: The regional feature parameters and global feature parameters are combined into a model input vector; The input vector is fed into a pre-trained long short-term memory neural network model; The long short-term memory neural network model calculates the weights of the feature parameters of each region through its internal attention mechanism layer, and performs a weighted summation of the feature parameters of the regions to focus on the features of high-influence regions. The processing layer of the long short-term memory neural network model performs calculations on the weighted features and outputs a predicted value representing the normalized remaining lifetime. The normalized remaining lifetime prediction is denormalized to obtain the final remaining lifetime prediction.

7. The method for predicting the lifespan of a fully-motion simulator projector according to claim 1, characterized in that, The operating status parameters include at least brightness parameters, color parameters, current parameters, and temperature parameters.

8. The method for predicting the lifespan of a fully-motion simulator projector according to claim 1, characterized in that, A maintenance warning is issued when the predicted value is lower than a preset threshold.

9. A lifespan prediction system for a fully motion simulator projector, used to implement the lifespan prediction method for a fully motion simulator projector as described in any one of claims 1-8, characterized in that, The system includes: The data acquisition module is configured to activate the projector's dark field mode, divide the projected image into multiple independent areas, and collect the operating status parameters, transmission delay response time, and ambient temperature and humidity parameters of each area. The data calculation module is configured to calculate the brightness change rate and color change rate based on the operating status parameters of each area, and compare the current transmission delay response time with the standard reference value to obtain the transmission delay deviation rate. The threshold update module is configured to dynamically adjust the anomaly detection threshold based on the device's cumulative working time, historical parameter fluctuations, and environmental stability. The trigger condition determination module is configured to determine whether the cross-parameter joint trigger condition is met based on the brightness change rate, color change rate, transmission delay deviation rate, and the adjusted anomaly determination threshold. The joint trigger condition includes two-parameter association triggering, transmission delay and physical parameter coupling triggering, or multi-parameter trend consistency triggering. The acquisition status adjustment module is configured to increase the acquisition frequency of the operating status parameters and shorten the delay sampling interval for areas that meet the trigger conditions, and decrease the corresponding acquisition frequency and interval for areas that do not meet the conditions. The data extraction module is configured to preprocess the real-time collected operating status parameters, transmission delay response time, and environmental temperature and humidity parameters, and extract regional brightness attenuation trend, color drift, delay deviation trend, parameter correlation characteristics, and global fluctuation entropy characteristics. The lifespan prediction module is configured to input feature parameters into a long short-term memory neural network model with an attention mechanism and output a predicted remaining lifespan value.

10. An electronic device, characterized in that, include: At least one processor; as well as A memory communicatively connected to at least one of the processors; wherein, The memory stores instructions that can be executed by the processor to implement the life prediction method for a full-motion simulator projector as described in any one of claims 1-8.

Images