Method and system for electrically and intelligently controlling flood control door and window

Abstract

The invention discloses a method and system for electrically and intelligently controlling flood control doors and windows, and relates to the technical field of intelligent disaster prevention, comprising the following steps: collecting environmental data in real time, processing the collected data by using a deep learning algorithm, and identifying an early stage phenomenon of flood occurrence; according to a data processing result, utilizing a time sequence analysis algorithm to predict a water level change trend and the possibility of flood occurrence, generating a control instruction through an adaptive control algorithm according to a prediction result, executing opening, closing and sealing operations of doors and windows according to the control instruction, and designing a real-time monitoring algorithm to monitor whether abnormal data occurs or not; if abnormity is found, an early warning mechanism is remotely started, alarm information is sent to a user and related personnel, a preset safety program is executed, and the deep learning algorithm model is periodically updated and optimized. Multiple flood recognition methods are set, corresponding modes are selected according to different flood early warning degrees, and the problem that the window is not closed in time manually is solved as much as possible.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent disaster prevention, and in particular to a method and system for electrically intelligently controlling flood-proof doors and windows. Background Art

[0004] On the basis of the improvement of the management center walls and the flood control facilities outside the power station buildings, it is particularly important to study the layout of electric intelligent controlled flood control gates at the entrance gates of the management and control center and the entrance gates of the power station plant areas that may be affected by floods, so as to apply them to flood control and disaster prevention at the entrances of production and living areas under extreme circumstances.

[0005] Underground factories are generally equipped with ventilation windows and exhaust fan ports. Some of these windows are located at higher positions, and the installed manual waterproof and sealed windows are extremely inconvenient to operate and maintain. It is necessary to develop a waterproof and sealed window that can be electrically remotely controlled and intelligently controlled to solve the problem of inconvenient operation and maintenance. Summary of the invention

[0006] In view of the above existing problems, the present invention provides a method and system for electrically intelligently controlling flood-proof doors and windows, so as to solve the problem that manual waterproof and airtight windows in the prior art are extremely inconvenient to operate and maintain.

[0007] In order to solve the above technical problems, a method for electrically intelligently controlling flood-proof doors and windows is proposed, comprising:

[0008] Acquire environmental impact data and real-time power generation data of thermal power units, and monitor the operating status of thermal power units in real time to obtain key parameters such as generator speed, grid frequency and load demand; build an environment-load coupling prediction model to obtain predicted electricity demand and unit load demand, and adjust the unit operation mode based on the comprehensive prediction results; under the adjusted operation mode, adopt a multi-mode combination mode to maximize resource utilization, continuously update the prediction results, and perform electric intelligent control of flood control doors and windows.

[0009] As a preferred solution of the method for electric intelligent control of flood-proof doors and windows described in the present invention, the collection of environmental data includes collecting water level, rainfall, wind speed, air pressure and temperature data through intelligent monitoring sensors, and processing the collected data using deep learning algorithms.

[0010] The data processing includes removing erroneous data, data normalization and data labeling; the deep learning algorithm includes selecting a model architecture, determining the input layer, hidden layer and output layer, dividing the data, compiling it using a loss function, and performing model training, and inputting the data into the trained model.

[0011] As a preferred solution of the method for electric intelligent control of flood-proof doors and windows described in the present invention, the early phenomena of flood occurrence are identified by outputting through a deep learning model and setting an output threshold, and the early phenomena of flood occurrence are identified by comparing the output with the threshold.

[0012] The loss function formula is:

[0013]

[0014] Among them, L is the loss function, y i is the true label, is the predicted probability, i is the variable index, and n is the number of samples.

[0015] The output of the deep learning model is:

[0016]

[0017] Among them, P is the probability of flood occurrence, β0, β1...β n are model parameters, X2, X3, ... n is the processed environmental factor, and n is the variable index.

[0018] As a preferred solution of the method for electrically intelligently controlling flood-proof doors and windows described in the present invention, the time series analysis algorithm includes predicting the water level change trend and the possibility of flood occurrence using the time series analysis algorithm based on data processing results.

[0019] The method for predicting the water level change trend includes determining the window size of the time series data, using a regression moving average model for modeling, determining model parameters, training the model, and using the trained model for water level prediction.

