Exhibit dynamic environment monitoring and regulation system and method based on Internet of Things technology

Abstract

The invention discloses an exhibit dynamic environment monitoring and regulation system and method based on the Internet of Things technology. The method comprises the following steps: S1, deploying a plurality of Internet of Things sensors; s2, transmitting the acquired environmental data to a cloud platform, and performing preprocessing to generate a risk assessment report; s3, generating a regulation and control instruction; s4, acquiring a prediction result by adopting an autoregressive integral moving average model, and adjusting environment setting in advance according to the prediction result; s5, calculating and updating a preset safety threshold value of the environmental parameters, setting a tolerance range, and automatically alarming when the environmental parameters exceed the preset safety threshold value; s6, providing an administrator remote access interface; s7, fault detection is carried out through a self-diagnosis function; and S8, generating a statistical report and trend analysis of the environmental data. According to the method, an efficient and scientific optimization scheme can be provided in dynamic environment monitoring and regulation of the exhibits, and remarkable technical value and economic benefits are brought to practical application.

Description

Technical Field

[0001] The present invention relates to the field of exhibit environment monitoring, and particularly to a dynamic environment monitoring and regulation system and method for exhibits based on Internet of Things technology. Background Art

[0002] With the rapid development of Internet of Things technology, more and more industries have started to use Internet of Things devices for environmental monitoring and regulation. In the field of exhibit display, the display environment of exhibits is crucial for protecting exhibits and improving the audience experience. Traditional environmental monitoring systems usually rely on a single sensor and manual adjustment devices, and this method has many limitations. First of all, traditional exhibit environment monitoring systems often lack real-time performance, and there are delays in data collection and transmission, unable to reflect environmental changes in a timely manner. In addition, existing systems usually cannot comprehensively process data from different sensors, and also lack an intelligent feedback mechanism. Once a certain parameter is abnormal, manual intervention is often required, with low efficiency and prone to operation errors or delays. The control of the exhibit display environment mainly relies on manual setting and simple automatic adjustment of devices, and cannot achieve automatic optimization and adjustment according to environmental changes, which poses great challenges to the exhibit protection work in a dynamic and complex display environment.

[0003] At the same time, the existing monitoring systems also have relatively limited capabilities in processing and analyzing environmental data. Most systems can only simply store and display environmental data, lacking in-depth analysis and prediction of the data. In the face of complex environmental changes, the system often cannot make intelligent decisions, resulting in exhibits possibly encountering unsuitable display conditions. For example, changes in parameters such as temperature, humidity, and light in the environment may affect exhibits in a short period of time, and the existing monitoring systems cannot predict these changes in advance and cannot take effective measures to intervene at the initial stage of the changes. Therefore, the existing systems cannot ensure the long-term and stable protection of exhibits under various complex environmental conditions, and lack necessary safety guarantees during the exhibition period.

[0004] In addition to the lag of monitoring data and the lack of intelligent analysis, there are also problems in device management in existing systems. When a device fails or environmental parameters are abnormal, the system lacks an effective self-diagnosis function and usually requires manual inspection and maintenance, which not only increases the workload of managers but also increases the response time when the system fails. In some complex environments, device failures may cause damage to exhibits, especially when the device failure is detected late. In addition, after a failure occurs in the existing system, in most cases, it cannot automatically recover and still requires manual intervention to resume normal operation. Such manual intervention is not only inefficient but also may cause unnecessary risks during the recovery process.

[0005] Based on the deficiencies of the above-mentioned existing technologies, how to improve the real-time, intelligent, reliable, and automated levels of the environmental monitoring and control system has become an urgent need for the current technological development. Therefore, an intelligent dynamic environmental monitoring and control system for exhibits based on Internet of Things technology has emerged. By collecting various environmental parameters in real time and combining intelligent algorithms for data analysis and prediction, it can respond in a timely manner when the environment where the exhibits are located changes, automatically adjust the environmental parameters, and at the same time have the ability of fault diagnosis and automatic recovery to ensure the efficient and stable operation of the system. The proposal of this technology can not only improve the safety and display effect of the exhibits, but also provide a more convenient and efficient operation method for exhibition managers, thus greatly improving the management quality of the exhibit environment. Summary of the Invention

[0006] An object of the present invention is to propose an exhibit dynamic environmental monitoring and control system and method based on Internet of Things technology. The present invention can provide an efficient and scientific optimization scheme in the dynamic environmental monitoring of exhibits, bringing significant technical value and economic benefits to practical applications.

[0007] An exhibit dynamic environmental monitoring and control method based on Internet of Things technology according to an embodiment of the present invention includes the following steps:

[0008] S1. Deploy a variety of Internet of Things sensors in the exhibit display area, and each sensor is connected to the Internet of Things gateway through a wireless communication protocol;

[0009] S2. The Internet of Things gateway transmits the environmental data collected by each sensor to the cloud platform. The cloud platform preprocesses the real-time collected environmental data, and obtains an analysis result by using a data analysis module based on the preprocessed environmental data. The data analysis module includes a trend analysis module, an anomaly detection module, and a pattern recognition module, and generates a risk assessment report based on the analysis result;

[0010] S3. The cloud platform generates a control instruction according to the risk assessment report, and sends the control instruction to the control device through the Internet of Things protocol to automatically adjust the environmental parameters;

[0011] S4. Use an autoregressive integrated moving average model to analyze the real-time environmental data and historical data to obtain a prediction result. The cloud platform sets a confidence interval by fitting the environmental parameters, and adjusts the prediction result based on the confidence interval, and adjusts the environmental settings in advance according to the prediction result;

[0012] S5. The cloud platform automatically calculates and updates the preset safety threshold of the environmental parameters according to the real-time collected environmental data and historical data, and sets a tolerance range. When the environmental parameters exceed the preset safety threshold, the system automatically determines the alarm level according to the set alarm priority, and uses the Internet of Things device to send out alarm information in real time, and notifies the administrator through text messages, emails, and APP push methods;

[0013] S6. Through the real-time data monitoring interface provided by the mobile terminal and the PC terminal, the administrator can remotely access and control and optimize the display environment;

[0014] S7. When a device fails, the IoT gateway performs fault detection through the self-diagnosis function and notifies the administrator. At the same time, it triggers the automatic recovery mechanism. After the recovery is completed, the IoT gateway will calculate the recovery status evaluation value and determine whether the recovery operation is completed according to the recovery status evaluation value;

[0015] S8. The cloud platform generates statistical reports and trend analyses of environmental data to support the exhibition party in optimizing the environmental control equipment and planning future display activities.

