Intelligent glass and environment dynamic adjusting system thereof

Abstract

The invention relates to the technical field of intelligent glass, in particular to intelligent glass and an environment dynamic adjusting system thereof, and the intelligent glass comprises a glass substrate, a near-infrared shielding layer, an electrochromic assembly and a transparent conductive layer; the near-infrared shielding layer is arranged on the glass substrate, the near-infrared shielding layer comprises a tungsten bronze material, and alkali metal ions are contained in the tungsten bronze material; the electrochromic assembly is arranged on the near-infrared shielding layer, the electrochromic assembly comprises an electrochromic layer, an electrolyte layer and a counter electrode layer, and the electrochromic layer comprises a tungsten oxide film; the transparent conductive layer is arranged on at least one side of the electrochromic layer and the counter electrode layer and is used for applying voltage to the electrochromic layer, so that the electrochromic layer is subjected to reversible electrochemical reaction through ion intercalation and deintercalation to change the light transmission state of the glass. Cooperative adjustment of near-infrared passive shading and electrochromic active light control is achieved.

Description

Technical Field

[0001] This invention relates to the field of smart glass technology, and in particular to a smart glass and its environmental dynamic adjustment system. Background Technology

[0002] With the development of building energy-saving technologies, smart glass is increasingly being applied to building windows, curtain walls, and skylights to regulate the intensity of light entering the room and improve the indoor environment. Existing technologies employ two main approaches: one uses insulated or low-emissivity glass, which reduces indoor temperature by applying a functional film layer to the glass surface to decrease solar radiation entering the room; the other uses electrochromic glass, which uses an electrochromic layer within the glass structure and applies a driving voltage to reversibly switch between a transparent and tinted state, thus actively regulating light transmittance. These technologies can improve building lighting and thermal environment to a certain extent and are therefore widely used in smart and energy-efficient building applications.

[0003] In practical applications, existing glass structures often struggle to simultaneously achieve both visible light transmittance and near-infrared radiation shielding capabilities. Ordinary electrochromic glass primarily controls light transmission by adjusting visible light transmittance, but its shielding capability for near-infrared radiation is limited. Consequently, it is difficult to effectively reduce heat input from near-infrared radiation while maintaining good lighting conditions. Summary of the Invention

[0004] To overcome the above shortcomings, the present invention provides a smart glass and its environmental dynamic adjustment system, which aims to improve the problem of effectively reducing heat input from near-infrared radiation while maintaining good lighting conditions.

[0005] In a first aspect, the present invention provides the following technical solution: a smart glass, comprising: Glass substrate, near-infrared shielding layer, electrochromic component, and transparent conductive layer; The near-infrared shielding layer is disposed on the surface of the glass substrate, and the near-infrared shielding layer comprises tungsten bronze. Materials, among which They are alkali metal ions; The electrochromic component is disposed on the side of the near-infrared shielding layer away from the glass substrate. The electrochromic component includes an electrochromic layer, an electrolyte layer, and a counter electrode layer, wherein the electrochromic layer includes tungsten oxide. film; The electrolyte layer is disposed on the side of the electrochromic layer away from the near-infrared shielding layer, and the counter electrode layer is disposed on the side of the electrolyte layer away from the electrochromic layer. The transparent conductive layer is disposed on at least one side of the electrochromic layer and the counter electrode layer, and is electrically connected to the electrochromic layer. It is used to apply a voltage to the electrochromic layer, so that the electrochromic layer undergoes a reversible electrochemical reaction through ion insertion and deintercalation to change the light transmission state of the glass.

[0006] By adopting the above technical solution, a composite structure of near-infrared shielding layer and electrochromic component is realized on the glass substrate. This achieves the coordinated adjustment of near-infrared passive shielding and electrochromic active dimming, thereby shielding near-infrared radiation while maintaining visible light transmittance. This solves the problem that existing glass structures are unable to effectively reduce heat input from near-infrared radiation while maintaining good lighting conditions.

[0007] Secondly, the present invention provides the following technical solution: an environmental dynamic adjustment system for smart glass, the system comprising: The environmental data acquisition module is used to collect the light intensity outside the building windows and the indoor temperature according to a preset sampling period, and to record the current light transmittance of the smart glass. The data processing module is used to perform differential calculations on the light intensity data within multiple consecutive sampling periods to obtain the light intensity change, and to compare the light intensity change with a preset change threshold to determine whether the ambient light is a short-term disturbance. The machine learning decision module constructs training samples based on environmental data and the corresponding electrochromic layer operating status, and trains the training samples using a support vector machine model. It then inputs the current environmental data into the support vector machine model to obtain the predicted operating status of the electrochromic layer. The control module maintains the current light transmittance of the smart glass for a preset time when it is determined to be a short-term disturbance, and determines the target light transmittance level based on the light intensity, indoor temperature and operation status prediction results when it is not determined to be a short-term disturbance. The predictive control module predicts the direction of indoor temperature change in the future time period based on the trend of indoor temperature change within a continuous sampling period, and corrects the target light transmittance level based on the prediction results. The drive control module applies a corresponding drive voltage to the transparent conductive layer of the smart glass according to the corrected target light transmittance level, so as to change the light transmittance state of the electrochromic layer.

[0008] Preferably, in the environmental data acquisition module, the step of acquiring the light intensity outside the building windows and the indoor temperature according to a preset sampling period includes: The environmental monitoring unit is activated at the beginning of each preset sampling period; Outdoor light intensity is collected by a light sensor installed on the outside of the building windows, and indoor temperature is collected by a temperature sensor installed inside the building during the same sampling period. The collected light intensity and indoor temperature data are stored along with the sampling timestamps to form an environmental data sequence arranged in chronological order; The environmental data sequence is updated over multiple consecutive sampling periods.

[0009] Preferably, in the data processing module, the step of performing differential calculation on the light intensity data within multiple consecutive sampling periods to obtain the light intensity change includes: Read the light intensity data of the current sampling period and the light intensity data of the previous sampling period from the environmental data sequence; Calculate the difference between the light intensity of the current sampling period and the light intensity of the previous sampling period to obtain the light change value between adjacent sampling periods; The illumination change values ​​within multiple consecutive sampling periods are accumulated or averaged to obtain the illumination change within the corresponding time window.