[0020] The model parameters include the number of autoregressive terms, the difference order and the number of moving average terms; the water level prediction formula is:

[0021]

[0022] in, is the predicted water level at time t, H t-i is the actual water level at time ti, i = 1, 2…, p, i is the variable index, and ARIMA is the autoregressive moving average model.

[0023] As a preferred solution of the method for electric intelligent control of flood-proof doors and windows described in the present invention, the generation of control instructions includes generating control instructions based on the current predicted water level and flood occurrence warning, setting the water level threshold and the flood probability threshold, and outputting control instructions based on comparison, and executing corresponding operations according to the output instructions.

[0024] The set water level thresholds include setting the warning water level to 0.5 meters, the action water level to 1 meter, the emergency water level to 1.5 meters and the extreme water level to 2 meters; the flood probability threshold is 0.6.

[0025] When the water level When the water level is higher than 1 meter, it indicates that the water level is in a safe area and monitoring should continue. When When the system automatically closes the doors and windows to prevent flooding; when When the system initiates emergency response measures, including closing all entrances, activating the alarm system, and notifying emergency services; When the flood probability is greater than or equal to 0.6, the system triggers an early warning, and the system determines that a flood will occur, and measures must be taken; when the flood probability is less than 0.6, the system does not trigger an early warning and continues to monitor environmental data; the flood probability is the output of the deep learning model.

[0026] As a preferred solution of the method for electric intelligent control of flood-proof doors and windows described in the present invention, the design of a real-time monitoring algorithm includes receiving sensor data streams in real time, applying an anomaly detection algorithm to each data point, identifying whether the data point deviates from the normal behavior pattern, setting anomaly judgment criteria, calculating the statistics of the data point and comparing it with a preset threshold.

[0027] The anomaly detection algorithm formula is:

[0028]

[0029] Among them, Z is the standardized distance between the data point and the mean, Y is the currently observed data point value, μ is the mean of the data set, and σ is the standard deviation of the data set.

[0030] Among them, the Z threshold is set to 2. When |Z|>2, it means that the current data is abnormal and needs to be removed; when |Z|≤2, it means that the data is normal and needs to be input into the model for subsequent processing.

[0031] As a preferred solution of the method for electric intelligent control of flood-prevention doors and windows described in the present invention, the starting early warning mechanism includes: when abnormal data is detected, the system performs a secondary confirmation. After confirming the abnormality, the early warning system is started through the remote control module, and alarm information is sent to users and related personnel through SMS, email and application push, and pre-set safety procedures are automatically executed.

[0032] The early warning system includes sound alarms, light alarms and remote notifications; the alarm information includes abnormality description, occurrence time, location and recommended actions; the pre-set safety procedures include closing doors and windows, activating the drainage system and cutting off power.

[0033] The periodic updating and optimization of the deep learning algorithm model includes regularly accumulating new monitoring data for model training and analysis, retraining the deep learning algorithm model using the accumulated data, evaluating the performance of the model on an independent validation set, and using the optimized model for flood monitoring, and timely feedback of model optimization data; the retraining includes adjusting model parameters and optimizing network structure.

[0034] As a preferred solution of the system for electric intelligent control of flood-proof doors and windows described in the present invention, it is characterized by including an environmental data acquisition and preprocessing module, a deep learning analysis and recognition module, a time series analysis and prediction module, an adaptive control instruction generation and execution module, and a real-time monitoring and early warning module.

[0035] The environmental data acquisition and preprocessing module is used to collect water level, rainfall, wind speed, air pressure and temperature data in real time through intelligent monitoring sensors, and clean, normalize and annotate the collected data to ensure that the data quality is suitable for subsequent deep learning processing.

[0036] The deep learning analysis and recognition module is used to select the deep learning model architecture and determine the structure of the input layer, hidden layer and output layer, use the processed data to train the model, compile the model through the loss function, optimize the model parameters, use the trained model to output the probability of flood occurrence, and identify the early phenomenon of flood occurrence by setting the output threshold.

[0037] The time series analysis and prediction module is used to use the time series analysis algorithm to model and predict the water level change trend, determine the model parameters, train the model, and use the trained model to predict the water level change.