[0016] Optionally, S1 includes the following steps:

[0017] S11. Select multiple sensors suitable for different environmental conditions in the exhibit display area for deployment. The sensors include: temperature and humidity sensors, light sensors, gas sensors, vibration sensors, smoke sensors;

[0018] S12. Install the sensors in the display area according to the predetermined layout and connect them to the IoT gateway through a wireless communication protocol;

[0019] S13. Each sensor is set with a unique identifier, and the collected environmental data is sent to the IoT gateway through the IoT protocol. The IoT gateway classifies, marks and transmits the environmental data to the cloud platform according to the timestamp of the data and the sensor identifier;

[0020] S14. The communication between the sensor and the IoT gateway uses an encryption algorithm for data protection;

[0021] S15. The sampling frequency of the sensor is set according to the actual needs of the display area, and the sampling frequency is f sample , and it satisfies f sample >f min , f min is the required minimum sampling frequency;

[0022] S16. The operating temperature range of the sensor is set to T min ≤T≤T max , T min is the minimum operating temperature of the sensor, and T max is the maximum operating temperature of the sensor.

[0023] Optionally, S2 includes the following steps:

[0024] S21. The IoT gateway transmits the environmental data collected from each sensor to the cloud platform via a wireless communication protocol, and preliminarily screens and preprocesses the environmental data;

[0025] S22. On the cloud platform, the real-time environmental data is stored together with the corresponding timestamps. The environmental data storage model uses a time-series database for data query and analysis in chronological order;

[0026] S23. The cloud platform processes the abnormal data using a data cleaning algorithm, which includes interpolation, mean filling, and data smoothing methods;

[0027] S24. Normalize the processed environmental data;

[0028] S25. The cloud platform inputs the processed data into the data analysis module, which includes a trend analysis module, an anomaly detection module, and a pattern recognition module;

[0029] In the trend analysis module, a time-series analysis method is used to analyze the trend of environmental data. The time-series analysis method uses an autoregressive model and predicts the environmental parameters at a future moment through the following formula:

[0030] T forecast (t) = αT t-1 + βH t-1 + γL t-1 + ε t ;

[0031] where, T forecast (t) is the environmental temperature at the prediction moment t, T t-1 is the temperature at time t - 1, H t-1 is the humidity at time t - 1, L t-1 is the illumination at time t - 1, α, β, γ are coefficients, and ε t is the noise term

[0032] In the anomaly detection module, the environmental parameters are detected for anomalies by combining the real-time environmental data with the preset environmental parameter thresholds. The anomaly detection method uses a distance-based method to determine whether an anomaly occurs by calculating the anomaly score for each time point:

[0033]

[0034] where, Score abnormal is the anomaly score, x i is the data value of the i-th sensor, μ i is the mean of the i-th sensor, σ i is the data standard deviation of the i-th sensor, and n is the total number of sensors;

[0035] In the pattern recognition module, a support vector machine is used to perform pattern recognition on environmental data to identify normal environmental patterns and abnormal environmental patterns:

[0036]

[0037] Among them, is the predicted environmental pattern category, w i is the weight of the i-th feature, x i is the data value of the i-th sensor, b is the bias term, and m is the number of features;

[0038] S26. Based on the results of trend analysis, anomaly detection, and pattern recognition, the cloud platform generates a risk assessment report for environmental data to identify whether the currently displayed environment is in a normal state.

[0039] Optionally, the S3 includes the following steps:

[0040] S31. According to the risk assessment report, the cloud platform generates a regulation instruction, and the regulation instruction includes the type of the control and adjustment device and the required adjustment parameters. The adjustment devices include air conditioners, humidifiers, air purifiers, and intelligent lighting systems;

[0041] S32. The regulation instruction is sent to the IoT gateway through the IoT protocol, and the IoT gateway adjusts the environmental parameters of the device according to the received regulation instruction;

[0042] S33. The cloud platform monitors the response status of the adjustment device in real time and obtains the working status of the device through a feedback mechanism. If the adjustment device fails to respond or malfunctions, the system triggers a fault alarm and notifies the administrator for maintenance;

[0043] S34. According to the changes in the actual environment, adjust the working frequency and operation mode of the regulation device.

[0044] Optionally, the S4 includes the following steps:

[0045] S41. The cloud platform performs data modeling based on real-time environmental data and historical data to predict the change trend of future environmental parameters. The autoregressive integrated moving average model is used to perform time series prediction on temperature, humidity, and light environmental parameters:

[0046]

[0047] Among them, X t is the predicted value at time t, μ is the constant term, is the autoregressive term coefficient, θ1, θ2,..., θ q is the moving average term coefficient, ε t is the error term;

[0048] S43. During the prediction process, the cloud platform fits each environmental parameter, calculates the error range, and adjusts the prediction result according to the set confidence interval, where the confidence interval is calculated based on the standard deviation of the historical data error and the set confidence level:

[0049]

[0050] Among them, is the predicted value, Z is the critical value of the standard normal distribution, and σ historical is the standard deviation of the historical data;

[0051] S44. Smooth the prediction result by the weighted average method to eliminate the error caused by sudden changes. The formula of the weighted average method is:

[0052]

[0053] Among them, X i is the predicted value at the i-th moment, w i is the weight at the i-th moment, and n is the size of the time window;

[0054] S45. According to the prediction result, the cloud platform adjusts the working parameters of the regulating device to make environmental adjustments in advance to adapt to the upcoming environmental changes;

[0055] S46. The cloud platform continuously updates the prediction model based on the prediction error and the adjusted environmental data, and provides real-time feedback on the adjustment effect of the regulating device.