[0010] Preferably, in the data processing module, the step of comparing the change in illumination with a preset change threshold to determine whether the ambient illumination constitutes a short-term disturbance includes: The illumination change over multiple consecutive sampling periods is obtained, and the illumination change is compared with a preset change threshold. When the change in illumination exceeds the preset change threshold, the sampling period is recorded as an abnormal illumination period. The number of abnormal lighting cycles within a preset time window is counted. When the number of abnormal lighting cycles is less than the preset cycle threshold, the ambient lighting is determined to be a short-term disturbance.

[0011] Preferably, in the machine learning decision module, constructing training samples based on environmental data and the corresponding electrochromic layer operating state includes: Acquire environmental data and the corresponding electrochromic layer operating status within multiple consecutive sampling periods; Environmental data features are extracted and formed into environmental feature vectors; The environmental feature vectors are matched with the corresponding electrochromic layer operating states to construct training sample pairs; The training sample pairs are stored in chronological order to form a training sample set.

[0012] Preferably, in the control module, the preset duration for which the current light transmittance state of the smart glass is maintained when a short-term disturbance is detected includes: Record the current light transmission state and corresponding time at the moment when it is determined to be a short-term disturbance, and start the hold timer; The light intensity is continuously collected and new changes in light intensity are calculated while the timer is running. The hold timer is terminated early when the new change in illumination is less than the preset stability threshold for multiple consecutive sampling periods. The illumination disturbance determination will be re-executed when the hold timer reaches the preset hold time or the early termination condition is met. The light transmittance of the smart glass remains unchanged while the timer is running.

[0013] Preferably, in the control module, determining the target light transmittance level based on the prediction results of light intensity, indoor temperature, and operating status when not determined to be a short-term disturbance includes: Acquire light intensity, indoor temperature data, and operational status prediction results for the current sampling period; The light intensity is mapped to a preset light level range to determine the basic light transmittance level; The temperature correction factor is calculated based on the comparison between the indoor temperature and the preset temperature threshold. Adjust the basic light transmittance level based on the operational status prediction results; The adjusted light transmittance level is weighted and corrected based on the temperature correction factor; The corrected light transmittance level is limited to the preset light transmittance level range and output as the target light transmittance level.

[0014] Preferably, in the predictive control module, predicting the direction of indoor temperature change in the future time period based on the trend of indoor temperature change within a continuous sampling period includes: Acquire indoor temperature data over multiple consecutive sampling periods and form a temperature data sequence; Calculate the indoor temperature difference between adjacent sampling periods to obtain the temperature change; The temperature change over multiple consecutive sampling periods is averaged to obtain the temperature change trend value. Compare the temperature change trend value with the preset temperature change threshold; When the temperature change trend value is greater than the preset temperature change threshold, the indoor temperature is determined to be rising; when the temperature change trend value is less than the preset temperature change threshold, the indoor temperature is determined to be falling.

[0015] Preferably, in the drive control module, applying a corresponding drive voltage to the transparent conductive layer of the smart glass according to the corrected target light transmittance level includes: Obtain the corrected target light transmittance level; The driving voltage value corresponding to the target light transmittance level is determined based on the preset correspondence between light transmittance level and driving voltage. The driving voltage is applied to the transparent conductive layer of the smart glass in the form of a pulse voltage, and the light transmission state of the electrochromic layer is controlled according to the pulse duration.

[0016] The present invention has the following beneficial effects: 1. In this invention, by setting a composite structure of a near-infrared shielding layer and an electrochromic component on a glass substrate, the synergistic adjustment of near-infrared passive shading and electrochromic active light control is achieved, solving the problem that traditional glass cannot simultaneously achieve visible light transmittance and near-infrared thermal radiation shielding capability.

[0017] 2. In this invention, by introducing a support vector machine model to construct training samples based on environmental data and the operating state of the electrochromic layer and then learning and training them, an adaptive control method for predicting the operating state of the electrochromic layer based on real-time environmental data is realized, which solves the problem that traditional smart glass relies on fixed control rules and is difficult to adapt to complex environmental changes.

[0018] 3. In this invention, by introducing a support vector machine model to construct training samples based on environmental data and the operating state of the electrochromic layer and then learning and training them, an adaptive control method for predicting the operating state of the electrochromic layer based on real-time environmental data is realized, which solves the problem that traditional smart glass relies on fixed control rules and is difficult to adapt to complex environmental changes.

[0019] 4. In this invention, by predicting the direction of temperature change in the future time period based on the trend of indoor temperature change within a continuous sampling period, and correcting the target light transmittance level, dynamic adjustment of light transmittance state in combination with environmental change trend is realized, which solves the problem that traditional control methods only adjust based on current environmental data and lack trend prediction ability. Attached Figure Description

[0020] Figure 1 This is a schematic diagram of the structure of a smart glass proposed in this invention; Figure 2 This is a flowchart illustrating the operation of an intelligent glass environmental dynamic adjustment system proposed in this invention.

[0021] The structure consists of: 1. Glass substrate; 2. Near-infrared shielding layer; 3. Electrochromic layer; 4. Electrolyte layer; 5. Transparent conductive layer; and 6. Counter electrode layer. Detailed Implementation

[0022] The technical solutions in 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] Example 1: In a first embodiment of the present invention, the present invention provides a smart glass, such as... Figure 1 As shown, it includes: 1. Glass substrate; 2. Near-infrared shielding layer; 3. Electrochromic component; 4. Transparent conductive layer; 5. Near-infrared shielding layer 2 is disposed on the surface of glass substrate 1, and near-infrared shielding layer 2 includes tungsten bronze. Materials, among which They are alkali metal ions; The electrochromic component is disposed on the side of the near-infrared shielding layer 2 away from the glass substrate 1. The electrochromic component includes an electrochromic layer 3, an electrolyte layer 4, and a counter electrode layer 6, wherein the electrochromic layer 3 includes tungsten oxide. film; The electrolyte layer 4 is disposed on the side of the electrochromic layer 3 away from the near-infrared shielding layer 2, and the counter electrode layer 6 is disposed on the side of the electrolyte layer 4 away from the electrochromic layer 3. A transparent conductive layer 5 is disposed on at least one side of the electrochromic layer 3 and the counter electrode layer 6, and is electrically connected to the electrochromic layer 3. It is used to apply a voltage to the electrochromic layer 3, so that the electrochromic layer 3 undergoes a reversible electrochemical reaction through ion insertion and deintercalation to change the light transmission state of the glass.