[0038] The adaptive control instruction generation and execution module is used to set the water level threshold and flood probability threshold according to the water level prediction results and the flood occurrence probability, generate control instructions, and execute the opening, closing and sealing of doors and windows according to the control instructions to deal with different levels of flood threats.

[0039] The real-time monitoring and early warning module is used to monitor the sensor data stream in real time, apply the anomaly detection algorithm to identify abnormal data, and when abnormal data is detected, start the early warning system through the remote control module, send alarm information to users and related personnel, automatically execute pre-set safety procedures, and periodically accumulate new monitoring data to retrain and optimize the deep learning algorithm model to improve prediction accuracy and system adaptability.

[0040] A computer device includes a memory and a processor, wherein the memory stores a computer program, and is characterized in that when the processor executes the computer program, the steps of the method described in the electric intelligent control of flood-proof doors and windows are implemented.

[0041] A computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps of the method described in the electric intelligent control of flood-proof doors and windows are implemented.

[0042] Beneficial effects of the present invention: The present invention realizes the rapid identification of early flood phenomena by collecting environmental data in real time and processing it using a deep learning algorithm, thereby providing timely information for flood prevention and early warning. The time series analysis algorithm is used to predict the trend of water level changes, thereby improving the foresight and accuracy of flood prevention decisions. The control instructions generated by the adaptive control algorithm can automatically adjust the status of doors and windows, effectively respond to different levels of flood threats, and ensure the safety inside the building. The design of the real-time monitoring algorithm improves the stability and reliability of the system, timely discovers and handles data anomalies, and ensures the effectiveness of the early warning system. When abnormal data is detected, the remotely initiated early warning mechanism and the automatically executed safety program can quickly notify relevant personnel and take necessary measures to minimize potential losses. The deep learning algorithm model is periodically updated and optimized to ensure the continuous improvement of the system's prediction ability and adaptability. Overall, the present invention forms an efficient, automatic, and reliable intelligent flood control system, which greatly improves the efficiency and effectiveness of flood prevention work and provides strong technical support for protecting the safety of people and property. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work, among which:

[0044] Figure 1 An overall flow chart of a method for electrically intelligently controlling flood-proof doors and windows provided for one embodiment of the present invention.

[0045] Figure 2A system solution flow chart of a system for electrically intelligently controlling flood-proof doors and windows provided in accordance with an embodiment of the present invention. DETAILED DESCRIPTION

[0046] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0047] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0048] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor is it an embodiment that is mutually exclusive with other embodiments, either individually or selectively.

[0049] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0050] At the same time, in the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the directions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0051] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0052] Example 1, reference Figure 1 , which is the first embodiment of the present invention, provides a method for electrically intelligently controlling flood-proof doors and windows, comprising:

[0053] S1: Collect environmental data in real time and use deep learning algorithms to process the collected data and identify early signs of flooding.

[0054] It should be noted that the collection of environmental data includes collecting water level, rainfall, wind speed, air pressure and temperature data through intelligent monitoring sensors, and processing the collected data using deep learning algorithms.

[0055] The data processing includes removing erroneous data, data normalization and data labeling; the deep learning algorithm includes selecting a model architecture, determining the input layer, hidden layer and output layer, dividing the data, compiling it using a loss function, and performing model training, and inputting the data into the trained model.

[0056] It should be further explained that the identification of early phenomena of flood occurrence includes outputting through a deep learning model, setting an output threshold, and identifying early phenomena of flood occurrence by comparing the output with the threshold.

[0057] The loss function formula is:

[0058]

[0059] Among them, L is the loss function, y i is the true label, is the predicted probability, i is the variable index, and n is the number of samples.

[0060] The output of the deep learning model is:

[0061]

[0062] Among them, P is the probability of flood occurrence, β0, β1...β n are model parameters, X2, X3, ... n is the processed environmental factor, and n is the variable index.

[0063] S2: Based on the data processing results, the water level change trend and the possibility of flood occurrence are predicted using the time series analysis algorithm, and control instructions are generated through the adaptive control algorithm based on the prediction results. The opening, closing and sealing operations of doors and windows are performed according to the control instructions.