[0056] Optionally, the said S5 includes the following steps:

[0057] S51. The cloud platform conducts statistical analysis on the real-time collected environmental data and historical data, and calculates the basic statistics of each environmental parameter, including the mean value, maximum value, minimum value, and standard deviation;

[0058] S52. Smooth the real-time environmental data by the moving average method based on the time window, and calculate the mean value within each time window to remove the noise in the data:

[0059]

[0060] Among them, is the smoothed temperature value at time t, w is the size of the time window, and T i is the temperature value at time i;

[0061] S53. The cloud platform automatically calculates and updates the preset safety threshold of the environmental parameter according to the statistical result of the historical data, and sets a reasonable tolerance range:

[0062] T alarm = μ T ± k·σ T ;

[0063] Wherein, T alarm is the safety threshold of temperature, k is the adjustment coefficient, μ T is the mean value of temperature, σ T is the standard deviation of temperature;

[0064] S54. The cloud platform compares the real-time collected environmental data with the preset safety threshold, generates an alarm log, and pushes the abnormal information to the administrator in real time, notifying the administrator by means such as SMS, email, and APP push:

[0065]

[0066] Wherein, T current is the current temperature value, H current is the current humidity value, μ T is the mean value of temperature, μ H is the mean humidity value, T alarm is the safety threshold of temperature, H alarm is the safety threshold of humidity, True indicates that the alarm is triggered, and False indicates that the alarm is not triggered;

[0067] S55. When the environmental data is abnormal, the system automatically determines the alarm level according to the set alarm priority. The alarm level is divided into three levels: high, medium, and low. The specific rules are as follows:

[0068]

[0069] Wherein, Level is the alarm level, T set is the target temperature, C gas is the current gas concentration, C set is the target gas concentration, ΔT is the tolerance of temperature, ΔC gas is the tolerance of gas concentration, High indicates that the alarm level is high, Medium indicates that the alarm level is medium, and Low indicates that the alarm level is low.

[0070] Optionally, the S7 includes the following steps:

[0071] S71. When the device fails, the IoT gateway performs fault detection through the self-diagnosis function. The self-diagnosis function includes detecting the working status, communication status, power status, response time, and device load parameters of the sensor;

[0072] S72. The IoT gateway compares the real-time values of each monitoring parameter with the preset standard value and calculates the fault score Scorediagnostic :

[0073]

[0074] Among them, T current is the current temperature, C current is the current communication signal strength, P current is the current power supply current, R current is the value of the current response time, T min is the minimum allowable value of temperature, T max is the maximum allowable value of temperature, C min is the minimum allowable value of communication signal strength, C max is the maximum allowable value of communication signal strength, P max is the maximum allowable value of power supply current, R thresh is the response time threshold, w1, w2, w3, w4 are the weights of each parameter, k is the adjustment coefficient, exp(.) is the natural exponential function;

[0075] S73. When the fault score Score diagnostic is lower than the preset fault threshold Score threshold the system automatically triggers a fault alarm, and the alarm information includes the type of faulty device, the cause of the fault, the scoring analysis result, the alarm time, and is pushed to the administrator in real time through the wireless communication protocol;

[0076] S74. The IoT gateway determines whether to start the automatic recovery mechanism according to the following formula:

[0077]

[0078] Among them, Recovery t is the automatic recovery mechanism trigger status, P current is the current power supply current, P min is the minimum allowable value of power supply current, True indicates that recovery is required, and False indicates that no recovery is required;

[0079] S75. When the automatic recovery mechanism is triggered, the IoT gateway controls the device to perform recovery operations. The recovery operations include restarting the faulty device, switching to the backup device, restoring the communication connection, and adjusting the sensor accuracy. During the recovery process, the recovery effect is judged according to the following composite evaluation formula:

[0080]

[0081] Among them, Recovery status is the recovery status evaluation value, X i,current is the monitored parameter values of the current faulty device, X i,thresh is the preset threshold, Xi,max is the maximum allowable value of the monitoring parameters for the current faulty device, X i,min is the minimum allowable value of the monitoring parameters for the current faulty device, w i is the weight of the monitoring parameters for the current faulty device, and n is the number of monitoring parameters;

[0082] S76. After the device is restored, the IoT gateway determines whether the restoration is successful through logical checks. When the restoration status evaluation value Recovery status is greater than or equal to 0.85, the system status is "normal"; otherwise, it is in the "fault" state;

[0083] S77. The administrator can view the fault alarms, restoration process, and restoration status evaluation in real time through the cloud platform management interface. The management interface provides detailed device diagnostic reports, restoration effects, and handling suggestions to help the administrator make decisions;

[0084] S78. After the device is restored, the cloud platform records all key data during the restoration process and generates a fault handling report. The report includes fault diagnosis analysis, restoration operation details, restoration status evaluation results, and suggestions. The report is automatically generated and stored.

[0085] An exhibit dynamic environment monitoring and regulation system based on IoT technology according to an embodiment of the present invention includes the following modules:

[0086] A data preprocessing module for real-time collecting environmental parameters such as temperature, humidity, light, and gas concentration in the exhibit display area, and transmitting the data to the IoT gateway for preprocessing and storage through a wireless communication protocol;

[0087] An intelligent analysis module for trend prediction, anomaly detection, and fault diagnosis based on real-time environmental data and historical data, analyzing the change trend of environmental parameters, and generating regulation suggestions;

[0088] An automatic adjustment module for automatically controlling environmental devices according to the analysis results, including air conditioners, humidity control devices, and light regulation systems;

[0089] A prediction and optimization module for predicting future environmental changes and optimizing the operation efficiency and energy-saving performance of devices during system adjustment;

[0090] A fault detection and recovery module for detecting device faults through self-diagnosis functions and automatically starting backup devices or recovery measures;

[0091] An alarm and notification module for sending alarm messages in real time when the environment is abnormal or a device fails, notifying the administrator through multiple communication channels and handling;

[0092] A data recording and reporting module for generating statistical reports, trend analysis charts, and fault handling reports of environmental data.

[0093] The beneficial effects of the present invention are as follows:

[0094] (1) The present invention effectively solves many deficiencies in the prior art and provides significant beneficial effects. First of all, the real-time data acquisition and processing capabilities of the system greatly improve the accuracy and timeliness of the exhibition environment monitoring. Different types of sensors, such as temperature and humidity sensors, light sensors, and gas sensors, can monitor various environmental parameters in the exhibition area of the exhibits in real time and transmit the data to the Internet of Things gateway. After being stored and analyzed by the cloud platform, in this way, the system can quickly capture changes when the environmental parameters are abnormal and provide instant alarm information for the management personnel, thus realizing the rapid response and adjustment of the exhibition environment.

[0095] (2) By introducing intelligent algorithms, the environmental monitoring of the present invention is not only limited to the acquisition of real-time data, but also can analyze historical data and predict trends. Using time series analysis and machine learning algorithms, the system can predict future environmental changes and adjust the display environment in advance according to the prediction results to ensure that the exhibits are always in the best display conditions. This predictive control method reduces the lag of relying on manual operation in the traditional system, makes the control of the exhibition environment more intelligent and adaptive, and improves the safety and display effect of the exhibits.