[0024] Specifically, when smart glass is installed in a building window, sunlight first enters the glass structure surface, where the electrochromic layer 3 in the electrochromic component uses tungsten oxide. As the core functional material, when a voltage is applied to the system through the transparent conductive layer 5, cations from the electrolyte layer 4 and external electrons are embedded together into the tungsten oxide lattice structure, causing some hexavalent tungsten ions to be reduced to pentavalent tungsten ions, thereby forming a tungsten bronze structure. In this process, electrons are mainly localized in the form of small polarons. At the center, the internal energy level structure of the material changes and the absorption of visible light is enhanced, causing the glass to gradually change from a transparent state to a colored state to reduce light transmittance. When the applied voltage is changed or removed, the embedded ions and electrons are de-embedded from the crystal lattice, and the material returns to a transparent state. This achieves reversible adjustment between the light-transmitting state and the light-blocking state of the glass, allowing users to dynamically adjust the indoor light intensity through system control under different lighting environments. Meanwhile, the near-infrared shielding layer 2 set on the glass substrate 1 is made of tungsten bronze containing alkali metal ions. In terms of material composition, when external light passes through the glass, the free electrons in the tungsten bronze material generate a local surface plasmon resonance effect in the nanoscale structure, which works in conjunction with the small polaron transitions inside the material. This causes the material to significantly absorb or reflect near-infrared light while maintaining high transmittance for visible light. This effectively reduces the proportion of near-infrared heat from solar radiation entering the room while ensuring indoor lighting. Through the synergistic effect of the electrochromic layer 3 regulating visible light transmittance and the near-infrared shielding layer 2 blocking infrared radiation, the smart glass enables users to dynamically control the light intensity and reduce the increase in indoor temperature caused by solar radiation, thereby improving the overall effect of building lighting and heat insulation.

[0025] Example 2: In actual use of building windows, outdoor ambient light and indoor temperature change constantly over time. For example, in cloudy weather or when clouds are moving rapidly, the intensity of outdoor light may fluctuate significantly in a short period. If the smart glass system adjusts based solely on a single sample of light intensity or fixed control rules, it may lead to frequent switching of the glass's light transmission state, affecting not only the stability of the indoor lighting environment but also potentially reducing the stability of the system's operation. To address these issues, this invention provides a smart glass environmental dynamic adjustment system, the structure of which is as follows: Figure 2 As shown. The specific implementation process of this system is as follows: The environmental data acquisition module is used to collect the light intensity outside the building windows and the indoor temperature according to a preset sampling period, and to record the current light transmittance of the smart glass. Furthermore, in the environmental data acquisition module, the light intensity outside the building windows and the indoor temperature are collected according to a preset sampling period, including: The environmental monitoring unit is activated at the beginning of each preset sampling period; Outdoor light intensity is collected by a light sensor installed on the outside of the building windows, and indoor temperature is collected by a temperature sensor installed inside the building during the same sampling period. The collected light intensity and indoor temperature data are stored along with the sampling timestamps to form an environmental data sequence arranged in chronological order; Update the environmental data sequence over multiple consecutive sampling periods.

[0026] Specifically, the environmental data acquisition module is used to acquire the light intensity outside the building windows and the indoor ambient temperature according to a preset sampling period, and simultaneously record the current light transmittance of the smart glass, thereby providing basic data for subsequent environmental change analysis and control decisions. During system operation, the control unit triggers the environmental monitoring unit to start the data acquisition process according to the preset sampling period. The preset sampling period can be set according to the actual application environment, for example, it can be optionally set to any time interval between several seconds and several minutes. This periodic triggering ensures that the system can continuously obtain stable environmental change information. At the beginning of each sampling period, the environmental monitoring unit sends sampling commands to each sensor, causing the light sensor installed outside the building windows to acquire light intensity information in the outdoor environment, and simultaneously, the temperature sensor installed indoors to acquire the current indoor air temperature data. Both types of sensors complete data acquisition within the same sampling period, ensuring that different environmental parameters have a consistent time reference. In one possible implementation, the light sensor outputs the light intensity value. The temperature sensor outputs the indoor temperature value. At the same time, the system reads the light transmittance of the smart glass at the current moment. The light transmittance state can be characterized by recording the light transmittance level or driving voltage state corresponding to the current electrochromic layer 3, thereby forming a complete set of environmental operation data at each sampling moment; After data acquisition, the system stores the light intensity, indoor temperature, and light transmittance in relation to the sampling time, thus forming a time-ordered environmental data sequence. In one implementation, each set of sampled data can be represented as an environmental state vector. Its expression is: ; in Indicates the first Outdoor light intensity collected in each sampling period, Indicates the first Indoor temperature corresponding to each sampling period This indicates the light transmittance of the smart glass at the time of sampling. This represents the corresponding sampling timestamp; by storing data obtained from multiple consecutive sampling periods in chronological order, an environmental data sequence can be formed. ; in Represents a set of environmental data. This indicates the number of data samples currently collected. As the system continues to run, new sampled data will be continuously added to this data sequence and updated to update the environmental data sequence, thus obtaining time-series environmental data that reflects the trend of environmental changes. This environmental data sequence is then used by the data processing module to calculate the amount of light change and identify environmental disturbances. It also provides basic input data for the construction of training samples for the machine learning decision module and subsequent light transmission state control, thereby realizing the continuous environmental perception and state recording process of smart glass in actual use environment.