[0064] Furthermore, the time series analysis algorithm includes predicting the water level change trend and the possibility of flood occurrence using the time series analysis algorithm according to the data processing results.

[0065] The method for predicting the water level change trend includes determining the window size of the time series data, using a regression moving average model for modeling, determining model parameters, training the model, and using the trained model for water level prediction.

[0066] The model parameters include the number of autoregressive terms, the difference order and the number of moving average terms; the water level prediction formula is:

[0067]

[0068] in, is the predicted water level at time t, H t-i is the actual water level at time ti, i = 1, 2…, p, i is the variable index, and ARIMA is the autoregressive moving average model.

[0069] Furthermore, the generation of control instructions includes generating control instructions based on the current predicted water level and flood warning, setting a water level threshold and a flood probability threshold, and outputting control instructions based on comparison, and executing corresponding operations according to the output instructions.

[0070] The set water level thresholds include setting the warning water level to 0.5 meters, the action water level to 1 meter, the emergency water level to 1.5 meters and the extreme water level to 2 meters; the flood probability threshold is 0.6.

[0071] When the water level When the water level is higher than 1 meter, it indicates that the water level is in a safe area and monitoring should continue. When When the system automatically closes the doors and windows to prevent flooding; when When the system initiates emergency response measures, including closing all entrances, activating the alarm system, and notifying emergency services; When the flood probability is greater than or equal to 0.6, the system triggers an early warning, and the system determines that a flood will occur, and measures must be taken; when the flood probability is less than 0.6, the system does not trigger an early warning and continues to monitor environmental data; the flood probability is the output of the deep learning model.

[0072] S3: Design a real-time monitoring algorithm to monitor whether there is any abnormal data. If an abnormality is found, the early warning mechanism will be remotely activated to send alarm information to users and relevant personnel, and the pre-set safety procedures will be executed to periodically update and optimize the deep learning algorithm model.

[0073] Furthermore, the design of the real-time monitoring algorithm includes receiving the sensor data stream in real time, applying an anomaly detection algorithm to each data point, identifying whether the data point deviates from the normal behavior pattern, setting anomaly determination criteria, calculating the statistics of the data point and comparing it with a preset threshold.

[0074] The anomaly detection algorithm formula is:

[0075]

[0076] Among them, Z is the standardized distance between the data point and the mean, Y is the currently observed data point value, μ is the mean of the data set, and σ is the standard deviation of the data set.

[0077] Among them, the Z threshold is set to 2. When |Z|>2, it means that the current data is abnormal and needs to be removed; when |Z|≤2, it means that the data is normal and needs to be input into the model for subsequent processing.

[0078] Furthermore, the activation of the early warning mechanism includes that when abnormal data is detected, the system performs a secondary confirmation. After confirming the abnormality, the early warning system is activated through the remote control module, and alarm information is sent to users and related personnel through SMS, email and application push, and pre-set safety procedures are automatically executed.

[0079] The early warning system includes sound alarms, light alarms and remote notifications; the alarm information includes abnormality description, occurrence time, location and recommended actions; the pre-set safety procedures include closing doors and windows, activating the drainage system and cutting off power.

[0080] The periodic updating and optimization of the deep learning algorithm model includes regularly accumulating new monitoring data for model training and analysis, retraining the deep learning algorithm model using the accumulated data, evaluating the performance of the model on an independent validation set, and using the optimized model for flood monitoring, and timely feedback of model optimization data; the retraining includes adjusting model parameters and optimizing network structure.

[0081] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

[0082] Example 2, reference Figure 2, which is the second embodiment of the present invention, provides a system for electric intelligent control of flood-proof doors and windows, including an environmental data acquisition and preprocessing module 100, a deep learning analysis and recognition module 200, a time series analysis and prediction module 300, an adaptive control instruction generation and execution module 400, and a real-time monitoring and early warning module 500.

[0083] The environmental data acquisition and preprocessing module 100 is used to collect water level, rainfall, wind speed, air pressure and temperature data in real time through intelligent monitoring sensors, and clean, normalize and annotate the collected data to ensure that the data quality is suitable for subsequent deep learning processing.