[0096] (3) By optimizing data security and device stability, the reliability of the system is improved. During the data transmission process, encryption technology is adopted to ensure the security of the data, effectively preventing the risk of data leakage or being tampered with. In addition, the system has the ability of self-diagnosis and intelligent recovery of faults, which can ensure that even if a device failure occurs, the system can quickly return to the normal operation state, reducing the potential safety hazards that may be encountered during the exhibition of the exhibits. Description of the Drawings

[0097] The drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation to the present invention. In the drawings:

[0098] Figure 1 is a flowchart of a method for dynamically monitoring and regulating the exhibition environment of exhibits based on Internet of Things technology proposed by the present invention;

[0099] Figure 2 is a flowchart of the automatic fault detection of the Internet of Things gateway in a method for dynamically monitoring and regulating the exhibition environment of exhibits based on Internet of Things technology proposed by the present invention. Detailed Embodiments

[0100] The present invention will now be described in further detail with reference to the accompanying drawings. These drawings are all simplified schematic diagrams, only illustrating the basic structure of the present invention in a schematic manner, so they only show the components related to the present invention.

[0101] Reference Figure 1 - Figure 2 , a method for dynamic environment monitoring and regulation of exhibits based on Internet of Things technology, comprising the following steps:

[0102] S1. Deploy a variety of Internet of Things sensors in the exhibit display area, and each sensor is connected to the Internet of Things gateway through a wireless communication protocol;

[0103] S2. The Internet of Things gateway transmits the environmental data collected by each sensor to the cloud platform. The cloud platform preprocesses the real-time collected environmental data, and obtains an analysis result based on the preprocessed environmental data using a data analysis module. The data analysis module includes a trend analysis module, an anomaly detection module, and a pattern recognition module, and generates a risk assessment report based on the analysis result;

[0104] S3. The cloud platform generates a regulation instruction according to the risk assessment report, and sends the regulation instruction to the regulation device through the Internet of Things protocol to automatically adjust the environmental parameters;

[0105] S4. Use an autoregressive integrated moving average model to analyze the real-time environmental data and historical data to obtain a prediction result. The cloud platform sets a confidence interval by fitting the environmental parameters, and adjusts the prediction result based on the confidence interval, and adjusts the environmental settings in advance according to the prediction result;

[0106] S5. The cloud platform automatically calculates and updates the preset safety threshold of the environmental parameters according to the real-time collected environmental data and historical data, and sets a tolerance range. When the environmental parameters exceed the preset safety threshold, the system automatically determines the alarm level according to the set alarm priority, and uses the Internet of Things device to send an alarm message in real time, and notifies the administrator through SMS, email, and APP push methods;

[0107] S6. Through the real-time data monitoring interface provided by the mobile terminal and the PC terminal, the administrator can remotely access and control and optimize the display environment;

[0108] S7. When a device fails, the Internet of Things gateway performs fault detection through a self-diagnosis function and notifies the administrator, and at the same time triggers an automatic recovery mechanism. After the recovery is completed, the Internet of Things gateway will calculate a recovery status evaluation value, and determine whether the recovery operation is completed according to the recovery status evaluation value;

[0109] S8. The cloud platform generates a statistical report and trend analysis of the environmental data to support the optimization of the environmental regulation equipment by the exhibition party and the planning of future exhibition activities.

[0110] In this embodiment, S1 includes the following steps:

[0111] S11. Select multiple sensors suitable for different environmental conditions in the exhibition area for deployment. The sensors include: temperature and humidity sensors, light sensors, gas sensors, vibration sensors, and smoke sensors.

[0112] S12. Install the sensors in the exhibition area according to a predetermined layout and connect them to the Internet of Things gateway through a wireless communication protocol.

[0113] S13. Each sensor is set with a unique identifier, and the collected environmental data is sent to the Internet of Things gateway through the Internet of Things protocol. The Internet of Things gateway classifies, marks, and transmits the environmental data to the cloud platform according to the timestamp and sensor identifier of the data.

[0114] S14. The communication between the sensor and the Internet of Things gateway uses an encryption algorithm for data protection.

[0115] S15. The sampling frequency of the sensor is set according to the actual needs of the exhibition area, and the sampling frequency is f sample , and it satisfies f sample > f min , f min is the required minimum sampling frequency.

[0116] S16. The operating temperature range of the sensor is set to T min ≤T≤T max , T min is the minimum operating temperature of the sensor, and T max is the maximum operating temperature of the sensor.

[0117] In this embodiment, S2 includes the following steps:

[0118] S21. The Internet of Things gateway transmits the environmental data collected from each sensor to the cloud platform through a wireless communication protocol and performs preliminary screening and preprocessing on the environmental data.

[0119] S22. On the cloud platform, the real-time environmental data is stored together with the corresponding timestamp. The environmental data storage model uses a time series database for data query and analysis in chronological order.

[0120] S23. The cloud platform processes the abnormal data using a data cleaning algorithm according to the collected environmental data. The data cleaning algorithm includes interpolation method, mean filling, and data smoothing method.

[0121] S24. Perform normalization processing on the processed environmental data.

[0122] S25. The cloud platform inputs the processed data into the data analysis module, which includes a trend analysis module, an anomaly detection module, and a pattern recognition module.

[0123] In the trend analysis module, time series analysis method is used to analyze the trend of environmental data. The time series analysis method adopts an autoregressive model and predicts the environmental parameters at a future moment through the following formula:

[0124] T forecast (t)=αT t-1 +βH t-1 +γL t-1 +ε t ;

[0125] Where, T forecast (t) is the environmental temperature at the prediction moment t, T t-1 is the temperature at the moment t - 1, H t-1 is the humidity at the moment t - 1, L t-1 is the illumination at the moment t - 1, α, β, γ are coefficients, and ε t is the noise term

[0126] In the anomaly detection module, the environmental parameters are detected for anomalies by combining the real-time environmental data with the preset environmental parameter thresholds. The anomaly detection method adopts a distance-based method and determines whether an anomaly occurs by calculating the anomaly score for each time point:

[0127]

[0128] Where, Score abnormal is the anomaly score, x i is the data value of the i-th sensor, μ i is the mean of the i-th sensor, σ i is the data standard deviation of the i-th sensor, and n is the total number of sensors;

[0129] In the pattern recognition module, a support vector machine is used to perform pattern recognition on the environmental data to identify the normal environmental pattern and the abnormal environmental pattern:

[0130]

[0131] Where, is the predicted environmental pattern category, w i is the weight of the i-th feature, x i is the data value of the i-th sensor, b is the bias term, and m is the number of features;

[0132] S26. Based on the results of trend analysis, anomaly detection, and pattern recognition, the cloud platform generates a risk assessment report for environmental data to identify whether the current display environment is in a normal state.