[0027] The data processing module is used to perform differential calculations on the light intensity data within multiple consecutive sampling periods to obtain the light intensity change, and to compare the light intensity change with a preset change threshold to determine whether the ambient light is a short-term disturbance. Furthermore, in the data processing module, the change in illumination is obtained by differential calculation of the illumination intensity data over multiple consecutive sampling periods, including: Read the light intensity data of the current sampling period and the light intensity data of the previous sampling period from the environmental data sequence; Calculate the difference between the light intensity of the current sampling period and the light intensity of the previous sampling period to obtain the light change value between adjacent sampling periods; The illumination change values ​​within multiple consecutive sampling periods are accumulated or averaged to obtain the illumination change within the corresponding time window.

[0028] Furthermore, in the data processing module, determining whether the ambient light level constitutes a short-term disturbance involves comparing the change in illumination with a preset threshold. The illumination change over multiple consecutive sampling periods is obtained, and the illumination change is compared with a preset change threshold. When the change in illumination exceeds a preset threshold, the sampling period is recorded as an abnormal illumination period. The number of abnormal lighting cycles within a preset time window is counted. When the number of abnormal lighting cycles is less than the preset cycle threshold, the ambient lighting is determined to be a short-term disturbance.

[0029] Specifically, the data processing module analyzes the changes in light intensity data acquired in continuous sampling periods and identifies whether the ambient light is subject to short-term disturbances based on the characteristics of these changes. This provides a basis for the subsequent control module to determine whether to maintain the current light transmittance. The environmental data acquisition module continuously generates a time-sequenced sequence of environmental data. The data processing module extracts the light intensity data corresponding to each continuous sampling period from this sequence and performs differential calculations over time to characterize the changes in light intensity between adjacent sampling periods. During operation, the data processing module first reads the light intensity data corresponding to the current sampling period and the light intensity data corresponding to the previous sampling period, denoted as follows: and ,in Indicates the first Outdoor light intensity values ​​collected in each sampling period Indicates the first The outdoor light intensity values ​​collected in each sampling period are used to obtain the light intensity change value between adjacent sampling periods by performing a difference operation on the two values. Its calculation method can be expressed as: ; in Indicates the first Each sampling period represents the change in illumination relative to the previous sampling period. This change reflects the magnitude of the change in illumination intensity between consecutive time points. When the system runs continuously, a sequence of illumination change values ​​can be obtained over multiple consecutive sampling periods. ,in This indicates the number of sampling periods involved in the calculation. To reduce the impact of single-measurement noise or random fluctuations on the judgment of environmental changes, the data processing module performs statistical processing on multiple illumination change values ​​within a certain time window. In one implementation, the illumination change values ​​within consecutive sampling periods can be accumulated or averaged. For example, the illumination change DDD can be obtained by calculating the average illumination change within the time window, and its expression can be expressed as: ; in This represents the change in illumination calculated within a preset time window. This indicates the number of sampling periods involved in the statistical calculation. This represents the absolute value of the change in illumination. By taking the absolute value, we can avoid the influence of the direction of illumination change on the statistical results, thus making the calculation results more stable. Through the above calculation process, we can obtain the illumination change parameter that reflects the degree of illumination change within a short time range. After obtaining the amount of light change, the data processing module continues to analyze the light change characteristics for disturbance judgment. By comparing the calculated amount of light change with a preset change threshold, it determines whether the current ambient light change belongs to a short-term disturbance. The preset change threshold can be set according to the actual application scenario. For example, in the application environment of building windows, a reasonable threshold range can be determined based on the statistical results of historical light change data. When the amount of light change is greater than the preset change threshold, the data processing module records the corresponding sampling period as an abnormal light period and generates an abnormal period marker in the system. Subsequently, the number of abnormal light periods is counted within a preset time window. The time window can correspond to a time interval formed by several consecutive sampling periods, such as a group of several consecutive sampling periods. The system establishes an observation window and counts the number of abnormal cycles within that window, comparing them with a preset cycle threshold. If the number of abnormal cycles is less than the preset cycle threshold, the light change is considered to have only fluctuated for a short period and then returned to a stable state, thus determining the ambient light as a short-term disturbance. Conversely, when the number of abnormal cycles reaches or exceeds the cycle threshold, it indicates that the ambient light has been changing continuously over a longer period, and this change is no longer considered a short-term disturbance. Through the above-mentioned differential calculation, change statistics, and threshold determination process, the data processing module can identify light fluctuations caused by cloud cover, instantaneous weather changes, or local shadows in continuous environmental monitoring data, thereby providing a reliable basis for the subsequent control module to determine whether to maintain the current light transmittance.

[0030] The machine learning decision module constructs training samples based on environmental data and the corresponding operating state of electrochromic layer 3, and trains the training samples using a support vector machine model. The current environmental data is input into the support vector machine model to obtain the predicted operating state of electrochromic layer 3. Furthermore, in the machine learning decision-making module, the construction of training samples based on environmental data and the corresponding operating state of the electrochromic layer 3 includes: Acquire environmental data and the corresponding operating status of the electrochromic layer 3 within multiple consecutive sampling periods; Environmental data features are extracted and formed into environmental feature vectors; The environmental feature vectors are matched with the corresponding electrochromic layer 3 operating states to construct training sample pairs; The training sample pairs are stored in chronological order to form a training sample set.