[0084] The deep learning analysis and identification module 200 is used to select a deep learning model architecture and determine the structure of the input layer, hidden layer and output layer, use the processed data to train the model, compile the model through a loss function, optimize the model parameters, use the trained model to output the probability of flood occurrence, and identify early phenomena of flood occurrence by setting an output threshold.

[0085] The time series analysis and prediction module 300 is used to use a time series analysis algorithm to model and predict water level change trends, determine model parameters, train the model, and use the trained model to predict water level changes.

[0086] The adaptive control instruction generation and execution module 400 is used to set the water level threshold and flood probability threshold according to the water level prediction results and the flood occurrence probability, generate control instructions, and execute the opening, closing and sealing of doors and windows according to the control instructions to deal with different levels of flood threats.

[0087] The real-time monitoring and early warning module 500 is used to monitor the sensor data stream in real time, apply the anomaly detection algorithm to identify abnormal data, and when abnormal data is detected, activate the early warning system through the remote control module, send alarm information to users and related personnel, automatically execute pre-set safety procedures, and periodically accumulate new monitoring data to retrain and optimize the deep learning algorithm model to improve prediction accuracy and system adaptability.

[0088] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

[0089] Embodiment 3, the third embodiment of the present invention, is different from the first two embodiments in that:

[0090] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, and other media that can store program codes.

[0091] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0092] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0093] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

Claims

1. A method for electrically intelligently controlling flood-proof doors and windows, characterized in that: include, Collect environmental data in real time and use deep learning algorithms to process the collected data and identify early signs of flooding; Based on the data processing results, the time series analysis algorithm is used to predict the water level change trend and the possibility of flood occurrence, and the control instructions are generated through the adaptive control algorithm according to the prediction results. The opening, closing and sealing operations of doors and windows are performed according to the control instructions; A real-time monitoring algorithm is designed to monitor whether abnormal data occurs. If an abnormality is found, the early warning mechanism is remotely activated to send alarm information to users and relevant personnel, and pre-set safety procedures are executed to periodically update and optimize the deep learning algorithm model.

2. A method for electrically intelligently controlling flood-proof doors and windows as claimed in claim 1, characterized in that: The collecting of environmental data includes collecting water level, rainfall, wind speed, air pressure and temperature data through intelligent monitoring sensors, and processing the collected data using deep learning algorithms; The data processing includes removing erroneous data, data normalization and data labeling; the deep learning algorithm includes selecting a model architecture, determining the input layer, hidden layer and output layer, dividing the data, compiling it using a loss function, and performing model training, and inputting the data into the trained model.

3. A method for electrically intelligently controlling flood-proof doors and windows as claimed in claim 2, characterized in that: The identifying early phenomena of flood occurrence includes, outputting through a deep learning model, setting an output threshold, and identifying early phenomena of flood occurrence by comparing the output with the threshold; The loss function formula is: Among them, L is the loss function, y i is the true label, is the predicted probability, i is the variable index, and n is the number of samples; The output of the deep learning model is: Among them, P is the probability of flood occurrence, β0, β1...β n are model parameters, X2, X3, ... n is the processed environmental factor, and n is the variable index.

4. A method for electrically intelligently controlling flood-proof doors and windows as claimed in claim 3, characterized in that: The time series analysis algorithm includes predicting the water level change trend and the possibility of flood occurrence using the time series analysis algorithm according to the data processing results; The predicting of water level change trend includes determining the window size of time series data, and using a regression moving average model to build a model, determining model parameters, and training the model, and using the trained model to predict the water level; The model parameters include the number of autoregressive terms, the difference order and the number of moving average terms; the water level prediction formula is: in, is the predicted water level at time t, H t-i is the actual water level at time ti, i = 1, 2…, p, i is the variable index, and ARIMA is the autoregressive moving average model.