[0133] In this embodiment, S3 includes the following steps:

[0134] S31. According to the risk assessment report, the cloud platform generates a regulation instruction, and the regulation instruction includes the type of the control and adjustment device and the required adjustment parameters. The adjustment devices include air conditioners, humidifiers, air purifiers, and intelligent lighting systems.

[0135] S32. The regulation instruction is sent to the IoT gateway through the IoT protocol, and the IoT gateway regulates the device to adjust the environmental parameters according to the received regulation instruction.

[0136] S33. The cloud platform monitors the response status of the adjustment device in real time and obtains the working status of the device through a feedback mechanism. If the adjustment device fails to respond or malfunctions, the system triggers a fault alarm and notifies the administrator for maintenance.

[0137] S34. According to the changes in the actual environment, adjust the working frequency and operation mode of the regulation device.

[0138] In this embodiment, S4 includes the following steps:

[0139] S41. The cloud platform performs data modeling based on real-time environmental data and historical data to predict the change trend of future environmental parameters. By using the autoregressive integrated moving average model, time series prediction is performed on temperature, humidity, and lighting environmental parameters:

[0140]

[0141] where, X t is the predicted value at time t, μ is the constant term, is the autoregressive term coefficient, θ1, θ2,..., θ q is the moving average term coefficient, ε t is the error term;

[0142] S43. During the prediction process, the cloud platform fits each environmental parameter, calculates the error range, and adjusts the prediction result according to the set confidence interval. The confidence interval is calculated based on the standard deviation of the historical data error and the set confidence level:

[0143]

[0144] where, is the predicted value, Z is the critical value of the standard normal distribution, σ historical is the standard deviation of the historical data;

[0145] S44. Smooth the prediction results by the weighted average method to eliminate the errors caused by sudden changes. The formula of the weighted average method is:

[0146]

[0147] where X i is the predicted value at the i-th moment, w i is the weight at the i-th moment, and n is the size of the time window;

[0148] S45. According to the prediction results, the cloud platform adjusts the working parameters of the regulating device and makes environmental adjustments in advance to adapt to the upcoming environmental changes;

[0149] S46. Based on the prediction error and the adjusted environmental data, the cloud platform continuously updates the prediction model and real-time feedbacks the adjustment effect of the regulating device.

[0150] In this embodiment, S5 includes the following steps:

[0151] S51. The cloud platform conducts statistical analysis based on the real-time collected environmental data and historical data, and calculates the basic statistics of each environmental parameter, including the average value, maximum value, minimum value, and standard deviation;

[0152] S52. Smooth the real-time environmental data by the sliding average method based on the time window, and calculate the mean value within each time window to remove the noise in the data:

[0153]

[0154] where is the smoothed temperature value at time t, w is the size of the time window, and T i is the temperature value at time i;

[0155] S53. According to the statistical results of the historical data, the cloud platform automatically calculates and updates the preset safety threshold of the environmental parameter, and sets a reasonable tolerance range:

[0156] T alarm = μ T ± k·σ T ;

[0157] where T alarm is the safety threshold of the temperature, k is the adjustment coefficient, μ T is the mean value of the temperature, and σ T is the standard deviation of the temperature;

[0158] S54. The cloud platform compares the real-time collected environmental data with the preset safety thresholds, generates alarm logs, and pushes the abnormal information to the administrator in real time, notifying the administrator through methods such as SMS, email, and APP push:

[0159]

[0160] Among them, T current is the current temperature value, H current is the current humidity value, μ T is the average value of temperature, μ H is the average humidity value, T alarm is the safety threshold of temperature, H alarm is the safety threshold of humidity, True indicates that the alarm is triggered, and False indicates that the alarm is not triggered;

[0161] S55. When the environmental data is abnormal, the system automatically determines the alarm level according to the set alarm priority. The alarm level is divided into three levels: high, medium, and low. The specific rules are as follows:

[0162]

[0163] Among them, Level is the alarm level, T set is the target temperature, C gas is the current gas concentration, C set is the target gas concentration, ΔT is the temperature tolerance, ΔC gas is the gas concentration tolerance, High indicates that the alarm level is high, Medium indicates that the alarm level is medium, and Low indicates that the alarm level is low.

[0164] In this embodiment, S7 includes the following steps:

[0165] S71. When a device fails, the IoT gateway performs fault detection through the self-diagnosis function. The self-diagnosis function includes detecting the working status, communication status, power status, response time, and device load parameters of the sensor;

[0166] S72. The IoT gateway compares the real-time values of each monitoring parameter with the preset standard values and calculates the fault score Score diagnostic :

[0167]

[0168] Among them, T current is the current temperature, C current is the current communication signal strength, P current is the current power supply current, R current is the current value of the response time, T minis the minimum allowable temperature value, T max is the maximum allowable temperature value, C min is the minimum allowable communication signal strength value, C max is the maximum allowable communication signal strength value, P max is the maximum allowable power supply current value, R thresh is the response time threshold, w1, w2, w3, w4 are the weights of each parameter, k is the adjustment coefficient, and exp(.) is the natural exponential function;

[0169] S73. When the fault score Score diagnostic is lower than the preset fault threshold Score threshold the system automatically triggers a fault alarm. The alarm information includes the type of faulty device, the cause of the fault, the scoring analysis result, and the alarm time, and is pushed to the administrator in real time through the wireless communication protocol;

[0170] S74. The IoT gateway determines whether to start the automatic recovery mechanism according to the following formula:

[0171]

[0172] where, Recovery t is the trigger status of the automatic recovery mechanism, P current is the current power supply current, P min is the minimum allowable power supply current value. True indicates that recovery is required, and False indicates that no recovery is required;

[0173] S75. After the automatic recovery mechanism is triggered, the IoT gateway controls the device to perform recovery operations. The recovery operations include restarting the faulty device, switching to the backup device, restoring the communication connection, and adjusting the sensor accuracy. During the recovery process, the recovery effect is judged according to the following composite evaluation formula:

[0174]

[0175] where, Recovery status is the evaluation value of the recovery status, X i,current is the monitored parameter values of the current faulty device, X i,thresh is the preset threshold, X i,max is the maximum allowable value of the monitored parameter of the current faulty device, X i,min is the minimum allowable value of the monitored parameter of the current faulty device, w i is the weight of the monitored parameter of the current faulty device, and n is the number of monitored parameters;

[0176] S76. After the device is restored, the IoT gateway determines whether the restoration is successful through logical inspection. When the recovery status evaluation value Recovery statusWhen it is greater than or equal to 0.85, the system status is "normal", otherwise it is in the "fault" status;

[0177] S77. The administrator can view the fault alarm, recovery process, and recovery status assessment in real time through the cloud platform management interface. The management interface provides detailed device diagnostic reports, recovery effects, and treatment suggestions to help the administrator make decisions;

[0178] S78. After the device is restored, the cloud platform records all key data during the recovery process and generates a fault handling report. The report includes fault diagnosis analysis, details of recovery operations, recovery status assessment results, and suggestions. The report is automatically generated and stored.