[0031] Specifically, the machine learning decision module is used to construct training samples based on the correspondence between environmental data and the operating state of the electrochromic layer 3, and to learn and train on historical operating data through a support vector machine model, thereby establishing a mapping relationship between environmental state and the execution state of the electrochromic layer 3, enabling the system to predict the light transmission state that the smart glass should adopt under new environmental conditions; the environmental data acquisition module continuously generates an environmental data sequence arranged in chronological order, and the machine learning decision module reads the environmental data corresponding to multiple consecutive sampling periods from the environmental data sequence, and simultaneously obtains the operating state information of the electrochromic layer 3 corresponding to the same sampling time. The operating state of the electrochromic layer 3 can be characterized by the current light transmission level or drive control state, thereby forming a one-to-one correspondence between environmental state and execution state under the same time reference; After obtaining continuous time series data, the machine learning decision module performs data preprocessing and feature extraction on the environmental data, transforming the original environmental parameters into feature vectors suitable for machine learning model processing. In one implementation, the environmental data includes parameters such as outdoor light intensity, indoor temperature, ambient humidity, and weather conditions. By performing outlier removal, missing value imputation, and normalization on the collected data, environmental parameters of different dimensions are brought to a uniform data scale, thereby ensuring the stability of the subsequent model training process. After preprocessing, the environmental state of each sampling period can be represented as an environmental feature vector. Its expression is: ; in Indicates the first Environmental feature vector for each sampling period This represents the outdoor light intensity parameter for that sampling period. Indicates indoor temperature parameter, Indicates the ambient humidity parameter. This represents weather conditions or other environmental characteristic parameters; subsequently, the environmental feature vector is matched with the corresponding operating state of the electrochromic layer 3 to form training sample pairs. ,in The label indicates the operating status of the electrochromic layer 3. This label is used to characterize the execution state of the electrochromic layer 3 under corresponding environmental conditions. In one possible implementation, the operating status label can be represented in a binary classification form, that is, when the electrochromic layer 3 is in a high light transmittance state, it is labeled as follows: When the electrochromic layer 3 is in a low light transmittance state, take By storing the above training sample pairs in chronological order, the training sample set can be obtained: ; in Represents the training sample set, Indicates the number of training samples. Represents the environmental feature vector. Indicates the corresponding running status label; After obtaining the training sample set, the machine learning decision module uses a support vector machine (SVM) model to learn and train on the training samples. SVM is a type of supervised learning-based classification algorithm. Its basic idea is to find an optimal classification hyperplane in the feature space that can distinguish between different classes of samples. During training, the optimal classification hyperplane is determined by finding the weight vectors. With bias parameters This ensures that the training samples maintain the maximum classification margin on both sides of the classification hyperplane, thereby improving the model's ability to classify different environmental states. In one implementation, the support vector machine model completes model training by solving the following optimization problem: ; ; in The weight vector represents the classification hyperplane. Indicates the bias parameter. Represents the environmental feature vector. This represents the corresponding running state label; after training, the corresponding classification decision function can be obtained: ; in This indicates the classification output result. The function represents the sign; a positive output indicates that the electrochromic layer 3 should be in a high-transmittance state, while a negative output indicates that it should be in a low-transmittance state. During system operation, environmental data from the current sampling period is processed to form a new environmental feature vector, which is then input into a trained support vector machine model for classification calculation. This yields a prediction of the operating state of the electrochromic layer 3, which is then transmitted to the control module as a crucial basis for transmittance control decisions. This allows the system to combine historical environmental change data and the operating patterns of the electrochromic layer 3 to predict and adjust the transmittance of the smart glass under the current environmental conditions, thereby achieving adaptive operation of the smart glass in practical application environments.

[0032] The control module maintains the current light transmittance of the smart glass for a preset time when it is determined to be a short-term disturbance, and determines the target light transmittance level based on the light intensity, indoor temperature and operation status prediction results when it is not determined to be a short-term disturbance. Furthermore, in the control module, the preset duration for maintaining the current light transmission state of the smart glass when a short-term disturbance is detected includes: Record the current light transmission state and corresponding time at the moment when it is determined to be a short-term disturbance, and start the hold timer; The light intensity is continuously collected and new changes in light intensity are calculated while the timer is running. The hold timer is terminated early when the new change in illumination is less than the preset stability threshold for multiple consecutive sampling periods. The illumination disturbance determination will be re-executed when the hold timer reaches the preset hold time or the early termination condition is met. The light transmittance of the smart glass remains unchanged while the timer is running.

[0033] Furthermore, in the control module, when the disturbance is not determined to be short-term, the target light transmittance level is determined based on the predicted results of light intensity, indoor temperature, and operating status, including: Acquire light intensity, indoor temperature data, and operational status prediction results for the current sampling period; The light intensity is mapped to a preset light level range to determine the basic light transmittance level; The temperature correction factor is calculated based on the comparison between the indoor temperature and the preset temperature threshold. Adjust the basic light transmittance level based on the operational status prediction results; The adjusted light transmittance level is weighted and corrected based on the temperature correction factor; The corrected light transmittance level is limited to the preset light transmittance level range and output as the target light transmittance level.

[0034] Specifically, the control module maintains the current light transmittance of the smart glass when a short-term disturbance occurs in ambient light. When the ambient light is not considered a short-term disturbance, it determines the target light transmittance level by combining real-time environmental parameters with the operational state prediction results output by the machine learning decision module. This allows the control process to simultaneously suppress short-term disturbances and adaptively adjust to the environmental state. After the data processing module completes the calculation of the light change and outputs the disturbance determination result, the control module first reads the current light transmittance state of the smart glass. and corresponding time ,in This indicates the current light transmittance level of the smart glass when a short-term disturbance is determined to be valid. This indicates the start time when the current light transmittance level is recorded. Subsequently, the control module starts a hold timer to continuously monitor changes in ambient light within a preset hold time interval. During the hold timer's operation, the system continues to collect new light intensity data according to a preset sampling period, and the data processing module calculates the new light change. When the light change corresponding to multiple consecutive sampling periods is less than a preset stability threshold, it indicates that the current ambient light has transitioned from a short-term fluctuating state to a relatively stable state. At this point, the control module can terminate the hold timer early and re-execute the disturbance judgment. When the hold timer reaches the preset hold time or meets the early termination condition, the control module re-enters the environmental state judgment process. Throughout the entire hold timer's operation, the control module maintains the light transmittance of the smart glass at a certain level. This avoids frequent switching of light transmission state in a short period of time due to instantaneous light fluctuations. The control logic is connected with the short-term disturbance identification process in the preceding data processing module, so that the environmental disturbance judgment result can truly participate in the subsequent light transmission control process. When the ambient light is not determined to be a short-term disturbance, the control module enters the target transmittance calculation process. During this process, the control module acquires the light intensity data of the current sampling period, indoor temperature data, and the operation status prediction results output by the machine learning decision module. The operation status prediction results are used to reflect the target operation trend that the electrochromic layer 3 should perform under the current environmental conditions. The control module first maps the current light intensity to a preset light level range to determine the basic transmittance level. The basic light transmittance level is used to characterize the initial light transmittance state that the smart glass should achieve under the current incident light conditions; then the control module calculates the temperature correction coefficient based on the relationship between the indoor temperature and the preset temperature threshold. The temperature correction coefficient is used to characterize the degree of correction of the indoor thermal environment on the light transmittance control. In one implementation, when the indoor temperature is higher than the preset temperature threshold, the temperature correction coefficient is used to reduce the light transmittance level, and when the indoor temperature is lower than the preset temperature threshold, the temperature correction coefficient is used to maintain or appropriately increase the light transmittance level. At the same time, the operation status prediction result is used to adjust the basic light transmittance level. This adjustment reflects the prediction result obtained by the machine learning decision module based on historical environmental data and the operation status of the electrochromic layer 3. This allows the control module to further introduce historical environmental patterns and glass operation habits information in addition to real-time environmental parameters, so that the determination of the target light transmittance level depends not only on the environmental measurement value at a single moment, but also on the prediction judgment of the current operation status. After determining the basic light transmittance level, adjusting the operating status, and calculating the temperature correction coefficient, the control module performs a weighted correction on the adjusted light transmittance level. In one implementation, the target light transmittance level after weighted correction is... It can be represented as: ; in, This indicates the corrected target light transmittance level. This indicates the basic light transmittance level obtained by mapping based on light intensity. This represents the temperature correction amount obtained by comparing the indoor temperature with a preset temperature threshold. This represents the state correction amount determined based on the operational state prediction results; when the calculated... When the light transmittance exceeds the preset range, the control module will... Limiting processing is performed to keep the target light transmittance level within the system's allowable range, thereby ensuring that the subsequent drive control process can operate within the predetermined control level range. Through the above processing, the control module can maintain the current light transmittance state through a holding mechanism under short-term light disturbances, and determine the target light transmittance level comprehensively based on light intensity, indoor temperature, and operating status prediction results under normal environmental changes. This gives the control process a clear data source, state judgment logic, and light transmittance calculation path, and provides stable and consistent target control parameters for the subsequent predictive control module and drive control module.