5. A method for electrically intelligently controlling flood-proof doors and windows as claimed in claim 4, characterized in that: The generating control instruction includes generating the control instruction according to the currently predicted water level and flood occurrence warning, setting the water level threshold and the flood probability threshold, and outputting the control instruction according to the comparison, and executing the corresponding operation according to the output instruction; The set water level thresholds include setting the warning water level to 0.5 meters, the action water level to 1 meter, the emergency water level to 1.5 meters and the extreme water level to 2 meters; the flood probability threshold is 0.6; When the water level When the water level is higher than 1 meter, it indicates that the water level is in a safe area and monitoring should continue. When When the system automatically closes the doors and windows to prevent flooding; when When the system initiates emergency response measures, including closing all entrances, activating the alarm system, and notifying emergency services; When the flood probability is greater than or equal to 0.6, the system triggers an early warning, and the system determines that a flood will occur, and measures must be taken; when the flood probability is less than 0.6, the system does not trigger an early warning and continues to monitor environmental data; the flood probability is the output of the deep learning model.

6. A method for electrically intelligently controlling flood-proof doors and windows as claimed in claim 5, characterized in that: The design of the real-time monitoring algorithm includes receiving the sensor data stream in real time, applying an anomaly detection algorithm to each data point, identifying whether the data point deviates from the normal behavior pattern, setting anomaly determination criteria, calculating statistics of the data point and comparing with a preset threshold; The anomaly detection algorithm formula is: Where Z is the standardized distance between the data point and the mean, Y is the currently observed data point value, μ is the mean of the data set, and σ is the standard deviation of the data set; Among them, the Z threshold is set to 2. When |Z|>2, it means that the current data is abnormal and needs to be removed; when |Z|≤2, it means that the data is normal and needs to be input into the model for subsequent processing.

7. A method for electrically intelligently controlling flood-proof doors and windows as claimed in claim 6, characterized in that: The activation of the early warning mechanism includes: when abnormal data is detected, the system performs a secondary confirmation, and after confirming the abnormality, the early warning system is activated through the remote control module, and alarm information is sent to users and related personnel through SMS, email and application push, and the pre-set safety procedures are automatically executed; The early warning system includes sound alarm, light alarm and remote notification; the alarm information includes abnormal description, occurrence time, location and recommended actions; the pre-set safety procedures include closing doors and windows, activating drainage system and cutting off power; The periodic updating and optimization of the deep learning algorithm model includes regularly accumulating new monitoring data for model training and analysis, retraining the deep learning algorithm model using the accumulated data, evaluating the performance of the model on an independent validation set, and using the optimized model for flood monitoring, and timely feedback of model optimization data; the retraining includes adjusting model parameters and optimizing network structure.

8. A system using the method of electrically intelligently controlling flood-proof doors and windows as claimed in any one of claims 1 to 7, characterized in that: It includes environmental data acquisition and preprocessing module, deep learning analysis and recognition module, time series analysis and prediction module, adaptive control instruction generation and execution module, and real-time monitoring and early warning module; The environmental data acquisition and preprocessing module is used to collect water level, rainfall, wind speed, air pressure and temperature data in real time through intelligent monitoring sensors, and clean, normalize and annotate the collected data to ensure that the data quality is suitable for subsequent deep learning processing; The deep learning analysis and identification module is used to select the deep learning model architecture and determine the structure of the input layer, hidden layer and output layer, use the processed data to train the model, compile the model through the loss function, optimize the model parameters, use the trained model to output the probability of flood occurrence, and identify the early phenomenon of flood occurrence by setting the output threshold; The time series analysis and prediction module is used to model and predict the water level change trend using a time series analysis algorithm, determine model parameters, train the model, and use the trained model to predict water level changes; The adaptive control instruction generation and execution module is used to set the water level threshold and flood probability threshold according to the water level prediction results and the flood occurrence probability, generate control instructions, and execute the opening, closing and sealing of doors and windows according to the control instructions to deal with different levels of flood threats; The real-time monitoring and early warning module is used to monitor the sensor data stream in real time, apply the anomaly detection algorithm to identify abnormal data, and when abnormal data is detected, start the early warning system through the remote control module, send alarm information to users and related personnel, automatically execute pre-set safety procedures, and periodically accumulate new monitoring data to retrain and optimize the deep learning algorithm model to improve prediction accuracy and system adaptability.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method for electrically intelligently controlling flood-proof doors and windows described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of a method for electrically intelligently controlling flood-proof doors and windows as claimed in any one of claims 1 to 7 are implemented.

Images