[0179] Embodiment:

[0180] In a temporary exhibition in a large museum, the exhibits include precious cultural relics and artworks, and these exhibits have very high requirements for the display environment. The exhibition planning team decided to deploy a dynamic environment monitoring and control system based on Internet of Things technology in the display area to ensure that the exhibits are always in the best environmental conditions during the exhibition and avoid damage caused by environmental changes.

[0181] There are multiple environmental monitoring points in the exhibition area, and each monitoring point is installed with devices such as temperature and humidity sensors, light sensors, and gas sensors to collect various environmental parameters in real time. These devices are connected to the Internet of Things gateway through a wireless network and transmit the data to the cloud platform for analysis and processing. On this basis, the system can automatically adjust parameters such as temperature, humidity, and light intensity around the exhibits according to environmental changes.

[0182] During the exhibition, the display environment of the exhibits is frequently affected by external weather changes and the flow of exhibition visitors. In particular, some high-value cultural relics in the museum have very strict requirements for temperature, humidity, and light. Without an intelligent environment control system, the staff need to continuously check and manually adjust devices such as air conditioners, humidity adjustment devices, and lighting, which is time-consuming and prone to errors, resulting in unstable display conditions for the exhibits and increasing the risk of human operation errors.

[0183] To better protect these precious exhibits, this system has played an important role throughout the exhibition. The system continuously collects environmental data and conducts intelligent analysis, monitors the display environment of the exhibits in real time, and automatically adjusts environmental parameters according to real-time data and prediction results. For example, when the external temperature of the museum suddenly rises, the system can identify the change in the temperature in the exhibition hall within a few minutes and automatically start the air conditioning system to lower the indoor temperature and keep it within an appropriate range. At the same time, when the humidity exceeds the preset threshold, the system will also automatically start the dehumidification device to prevent the cultural relics from being damaged due to excessive humidity.

[0184] To better demonstrate the beneficial effects of the system, Table 1 below shows some environmental data records and system responses during the exhibition:

[0185] Table 1 Key performance comparison between the present invention and traditional methods in the process of optimizing the layout of wear-resistant materials for labor protection shoes

[0186]

[0187] In the above table, the system can detect environmental anomalies in a timely manner based on the real-time collected temperature, humidity, and light data, and automatically activate the corresponding devices for adjustment. For example, at 2:00 pm on February 1, 2025, the system detected that the temperature rapidly increased from 22.5°C to 25°C, the humidity rose from 60% to 65%, and the light also reached 550 Lux, indicating the instability of the exhibition environment. At this time, the system judged through intelligent algorithms that these changes exceeded the preset safety range, automatically activated the air conditioning system to lower the indoor temperature, and continuously monitored the humidity change.

[0188] In addition, the system can also effectively respond to sudden changes in the environment. For example, at 2:30 pm on February 2, 2025, the humidity in the exhibition area suddenly increased to 67%, exceeding the humidity range required for cultural relics. After detecting this change, the system immediately activated the air conditioning and dehumidification equipment to ensure that the humidity quickly dropped to an appropriate range, thus avoiding damage to the exhibits caused by excessive humidity.

[0189] In the whole embodiment, the implementer successfully solved the deficiencies of the traditional exhibit environment monitoring system in data collection, environmental adjustment, and equipment management through the exhibit dynamic environment monitoring and control system based on Internet of Things technology of the present invention, and improved the stability and safety of the exhibit display environment. Especially when dealing with environmental changes and equipment failures, this system ensures that the exhibits are always in the best display conditions through intelligent algorithms and automatic recovery mechanisms, avoiding the impact of human operation errors and equipment failures on the safety of the exhibits.

[0190] By combining Internet of Things technology with the environment monitoring system, the present invention can, by means of real-time environmental data collection and cloud platform data analysis, respond in a timely manner to changes in environmental parameters such as temperature, humidity, and light during the exhibit display process. By introducing intelligent prediction algorithms, the system can predict the trend of environmental changes in advance and automatically adjust environmental equipment according to the changes, realizing the intelligence and self-adaptability of environmental control. In this process, compared with traditional manual adjustment, the system can react faster and more precisely, ensuring continuous and stable protection of the exhibits during the exhibition.

[0191] Through the fault self-diagnosis and automatic recovery mechanism, the present invention solves the drawback of relying on manual intervention in the existing system. When a device fails or the environmental parameters exceed the preset range, the system can quickly identify and automatically initiate recovery measures to ensure the continuity and safety of the exhibition environment of the exhibits. In addition, the system also has an intelligent alarm function. When an environmental anomaly is detected, it can immediately notify the administrator to perform corresponding operations, improving the safety guarantee level of the exhibition of the exhibits.

[0192] By introducing data security encryption and an automatic recovery mechanism, the present invention ensures the reliability and stability of the system during long-term operation, effectively avoiding the risks of data leakage and equipment failure. At the same time, through the self-diagnosis and recovery process of faults, the interruption of the exhibition of the exhibits and data loss caused by equipment failures are reduced, effectively improving the efficiency and guarantee ability of the exhibition of the exhibits.

[0193] The above are only the preferred specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention, according to the technical solution and inventive concept of the present invention, making equivalent substitutions or changes should be covered within the protection scope of the present invention.