[0035] The predictive control module predicts the direction of indoor temperature change in the future time period based on the trend of indoor temperature change within a continuous sampling period, and corrects the target light transmittance level based on the prediction results. Furthermore, in the predictive control module, the prediction of the direction of indoor temperature change in the future time period based on the trend of indoor temperature change within a continuous sampling period includes: Acquire indoor temperature data over multiple consecutive sampling periods and form a temperature data sequence; Calculate the indoor temperature difference between adjacent sampling periods to obtain the temperature change; The temperature change over multiple consecutive sampling periods is averaged to obtain the temperature change trend value. Compare the temperature change trend value with the preset temperature change threshold; When the temperature change trend value is greater than the preset temperature change threshold, the indoor temperature is determined to be rising; when the temperature change trend value is less than the preset temperature change threshold, the indoor temperature is determined to be falling.

[0036] Specifically, the predictive control module is used to predict the direction of indoor temperature change in the future time period based on the changes in indoor temperature data within a continuous sampling period. On this basis, it performs feedforward correction on the target light transmittance level output by the control module, so that the light transmittance adjustment of the smart glass not only responds to the current environmental state, but also can be controlled in advance based on the changing trend of the indoor thermal environment. Since the indoor temperature in the environment where the building window is located is continuously changed over time due to solar radiation, indoor air exchange, and the heat storage process of the building envelope, the temperature value at a single sampling moment is difficult to fully reflect the changing trend of the thermal environment. Therefore, the predictive control module uses the indoor temperature data obtained in multiple consecutive sampling periods as the analysis object, judges the trend of indoor temperature change on the time axis, and uses the result of the trend judgment as the input basis for the target light transmittance level correction. During operation, the predictive control module first reads indoor temperature data corresponding to multiple consecutive sampling periods from the environmental data sequence, and forms a temperature data sequence according to the sampling time order. In one implementation, the temperature data sequence can be represented as: ; in, Represents a temperature data sequence. Indicates the first Indoor temperature values ​​collected in each sampling period. This indicates the number of sampling periods involved in the trend analysis. After obtaining the temperature data sequence, the predictive control module calculates the indoor temperature difference between adjacent sampling periods to obtain the temperature change corresponding to each sampling period. In one implementation, the first... The temperature change corresponding to each sampling period is denoted as The calculation method is as follows: ; in, Indicates the first The change in indoor temperature in each sampling period relative to the previous sampling period. Indicates the first Indoor temperature for each sampling period, This represents the indoor temperature of the previous sampling period. By calculating the difference above, a sequence of temperature changes over multiple consecutive sampling periods can be obtained, thereby transforming discrete temperature sample values ​​into an analytical object that can reflect the direction and rate of temperature change. After obtaining the temperature change sequence, the predictive control module averages the temperature changes over multiple consecutive sampling periods to obtain a temperature change trend value. In one implementation, this temperature change trend value is denoted as... Its calculation method can be expressed as: ; in, Values ​​indicating the trend of temperature change. This indicates the number of sampling periods involved in the calculation. Indicates the first The temperature change corresponding to each sampling period; by averaging the temperature changes across multiple sampling periods, the impact of single temperature fluctuations or local disturbances on trend judgment can be reduced, making the trend calculation results more consistent with the overall changes in the indoor thermal environment within the current time interval; after obtaining the temperature change trend value, the predictive control module compares it with a preset temperature change threshold to determine the direction of indoor temperature change in the future time period. In one implementation, when When the temperature change exceeds a preset threshold, the indoor temperature is determined to be trending upwards. When the temperature change is less than a preset threshold, the indoor temperature is determined to be decreasing. When the temperature is within a stable range near the threshold, it can be optionally determined that the indoor temperature is in a basically stable state. The preset temperature change threshold is used to characterize whether the temperature change is sufficient to trigger the light transmission control correction. Its value can be set according to the building usage scenario, sampling period length and temperature control requirements. After determining the direction of temperature change, the predictive control module transmits the prediction results to the subsequent correction process, correcting the target light transmittance level previously determined by the control module based on light intensity, indoor temperature, and operating status. When the prediction results indicate an upward trend in indoor temperature, it suggests that the indoor thermal environment may continue to increase in the future. In this case, reducing the target light transmittance level can reduce the solar radiation input entering the room. When the prediction results indicate a downward trend in indoor temperature, it suggests that the current indoor thermal load is weakening. In this case, the original target light transmittance level can be maintained or the target light transmittance level can be increased, allowing the subsequent drive control module to output the corresponding drive voltage based on the corrected target light transmittance level. In this way, the predictive control module transforms the temperature change information formed by continuous sampling periods into a judgment result on the future direction of temperature change and incorporates this judgment result into the light transmittance control decision process. This gives the smart glass's adjustment logic a trend prediction basis in addition to real-time environmental response, thus forming a complete control link that connects with the environmental data acquisition module, data processing module, control module, and drive control module.