Claims

1. An exhibit dynamic environment monitoring and regulation method based on Internet of Things technology, characterized in that, It includes the following steps: S1. Deploy a variety of Internet of Things sensors in the exhibition area, and each sensor is connected to the Internet of Things gateway through a wireless communication protocol; S2. The Internet of Things gateway transmits the environmental data collected by each sensor to the cloud platform. The cloud platform preprocesses the real-time collected environmental data, and uses a data analysis module to obtain analysis results based on the preprocessed environmental data. The data analysis module includes a trend analysis module, an anomaly detection module, and a pattern recognition module, and generates a risk assessment report based on the analysis results; S3. The cloud platform generates a control instruction according to the risk assessment report, and sends the control instruction to the control device through the Internet of Things protocol to automatically adjust the environmental parameters; S4. Use the autoregressive integrated moving average model to analyze the real-time environmental data and historical data to obtain a prediction result. The cloud platform sets a confidence interval by fitting the environmental parameters, and adjusts the prediction result based on the confidence interval, and adjusts the environmental settings in advance according to the prediction result; S5. The cloud platform automatically calculates and updates the preset safety threshold of the environmental parameters according to the real-time collected environmental data and historical data, and sets a tolerance range. When the environmental parameters exceed the preset safety threshold, the system automatically determines the alarm level according to the set alarm priority, and uses the Internet of Things device to send out alarm information in real time, and notifies the administrator through text messages, emails, and APP push methods; S6. Through the real-time data monitoring interface provided by the mobile terminal and the PC terminal, the administrator can remotely access and control and optimize the exhibition environment; S7. When a device fails, the Internet of Things gateway performs fault detection through the self-diagnosis function and notifies the administrator, and at the same time triggers an automatic recovery mechanism. After the recovery is completed, the Internet of Things gateway will calculate the recovery status evaluation value and determine whether the recovery operation is completed according to the recovery status evaluation value; S8. The cloud platform generates a statistical report and trend analysis of the environmental data to support the optimization of the environmental control equipment by the exhibition party and the planning of future exhibition activities.

2. The method for dynamically monitoring and regulating the environment of an exhibit based on Internet of Things technology according to claim 1, characterized in that, The S1 includes the following steps: S11. Select multiple sensors suitable for different environmental conditions in the exhibition area for deployment. The sensors include: temperature and humidity sensors, light sensors, gas sensors, vibration sensors, and smoke sensors; S12. Install the sensors in the exhibition area according to a predetermined layout and connect them to the Internet of Things gateway through a wireless communication protocol; S13. Each sensor sets a unique identifier, and sends the collected environmental data to the Internet of Things gateway through the Internet of Things protocol. The Internet of Things gateway classifies, marks and transmits the environmental data to the cloud platform according to the timestamp and sensor identifier of the data; S14. The communication between the sensor and the Internet of Things gateway uses an encryption algorithm for data protection; S15. The sampling frequency of the sensor is set according to the actual requirements of the display area, and the sampling frequency is f sample , and it satisfies f sample > f min , f min is the required minimum sampling frequency; S16. The operating temperature range of the sensor is set to T min ≤T≤T max , T min is the minimum operating temperature of the sensor, and T max is the maximum operating temperature of the sensor.

3. The method for dynamically monitoring and regulating the exhibition environment based on the Internet of Things technology according to claim 1, wherein The S2 includes the following steps: S21. The Internet of Things gateway transmits the environmental data collected from each sensor to the cloud platform through a wireless communication protocol, and performs preliminary screening and preprocessing on the environmental data; S22. On the cloud platform, the real-time environmental data is stored together with the corresponding timestamp. The environmental data storage model uses a time series database for data query and analysis in chronological order; S23. The cloud platform processes the abnormal data by using a data cleaning algorithm according to the collected environmental data. The data cleaning algorithm includes interpolation method, mean filling and data smoothing method; S24. Normalize the processed environmental data; S25. The cloud platform inputs the processed data into the data analysis module, which includes a trend analysis module, an anomaly detection module and a pattern recognition module; In the trend analysis module, the time series analysis method is used to analyze the trend of environmental data. The time series analysis method adopts an autoregressive model and predicts the environmental parameters at a future moment through the following formula: T forecast f(t) = αT t-1 + βH t-1 + γL t-1 + ε t ; Among them, T forecast (t) is the ambient temperature at the prediction time t, T t-1 is the temperature at time t - 1, H t-1 is the humidity at time t - 1, L t-1 is the light at time t - 1, α, β, γ are coefficients, ε t is the noise term In the anomaly detection module, the environmental parameters are detected for anomalies by combining the real-time environmental data with the preset environmental parameter thresholds. The anomaly detection method adopts a distance-based method and determines whether an anomaly occurs by calculating the anomaly score at each time point: Among them, Score abnormal is the anomaly score, x i is the data value of the i-th sensor, μ i is the mean of the i-th sensor, σ i is the standard deviation of the data of the i-th sensor, and n is the total number of sensors; In the pattern recognition module, a support vector machine is used to perform pattern recognition on the environmental data to identify the normal environmental pattern and the abnormal environmental pattern; wherein, is the predicted environmental pattern category, w i is the weight of the i-th feature, x i is the data value of the i-th sensor, b is the bias term, and m is the number of features; S26. Based on the results of trend analysis, anomaly detection and pattern recognition, the cloud platform generates a risk assessment report of the environmental data to identify whether the current displayed environment is in a normal state.

4. A method for dynamic environment monitoring and regulation of exhibits based on Internet of Things technology according to claim 1, characterized in that, The S3 includes the following steps: S31. According to the risk assessment report, the cloud platform generates a regulation instruction, which includes the type of the control and adjustment device and the required adjustment parameters. The adjustment devices include air conditioners, humidifiers, air purifiers, and intelligent lighting systems; S32. The regulation instruction is sent to the IoT gateway through the IoT protocol, and the IoT gateway adjusts the environmental parameters of the device according to the received regulation instruction; S33. The cloud platform monitors the response status of the adjustment device in real time and obtains the working status of the device through a feedback mechanism. If the adjustment device fails to respond or malfunctions, the system triggers a fault alarm and notifies the administrator for maintenance; S34. According to the changes in the actual environment, adjust the working frequency and operation mode of the regulation device.

5. A method for dynamically monitoring and regulating the environment of exhibits based on Internet of Things technology according to claim 1, characterized in that, The S4 includes the following steps: S41. The cloud platform performs data modeling based on the real-time environmental data and historical data to predict the change trend of future environmental parameters. The autoregressive integrated moving average model is used to perform time series prediction on temperature, humidity, and light environmental parameters; where X t is the predicted value at time t, μ is the constant term, is the coefficient of the autoregressive term, θ1, θ2, ..., θ q are the coefficients of the moving average terms, and ε t is the error term; S43. During the prediction process, the cloud platform fits each environmental parameter, calculates the error range, and adjusts the prediction result according to the set confidence interval. The confidence interval is calculated based on the standard deviation of the historical data error and the set confidence level; Among them, is the predicted value, Z is the critical value of the standard normal distribution, and σ historical is the standard deviation of historical data; S44. Smooth the prediction result by using the weighted average method to eliminate the error caused by sudden changes. The formula of the weighted average method is: where X i is the predicted value at the i-th moment, w i is the weight at the i-th moment, and n is the size of the time window; S45. According to the prediction result, the cloud platform adjusts the working parameters of the adjustment device to perform environmental adjustment in advance to adapt to the upcoming environmental changes; S46. The cloud platform continuously updates the prediction model based on the prediction error and the adjusted environmental data, and provides real-time feedback on the adjustment effect of the regulation device.