[0037] The drive control module applies a corresponding drive voltage to the transparent conductive layer 5 of the smart glass according to the corrected target light transmittance level, so as to change the light transmittance state of the electrochromic layer 3.

[0038] Furthermore, in the drive control module, applying a corresponding drive voltage to the transparent conductive layer 5 of the smart glass according to the corrected target light transmittance level includes: Obtain the corrected target light transmittance level; The driving voltage value corresponding to the target light transmittance level is determined based on the preset correspondence between light transmittance level and driving voltage. The driving voltage is applied to the transparent conductive layer 5 of the smart glass in the form of a pulse voltage, and the light transmission state of the electrochromic layer 3 is controlled according to the pulse duration.

[0039] Specifically, the drive control module generates a corresponding drive control signal based on the corrected target transmittance level output by the predictive control module, and applies a drive voltage to the electrochromic component through the transparent conductive layer 5, causing the electrochromic layer 3 to change its optical transmittance characteristics under the action of electrochemical reaction, thereby enabling the smart glass to achieve a transmittance state corresponding to the target transmittance level; the electrochromic component uses tungsten oxide film as the electrochromic material. When a voltage is applied across the two ends of the transparent conductive layer 5, ions and electrons in the electrolyte are inserted into or extracted from the tungsten oxide lattice structure, thereby causing a reversible electrochromic reaction in the material. During this reaction, the change in the valence state inside the material will cause a change in the transmittance of visible light. Therefore, the transmittance state can be adjusted by adjusting the amplitude and duration of the applied voltage. During system operation, the drive control module first receives the corrected target transmittance level output by the predictive control module, and determines the corresponding drive voltage value based on the pre-established mapping relationship between transmittance level and drive voltage in the system. In one implementation, the system establishes a functional relationship model between transmittance level and drive voltage through experimental calibration during the initialization phase, ensuring that different transmittance levels correspond to a unique drive voltage range. The drive control module obtains the drive voltage value corresponding to the target transmittance level through table lookup or function calculation. In another possible implementation, the relationship between transmittance level and drive voltage can be represented as a linear or piecewise linear relationship, for example: ; in, Indicates the driving voltage value. This indicates the corrected target light transmittance level. This represents the proportionality coefficient between the light transmittance level and the driving voltage. This represents the voltage bias parameter, which is used to compensate for the electrochemical driving requirements of the electrochromic material in its initial state. In practical applications, this mapping relationship can be set according to the characteristics of the electrochromic material, the glass structure parameters, and the characteristics of the driving circuit. After obtaining the target driving voltage, the driving control module applies a pulsed driving voltage signal to the transparent conductive layer 5 through the driving circuit. Using a pulsed driving method can ensure the electrochromic reaction proceeds fully while reducing material fatigue or energy consumption caused by continuous DC voltage. In one implementation, the driving control module calculates the required pulse duration based on the target light transmittance level and adjusts the ion embedding degree of the electrochromic layer 3 by controlling the pulse width. The pulse duration is denoted as... Its value can be determined according to the range of change in light transmittance. For example, when there is a large difference between the current light transmittance and the target light transmittance, the drive control module increases the pulse duration. When the range of change in light transmittance is small, a shorter pulse duration is used to achieve fine adjustment. During the application of the driving voltage, the transparent conductive layer 5 acts as an electrode to uniformly apply the driving voltage to the surface of the electrochromic layer 3, causing ion migration and electronic conduction processes within the electrochromic material. As the ion insertion or deintercalation reaction proceeds, the optical transmittance of the electrochromic layer 3 gradually changes and approaches the target transmittance level. After each driving cycle, the driving control module can read the current transmittance state and compare it with the target transmittance level. If there is still a deviation between the current transmittance level and the target transmittance level, a driving pulse can be output again for compensation and adjustment, thus forming a closed-loop adjustment process. Through the above control process, the driving control module can convert the target transmittance level generated by the control module and the predictive control module into an actual voltage driving signal, causing the electrochromic layer 3 to change its transmittance state under the action of electrochemical reaction, thereby realizing the dynamic adjustment process of the transmittance state of the smart glass.

[0040] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A type of smart glass, characterized in that, include: Glass substrate (1), near-infrared shielding layer (2), electrochromic component and transparent conductive layer (5); The near-infrared shielding layer (2) is disposed on the surface of the glass substrate (1), and the near-infrared shielding layer (2) comprises tungsten bronze. Materials, among which They are alkali metal ions; The electrochromic component is disposed on the side of the near-infrared shielding layer (2) away from the glass substrate (1). The electrochromic component includes an electrochromic layer (3), an electrolyte layer (4), and a counter electrode layer (6). The electrochromic layer (3) includes tungsten oxide. film; The electrolyte layer (4) is disposed on the side of the electrochromic layer (3) away from the near-infrared shielding layer (2), and the counter electrode layer (6) is disposed on the side of the electrolyte layer (4) away from the electrochromic layer (3). The transparent conductive layer (5) is disposed on at least one side of the electrochromic layer (3) and the counter electrode layer (6) and is electrically connected to the electrochromic layer (3). It is used to apply voltage to the electrochromic layer (3) so that the electrochromic layer (3) undergoes a reversible electrochemical reaction through ion insertion and deintercalation to change the light transmission state of the glass.

2. An environmental dynamic adjustment system for smart glass, characterized in that, For use in a smart glass according to claim 1, the system comprises: The environmental data acquisition module is used to collect the light intensity outside the building windows and the indoor temperature according to a preset sampling period, and to record the current light transmittance of the smart glass. The data processing module is used to perform differential calculations on the light intensity data within multiple consecutive sampling periods to obtain the light intensity change, and to compare the light intensity change with a preset change threshold to determine whether the ambient light is a short-term disturbance. The machine learning decision module constructs training samples based on environmental data and the corresponding electrochromic layer (3) operating status, and trains the training samples using a support vector machine model. Based on the current environmental data, it inputs the support vector machine model to obtain the predicted operating status of the electrochromic layer (3). The control module maintains the current light transmittance of the smart glass for a preset time when it is determined to be a short-term disturbance, and determines the target light transmittance level based on the light intensity, indoor temperature and operation status prediction results when it is not determined to be a short-term disturbance. The predictive control module predicts the direction of indoor temperature change in the future time period based on the trend of indoor temperature change within a continuous sampling period, and corrects the target light transmittance level based on the prediction results. The drive control module applies a corresponding drive voltage to the transparent conductive layer (5) of the smart glass according to the corrected target light transmittance level, so as to change the light transmittance state of the electrochromic layer (3).

3. The intelligent glass environmental dynamic adjustment system according to claim 2, characterized in that, In the environmental data acquisition module, the step of collecting the light intensity outside the building windows and the indoor temperature according to a preset sampling period includes: The environmental monitoring unit is activated at the beginning of each preset sampling period; Outdoor light intensity is collected by a light sensor installed on the outside of the building windows, and indoor temperature is collected by a temperature sensor installed inside the building during the same sampling period. The collected light intensity and indoor temperature data are stored along with the sampling timestamps to form an environmental data sequence arranged in chronological order. The environmental data sequence is updated over multiple consecutive sampling periods.

4. The environmental dynamic adjustment system for smart glass according to claim 2, characterized in that, In the data processing module, the step of performing differential calculations on the illumination intensity data over multiple consecutive sampling periods to obtain the illumination change includes: Read the light intensity data of the current sampling period and the light intensity data of the previous sampling period from the environmental data sequence; Calculate the difference between the light intensity of the current sampling period and the light intensity of the previous sampling period to obtain the light change value between adjacent sampling periods; The illumination change values ​​within multiple consecutive sampling periods are accumulated or averaged to obtain the illumination change within the corresponding time window.

5. The environmental dynamic adjustment system for smart glass according to claim 2, characterized in that, In the data processing module, the step of comparing the change in illumination with a preset change threshold to determine whether the ambient illumination constitutes a short-term disturbance includes: The illumination change over multiple consecutive sampling periods is obtained, and the illumination change is compared with a preset change threshold. When the change in illumination exceeds the preset change threshold, the sampling period is recorded as an abnormal illumination period. The number of abnormal lighting cycles within a preset time window is counted. When the number of abnormal lighting cycles is less than a preset cycle threshold, the ambient lighting is determined to be a short-term disturbance.

6. The environmental dynamic adjustment system for smart glass according to claim 2, characterized in that, In the machine learning decision module, the construction of training samples based on environmental data and the corresponding electrochromic layer (3) operating state includes: Acquire environmental data and the corresponding electrochromic layer (3) operating status within multiple consecutive sampling periods; Environmental data features are extracted and formed into environmental feature vectors; The environmental feature vectors are matched with the corresponding electrochromic layer (3) operating states to construct training sample pairs; The training sample pairs are stored in chronological order to form a training sample set.

7. The environmental dynamic adjustment system for smart glass according to claim 2, characterized in that, In the control module, the preset duration for maintaining the current light transmittance state of the smart glass when a short-term disturbance is detected includes: Record the current light transmission state and corresponding time at the moment when it is determined to be a short-term disturbance, and start the hold timer; The light intensity is continuously collected and new changes in light intensity are calculated while the timer is running. The hold timer is terminated early when the new change in illumination is less than the preset stability threshold for multiple consecutive sampling periods. The illumination disturbance determination will be re-executed when the hold timer reaches the preset hold time or the early termination condition is met. The light transmittance of the smart glass remains unchanged while the timer is running.

8. The environmental dynamic adjustment system for smart glass according to claim 2, characterized in that, In the control module, determining the target light transmittance level based on the prediction results of light intensity, indoor temperature, and operating status when not determined to be a short-term disturbance includes: Acquire light intensity, indoor temperature data, and operational status prediction results for the current sampling period; The light intensity is mapped to a preset light level range to determine the basic light transmittance level; The temperature correction factor is calculated based on the comparison between the indoor temperature and the preset temperature threshold. Adjust the basic light transmittance level based on the operational status prediction results; The adjusted light transmittance level is weighted and corrected based on the temperature correction factor; The corrected light transmittance level is limited to the preset light transmittance level range and output as the target light transmittance level.

9. The environmental dynamic adjustment system for smart glass according to claim 2, characterized in that, In the predictive control module, predicting the direction of indoor temperature change in the future time period based on the trend of indoor temperature change within a continuous sampling period includes: Acquire indoor temperature data over multiple consecutive sampling periods and form a temperature data sequence; Calculate the indoor temperature difference between adjacent sampling periods to obtain the temperature change; The temperature change over multiple consecutive sampling periods is averaged to obtain the temperature change trend value. Compare the temperature change trend value with the preset temperature change threshold; When the temperature change trend value is greater than the preset temperature change threshold, the indoor temperature is determined to be rising; when the temperature change trend value is less than the preset temperature change threshold, the indoor temperature is determined to be falling.

10. The environmental dynamic adjustment system for smart glass according to claim 2, characterized in that, In the drive control module, applying a corresponding drive voltage to the transparent conductive layer (5) of the smart glass according to the corrected target light transmittance level includes: Obtain the corrected target light transmittance level; The driving voltage value corresponding to the target light transmittance level is determined based on the preset correspondence between light transmittance level and driving voltage. The driving voltage is applied to the transparent conductive layer (5) of the smart glass in the form of a pulse voltage, and the light transmission state of the electrochromic layer (3) is controlled according to the pulse duration.

Images