6. The method for dynamically monitoring and regulating the environment of exhibits based on Internet of Things technology according to claim 1, characterized in that, The S5 includes the following steps: S51. The cloud platform performs statistical analysis on the real-time collected environmental data and historical data, and calculates the basic statistics of each environmental parameter, including the mean, maximum value, minimum value, and standard deviation. S52. Use the moving average method based on a time window to smooth the real-time environmental data, and calculate the mean value within each time window to remove the noise in the data. Among them, is the smoothed temperature value at time t, w is the time window size, and T i is the temperature value at time i; S53. The cloud platform automatically calculates and updates the preset safety thresholds of environmental parameters according to the statistical results of historical data, and sets a reasonable tolerance range. T alarm = μ T ± k·σ T ; Among them, T alarm is the safety threshold of temperature, k is the adjustment coefficient, μ T is the mean value of temperature, σ T is the standard deviation of temperature; S54. The cloud platform compares the real-time collected environmental data with the preset safety thresholds, generates alarm logs, and pushes the abnormal information to the administrator in real time, notifying the administrator by means such as SMS, email, and APP push. Among them, T current is the current temperature value, H current is the current humidity value, μ T is the mean value of temperature, μ H is the mean value of humidity, T alarm is the safety threshold of temperature, H alarm is the safety threshold of humidity, True indicates that the alarm is triggered, and False indicates that the alarm is not triggered; S55. When the environmental data is abnormal, the system automatically determines the alarm level according to the set alarm priority. The alarm level is divided into three levels: high, medium, and low. The specific rules are as follows: Among them, Level is the alarm level, T set is the target temperature, C gas is the current gas concentration, C set is the target gas concentration, ΔT is the tolerance of temperature, ΔC gas is the tolerance of gas concentration, High indicates that the alarm level is high, Medium indicates that the alarm level is medium, and Low indicates that the alarm level is low.

7. A method for dynamically monitoring and regulating the environment of exhibits based on Internet of Things technology according to claim 1, characterized in that, The above S7 includes the following steps: S71. When a device fails, the IoT gateway performs fault detection through the self-diagnosis function. The self-diagnosis function includes detecting the working status, communication status, power status, response time, and device load parameters of the sensor. S72. The IoT gateway calculates the fault score Score by comparing the real-time values of the monitoring parameters with the preset standard values. diagnostic : Among them, T current is the current temperature, C current is the current communication signal strength, P current is the current power supply current, R current is the value of the current response time, T min is the minimum allowable value of temperature, T max is the maximum allowable value of temperature, C min is the minimum allowable value of communication signal strength, C max is the maximum allowable value of communication signal strength, P max is the maximum allowable value of power supply current, R thresh is the response time threshold, w1, w2, w3, w4 are the weights of each parameter, k is the adjustment coefficient, exp(.) is the natural exponential function; S73. When the fault score Score diagnostic is lower than the preset fault threshold Score threshold the system automatically triggers a fault alarm. The alarm information includes the type of faulty equipment, the cause of the fault, the scoring analysis result, and the alarm time, and is pushed to the administrator in real time through a wireless communication protocol; S74. The IoT gateway determines whether to start the automatic recovery mechanism according to the following formula: Among them, Recovery t is the trigger state of the automatic recovery mechanism, P current is the current power supply current, P min is the minimum allowable value of the power supply current. True indicates that recovery is required, and False indicates that no recovery is required; S75. After the automatic recovery mechanism is triggered, the IoT gateway controls the device to perform recovery operations. The recovery operations include restarting the faulty device, switching to the backup device, restoring the communication connection, and adjusting the sensor accuracy. During the recovery process, the recovery effect is judged according to the following composite evaluation formula: Among them, Recovery status is the recovery status evaluation value, X i,current is the value of each monitoring parameter of the current faulty device, X i,thresh is the preset threshold value, X i,max is the maximum allowable value of the monitoring parameter of the current faulty device, X i,min is the minimum allowable value of the monitoring parameter of the current faulty device, w i is the weight of the monitoring parameter of the current faulty device, and n is the number of monitoring parameters; S76. After the device is restored, the IoT gateway determines whether the restoration is successful through logical checks. When the restoration status evaluation value Recovery status is greater than or equal to 0.85, the system status is "normal"; otherwise, it is in the "fault" state. S77. The administrator can view the fault alarms, recovery process, and recovery status evaluation in real time through the cloud platform management interface. The management interface provides a detailed device diagnosis report, recovery effect, and handling suggestions to help the administrator make decisions. S78. After the device is restored, the cloud platform records all key data during the recovery process and generates a fault handling report. The report includes fault diagnosis analysis, details of recovery operations, recovery status evaluation results, and suggestions. The report is automatically generated and stored.

8. An exhibit dynamic environment monitoring and regulation system based on Internet of Things technology, which executes the method for monitoring and regulating the dynamic environment of an exhibit based on Internet of Things technology according to any one of claims 1 to 7, characterized in that, It includes the following modules: The data preprocessing module is used to collect the environmental parameters of temperature, humidity, light, and gas concentration in the exhibition area of the exhibit in real time, and transmit the data to the IoT gateway through a wireless communication protocol for preprocessing and storage. The intelligent analysis module is used to perform trend prediction, anomaly detection, and fault diagnosis based on real-time environmental data and historical data, analyze the change trend of environmental parameters, and generate regulation suggestions. The automatic adjustment module is used to automatically control environmental devices according to the analysis results, including air conditioners, humidity control devices, and light adjustment systems. The prediction and optimization module is used to predict future environmental changes and optimize the operation efficiency and energy-saving performance of the device during the system adjustment process. The fault detection and recovery module is used to detect device faults through the self-diagnosis function and automatically start the backup device or recovery measures. The alarm and notification module is used to send alarm information in real time when the environment is abnormal or the device fails, notify the administrator through multiple communication channels, and handle it. A data recording and reporting module for generating statistical reports, trend analysis charts, and fault handling reports of environmental data.

Images